The new coronavirus (now named SARS-CoV-2) causing the disease pandemic in 2019 (COVID-19), has so far infected over 35 million people worldwide and killed more than 1 million. Most people with COVID-19 have no symptoms or only mild symptoms. But some become seriously ill and need hospitalization. The sickest are admitted to an Intensive Care Unit (ICU) and may need mechanical ventilation to help them breath. Being able to predict which patients with COVID-19 will become severely ill could help hospitals around the world manage the huge influx of patients caused by the pandemic and save lives.

Now, Hao, Sotudian, Wang, Xu et al. show that computer models using artificial intelligence technology can help predict which COVID-19 patients will be hospitalized, admitted to the ICU, or need mechanical ventilation. Using data of 2,566 COVID-19 patients from five Massachusetts hospitals, Hao et al. created three separate models that can predict hospitalization, ICU admission, and the need for mechanical ventilation with more than 86% accuracy, based on patient characteristics, clinical symptoms, laboratory results and chest x-rays.

Hao et al. found that the patients’ vital signs, age, obesity, difficulty breathing, and underlying diseases like diabetes, were the strongest predictors of the need for hospitalization. Being male, having diabetes, cloudy chest x-rays, and certain laboratory results were the most important risk factors for intensive care treatment and mechanical ventilation. Laboratory results suggesting tissue damage, severe inflammation or oxygen deprivation in the body's tissues were important warning signs of severe disease.

The results provide a more detailed picture of the patients who are likely to suffer from severe forms of COVID-19. Using the predictive models may help physicians identify patients who appear okay but need closer monitoring and more aggressive treatment. The models may also help policy makers decide who needs workplace accommodations such as being allowed to work from home, which individuals may benefit from more frequent testing, and who should be prioritized for vaccination when a vaccine becomes available.

As a result of the SARS-CoV-2 pandemic, many hospitals across the world have resorted to drastic measures: canceling elective procedures, switching to remote consultations, designating most beds to COVID-19, expanding Intensive Care Unit (ICU) capacity, and re-purposing doctors and nurses to support COVID-19 care. In the U.S., the CDC estimates more than 310,000 COVID-19 hospitalizations from March 1 to June 13, 2020 (CDC, 2020).

Much of the modeling work related to the pandemic has focused on spread dynamics (Kucharski et al., 2020). Others have described patients who were hospitalized (Richardson et al., 2020) (n = 5700) and (Buckner et al., 2020) (n = 105), became critically ill (Gong et al., 2020) (n = 372), or succumbed to the disease (n = 1625 (Onder et al., 2020), n = 270 [Wu et al., 2020]). In data from the New York City, 14.2% required ICU treatment and 12.2% mechanical ventilation (Richardson et al., 2020). With such rates, the logistical and ethical implications of bed allocation and potential rationing of care delivery are immense (White and Lo, 2020). To date, while state- or country-level prognostication has developed to examine resource allocation at a mass scale, there is inadequate evidence based on a large cohort on accurate prediction of the disease progress at the individual patient level. A string of recent studies developed models to predict severe disease or mortality based on clinical and laboratory findings, for example (Yan et al., 2020) (n = 485), (Gong et al., 2020) (n = 372), (Bhargava et al., 2020) (n = 197), (Ji et al., 2020) (n = 208), and (Wang et al., 2020) (n = 296). In these studies, several variables such as Lactate Dehydrogenase (LDH) (Gong et al., 2020; Ji et al., 2020; Yan et al., 2020) and C-reactive protein (CRP) have been identified as important predictors. All of these studies considered relatively small cohorts and, with the exception of Bhargava et al., 2020, considered patients in China. Although it is believed that the virus remains the same around the globe, the physiologic response to the virus and the eventual course of disease depend on multiple other factors, many of them regional (e.g. population characteristics, hospital practices, prevalence of pre-existing conditions) and not applicable universally. Triage of adult patients with COVID-19 remains challenging with most evidence coming from expert recommendations; evidence-based methods based on larger U.S.-based cohorts have not been reported (Sprung et al., 2020).

Leveraging data from five hospitals of the largest health care system in Massachusetts, we seek to develop personalized, interpretable predictive models of (i) hospitalization, (ii) ICU treatment, and (iii) mechanical ventilation, among SARS-CoV-2 positive patients. To develop these models, we developed a pipeline leveraging state-of-the-art Natural Language Processing (NLP) tools to extract information from the clinical reports for each patient, employing statistical feature selection methods to retain the most predictive features for each model, and adapting a host of advance machine learning-based classification methods to develop parsimonious (hence, easier to use and interpret) predictive models. We found that the more interpretable models can, for the most part, deliver similar predictive performance compared to more complex, ‘black-box’ models involving ensembles of many decision trees. Our results support our initial hypothesis that important clinical outcomes can be predicted with a high degree of accuracy upon the patient’s first presentation to the hospital using a relatively small number of features, which collectively compose a ‘signature’ of the novel COVID-19 disease.

We extracted data for all patients (n = 2566) who had a positive RT-PCR SARS-CoV-2 test between March 4 and April 13, 2020 at five Massachusetts hospitals, included in the same health care system (Massachusetts General Hospital (MGH), Brigham and Women’s Hospital (BWH), Faulkner Hospital (FH), Newton-Wellesley Hospital (NWH), and North Shore Medical Center (NSM)). The study was approved by the pertinent Institutional Review Boards.

Demographics, pre-hospital medications, and comorbidities were extracted for each patient based on the electronic medical record. Patient symptoms, vital signs, radiologic findings, and laboratory results were recorded at their first hospital presentation (either clinic or emergency department) before testing positive for SARS-CoV-2. A total of 164 features were extracted for each patient. ICU admission and mechanical ventilation were determined for each patient. Complete blood count values were considered as absolute counts. Representative statistics comparing hospitalized, ICU admitted, and mechanically ventilated patients are provided in Table A1 (Appendix). Table A2 (Appendix) reports how patients were distributed among the five hospitals.

Among the 2566 patients with a positive test, 930 (36.2%) were hospitalized. Among the hospitalized, 273 (29.4% of the hospitalized) required ICU care of which 217 (79.5%) required mechanical ventilation. The mean age over all patients was 51.9 years (SD: 18.9 years) and 45.6% were male.

We developed three models to predict need for hospitalization, ICU admission, and mechanical ventilation in patients with COVID-19. The prediction models are not meant to replace clinicians’ judgment for determining level of care. Instead, they are designed to assist clinicians in identifying patients at risk of future decompensation. Patient vital signs were the most important predictors of hospitalization. This is expected as vital signs reflect underlying disease severity, the need for cardiorespiratory resuscitation, and the risk of future decompensation without adequate medical support. Older age and BMI were also important predictors for hospitalization. Age has been recognized as an important factor associated with severe COVID-19 in previous series (Grasselli et al., 2020; Guan et al., 2020; Richardson et al., 2020). However, it is not known whether age itself or the presence of comorbidities place patients at risk for severe disease. Our results demonstrate that age is a stronger predictor of severe COVID-19 than a host of underlying comorbidities.

In terms of patient comorbidities, adrenal insufficiency, prior transplantation, and chronic kidney disease were strongly associated with need for hospitalization. Diabetes mellitus was associated with a need for ICU admission and mechanical ventilation, which might be due to its detrimental effects on immune function.

For the ICU and ventilation prediction models screening all at-risk (COVID-19-positive patients), opacities observed in a chest scan, age, and male gender emerge as important variables. Males have been found to have worse in-hospital outcomes in other studies as well (Palaiodimos et al., 2020).

We also identified several routine laboratory values that are predictive of ICU admission and mechanical ventilation. Elevated serum LDH, CRP, anion gap, and glucose, as well as decreased serum calcium, sodium, and albumin were strong predictors of ICU admission and mechanical ventilation. LDH is an indicator of tissue damage and has been found to be a marker of severity in P. jirovecii pneumonia (Zaman and White, 1988). Along with CRP, it was among the two most important predictors of ICU admission and ventilation in the parsimonious model among patients who had LDH and CRP measurements on admission. This finding is consistent with previous reports identifying LDH as an important prognostic factor (Gong et al., 2020; Ji et al., 2020; Mo et al., 2020; Yan et al., 2020). In addition, lower serum calcium is associated with cell lysis and tissue destruction, as it is often seen as part of the tumor lysis syndrome. Elevated serum anion gap is a marker of metabolic acidosis and ischemia, suggesting that tissue hypoxia and hypoperfusion may be components of severe disease.

For all three prognostic models, we developed predicting hospitalizations, ICU care, and mechanical ventilation, AUC ranges within 86–88%, which indicates strong predictive power. Interestingly, we can achieve AUC within 85–86% for ICU and ventilation prediction with a parsimonious linear model utilizing no more than 10 variables. In all cases, we can also develop a parsimonious model with binarized variables using medically suggested normal and abnormal variable thresholds. These binarized models have similar performance with their continuous counterparts. The ICU and ventilation models using all patients are very accurate, but, arguably, make a number of ‘easier’ decisions since more than 60% of the patients are never hospitalized. Many of these patients are younger, healthy, and likely present with mild-to-moderate symptoms. To test the robustness of the models to patients with potentially more ‘complex’ disease, we developed ICU and ventilation models on a restricted set of patients. This is the subset of patients who are hospitalized and most of the crucial labs are available for them (specifically CRP and LDH which emerged as important from our models). The best AUC for these models drops, but not below 82%, which indicates robustness of the model even when dealing with arguably harder to assess cases. LDH, CRP, calcium, lung opacity, anion gap, SpO2, sodium, and a comorbidity of insulin-controlled diabetes appear as the most significant for these patients. Interestingly, the corresponding binarized models have about 10% lower AUC; apparently, for the more severely ill, clinical variables deviate substantially from normal and knowing the exact values is crucial.

The models have been validated with two different approaches, using random splits of the data into training and testing, as well as training in some hospitals and testing at a different hospital. Performance metrics are relatively consistent with these two approaches. We also compared the models against standard pneumonia severity scores, PSI and CURB-65, establishing that our models are significantly stronger, which highlights the different clinical profile of COVID-19.

We also examined how much in advance of the ICU or ventilation outcomes our models are able to make a prediction. Of course, this is not entirely in our control; it depends on what state the patients get admitted and how soon their condition deteriorates to require ICU admission and/or ventilation. Table 6 reports the corresponding statistics. For example, the restricted ICU and ventilation models are making a correct prediction upon admission (using the lab results closest to that time) for outcomes that on average occur 38 and 35 hr later, respectively.

To further test the accuracy of the restricted ICU and ventilation models well in advance of the corresponding event, we considered an extended BWH test set (adding 11 more patients) and computed the accuracy of the models when the test set was restricted to patients whose outcome (ICU admission or ventilation) was more than x hours after the admission lab results based on which the prediction was made, with x being 6 hr, or 12 hr, or 18 hr, or 24 hr, or even 48 hr. The ICU model reaches an AUC of 87% and a weighted F1-score of 86% at x = 18 hr. The ventilation model reaches an AUC of 64% and an F1-score of 72% at x = 48 hr. These results demonstrate that the predictive models can indeed make predictions well into the future, when physicians would be less certain about the course of the disease and when there is potentially enough time to intervene and improve outcomes.

A manual review of the predictions by the models indicates that they performed well at predicting future ICU admissions for patients who presented with mild disease several days before ICU admission was necessary. Such patients were hemodynamically stable and had minimal oxygen requirements on the floor, before clinical deterioration necessitated ICU admission. We identified several such patients. A typical case is that of a 51-year-old male with a history of hypertension, obesity, and insulin-dependent type 2 diabetes mellitus, who presented with a 3-day history of dyspnea, cough and myalgias. In the emergency department, he was hemodynamically stable, saturating at 96–97% on 2 L of nasal cannula. The patient was admitted to the floor and did well for 3 days, saturating at 93–96% on room air. On the fourth day of hospitalization, he had increasing oxygen requirements and the decision was made to transfer him to the ICU. He was intubated and ventilated for 30 days. Our prediction models accurately predicted at the time of his presentation that he would eventually require ICU admission and mechanical ventilation. This prediction was based on such variables as an elevated LDH (241 U/L) and the presence of insulin-dependent diabetes mellitus. Another such case is that of a 59-year-old male without a significant prior medical history who presented with 2 days of dyspnea, nausea, and diarrhea. At the emergency department, he was tachycardic at 110 beats per minute and saturating at 96% on room air, and the patient was admitted. For 2 days, the patient was hemodynamically stable, saturating at 94–97% on room air. On the third day of hospitalization, he had increasing oxygen requirements, eventually requiring transfer to the ICU. He was intubated and ventilated for the next 14 days. Our prediction model predicted the patient’s decompensation at his presentation, due to elevations in LDH (348 U/L) and CRP (102.3 mg/L).

We also considered the role of ACEIs and ARBs and their potential association with the outcomes. It has been speculated that ACEIs may worsen COVID-19 outcomes because they upregulate the expression of ACE2, which the virus targets for cell entry. No such evidence has been reported in earlier studies (Kuster et al., 2020; Patel and Verma, 2020). In fact, a smaller study (Zhang et al., 2020) (n = 1128 vs. 2566 in our case) reported a beneficial effect and (Rossi et al., 2020) warn of potential harmful effects of discontinuing ACEIs or ARBs due to COVID-19. Our hospitalization model suggests that ACEIs do not increase hospitalization risk and may slightly reduce it (OR 95% CI is (0.52,1.04) with a mean of 0.73). In the ICU and ventilation models, the role of these two medications is statistically weaker to observe any meaningful association.

The models we derived can be used for a variety of purposes: (i) guiding patient triage to appropriate inpatient units, (ii) guiding staffing and resource planning logistics, and (iii) understanding patient risk profiles to inform future policy decisions, such as targeted risk-based stay-at-home restrictions, testing, and vaccination prioritization guidelines once a vaccine becomes available.

Calculators implementing the parsimonious models corresponding to each of the Tables 1, 2, 3, 4, 5 have been made available online (Hao et al., 2020).

Source code for processing patient data is provided together with the submission. Due to HIPAA restrictions and Data Use Agreements we can not make the original patient data publicly available. Interested parties may submit a request to obtain access to de-identified data to the authors. The authors would request pertinent IRB approval to make available a de-identified version of the data, stripped of any protected health information as specified under HIPAA rules. The IRB of the hospital system approved the study under Protocol #2020P001112 and the Boston University IRB found the study as being Not Human Subject Research under Protocol #5570X (the BU team worked with a de-identified limited dataset).

1. 1. Bhargava A
   2. Fukushima EA
   3. Levine M
   4. Zhao W
   5. Tanveer F
   6. Szpunar SM
   7. Saravolatz L

   (2020) Predictors for severe COVID-19 infection

   Clinical Infectious Diseases 395:ciaa674.

   https://doi.org/10.1093/cid/ciaa674

   • Google Scholar
2. 1. Breiman L

   (2001) Random forests

   Machine Learning 45:5–32.

   https://doi.org/10.1023/A:1010933404324

   • Google Scholar
3. 1. Buckner FS
   2. McCulloch DJ
   3. Atluri V
   4. Blain M
   5. McGuffin SA
   6. Nalla AK
   7. Huang M-L
   8. Greninger AL
   9. Jerome KR
   10. Cohen SA
   11. Neme S
   12. Green ML
   13. Chu HY
   14. Kim HN

   (2020) Clinical features and outcomes of 105 hospitalized patients with COVID-19 in Seattle, Washington

   Clinical Infectious Diseases 395:ciaa632.

   https://doi.org/10.1093/cid/ciaa632

   • Google Scholar
4. Website

   1. CDC

   (2020) COVIDView, key updates for week 18. centers for disease control and prevention

   Accessed October 3, 2020.

   https://www.cdc.gov/coronavirus/2019-ncov/covid-data/covidview/index.html
5. Conference

   1. Chen T
   2. Guestrin C

   (2016)

   Xgboost

   A Scalable Tree Boosting systemProceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining. pp. 785–794.

   • Google Scholar
6. 1. Chen R
   2. Paschalidis IC

   (2018)

   A robust learning approach for regression models based on distributionally robust optimization

   Journal of Machine Learning Research 19:1–48.

   • Google Scholar
7. 1. Cortes C
   2. Vapnik V

   (1995) Support-vector networks

   Machine Learning 20:273–297.

   https://doi.org/10.1007/BF00994018

   • Google Scholar
8. 1. Fine MJ
   2. Auble TE
   3. Yealy DM
   4. Hanusa BH
   5. Weissfeld LA
   6. Singer DE
   7. Coley CM
   8. Marrie TJ
   9. Kapoor WN

   (1997) A prediction rule to identify low-risk patients with community-acquired pneumonia

   New England Journal of Medicine 336:243–250.

   https://doi.org/10.1056/NEJM199701233360402

   • PubMed
   • Google Scholar
9. 1. Gong J
   2. Ou J
   3. Qiu X
   4. Jie Y
   5. Chen Y
   6. Yuan L
   7. Cao J
   8. Tan M
   9. Xu W
   10. Zheng F
   11. Shi Y
   12. Hu B

   (2020) A tool for early prediction of severe coronavirus disease 2019 (COVID-19): A multicenter study using the risk nomogram in Wuhan and Guangdong, China

   Clinical Infectious Diseases 71:833–840.

   https://doi.org/10.1093/cid/ciaa443

   • PubMed
   • Google Scholar
10. 1. Grasselli G
    2. Pesenti A
    3. Cecconi M

    (2020) Critical care utilization for the COVID-19 outbreak in Lombardy, Italy: early experience and forecast during an emergency response

    Jama 323:1545–1546.

    https://doi.org/10.1001/jama.2020.4031

    • PubMed
    • Google Scholar
11. 1. Guan WJ
    2. Ni ZY
    3. Hu Y
    4. Liang WH
    5. Ou CQ
    6. He JX
    7. Liu L
    8. Shan H
    9. Lei CL
    10. Hui DSC
    11. Du B
    12. Li LJ
    13. Zeng G
    14. Yuen KY
    15. Chen RC
    16. Tang CL
    17. Wang T
    18. Chen PY
    19. Xiang J
    20. Li SY
    21. Wang JL
    22. Liang ZJ
    23. Peng YX
    24. Wei L
    25. Liu Y
    26. Hu YH
    27. Peng P
    28. Wang JM
    29. Liu JY
    30. Chen Z
    31. Li G
    32. Zheng ZJ
    33. Qiu SQ
    34. Luo J
    35. Ye CJ
    36. Zhu SY
    37. Zhong NS
    38. China Medical Treatment Expert Group for Covid-19

    (2020) Clinical characteristics of coronavirus disease 2019 in China

    The New England Journal of Medicine 382:1708–1720.

    https://doi.org/10.1056/NEJMoa2002032

    • PubMed
    • Google Scholar
12. Website

    1. Hao B
    2. Sotudian S
    3. Wang T
    4. Xu T
    5. Paschalidis IC

    (2020) COVID calculators

    Network Optimization and Control Lab, Boston University. Accessed October 10, 2020.

    http://sites.bu.edu/paschalidis/research/covid-calculators/
13. 1. Ji D
    2. Zhang D
    3. Xu J
    4. Chen Z
    5. Yang T
    6. Zhao P
    7. Chen G
    8. Cheng G
    9. Wang Y
    10. Bi J
    11. Tan L
    12. Lau G
    13. Qin E

    (2020) Prediction for Progression Risk in Patients With COVID-19 Pneumonia: The CALL Score

    Clinical Infectious Diseases 71:1393–1399.

    https://doi.org/10.1093/cid/ciaa414

    • Google Scholar
14. 1. Kiperwasser E
    2. Goldberg Y

    (2016) Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

    Transactions of the Association for Computational Linguistics 4:313–327.

    https://doi.org/10.1162/tacl_a_00101

    • Google Scholar
15. 1. Kucharski AJ
    2. Russell TW
    3. Diamond C
    4. Liu Y
    5. Edmunds J
    6. Funk S
    7. Eggo RM
    8. Sun F
    9. Jit M
    10. Munday JD
    11. Davies N
    12. Gimma A
    13. van Zandvoort K
    14. Gibbs H
    15. Hellewell J
    16. Jarvis CI
    17. Clifford S
    18. Quilty BJ
    19. Bosse NI
    20. Abbott S
    21. Klepac P
    22. Flasche S

    (2020) Early dynamics of transmission and control of COVID-19: a mathematical modelling study

    The Lancet Infectious Diseases 20:553–558.

    https://doi.org/10.1016/S1473-3099(20)30144-4

    • Google Scholar
16. 1. Kuster GM
    2. Pfister O
    3. Burkard T
    4. Zhou Q
    5. Twerenbold R
    6. Haaf P
    7. Widmer AF
    8. Osswald S

    (2020) SARS-CoV2: should inhibitors of the renin–angiotensin system be withdrawn in patients with COVID-19?

    European Heart Journal 41:1801–1803.

    https://doi.org/10.1093/eurheartj/ehaa235

    • Google Scholar
17. 1. Lim WS
    2. Van der Eerden MM
    3. Laing R
    4. Boersma WG
    5. Karalus N
    6. Town GI
    7. Lewis SA
    8. Macfarlane JT

    (2003) Defining community acquired pneumonia severity on presentation to hospital: an international derivation and validation study

    Thorax 58:377–382.

    https://doi.org/10.1136/thorax.58.5.377

    • Google Scholar
18. Preprint

    1. Liu Y
    2. Ott M
    3. Goyal N
    4. Du J
    5. Joshi M
    6. Chen D
    7. Levy O
    8. Lewis M
    9. Zettlemoyer L
    10. Stoyanov V

    (2019) RoBERTa: a robustly optimized BERT pretraining approach

    arXiv.

    https://arxiv.org/abs/1907.11692

    • Google Scholar
19. 1. Mo P
    2. Xing Y
    3. Xiao Y
    4. Deng L
    5. Zhao Q
    6. Wang H
    7. Xiong Y
    8. Cheng Z
    9. Gao S
    10. Liang K
    11. Luo M
    12. Chen T
    13. Song S
    14. Ma Z
    15. Chen X
    16. Zheng R
    17. Cao Q
    18. Wang F
    19. Zhang Y

    (2020) Clinical characteristics of refractory COVID-19 pneumonia in Wuhan, China

    Clinical Infectious Diseases 1:ciaa270.

    https://doi.org/10.1093/cid/ciaa270

    • Google Scholar
20. 1. Onder G
    2. Rezza G
    3. Brusaferro S

    (2020) Case-Fatality rate and characteristics of patients dying in relation to COVID-19 in Italy

    Jama 323:1775–1776.

    https://doi.org/10.1001/jama.2020.4683

    • PubMed
    • Google Scholar
21. 1. Palaiodimos L
    2. Kokkinidis DG
    3. Li W
    4. Karamanis D
    5. Ognibene J
    6. Arora S
    7. Southern WN
    8. Mantzoros CS

    (2020) Severe obesity, increasing age and male sex are independently associated with worse in-hospital outcomes, and higher in-hospital mortality, in a cohort of patients with COVID-19 in the bronx, New York

    Metabolism 108:154262.

    https://doi.org/10.1016/j.metabol.2020.154262

    • PubMed
    • Google Scholar
22. 1. Patel AB
    2. Verma A

    (2020) Renin-Angiotensin-Aldosterone system inhibitors impact on COVID-19 mortality: what’s Next for ACE2?

    Clinical Infectious Diseases 323:ciaa627.

    https://doi.org/10.1093/cid/ciaa627

    • Google Scholar
23. 1. Richardson S
    2. Hirsch JS
    3. Narasimhan M
    4. Crawford JM
    5. McGinn T
    6. Davidson KW
    7. Barnaby DP
    8. Becker LB
    9. Chelico JD
    10. Cohen SL
    11. Cookingham J
    12. Coppa K
    13. Diefenbach MA
    14. Dominello AJ
    15. Duer-Hefele J
    16. Falzon L
    17. Gitlin J
    18. Hajizadeh N
    19. Harvin TG
    20. Hirschwerk DA
    21. Kim EJ
    22. Kozel ZM
    23. Marrast LM
    24. Mogavero JN
    25. Osorio GA
    26. Qiu M
    27. Zanos TP
    28. the Northwell COVID-19 Research Consortium

    (2020) Presenting characteristics, comorbidities, and outcomes among 5700 patients hospitalized with COVID-19 in the New York City area

    Jama 323:2052.

    https://doi.org/10.1001/jama.2020.6775

    • PubMed
    • Google Scholar
24. 1. Rossi GP
    2. Sanga V
    3. Barton M

    (2020) Potential harmful effects of discontinuing ACE-inhibitors and ARBs in COVID-19 patients

    eLife 9:e57278.

    https://doi.org/10.7554/eLife.57278

    • PubMed
    • Google Scholar
25. 1. Sprung CL
    2. Joynt GM
    3. Christian MD
    4. Truog RD
    5. Rello J
    6. Nates JL

    (2020) Adult ICU triage during the coronavirus disease 2019 pandemic: who will live and who will die? recommendations to improve survival

    Critical Care Medicine 48:1196–1202.

    https://doi.org/10.1097/CCM.0000000000004410

    • PubMed
    • Google Scholar
26. Website

    1. UMLS

    (2019) Unified medical language system (UMLS)

    Accessed October 10, 2020.

    https://www.nlm.nih.gov/research/umls/index.html
27. 1. Wang K
    2. Zuo P
    3. Liu Y
    4. Zhang M
    5. Zhao X
    6. Xie S
    7. Zhang H
    8. Chen X
    9. Liu C

    (2020) Clinical and laboratory predictors of in-hospital mortality in patients with COVID-19: a cohort study in Wuhan, China

    Clinical Infectious Diseases 1:ciaa538.

    https://doi.org/10.1093/cid/ciaa538

    • Google Scholar
28. 1. White DB
    2. Lo B

    (2020) A framework for rationing ventilators and critical care beds during the COVID-19 pandemic

    Jama 323:1773–1774.

    https://doi.org/10.1001/jama.2020.5046

    • PubMed
    • Google Scholar
29. 1. Wu S
    2. Du Z
    3. Shen S
    4. Zhang B
    5. Yang H
    6. Li X
    7. Cui W
    8. Chen F
    9. Huang J

    (2020) Identification and validation of a novel clinical signature to predict the prognosis in confirmed COVID-19 patients

    Clinical Infectious Diseases 1:ciaa793.

    https://doi.org/10.1093/cid/ciaa793

    • Google Scholar
30. 1. Yan L
    2. Zhang H-T
    3. Goncalves J
    4. Xiao Y
    5. Wang M
    6. Guo Y
    7. Sun C
    8. Tang X
    9. Jing L
    10. Zhang M
    11. Huang X
    12. Xiao Y
    13. Cao H
    14. Chen Y
    15. Ren T
    16. Wang F
    17. Xiao Y
    18. Huang S
    19. Tan X
    20. Huang N
    21. Jiao B
    22. Cheng C
    23. Zhang Y
    24. Luo A
    25. Mombaerts L
    26. Jin J
    27. Cao Z
    28. Li S
    29. Xu H
    30. Yuan Y

    (2020) An interpretable mortality prediction model for COVID-19 patients

    Nature Machine Intelligence 2:283–288.

    https://doi.org/10.1038/s42256-020-0180-7

    • Google Scholar
31. 1. Zaman MK
    2. White DA

    (1988) Serum lactate dehydrogenase levels and Pneumocystis carinii pneumonia. Diagnostic and prognostic significance

    American Review of Respiratory Disease 137:796–800.

    https://doi.org/10.1164/ajrccm/137.4.796

    • PubMed
    • Google Scholar
32. 1. Zhang P
    2. Zhu L
    3. Cai J
    4. Lei F
    5. Qin JJ
    6. Xie J
    7. Liu YM
    8. Zhao YC
    9. Huang X
    10. Lin L
    11. Xia M
    12. Chen MM
    13. Cheng X
    14. Zhang X
    15. Guo D
    16. Peng Y
    17. Ji YX
    18. Chen J
    19. She ZG
    20. Wang Y
    21. Xu Q
    22. Tan R
    23. Wang H
    24. Lin J
    25. Luo P
    26. Fu S
    27. Cai H
    28. Ye P
    29. Xiao B
    30. Mao W
    31. Liu L
    32. Yan Y
    33. Liu M
    34. Chen M
    35. Zhang XJ
    36. Wang X
    37. Touyz RM
    38. Xia J
    39. Zhang BH
    40. Huang X
    41. Yuan Y
    42. Loomba R
    43. Liu PP
    44. Li H

    (2020) Association of inpatient use of Angiotensin-Converting enzyme inhibitors and angiotensin II receptor blockers with mortality among patients with hypertension hospitalized with COVID-19

    Circulation Research 126:1671–1681.

    https://doi.org/10.1161/CIRCRESAHA.120.317134

    • PubMed
    • Google Scholar
33. Report

    1. Zhu H
    2. Paschalidis IC
    3. Tahmasebi A

    (2018)

    Clinical Concept Extraction with Contextual Word Embedding

    NeurIPS Machine Learning for Health Workshop.

    • Google Scholar

Author details

1. Boran Hao

   Center for Information and Systems Engineering, Boston University, Boston, United States

   Contribution

   Software, Formal analysis, Validation, Methodology, Writing - original draft

   Contributed equally with

   Shahabeddin Sotudian, Taiyao Wang and Tingting Xu

   Competing interests

   No competing interests declared

2. Shahabeddin Sotudian

   Center for Information and Systems Engineering, Boston University, Boston, United States

   Contribution

   Software, Formal analysis, Validation, Methodology, Writing - original draft

   Contributed equally with

   Boran Hao, Taiyao Wang and Tingting Xu

   Competing interests

   No competing interests declared

   "This ORCID iD identifies the author of this article:" 0000-0002-5864-6192

3. Taiyao Wang

   Center for Information and Systems Engineering, Boston University, Boston, United States

   Contribution

   Software, Formal analysis, Validation, Methodology, Writing - original draft

   Contributed equally with

   Boran Hao, Shahabeddin Sotudian and Tingting Xu

   Competing interests

   No competing interests declared

   "This ORCID iD identifies the author of this article:" 0000-0002-0331-3892

4. Tingting Xu

   Center for Information and Systems Engineering, Boston University, Boston, United States

   Contribution

   Software, Formal analysis, Validation, Methodology, Writing - original draft

   Contributed equally with

   Boran Hao, Shahabeddin Sotudian and Taiyao Wang

   Competing interests

   No competing interests declared

5. Yang Hu

   Center for Information and Systems Engineering, Boston University, Boston, United States

   Contribution

   Software, Formal analysis, Validation

   Competing interests

   No competing interests declared

6. Apostolos Gaitanidis

   Division of Trauma, Emergency Services, and Surgical Critical Care Massachusetts General Hospital, Harvard Medical School, Boston, United States

   Contribution

   Resources, Data curation, Software, Supervision, Validation, Investigation, Writing - review and editing

   Competing interests

   No competing interests declared

7. Kerry Breen

   Division of Trauma, Emergency Services, and Surgical Critical Care Massachusetts General Hospital, Harvard Medical School, Boston, United States

   Contribution

   Resources, Data curation, Validation, Investigation, Writing - review and editing

   Competing interests

   No competing interests declared

8. George C Velmahos

   Division of Trauma, Emergency Services, and Surgical Critical Care Massachusetts General Hospital, Harvard Medical School, Boston, United States

   Contribution

   Conceptualization, Resources, Supervision, Validation, Investigation, Project administration, Writing - review and editing

   Competing interests

   No competing interests declared

9. Ioannis Ch Paschalidis

   Center for Information and Systems Engineering, Boston University, Boston, United States

   Contribution

   Conceptualization, Resources, Formal analysis, Supervision, Funding acquisition, Validation, Investigation, Visualization, Methodology, Writing - original draft, Project administration, Writing - review and editing

   For correspondence

   yannisp@bu.edu

   Competing interests

   No competing interests declared

   "This ORCID iD identifies the author of this article:" 0000-0002-3343-2913

• 3,155

  Page views

• 279

  Downloads

• 41

  Citations

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