Despite recent advances in the prevention and treatment of childhood malnutrition, nearly 150 million children under-5 years of age were stunted in 2020 (UNICEF et al., 2021). Stunting is defined as a length- or height-for-age z-score (HAZ) 2 or more standard deviations below the population median (de Onis et al., 2013), and is considered both an indicator of underlying deficits (i.e., chronic malnutrition, The World Bank, 2021), as well as a potential contributor to future health problems (e.g., through poor immune system maturation, Rytter et al., 2014; Bourke et al., 2016). Furthermore, stunting has been consistently associated with increased risk of morbidity and mortality, delayed or deficient cognitive development, and reduced educational attainment (McDonald et al., 2013; Black et al., 2013; Olofin et al., 2013; Adair et al., 2013; de Onis and Branca, 2016; Black et al., 2008; Bhaskaram, 2002). Timely and accurate identification of children most likely to experience stunting offers an opportunity to prevent such negative health outcomes.

Stunting has been linked with diarrheal diseases across many settings (Checkley et al., 2008). An estimated 10.9% of global stunting is attributable to diarrhea (Danaei et al., 2016), and a child with diarrhea is more likely to have a lower HAZ or to die than age-matched controls (Kotloff et al., 2013). Given the 1.1 billion episodes of childhood diarrhea that occur globally every year (Collaborators GBDDD, 2018), assessment of children seeking healthcare for diarrhea treatment provides an opportunity to identify those at increased risk for negative outcomes, including stunting and death. Once identified, these children could be specifically targeted for intensive interventions, thereby more efficiently allocating public health resources.

In this study, we aimed to develop parsimonious, easy to implement clinical prediction rules (CPRs) to identify children under-5 most likely to experience linear growth faltering among community-dwelling children presenting to care for acute diarrhea. CPRs are algorithms that aid clinicians in interpreting clinical findings and making clinical decisions (Reilly and Evans, 2006). Linear growth faltering, or falling below standardized height/length growth trajectory projections, captures children whose growth has slowed precipitously and is a precursor of stunting. A number of prior studies have identified risk factors for linear growth faltering (Danaei et al., 2016; Prado et al., 2019; Sofiatin et al., 2019; Naylor et al., 2015; Zhang et al., 2017; Richter et al., 2018; Schott et al., 2013; Richard et al., 2019; Rogawski et al., 2017; Rogawski et al., 2018), but many of these were single-site studies using traditional model building approaches, some of which lacked appropriate assessments of model discrimination and calibration. Building on this body of literature, we used machine learning methods on data from two large multicenter studies to derive and externally validate prognostic prediction models for growth faltering, with the hopes of reliably identifying children that would most benefit from additional nutritional intervention after care for acute diarrhea.

By utilizing data from two large multicenter clinical studies of pediatric diarrhea, we used a combination of machine learning and conventional regression methods to derive and validate CPRs for linear growth faltering. The discriminative performance of our CPR for growth faltering was remarkably similar between the two datasets (AUC = 0.72, 95% CI: 0.72, 0.72, based on GEMS 0–59 months; 0.68, 95% CI: 0.67, 0.69 based on MAL-ED 0–24 months). We were then able to externally validate a 2-variable version, which also had similar discriminative ability between the datasets (AUC 0.64–0.68 for 0–23 and 0–24 months in GEMS and MAL-ED, respectively). Our findings suggest the potential for a parsimonious prediction rule-guided algorithm to identify young children with acute diarrhea for appropriate triage and follow-up.

The limited number of studies that aim to identify children most likely to growth falter after acute diarrhea have resulted in CPRs with varying discriminative and generalizability. Our full CPRs were better at identifying growth faltering than (Brander et al., 2019) (AUC = 0.67, 95% CI: 0.64, 0.69), which was not externally validated, and worse than (Hanieh et al., 2019) (AUC = 0.85, 95% CI: 0.80, 0.90), which only used data from a single country. The top predictors of growth faltering identified by random forests in our analysis were consistent with existing knowledge of the drivers of growth faltering – child demographics, child symptoms, and indicators of household wealth. The top 2 variables (used in our parsimonious externally validated CPR) were age and baseline HAZ. However, despite the inclusion of markers of disease severity (temperature, respiratory rate, number of days of diarrhea), overall ability to predict growth faltering was moderate, and consideration of additional factors related to nature of disease (etiology, antibiotics) did not improve discriminative ability. This is consistent with previous analysis in GEMS data that found treating diarrhea with antibiotics generally did not prevent growth faltering (except for Shigella infections, Nasrin et al., 2021).

Furthermore, the similar incidence of growth faltering in diarrhea cases and matched controls (particularly in the youngest children), as well as the almost identical predictive variables and similar AUCs, suggests that the impact of a single episode of acute diarrhea on growth trajectory may be relatively low. It is possible that the entire diarrheal history of a child (e.g., frequency and severity of acute diarrhea), or subclinical enteric infections that do not result in diarrhea, are more important to their growth trajectory than a single diarrheal episode, though evidence is mixed (Checkley et al., 2008; Rogawski et al., 2018; Deichsel et al., 2020). Indeed, while the design of GEMS does not allow for the exploration of this hypothesis, MAL-ED does. Total days in all diarrheal episodes, days with diarrhea so far this episode, and days since last diarrhea episode were all top 10 predictors of growth faltering in MAL-ED. Furthermore in GEMS, the average baseline HAZ at enrollment was 0.5 HAZ lower in children who did not experience growth faltering than in children who did (Figure 3—figure supplement 5), suggesting the possibility that children need to have high enough HAZ in order to have the potential to falter. In contrast, children enrolled in Mali had the highest median HAZ at enrollment, and also had the lowest proportion of children who experienced growth faltering (Supplementary file 1). It is also possible that the underlying cause(s) of stunting are complex and interrelated, and relatively simple predictive models are not able to accurately parse apart which children do and do not experience sufficient causes. In sensitivity analyses, we demonstrated our ability to predict any stunting at follow-up with high accuracy (Table 1, Supplementary file 1). However, this represents a related but distinct outcome from our original aim, namely a slowing down of growth as opposed to stunting, and may warrant different clinical intervention.

While effective interventions exist for treating acute malnutrition (e.g., exclusive breastfeeding for the first 6 months of life, inpatient- and community-based management of acute malnutrition using corn-soy blend or ready-to-use therapeutic food; WHO, 2013; Bergeron and Castleman, 2012; Keats et al., 2021), there are few evidence-based guidance on how to reverse the effects of chronic malnutrition once a child is stunted (Bergeron and Castleman, 2012; Leroy et al., 2015; Reinhardt and Fanzo, 2014; Pavlinac et al., 2018; WHO, 2015). We found that approximately one in five children experience severe growth faltering subsequent to acute diarrhea, that is, an additional ≥0.5 decrease in HAZ in the 2–3 months after acute diarrhea. Currently, presenting to care for an acute illness, such as diarrhea, offers an opportunity for medical personnel to assess and treat children for acute malnutrition through intensive feeding programs. Our CPR provides a tool for identifying patients likely to experience additional growth faltering after acute diarrhea. Current malnutrition recommendations are based on patient presentation – whether a child is underweight when they present to the clinic. Our CPR could be used to identify children not currently stunted and therefore not currently recommended for nutritional interventions, but who are likely to slow down in growth and therefore at higher risk of incident stunting. Identifying these children would allow clinicians to connect patients with community-based nutrition interventions (e.g., maternal support for safe introduction of weening foods, small quantity lipid nutrient supplements, etc.; Bhutta et al., 2013; Bhutta et al., 2008; Cole, 2020; Zhang et al., 2021) to prevent additional effects of chronic malnutrition, namely irreversible stunting. Given our ability to predict growth faltering in healthy controls in GEMS, community screening for those at risk of growth faltering (not just those presenting with acute diarrhea) may also be prudent. This would represent a different potential intervention strategy and future research should explore this possibility further.

Our study has a number of strengths and limitations. We derived CPRs for growth faltering from two multisite, prospective studies that included longitudinal follow-up with extensive etiologic testing. Unlike previous work in this area, we used random forests for variable selection which do not require assumptions about relationships between the underlying variables and generally outperform (Singal et al., 2013) conventional model building techniques. While our complete-case analysis strategy could introduce bias due to missing data, we were able to re-derive the 10-variable version in two distinct datasets with similar results. While we were only able to externally validate a 2-variable version of our growth faltering CPR, its discriminative performance was similar to the full 10-variable version, and was robust to external validation. Furthermore, while the observation windows were large for many variables in the MAL-ED dataset used for external validation (up to 90 days for dietary variables, and up to 6 months for household descriptors), the variables of interest in the 2-variable CPR were observed no more than 31 days from the start of diarrhea. In addition, we considered all diarrhea as an outcome of interest in MAL-ED, whereas the analysis in GEMS was limited to MSD. When limiting the MAL-ED analysis to MSD as defined in GEMS, the top predictors and discriminative ability were very similar. The quasi-external validation between continents within GEMS data, as well as the country-specific models within GEMS, all had similar top predictors and discriminative performance, further supporting the overall validity of our CPR. Finally, we explored a range of AFe cutoffs for etiology, with consistent results.

Our study can also serve as a guide for future CPR development. We used a prediction-based approach for variable selection, and compared multiple model fitting strategies. We assessed model calibration as well as discrimination, and reported the results from numerous sensitivity analyses. Finally, we designed our study a priori to incorporate external validation, lending additional confidence to the generalizability of our results.

In conclusion, we used data from two large multi-country studies to derive and validate a CPR for growth faltering in children presenting for diarrhea treatment. Our findings indicate that use of prediction rules, potentially applied as clinical decision support tools, could help to identify additional children at risk of poor outcomes after an episode of diarrheal illness, that is not currently stunted but likely to decelerate growth. In settings with high mortality and morbidity in early childhood, such tools could represent a cost-effective way to target resources toward those who need it most.

This is a secondary analysis of the GEMS and MAL-ED datasets. These data are available to the public through the following website https://clinepidb.org/ce/app/. Data requests are submitted through the website listed, and requests are reviewed and approved by the investigators of those original studies consistent with their protocols and data sharing policies. As of the time of submission of this manuscript, the GEMS Data Access Request asked for purpose, hypothesis/research question, analysis plan, dissemination plan, and if anyone from the GEMS study team had already been approached regarding this request. The MAL-ED data were available for download without submitting a Data Access Request. Data cleaning and statistical code needed to reproduce all parts of this analysis are available from the corresponding author's GitHub page: https://github.com/LeungLab/CPRgrowthfaltering, (copy archived at swh:1:rev:f3fd53b5713ef787d3ae2cd4a81f3286f52f2746). The following previously published datasets were used: Dataset 1: Gates Enterics Project, Levine MM, Kotloff K, Nataro J, Khan AZA, Saha D, Adegbola FR, Sow S, Alonso P, Breiman R, Sur D, Faruque A. 2018. Study GEMS1 Case Control. https://clinepidb.org/ce/app/record/dataset/DS_841a9f5259#Contacts. Database and Identifier: ClinEpiDB, DS_841a9f5259 Dataset 2: The Etiology, Risk Factors, and Interactions of Enteric Infections and Malnutrition and the Consequences for Child Health (MAL-ED). Primary Contact: David Spiro, Fogarty International Center, National Institutes of Health, Bethesda, MD, USA. https://clinepidb.org/ce/app/workspace/analyses/DS_5c41b87221/new/details.

1. 1. Adair LS
   2. Fall CHD
   3. Osmond C
   4. Stein AD
   5. Martorell R
   6. Ramirez-Zea M
   7. Sachdev HS
   8. Dahly DL
   9. Bas I
   10. Norris SA
   11. Micklesfield L
   12. Hallal P
   13. Victora CG
   14. COHORTS group

   (2013) Associations of linear growth and relative weight gain during early life with adult health and human capital in countries of low and middle income: findings from five birth cohort studies

   Lancet 382:525–534.

   https://doi.org/10.1016/S0140-6736(13)60103-8

   • PubMed
   • Google Scholar
2. Software

   1. Ahmed SM

   (2022) CPRgrowthfaltering, version swh:1:rev:f3fd53b5713ef787d3ae2cd4a81f3286f52f2746

   Software Heritage.

   https://archive.softwareheritage.org/swh:1:dir:43d85395d56e9aeef4786453a910afa447d6e48f;origin=https://github.com/LeungLab/CPRgrowthfaltering;visit=swh:1:snp:6ff83743e61a19d986916c85b8067b4e04468f3e;anchor=swh:1:rev:f3fd53b5713ef787d3ae2cd4a81f3286f52f2746
3. 1. Bergeron G
   2. Castleman T

   (2012) Program responses to acute and chronic malnutrition: divergences and convergences

   Advances in Nutrition 3:242–249.

   https://doi.org/10.3945/an.111.001263

   • PubMed
   • Google Scholar
4. 1. Bhaskaram P

   (2002) Micronutrient malnutrition, infection, and immunity: an overview

   Nutrition Reviews 60:S40–S55.

   https://doi.org/10.1301/00296640260130722

   • PubMed
   • Google Scholar
5. 1. Bhutta ZA
   2. Ahmed T
   3. Black RE
   4. Cousens S
   5. Dewey K
   6. Giugliani E
   7. Haider BA
   8. Kirkwood B
   9. Morris SS
   10. Sachdev HPS
   11. Shekar M
   12. Maternal and Child Undernutrition Study Group

   (2008) What works? interventions for maternal and child undernutrition and survival

   Lancet 371:417–440.

   https://doi.org/10.1016/S0140-6736(07)61693-6

   • PubMed
   • Google Scholar
6. 1. Bhutta ZA
   2. Das JK
   3. Rizvi A
   4. Gaffey MF
   5. Walker N
   6. Horton S
   7. Webb P
   8. Lartey A
   9. Black RE
   10. Lancet Nutrition Interventions Review Group, the Maternal and Child Nutrition Study Group

   (2013) Evidence-based interventions for improvement of maternal and child nutrition: what can be done and at what cost?

   Lancet 382:452–477.

   https://doi.org/10.1016/S0140-6736(13)60996-4

   • PubMed
   • Google Scholar
7. 1. Black RE
   2. Allen LH
   3. Bhutta ZA
   4. Caulfield LE
   5. de Onis M
   6. Ezzati M
   7. Mathers C
   8. Rivera J
   9. Maternal and Child Undernutrition Study Group

   (2008) Maternal and child undernutrition: global and regional exposures and health consequences

   Lancet 371:243–260.

   https://doi.org/10.1016/S0140-6736(07)61690-0

   • PubMed
   • Google Scholar
8. 1. Black RE
   2. Victora CG
   3. Walker SP
   4. Bhutta ZA
   5. Christian P
   6. de Onis M
   7. Ezzati M
   8. Grantham-McGregor S
   9. Katz J
   10. Martorell R
   11. Uauy R
   12. Maternal and Child Nutrition Study Group

   (2013) Maternal and child undernutrition and overweight in low-income and middle-income countries

   Lancet 382:427–451.

   https://doi.org/10.1016/S0140-6736(13)60937-X

   • PubMed
   • Google Scholar
9. 1. Bourke CD
   2. Berkley JA
   3. Prendergast AJ

   (2016) Immune dysfunction as a cause and consequence of malnutrition

   Trends in Immunology 37:386–398.

   https://doi.org/10.1016/j.it.2016.04.003

   • PubMed
   • Google Scholar
10. 1. Brander RL
    2. Pavlinac PB
    3. Walson JL
    4. John-Stewart GC
    5. Weaver MR
    6. Faruque ASG
    7. Zaidi AKM
    8. Sur D
    9. Sow SO
    10. Hossain MJ
    11. Alonso PL
    12. Breiman RF
    13. Nasrin D
    14. Nataro JP
    15. Levine MM
    16. Kotloff KL

    (2019) Determinants of linear growth faltering among children with moderate-to-severe diarrhea in the global enteric multicenter study

    BMC Medicine 17:214.

    https://doi.org/10.1186/s12916-019-1441-3

    • PubMed
    • Google Scholar
11. 1. Checkley W
    2. Buckley G
    3. Gilman RH
    4. Assis AM
    5. Guerrant RL
    6. Morris SS
    7. Mølbak K
    8. Valentiner-Branth P
    9. Lanata CF
    10. Black RE
    11. Childhood Malnutrition and Infection Network

    (2008) Multi-country analysis of the effects of diarrhoea on childhood stunting

    International Journal of Epidemiology 37:816–830.

    https://doi.org/10.1093/ije/dyn099

    • PubMed
    • Google Scholar
12. 1. Cole CR

    (2020) Optimizing interventions to prevent chronic malnutrition: the search for the Holy Grail

    The Journal of Pediatrics 222:17–18.

    https://doi.org/10.1016/j.jpeds.2020.03.008

    • PubMed
    • Google Scholar
13. 1. Collaborators GBDDD

    (2018) Estimates of the global, regional, and national morbidity, mortality, and aetiologies of diarrhoea in 195 countries: a systematic analysis for the global burden of disease study 2016

    The Lancet. Infectious Diseases 18:1211–1228.

    https://doi.org/10.1016/S1473-3099(18)30362-1

    • PubMed
    • Google Scholar
14. 1. Danaei G
    2. Andrews KG
    3. Sudfeld CR
    4. Fink G
    5. McCoy DC
    6. Peet E
    7. Sania A
    8. Smith Fawzi MC
    9. Ezzati M
    10. Fawzi WW

    (2016) Risk factors for childhood stunting in 137 developing countries: a comparative risk assessment analysis at global, regional, and country levels

    PLOS Medicine 13:e1002164.

    https://doi.org/10.1371/journal.pmed.1002164

    • PubMed
    • Google Scholar
15. 1. de Onis M
    2. Dewey KG
    3. Borghi E
    4. Onyango AW
    5. Blössner M
    6. Daelmans B
    7. Piwoz E
    8. Branca F

    (2013) The world Health organization’s global target for reducing childhood stunting by 2025: rationale and proposed actions

    Maternal & Child Nutrition 9 Suppl 2:6–26.

    https://doi.org/10.1111/mcn.12075

    • PubMed
    • Google Scholar
16. 1. de Onis M
    2. Branca F

    (2016) Childhood stunting: a global perspective

    Maternal & Child Nutrition 12 Suppl 1:12–26.

    https://doi.org/10.1111/mcn.12231

    • PubMed
    • Google Scholar
17. 1. Deichsel EL
    2. John-Stewart GC
    3. Walson JL
    4. Mbori-Ngacha D
    5. Richardson BA
    6. Guthrie BL
    7. Farquhar C
    8. Bosire R
    9. Pavlinac PB

    (2020) Examining the relationship between diarrhea and linear growth in Kenyan HIV-exposed, uninfected infants

    PLOS ONE 15:e0235704.

    https://doi.org/10.1371/journal.pone.0235704

    • PubMed
    • Google Scholar
18. 1. Hanieh S
    2. Braat S
    3. Simpson JA
    4. Ha TTT
    5. Tran TD
    6. Tuan T
    7. Fisher J
    8. Biggs B-A

    (2019) The stunting tool for early prevention: development and external validation of a novel tool to predict risk of stunting in children at 3 years of age

    BMJ Global Health 4:e001801.

    https://doi.org/10.1136/bmjgh-2019-001801

    • PubMed
    • Google Scholar
19. 1. James G
    2. Witten D
    3. Hastie T
    4. Tibshirani R

    (2013)

    An Introduction to Statistical Learning with Applications in R

    An introduction to statistical learning, An Introduction to Statistical Learning with Applications in R, New York, NY, Springer, 10.1007/978-1-4614-7138-7.

    • Google Scholar
20. 1. Keats EC
    2. Das JK
    3. Salam RA
    4. Lassi ZS
    5. Imdad A
    6. Black RE
    7. Bhutta ZA

    (2021) Effective interventions to address maternal and child malnutrition: an update of the evidence

    The Lancet. Child & Adolescent Health 5:367–384.

    https://doi.org/10.1016/S2352-4642(20)30274-1

    • PubMed
    • Google Scholar
21. 1. Kotloff KL
    2. Blackwelder WC
    3. Nasrin D
    4. Nataro JP
    5. Farag TH
    6. van Eijk A
    7. Adegbola RA
    8. Alonso PL
    9. Breiman RF
    10. Faruque ASG
    11. Saha D
    12. Sow SO
    13. Sur D
    14. Zaidi AKM
    15. Biswas K
    16. Panchalingam S
    17. Clemens JD
    18. Cohen D
    19. Glass RI
    20. Mintz ED
    21. Sommerfelt H
    22. Levine MM

    (2012) The global enteric multicenter study of diarrheal disease in infants and young children in developing countries: epidemiologic and clinical methods of the case/control study

    Clinical Infectious Diseases 55 Suppl 4:S232–S245.

    https://doi.org/10.1093/cid/cis753

    • PubMed
    • Google Scholar
22. 1. Kotloff KL
    2. Nataro JP
    3. Blackwelder WC
    4. Nasrin D
    5. Farag TH
    6. Panchalingam S
    7. Wu Y
    8. Sow SO
    9. Sur D
    10. Breiman RF
    11. Faruque AS
    12. Zaidi AK
    13. Saha D
    14. Alonso PL
    15. Tamboura B
    16. Sanogo D
    17. Onwuchekwa U
    18. Manna B
    19. Ramamurthy T
    20. Kanungo S
    21. Ochieng JB
    22. Omore R
    23. Oundo JO
    24. Hossain A
    25. Das SK
    26. Ahmed S
    27. Qureshi S
    28. Quadri F
    29. Adegbola RA
    30. Antonio M
    31. Hossain MJ
    32. Akinsola A
    33. Mandomando I
    34. Nhampossa T
    35. Acácio S
    36. Biswas K
    37. O’Reilly CE
    38. Mintz ED
    39. Berkeley LY
    40. Muhsen K
    41. Sommerfelt H
    42. Robins-Browne RM
    43. Levine MM

    (2013) Burden and aetiology of diarrhoeal disease in infants and young children in developing countries (the global enteric multicenter study, gems): a prospective, case-control study

    Lancet 382:209–222.

    https://doi.org/10.1016/S0140-6736(13)60844-2

    • PubMed
    • Google Scholar
23. 1. Leroy JL
    2. Ruel M
    3. Habicht JP
    4. Frongillo EA

    (2015) Using height-for-age differences (had) instead of height-for-age z-scores (HAZ) for the meaningful measurement of population-level catch-up in linear growth in children less than 5 years of age

    BMC Pediatrics 15:145.

    https://doi.org/10.1186/s12887-015-0458-9

    • PubMed
    • Google Scholar
24. 1. MAL-ED Network Investigators

    (2014) The MAL-ED study: a multinational and multidisciplinary approach to understand the relationship between enteric pathogens, malnutrition, gut physiology, physical growth, cognitive development, and immune responses in infants and children up to 2 years of age in resource-poor environments

    Clinical Infectious Diseases 59:S193–S206.

    https://doi.org/10.1093/cid/ciu653

    • PubMed
    • Google Scholar
25. 1. McDonald CM
    2. Olofin I
    3. Flaxman S
    4. Fawzi WW
    5. Spiegelman D
    6. Caulfield LE
    7. Black RE
    8. Ezzati M
    9. Danaei G
    10. Nutrition Impact Model Study

    (2013) The effect of multiple anthropometric deficits on child mortality: meta-analysis of individual data in 10 prospective studies from developing countries

    The American Journal of Clinical Nutrition 97:896–901.

    https://doi.org/10.3945/ajcn.112.047639

    • PubMed
    • Google Scholar
26. 1. Nasrin D
    2. Blackwelder WC
    3. Sommerfelt H
    4. Wu Y
    5. Farag TH
    6. Panchalingam S
    7. Biswas K
    8. Saha D
    9. Jahangir Hossain M
    10. Sow SO
    11. Reiman RFB
    12. Sur D
    13. Faruque ASG
    14. Zaidi AKM
    15. Sanogo D
    16. Tamboura B
    17. Onwuchekwa U
    18. Manna B
    19. Ramamurthy T
    20. Kanungo S
    21. Omore R
    22. Ochieng JB
    23. Oundo JO
    24. Das SK
    25. Ahmed S
    26. Qureshi S
    27. Quadri F
    28. Adegbola RA
    29. Antonio M
    30. Mandomando I
    31. Nhampossa T
    32. Bassat Q
    33. Roose A
    34. O’Reilly CE
    35. Mintz ED
    36. Ramakrishnan U
    37. Powell H
    38. Liang Y
    39. Nataro JP
    40. Levine MM
    41. Kotloff KL

    (2021) Pathogens associated with linear growth faltering in children with diarrhea and impact of antibiotic treatment: the global enteric multicenter study

    The Journal of Infectious Diseases 224:S848–S855.

    https://doi.org/10.1093/infdis/jiab434

    • PubMed
    • Google Scholar
27. 1. Naylor C
    2. Lu M
    3. Haque R
    4. Mondal D
    5. Buonomo E
    6. Nayak U
    7. Mychaleckyj JC
    8. Kirkpatrick B
    9. Colgate R
    10. Carmolli M
    11. Dickson D
    12. van der Klis F
    13. Weldon W
    14. Steven Oberste M
    15. PROVIDE study teams
    16. Ma JZ
    17. Petri WA Jr

    (2015) Environmental enteropathy, oral vaccine failure and growth faltering in infants in Bangladesh

    EBioMedicine 2:1759–1766.

    https://doi.org/10.1016/j.ebiom.2015.09.036

    • PubMed
    • Google Scholar
28. 1. Olofin I
    2. McDonald CM
    3. Ezzati M
    4. Flaxman S
    5. Black RE
    6. Fawzi WW
    7. Caulfield LE
    8. Danaei G
    9. Nutrition Impact Model Study anthropometry cohort pooling

    (2013) Associations of suboptimal growth with all-cause and cause-specific mortality in children under five years: a pooled analysis of ten prospective studies

    PLOS ONE 8:e64636.

    https://doi.org/10.1371/journal.pone.0064636

    • PubMed
    • Google Scholar
29. 1. Pavlinac PB
    2. Brander RL
    3. Atlas HE
    4. John-Stewart GC
    5. Denno DM
    6. Walson JL

    (2018) Interventions to reduce post-acute consequences of diarrheal disease in children: a systematic review

    BMC Public Health 18:208.

    https://doi.org/10.1186/s12889-018-5092-7

    • PubMed
    • Google Scholar
30. 1. Platts-Mills JA
    2. McCormick BJJ
    3. Kosek M
    4. Pan WK
    5. Checkley W
    6. Houpt ER
    7. MAL-ED Network Investigators

    (2014) Methods of analysis of enteropathogen infection in the MAL-ED cohort study

    Clinical Infectious Diseases 59 Suppl 4:S233–S238.

    https://doi.org/10.1093/cid/ciu408

    • PubMed
    • Google Scholar
31. 1. Platts-Mills JA
    2. Babji S
    3. Bodhidatta L
    4. Gratz J
    5. Haque R
    6. Havt A
    7. McCormick BJ
    8. McGrath M
    9. Olortegui MP
    10. Samie A
    11. Shakoor S
    12. Mondal D
    13. Lima IF
    14. Hariraju D
    15. Rayamajhi BB
    16. Qureshi S
    17. Kabir F
    18. Yori PP
    19. Mufamadi B
    20. Amour C
    21. Carreon JD
    22. Richard SA
    23. Lang D
    24. Bessong P
    25. Mduma E
    26. Ahmed T
    27. Lima AA
    28. Mason CJ
    29. Zaidi AK
    30. Bhutta ZA
    31. Kosek M
    32. Guerrant RL
    33. Gottlieb M
    34. Miller M
    35. Kang G
    36. Houpt ER
    37. MAL-ED Network Investigators

    (2015) Pathogen-specific burdens of community diarrhoea in developing countries: a multisite birth cohort study (MAL-ED)

    The Lancet. Global Health 3:e564–e575.

    https://doi.org/10.1016/S2214-109X(15)00151-5

    • PubMed
    • Google Scholar
32. 1. Prado EL
    2. Yakes Jimenez E
    3. Vosti S
    4. Stewart R
    5. Stewart CP
    6. Somé J
    7. Pulakka A
    8. Ouédraogo JB
    9. Okronipa H
    10. Ocansey E
    11. Oaks B
    12. Maleta K
    13. Lartey A
    14. Kortekangas E
    15. Hess SY
    16. Brown K
    17. Bendabenda J
    18. Ashorn U
    19. Ashorn P
    20. Arimond M
    21. Adu-Afarwuah S
    22. Abbeddou S
    23. Dewey K

    (2019) Path analyses of risk factors for linear growth faltering in four prospective cohorts of young children in Ghana, Malawi and Burkina Faso

    BMJ Global Health 4:e001155.

    https://doi.org/10.1136/bmjgh-2018-001155

    • PubMed
    • Google Scholar
33. 1. Reilly BM
    2. Evans AT

    (2006) Translating clinical research into clinical practice: impact of using prediction rules to make decisions

    Annals of Internal Medicine 144:201–209.

    https://doi.org/10.7326/0003-4819-144-3-200602070-00009

    • PubMed
    • Google Scholar
34. 1. Reinhardt K
    2. Fanzo J

    (2014) Addressing chronic malnutrition through multi-sectoral, sustainable approaches: a review of the causes and consequences

    Frontiers in Nutrition 1:13.

    https://doi.org/10.3389/fnut.2014.00013

    • PubMed
    • Google Scholar
35. 1. Richard SA
    2. Barrett LJ
    3. Guerrant RL
    4. Checkley W
    5. Miller MA
    6. Investigators MEN

    (2014) Disease surveillance methods used in the 8-site MAL-ED cohort study

    Clinical Infectious Diseases 59 Suppl 4:S220–S224.

    https://doi.org/10.1093/cid/ciu435

    • PubMed
    • Google Scholar
36. 1. Richard SA
    2. McCormick BJJ
    3. Murray-Kolb LE
    4. Lee GO
    5. Seidman JC
    6. Mahfuz M
    7. Ahmed T
    8. Guerrant RL
    9. Petri WA
    10. Rogawski ET
    11. Houpt E
    12. Kang G
    13. Mduma E
    14. Kosek MN
    15. Lima AAM
    16. Shrestha SK
    17. Chandyo RK
    18. Bhutta Z
    19. Bessong P
    20. Caulfield LE
    21. MAL-ED Network Investigators

    (2019) Enteric dysfunction and other factors associated with attained size at 5 years: MAL-ED birth cohort study findings

    The American Journal of Clinical Nutrition 110:131–138.

    https://doi.org/10.1093/ajcn/nqz004

    • PubMed
    • Google Scholar
37. 1. Richter LM
    2. Orkin FM
    3. Roman GD
    4. Dahly DL
    5. Horta BL
    6. Bhargava SK
    7. Norris SA
    8. Stein AD
    9. COHORTS investigators

    (2018) Comparative models of biological and social pathways to predict child growth through age 2 years from birth cohorts in brazil, india, the philippines, and south africa

    The Journal of Nutrition 148:1364–1371.

    https://doi.org/10.1093/jn/nxy101

    • PubMed
    • Google Scholar
38. 1. Rogawski ET
    2. Bartelt LA
    3. Platts-Mills JA
    4. Seidman JC
    5. Samie A
    6. Havt A
    7. Babji S
    8. Trigoso DR
    9. Qureshi S
    10. Shakoor S
    11. Haque R
    12. Mduma E
    13. Bajracharya S
    14. Gaffar SMA
    15. Lima AAM
    16. Kang G
    17. Kosek MN
    18. Ahmed T
    19. Svensen E
    20. Mason C
    21. Bhutta ZA
    22. Lang DR
    23. Gottlieb M
    24. Guerrant RL
    25. Houpt ER
    26. Bessong PO
    27. MAL-ED Network Investigators

    (2017) Determinants and impact of Giardia infection in the first 2 years of life in the MAL-ED birth cohort

    Journal of the Pediatric Infectious Diseases Society 6:153–160.

    https://doi.org/10.1093/jpids/piw082

    • PubMed
    • Google Scholar
39. 1. Rogawski ET
    2. Liu J
    3. Platts-Mills JA
    4. Kabir F
    5. Lertsethtakarn P
    6. Siguas M
    7. Khan SS
    8. Praharaj I
    9. Murei A
    10. Nshama R
    11. Mujaga B
    12. Havt A
    13. Maciel IA
    14. Operario DJ
    15. Taniuchi M
    16. Gratz J
    17. Stroup SE
    18. Roberts JH
    19. Kalam A
    20. Aziz F
    21. Qureshi S
    22. Islam MO
    23. Sakpaisal P
    24. Silapong S
    25. Yori PP
    26. Rajendiran R
    27. Benny B
    28. McGrath M
    29. Seidman JC
    30. Lang D
    31. Gottlieb M
    32. Guerrant RL
    33. Lima AAM
    34. Leite JP
    35. Samie A
    36. Bessong PO
    37. Page N
    38. Bodhidatta L
    39. Mason C
    40. Shrestha S
    41. Kiwelu I
    42. Mduma ER
    43. Iqbal NT
    44. Bhutta ZA
    45. Ahmed T
    46. Haque R
    47. Kang G
    48. Kosek MN
    49. Houpt ER
    50. MAL-ED Network Investigators

    (2018) Use of quantitative molecular diagnostic methods to investigate the effect of enteropathogen infections on linear growth in children in low-resource settings: longitudinal analysis of results from the MAL-ED cohort study

    The Lancet. Global Health 6:e1319–e1328.

    https://doi.org/10.1016/S2214-109X(18)30351-6

    • PubMed
    • Google Scholar
40. 1. Rytter MJH
    2. Kolte L
    3. Briend A
    4. Friis H
    5. Christensen VB

    (2014) The immune system in children with malnutrition -- a systematic review

    PLOS ONE 9:e105017.

    https://doi.org/10.1371/journal.pone.0105017

    • PubMed
    • Google Scholar
41. 1. Schott WB
    2. Crookston BT
    3. Lundeen EA
    4. Stein AD
    5. Behrman JR
    6. Young Lives Determinants and Consequences of Child Growth Project Team

    (2013) Periods of child growth up to age 8 years in ethiopia, india, peru and vietnam: key distal household and community factors

    Social Science & Medicine 97:278–287.

    https://doi.org/10.1016/j.socscimed.2013.05.016

    • PubMed
    • Google Scholar
42. 1. Singal AG
    2. Mukherjee A
    3. Elmunzer BJ
    4. Higgins PDR
    5. Lok AS
    6. Zhu J
    7. Marrero JA
    8. Waljee AK

    (2013) Machine learning algorithms outperform conventional regression models in predicting development of hepatocellular carcinoma

    The American Journal of Gastroenterology 108:1723–1730.

    https://doi.org/10.1038/ajg.2013.332

    • PubMed
    • Google Scholar
43. 1. Sofiatin Y
    2. Pusparani A
    3. Judistiani TD
    4. Rahmalia A
    5. Diana A
    6. Alisjahbana A

    (2019) Maternal and environmental risk for faltered growth in the first 5 years for tanjungsari children in West Java, Indonesia

    Asia Pacific Journal of Clinical Nutrition 28:S32–S42.

    https://doi.org/10.6133/apjcn.201901_28(S1).0003

    • PubMed
    • Google Scholar
44. 1. Steyerberg EW
    2. Vergouwe Y

    (2014) Towards better clinical prediction models: seven steps for development and an ABCD for validation

    European Heart Journal 35:1925–1931.

    https://doi.org/10.1093/eurheartj/ehu207

    • PubMed
    • Google Scholar
45. Report

    1. The World Bank

    (2021)

    Levels and trends in child malnutrition: key findings of the 2021 edition of the joint child malnutrition estimates

    Geneva: World Health Organization.

    • Google Scholar
46. Report

    1. UNICEF
    2. World Health Organization
    3. The World Bank

    (2021)

    Levels and Trends in Child Malnutrition: Key Findings of the 2021 Edition of the Joint Child Malnutrition Estimates

    Geneva: World Health Organization.

    • Google Scholar
47. 1. Van Calster B
    2. McLernon DJ
    3. Van Smeden M
    4. Wynants L
    5. Steyerberg EW

    (2019) Topic group ’Evaluating diagnostic calibration: the achilles heel of predictive analytics

    BMC Med 17:230.

    https://doi.org/10.1186/s12916-019-1466-7

    • Google Scholar
48. Book

    1. WHO

    (2013)

    Guideline: Updates on the Management of Severe Acute Malnutiriton in Infants and Children

    Geneva: World Health Organization.

    • Google Scholar
49. Website

    1. WHO

    (2015) Stunting in a nutshell: World Health Organization

    Accessed November 19, 2015.

    https://www.who.int/news/item/19-11-2015-stunting-in-a-nutshell
50. 1. Zhang Y
    2. Zhou J
    3. Niu F
    4. Donowitz JR
    5. Haque R
    6. Petri WA Jr
    7. Ma JZ

    (2017) Characterizing early child growth patterns of height-for-age in an urban slum cohort of Bangladesh with functional principal component analysis

    BMC Pediatrics 17:84.

    https://doi.org/10.1186/s12887-017-0831-y

    • PubMed
    • Google Scholar
51. 1. Zhang Z
    2. Li F
    3. Hannon BA
    4. Hustead DS
    5. Aw MM
    6. Liu Z
    7. Chuah KA
    8. Low YL
    9. Huynh DTT

    (2021) Effect of oral nutritional supplementation on growth in children with undernutrition: a systematic review and meta-analysis

    Nutrients 13:3036.

    https://doi.org/10.3390/nu13093036

    • PubMed
    • Google Scholar

Decision letter after peer review:

Thank you for submitting your article "Derivation and external validation of clinical prediction rules identifying children at risk of linear growth faltering (stunting) presenting for diarrheal care" for consideration by eLife. Your article has been reviewed by 2 peer reviewers, and the evaluation has been overseen by me in my joint role as Reviewing Editor and Senior Editor. The following individual involved in review of your submission has agreed to reveal their identity: Andrew N Mertens (Reviewer #2).

As is customary in eLife, the reviewers have discussed their critiques with one another and with the Editors, and I prepared this decision letter to help you prepare a revised submission. Given the extent of the suggestions, I prefer to provide you with a compilation of the relevant suggestions in the two critiques to assist you in preparing the revisions for an eventual resubmission.

Essential revisions:

Although we expect that you will address these comments in your response letter, we also need to see the corresponding revision clearly marked in the text of the manuscript. Some of the reviewers' comments may seem to be simple queries or challenges that do not prompt revisions to the text. Please keep in mind, however, that readers may have the same perspective as the reviewers. Therefore, it is essential that you amend or expand the text to clarify the narrative accordingly.

The outcome used for prediction in a binary indicatory for a decrease in height-for-age Z-score >= 0.5. A child who fails to gain height by future measurements is of concern, but this outcome also misses children who are already experiencing growth failure, and is vulnerable to regression to the mean effect. The two most important predictors were age and current size, with current size having a positive association with risk of growth faltering. As mentioned in the discussion, there is "the possibility that children need to have high enough HAZ in order to have the potential to falter." Additionally, there may be children with erroneously high height measurements at the first measurement, so that the HAZ change >= 0.5 associated with high baseline HAZ is from measurement-error regression to the mean. I recommend also predicting absolute HAZ (or stunting status) as a secondary outcome and comparing if the important predictors change. Were alternative specifications (e.g., quantitative decrease in HAZ, incident stunting) considered?

In its current form, the results and conclusions from the results have problematic implications for the treatment of child malnutrition. The conclusion states: "In settings with high mortality and morbidity in early childhood, such tools could represent a cost-effective way to target resources towards those who need it most." If the current CPR was used in a resource-constrained setting, it would recommend that larger children should be prioritized for nutritional supplementation over already stunted children who may have reached their growth faltering floor. In addition, with a sensitivity of 80%, the tool would miss treating a large number of children who would experience growth faltering. The results of the clinical prediction tool need to be presented with care in how it could be used to prioritize treatment without missing treating children who would benefit from nutritional supplementation. Including absolute HAZ as an outcome will help, along with additional discussion of how the CPR fits alongside current treatment recommendations. For example, does this rule indicate treating children who aren't currently treated, or are there children who don't need treatment given current guidelines and the created CPR.

The results from these datasets may not have identified novel and strong predictors of growth faltering, as the current results indicate that additional predictors beyond current size and age don't help with predictions, but the analysis could be reframed as a template for developing a CPR, using this data as a case study. If age and current size are the only important predictors, then a simple rule based on age and a current HAZ cutoff could be created, negating the need for a more complicated model, but this manuscript also provides a good template for other clinical prediction analyses. Could you comment more on the methods and performance metrics used in the discussion, and make a recommendation for future analyses?

Why use the MAL-ED data to externally validate the CPR developed using GEMS data, given the different study designs, definitions of diarrheal disease, and predictors measured. Because GEMS is a multisite study, wouldn't it be easier, and allow more complex models to be validated, if the model was fit using data from some countries, then validated in populations from other countries?

In addition to the coefficients for the 10-variable model, it would be helpful to present coefficients for the final 2-variable model that was assessed in both GEMS and MAL-ED.

Although the authors opted to use logistic regression based on AUC, the AUC values for random forest models were only slightly lower (Figure S2), and random forest may provide simpler clinical prediction rules. It may be interesting to also describe the rules that were developed by the random forest models. The last panel in Figure S2 may be mislabeled (0-23 mo for MAL-ED instead of 0-59 mo).

I am not very familiar with the variable importance calculated from random forest models. What is the implication of certain features having high variable importance, but also having coefficient estimates that are indistinguishable from the null (e.g., age in MAL-ED, respiratory rate in GEMS in Table S4)?

In the Discussion (p.20), the authors note that the entire diarrheal history of a child may be a more important indicator of linear growth faltering than a single episode. These datasets seem potentially well-suited to directly explore this question ¬- were frequency/number of prior diarrheal episodes investigated as predictors in GEMS / MAL-ED?

For reproducibility, please specify the software and key packages with corresponding versions that were used for this analysis.

The best performing model was logistic regressions fit with variables chosen by random forest models. Any idea why this would be? Is it because they are simpler and the random forest models are overfit to the training data? I would expect them to perform worse because they don't allow for nonlinearity and interactions like a RF model. If generalized linear models perform better than random forest for prediction in this situation, penalized logistic regression models may also improve predictive performance by incorporating variable selection with prediction in a simpler model than random forests.

The conclusion in the abstract is "Our findings indicate that use of prediction rules could help identify children at risk of poor outcomes after an episode of diarrheal illness", but prediction performance is the same in control children, so while its important to retain the discussion of lack of association between diarrhea and growth, the framing of the paper could be expanded around all children in LMIC, rather than just children with acute diarrhea. This could just be a slight reframing in the writing, or you could expand the MAL-ED prediction model to use all children in addition to the prediction on the subset of children with diarrhea.

What is the rationale for comparing HAZ and MUAC as separate and combined predictors of growth? On one hand, it's interesting to compare which current measures of anthropometry are most associated with future measures of anthropometry, in which case you'd want to include other outcomes such as WHZ, WAZ, and MUAC. But if the goal is to develop the best clinical prediction tool, it makes more sense to include all measures of growth that can be easily clinically collected as predictors to see if performance increases by including WHZ, WAZ, and MUAC on top of HAZ.

Line 125-128: "Model performance was assessed using the receiver operating characteristic (ROC) curves and the cross-validated C-statistic (area under the ROC curve (AUC)), a measures which describes how well a model can discriminate between the two outcomes, from the cross-validation." Confusingly worded… do you mean "AUC is a measure which describes how well a model can predict a binary outcome in test data from the cross-validated folds."

Line 129-142: Model calibration performance metrics: these were new to me, and I wasn't sure what to be looking for or what story they could tell us about model performance beyond the AUC. What is the reader looking for? Can they tell us something different than the AUC?

Line 173: separately report missing versus implausible values, because the percent implausible gives an indication of data quality.

Lines 177-182: Report mean HAZ by country as well to show if it there is lower growth faltering in some countries because of high existing stunting by the age of first measurement.

Line 199: This is the first mention of death as an outcome (and the results of the CPR for death are not discussed).

Page 20: "It is possible that the entire diarrheal history of a child (e.g. frequency and severity of acute diarrhea), or subclinical enteric infections that do not result in diarrhea, are more important to their growth trajectory than a single diarrheal episode, though evidence is mixed." As you have longitudinal data from MAL-ED, can't you explicitly check this by using diarrhea history as a predictor?

Page 21: "Unlike previous work in this area, we used random forests for variable selection which do not require assumptions about the underlying variables and generally outperform(49) conventional model building techniques."

– Need to clarify that random forests have no assumptions about the relationship between variables, not about the variables themselves, which still have assumptions around how they are coded/categorized.

Tables S4- Age is the most important predictor, but the OR is 1 with 1,1 confidence intervals. Can you convert the predictor to age in months or report more decimal places so direction of effect can be seen?

Essential revisions:

Although we expect that you will address these comments in your response letter, we also need to see the corresponding revision clearly marked in the text of the manuscript. Some of the reviewers' comments may seem to be simple queries or challenges that do not prompt revisions to the text. Please keep in mind, however, that readers may have the same perspective as the reviewers. Therefore, it is essential that you amend or expand the text to clarify the narrative accordingly.

The outcome used for prediction in a binary indicatory for a decrease in height-for-age Z-score >= 0.5. A child who fails to gain height by future measurements is of concern, but this outcome also misses children who are already experiencing growth failure, and is vulnerable to regression to the mean effect. The two most important predictors were age and current size, with current size having a positive association with risk of growth faltering. As mentioned in the discussion, there is "the possibility that children need to have high enough HAZ in order to have the potential to falter." Additionally, there may be children with erroneously high height measurements at the first measurement, so that the HAZ change >= 0.5 associated with high baseline HAZ is from measurement-error regression to the mean. I recommend also predicting absolute HAZ (or stunting status) as a secondary outcome and comparing if the important predictors change. Were alternative specifications (e.g., quantitative decrease in HAZ, incident stunting) considered?

Thank you for this suggestion. We have added additional models for the following predictions: (a) growth faltering in those NOT stunted (HAZ≥-2) at presentation, (b) any stunting (HAZ<-2) at follow-up, and (c) any stunting at follow-up in those not stunted at presentation.

While we agree the addition of these models improves the manuscript, we also want to highlight that these models have distinct outcomes and therefore have separate clinical uses. Our original goal was to identify children whose growth was likely to slow down after diarrhea. As we show, top predictors and predictive performance is similar for growth faltering across baseline stunting status. We present any stunting at follow-up as a comparison, but argue that this is a different clinical outcome that may warrant different intervention.

P.22 L.335-339: “In sensitivity analyses, we demonstrated our ability to predict any stunting at follow-up with high accuracy (Table 1, Supplementary file 1E). However, this represents a related but distinct outcome from our original aim, namely a slowing down of growth as opposed to stunting, and may warrant different clinical intervention.”

P.23 L.349-353: “Current malnutrition recommendations are based on patient presentation – whether a child is underweight when they present to the clinic. Our CPR could be used to identify children not currently stunted and therefore not currently recommended for nutritional interventions, but who are likely to slow down in growth and therefore at higher risk of incident stunting.”

In its current form, the results and conclusions from the results have problematic implications for the treatment of child malnutrition. The conclusion states: "In settings with high mortality and morbidity in early childhood, such tools could represent a cost-effective way to target resources towards those who need it most." If the current CPR was used in a resource-constrained setting, it would recommend that larger children should be prioritized for nutritional supplementation over already stunted children who may have reached their growth faltering floor. In addition, with a sensitivity of 80%, the tool would miss treating a large number of children who would experience growth faltering. The results of the clinical prediction tool need to be presented with care in how it could be used to prioritize treatment without missing treating children who would benefit from nutritional supplementation. Including absolute HAZ as an outcome will help, along with additional discussion of how the CPR fits alongside current treatment recommendations. For example, does this rule indicate treating children who aren't currently treated, or are there children who don't need treatment given current guidelines and the created CPR.

We thank the Reviewers for pointing out this oversight. We have edited the Discussion for clarity as follows.

P.23 L.348-357: “Our CPR provides a tool for identifying patients likely to experience additional growth faltering after acute diarrhea. Current malnutrition recommendations are based on patient presentation – is a child underweight when they come to the clinic. Our CPR could be used to identify children not currently stunted and therefore not currently recommended for nutritional interventions, but who are likely to slow down in growth and therefore at higher risk of incident stunting. Identifying these children would allow clinicians to connect patients with community-based nutrition interventions (e.g. maternal support for safe introduction of weening foods, small quantity lipid nutrient supplements (SQ-LNS), etc. (45-48)) to prevent additional effects of chronic malnutrition, namely irreversible stunting.”

P.25 L.386-389: “Our findings indicate that use of prediction rules, potentially applied as clinical decision support tools, could help to identify additional children at risk of poor outcomes after an episode of diarrheal illness, i.e. not currently stunted but likely to decelerate growth.”

The results from these datasets may not have identified novel and strong predictors of growth faltering, as the current results indicate that additional predictors beyond current size and age don't help with predictions, but the analysis could be reframed as a template for developing a CPR, using this data as a case study. If age and current size are the only important predictors, then a simple rule based on age and a current HAZ cutoff could be created, negating the need for a more complicated model, but this manuscript also provides a good template for other clinical prediction analyses. Could you comment more on the methods and performance metrics used in the discussion, and make a recommendation for future analyses?

Thank you for this suggested. We have edited the Discussion as below:

P.24 L.380-384: “Our study can also serve as a guide for future CPR development. We used a prediction-based approach for variable selection, and compared multiple model fitting strategies. We assessed model calibration as well as discrimination, and reported the results from numerous sensitivity analyses. Finally, we designed our study a priori to incorporate external validation, lending additional confidence to the generalizability of our results.”

Why use the MAL-ED data to externally validate the CPR developed using GEMS data, given the different study designs, definitions of diarrheal disease, and predictors measured. Because GEMS is a multisite study, wouldn't it be easier, and allow more complex models to be validated, if the model was fit using data from some countries, then validated in populations from other countries?

We thank the Reviewers for this suggestion and have added country-specific CPRs in the Supplement. We have also added a sensitivity analysis whereby we fit models to all data from one continent in GEMS, and then validated that model on the other continent in GEMS data. As you can see from Supplementary file 1E top predictors and discriminative performance were similar across countries and continents

P.10 L.171-173: “Finally, we conducted a quasi-external validation within the GEMS data by fitting a model to one continent and validating it on the other.”

P.24 L.376-379: “The quasi-external validation between continents within GEMS data, as well as the country-specific models within GEMS, all had similar top predictors and discriminative performance, further supporting the overall validity of our CPR. Finally, we explored a range of AFe cutoffs for etiology, with consistent results.”

In addition to the coefficients for the 10-variable model, it would be helpful to present coefficients for the final 2-variable model that was assessed in both GEMS and MAL-ED.

We have added this as requested to the Supplementary file 1D.

Although the authors opted to use logistic regression based on AUC, the AUC values for random forest models were only slightly lower (Figure S2), and random forest may provide simpler clinical prediction rules. It may be interesting to also describe the rules that were developed by the random forest models. The last panel in Figure S2 may be mislabeled (0-23 mo for MAL-ED instead of 0-59 mo).

Thank you for the correction, we have edited the figure as appropriate. All of our Results are presented in our manuscript and Supplement, we did not develop additional CPRs.

I am not very familiar with the variable importance calculated from random forest models. What is the implication of certain features having high variable importance, but also having coefficient estimates that are indistinguishable from the null (e.g., age in MAL-ED, respiratory rate in GEMS in Table S4)?

We appreciate this is a very important question. As described on P.7 L116-118, we defined variable importance as mean squared prediction error achieved by including the variable in the predictive model. In other words, we selected variables based on how well they improved the predictive performance of the overall model. This is a different analytic goal than testing the hypothesis that a variable is or is not associated with the outcome (e.g. does the confidence interval for the odds ratio cross 1). If our goal had been to explore the association between potential risk factors and growth faltering, we would have implemented a different variable selection process. Please refer to Shmueli 2010 and van Diepen 2017 for additional details.

In the Discussion (p.20), the authors note that the entire diarrheal history of a child may be a more important indicator of linear growth faltering than a single episode. These datasets seem potentially well-suited to directly explore this question ¬- were frequency/number of prior diarrheal episodes investigated as predictors in GEMS / MAL-ED?

We thank the Reviewers for bringing this omission to our attention. The study design of GEMS does not make it possible to assess history of previous diarrhea episodes. There are a number of variables that approximate this in MAL-ED, which have already been considered as potential predictors in the re-derivation. We have the Discussion as follows to incorporate this.

P.22 L.322-328: “It is possible that the entire diarrheal history of a child (e.g. frequency and severity of acute diarrhea), or subclinical enteric infections that do not result in diarrhea, are more important to their growth trajectory than a single diarrheal episode, though evidence is mixed (13, 26, 37). Indeed, while the design of GEMS does not allow for the exploration of this hypothesis, MAL-ED does. Total days in all diarrheal episodes, days with diarrhea so far this episode, and days since last diarrhea episode were all top-10 predictors of growth faltering in MAL-ED.”

For reproducibility, please specify the software and key packages with corresponding versions that were used for this analysis.

Thanks for this suggestion, we have added as below.

P.10 L.173-174: “All analysis was conducted in R 4.0.2 using the packages “ranger,” “cvAUC,” and “pROC.””

The best performing model was logistic regressions fit with variables chosen by random forest models. Any idea why this would be? Is it because they are simpler and the random forest models are overfit to the training data? I would expect them to perform worse because they don't allow for nonlinearity and interactions like a RF model. If generalized linear models perform better than random forest for prediction in this situation, penalized logistic regression models may also improve predictive performance by incorporating variable selection with prediction in a simpler model than random forests.

We agree that exploring alternative model building strategies could prove fruitful. However, incorporating variable selection and prediction into a single model building process such as with ridge regression or elastic net could lead to a more complicated final model, as less important coefficients approach but do not reach 0. In any case, an exhaustive comparison between model building strategies was beyond the scope of this study.

The conclusion in the abstract is "Our findings indicate that use of prediction rules could help identify children at risk of poor outcomes after an episode of diarrheal illness", but prediction performance is the same in control children, so while its important to retain the discussion of lack of association between diarrhea and growth, the framing of the paper could be expanded around all children in LMIC, rather than just children with acute diarrhea. This could just be a slight reframing in the writing, or you could expand the MAL-ED prediction model to use all children in addition to the prediction on the subset of children with diarrhea.

We thank the Reviewer for this suggestion. We feel it is important to retain the focus on acute diarrhea, as this represents an easy point of access to identify children who are struggling. A community screening program that would utilize a CPR predicting growth faltering in both symptomatic and non symptomatic children could also be beneficial, but is a different goal and would fit in a different type of intervention than our original research goal. Per your suggestion, we have edited the Abstract and Discussion as follows to highlight this possibility.

P.2: “Abstract Conclusions: Our findings indicate that use of prediction rules could help identify children at risk of poor outcomes after an episode of diarrheal illness. They may also be generalizable to all children, regardless of diarrhea status.”

P.23 L357-360: “Given our ability to predict growth faltering in healthy controls in GEMS, community screening for those at risk of growth faltering (not just those presenting with acute diarrhea) may also be prudent. This would represent a different potential intervention strategy and future research should explore this possibility further.”

What is the rationale for comparing HAZ and MUAC as separate and combined predictors of growth? On one hand, it's interesting to compare which current measures of anthropometry are most associated with future measures of anthropometry, in which case you'd want to include other outcomes such as WHZ, WAZ, and MUAC. But if the goal is to develop the best clinical prediction tool, it makes more sense to include all measures of growth that can be easily clinically collected as predictors to see if performance increases by including WHZ, WAZ, and MUAC on top of HAZ.

Our goal was to develop the best clinical prediction tool in terms of predictive ability AND ease of use. As we show in Supplementary file 1E, the model considering HAZ as the only growth metric performed better than the model considering only MUAC, and performed just as well as the model considering both. Therefore, we concluded the most predictive and parsimonious model included HAZ as the only growth metric. Because our goal was to develop a clinical prediction rule for pediatric patients with acute diarrhea, we chose not to consider WHZ and WAZ. Child weight is highly susceptible to dehydration status, especially in the youngest children (Modi 2015). Therefore, weight-based growth metrics can be highly inaccurate during acute diarrheal illness.

Line 125-128: "Model performance was assessed using the receiver operating characteristic (ROC) curves and the cross-validated C-statistic (area under the ROC curve (AUC)), a measures which describes how well a model can discriminate between the two outcomes, from the cross-validation." Confusingly worded… do you mean "AUC is a measure which describes how well a model can predict a binary outcome in test data from the cross-validated folds."

Thanks for this suggestion, edits below

P.8 L.125-128: “Model performance was assessed using the receiver operating characteristic (ROC) curves and the cross-validated C-statistic (area under the ROC curve (AUC)). The AUC describes how well a model can discriminate between a binary outcome in the test data from the cross-validated folds.”

Line 129-142: Model calibration performance metrics: these were new to me, and I wasn't sure what to be looking for or what story they could tell us about model performance beyond the AUC. What is the reader looking for? Can they tell us something different than the AUC?

Model discrimination (e.g. AUC) and model calibration are indeed two different metrics for evaluating predictive performance. Discrimination refers to a model’s ability to correctly separate who does and does not experience the outcome of interest. Calibration refers to a model’s ability to correctly estimate the risk of the outcome. In other words, how similar is the predicted number of events to the observed number of events. We have added the following brief explanation to the manuscript and included an addition citation for interested readers.

P.8 L.129-130: “Calibration refers to a model’s ability to correctly estimate the risk of the outcome(34). We assessed model calibration both quantitatively and graphically… “

Line 173: separately report missing versus implausible values, because the percent implausible gives an indication of data quality.

We have edited as follows.

P.10 L.177-180: “There were 9439 children with acute diarrhea enrolled in GEMS. In the analysis of the primary outcome (growth faltering), 110 observations were dropped for having follow-up measurements taken <49 or >91 days after enrollment, and 1276 were dropped for having implausible HAZ measurements, leaving an analytic sample of 8053.”

Lines 177-182: Report mean HAZ by country as well to show if it there is lower growth faltering in some countries because of high existing stunting by the age of first measurement.

We thank the Reviewers for this excellent suggestion, and have added the requested data in Supplementary file 1B. We have edited the Discussion as follows.

P.22 L.328-333: “Furthermore, the average baseline HAZ at enrollment was 0.5 HAZ lower in children who did not experience growth faltering than in children who did (Supplemental Figure S4), suggesting the possibility that children need to have high enough HAZ in order to have the potential to falter. In contrast, children enrolled in Mali had the highest median HAZ at enrollment, and also had the lowest proportion of children who experienced growth faltering (Supplementary file 1B).”

Line 199: This is the first mention of death as an outcome (and the results of the CPR for death are not discussed).

This was an oversight from a previous draft of the manuscript and has been removed. Thanks for pointing this out.

Page 20: "It is possible that the entire diarrheal history of a child (e.g. frequency and severity of acute diarrhea), or subclinical enteric infections that do not result in diarrhea, are more important to their growth trajectory than a single diarrheal episode, though evidence is mixed." As you have longitudinal data from MAL-ED, can't you explicitly check this by using diarrhea history as a predictor?

Please see response and edits listed above.

Page 21: "Unlike previous work in this area, we used random forests for variable selection which do not require assumptions about the underlying variables and generally outperform(49) conventional model building techniques."

– Need to clarify that random forests have no assumptions about the relationship between variables, not about the variables themselves, which still have assumptions around how they are coded/categorized.

Thank you for pointing this out, we have edited as follows.

P.24 L.363-365: “Unlike previous work in this area, we used random forests for variable selection which do not require assumptions about relationships between the underlying variables and generally outperform(50) conventional model building techniques.”

Tables S4- Age is the most important predictor, but the OR is 1 with 1,1 confidence intervals. Can you convert the predictor to age in months or report more decimal places so direction of effect can be seen?

As discussed earlier in this Response to Reviewers, the goal of our CPRs was prediction, not to assess the association or effect of a risk factor on the outcome. Therefore, it is inappropriate, i.e. the analytic strategy does not support, to judge the relationship between risk factors and the outcome using these CPR models.

References

Shmueli, G. To explain or to predict? Statist. Sci. 25(3): 289-310 (August 2010). DOI:10.1214/10-STS330. https://arxiv.org/pdf/1101.0891.pdf.

van Diepen, M., Ramspek, C.L., Jager, K.J., Zoccali, C., Dekker, Friedo W. Predictionversus aetiology: common pitfalls and how to avoid them. Nephrol DialTransplant. 2017 Apr 1;32. PMID: 28339854.

Modi, P., Nasrin,S., Hawes, M., Glavis-Bloom, J., Alam N.H., Hossain, M.I., Levine, A.C. Midupper arm circumference outperforms weight-based measures of nutritionalstatus in children with diarrhea. J. Nutr. 2015 Jul; 145(7):1582-7. PMID:25972523.

Author details

1. Sharia M Ahmed

   Division of Infectious Diseases, University of Utah School of Medicine, Salt lake City, United States

   Contribution

   Conceptualization, Resources, Data curation, Software, Formal analysis, Validation, Investigation, Methodology, Writing - original draft, Writing - review and editing

   For correspondence

   sharia.m.ahmed@utah.edu

   Competing interests

   No competing interests declared

   "This ORCID iD identifies the author of this article:" 0000-0002-4060-5712

2. Ben J Brintz

   Division of Epidemiology, University of Utah School of Medicine, Salt Lake City, United States

   Contribution

   Software, Formal analysis, Validation, Methodology, Writing - review and editing

   Competing interests

   No competing interests declared

   "This ORCID iD identifies the author of this article:" 0000-0003-4695-0290

3. Patricia B Pavlinac

   Department of Global Health, Global Center for Integrated Health of Women, Adolescents and Children (Global WACh), University of Washington, Seattle, United States

   Contribution

   Conceptualization, Resources, Writing - review and editing

   Competing interests

   No competing interests declared

4. Lubaba Shahrin

   International Centre for Diarrhoeal Disease Research, Dhaka, Bangladesh

   Contribution

   Conceptualization, Writing - review and editing

   Competing interests

   No competing interests declared

5. Sayeeda Huq

   International Centre for Diarrhoeal Disease Research, Dhaka, Bangladesh

   Contribution

   Conceptualization, Writing - review and editing

   Competing interests

   No competing interests declared

6. Adam C Levine

   Department of Emergency Medicine, Warren Alpert Medical School of Brown University, Providence, United States

   Contribution

   Conceptualization, Resources, Writing - review and editing

   Competing interests

   No competing interests declared

7. Eric J Nelson

   Department of Pediatrics and Environmental and Global Health, Emerging Pathogens Institute, University of Florida, Gainesville, United States

   Contribution

   Conceptualization, Resources, Writing - review and editing

   Competing interests

   No competing interests declared

8. James A Platts-Mills

   Division of Infectious Diseases and International Health, University of Virginia, Charlottesville, United States

   Contribution

   Conceptualization, Resources, Writing - review and editing

   Competing interests

   No competing interests declared

9. Karen L Kotloff

   Department of Pediatrics, Center for Vaccine Development, University of Maryland School of Medicine, Baltimore, United States

   Contribution

   Conceptualization, Resources, Writing - review and editing

   Competing interests

   No competing interests declared

10. Daniel T Leung

    1. Division of Infectious Diseases, University of Utah School of Medicine, Salt lake City, United States
    2. Division of Microbiology & Immunology, University of Utah School of Medicine, Salt Lake City, United States

    Contribution

    Conceptualization, Resources, Supervision, Funding acquisition, Writing - review and editing

    For correspondence

    daniel.leung@utah.edu

    Competing interests

    No competing interests declared

    "This ORCID iD identifies the author of this article:" 0000-0001-8401-0801

• 300

  Page views

• 35

  Downloads

• 0

  Citations

Article citation count generated by polling the highest count across the following sources: Crossref, PubMed Central, Scopus.