Data-driven methodology for discovery and response to pulmonary symptomology in hypertension through statistical learning and data mining: Application to COVID-19 related pharmacovigilance

  1. Xuan Xu
  2. Jessica Kawakami
  3. Nuwan Indika Millagaha Gedara
  4. Jim Riviere
  5. Emma Meyer
  6. Gerald J Wyckoff
  7. Majid Jaberi-Douraki  Is a corresponding author
  1. Kansas State University, United States
  2. University of Missouri-Kansas City, United States

Abstract

Background: Potential therapy and confounding factors including typical co‐administered medications, patient's disease states, disease prevalence, patient demographics, medical histories, and reasons for prescribing a drug often are incomplete, conflicting, missing, or uncharacterized in spontaneous adverse drug event (ADE) reporting systems. These missing or incomplete features can affect and limit the application of quantitative methods in pharmacovigilance for meta-analyses of data during randomized clinical trials.

Methods: Data from patients with hypertension were retrieved and integrated from the FDA Adverse Event Reporting System. 134 antihypertensive drugs out of 1151 drugs were filtered and then evaluated using the Empirical Bayes Geometric Mean (EBGM) of the posterior distribution to build ADE-drug profiles with an emphasis on the pulmonary ADEs (pADE). Afterward, the Graphical Least Absolute Shrinkage and Selection Operator (GLASSO) captured drug associations based on pADEs by correcting hidden factors and confounder misclassification. Selected drugs were then compared using the Friedman test in drug classes and clusters obtained from GLASSO.

Results: Following multiple filtering stages to exclude insignificant and noise-driven reports, we found that drugs from antihypertensives agents, urologicals, and antithrombotic agents (macitentan, bosentan, epoprostenol, selexipag, sildenafil, tadalafil, and beraprost) form a similar class with a significantly higher incidence of pADEs. Macitentan and bosentan were associates with 64% and 56% of pADEs, respectively. Because these two medications are prescribed in diseases affecting pulmonary function and may be likely to emerge among the highest reported pADEs, in fact, they serve to validate the methods utilized here. Conversely, doxazosin and rilmenidine were found to have the least pADEs in selected drugs from hypertension patients. Nifedipine and candesartan were also found by signal detection methods to form a drug cluster, shown by several studies an effective combination of these drugs on lowering blood pressure and appeared an improved side effect profile in comparison with single-agent monotherapy.

Conclusions: We consider pADE profiles in multiple long-standing groups of therapeutics including antihypertensive agents, antithrombotic agents, beta-blocking agents, calcium channel blockers, or agents acting on the renin-angiotensin system, in patients with hypertension associated with high-risk for COVID-19. We found that several individual drugs have significant differences between their drug classes and compared to other drug classes. For instance, macitentan and bosentan from endothelin receptor antagonists show major concern while doxazosin and rilmenidine exhibited the least pADEs compared to the outcomes of other drugs. Using techniques in this study, we assessed and confirmed the hypothesis that drugs from the same drug class could have very different pADE profiles affecting outcomes in acute respiratory illness.

Funding: GJW and MJD accepted funding from BioNexus KC for funding on this project, but BioNexus KC had no direct role in this article.

Data availability

The source code and data used to produce results and analyses presented in this manuscript areavailable at:https://1data.life/pages/publication/data_driven_methodology_COVID19_related_pharmacovigilance/

The following previously published data sets were used

Article and author information

Author details

  1. Xuan Xu

    Department of Mathematics, Kansas State University, Olathe, United States
    Competing interests
    The authors declare that no competing interests exist.
  2. Jessica Kawakami

    School of Pharmacy, University of Missouri-Kansas City, Kansas City, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-7141-5698
  3. Nuwan Indika Millagaha Gedara

    Department of Mathematics, Kansas State University, Olathe, United States
    Competing interests
    The authors declare that no competing interests exist.
  4. Jim Riviere

    Department of Mathematics, Kansas State University, Olathe, United States
    Competing interests
    The authors declare that no competing interests exist.
  5. Emma Meyer

    Molecular Biology and Biochemistry, University of Missouri-Kansas City, Kansas City, United States
    Competing interests
    The authors declare that no competing interests exist.
  6. Gerald J Wyckoff

    Molecular Biology and Biochemistry, University of Missouri-Kansas City, Kansas City, United States
    Competing interests
    The authors declare that no competing interests exist.
  7. Majid Jaberi-Douraki

    Department of Mathematics, Kansas State University, Olathe, United States
    For correspondence
    jaberi@k-state.edu
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-8505-6550

Funding

BioNexus KC (20-7)

  • Gerald J Wyckoff
  • Majid Jaberi-Douraki

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Reviewing Editor

  1. Arduino A Mangoni, Flinders Medical Centre, Australia

Version history

  1. Received: May 27, 2021
  2. Preprint posted: June 12, 2021 (view preprint)
  3. Accepted: November 21, 2021
  4. Accepted Manuscript published: November 23, 2021 (version 1)
  5. Version of Record published: January 12, 2022 (version 2)

Copyright

© 2021, Xu et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 1,051
    Page views
  • 198
    Downloads
  • 4
    Citations

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

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Xuan Xu
  2. Jessica Kawakami
  3. Nuwan Indika Millagaha Gedara
  4. Jim Riviere
  5. Emma Meyer
  6. Gerald J Wyckoff
  7. Majid Jaberi-Douraki
(2021)
Data-driven methodology for discovery and response to pulmonary symptomology in hypertension through statistical learning and data mining: Application to COVID-19 related pharmacovigilance
eLife 10:e70734.
https://doi.org/10.7554/eLife.70734

Share this article

https://doi.org/10.7554/eLife.70734

Further reading

    1. Cell Biology
    2. Computational and Systems Biology
    Thomas Grandits, Christoph M Augustin ... Alexander Jung
    Research Article

    Computer models of the human ventricular cardiomyocyte action potential (AP) have reached a level of detail and maturity that has led to an increasing number of applications in the pharmaceutical sector. However, interfacing the models with experimental data can become a significant computational burden. To mitigate the computational burden, the present study introduces a neural network (NN) that emulates the AP for given maximum conductances of selected ion channels, pumps, and exchangers. Its applicability in pharmacological studies was tested on synthetic and experimental data. The NN emulator potentially enables massive speed-ups compared to regular simulations and the forward problem (find drugged AP for pharmacological parameters defined as scaling factors of control maximum conductances) on synthetic data could be solved with average root-mean-square errors (RMSE) of 0.47 mV in normal APs and of 14.5 mV in abnormal APs exhibiting early afterdepolarizations (72.5% of the emulated APs were alining with the abnormality, and the substantial majority of the remaining APs demonstrated pronounced proximity). This demonstrates not only very fast and mostly very accurate AP emulations but also the capability of accounting for discontinuities, a major advantage over existing emulation strategies. Furthermore, the inverse problem (find pharmacological parameters for control and drugged APs through optimization) on synthetic data could be solved with high accuracy shown by a maximum RMSE of 0.22 in the estimated pharmacological parameters. However, notable mismatches were observed between pharmacological parameters estimated from experimental data and distributions obtained from the Comprehensive in vitro Proarrhythmia Assay initiative. This reveals larger inaccuracies which can be attributed particularly to the fact that small tissue preparations were studied while the emulator was trained on single cardiomyocyte data. Overall, our study highlights the potential of NN emulators as powerful tool for an increased efficiency in future quantitative systems pharmacology studies.

    1. Computational and Systems Biology
    2. Neuroscience
    Domingos Leite de Castro, Miguel Aroso ... Paulo Aguiar
    Research Article Updated

    Closed-loop neuronal stimulation has a strong therapeutic potential for neurological disorders such as Parkinson’s disease. However, at the moment, standard stimulation protocols rely on continuous open-loop stimulation and the design of adaptive controllers is an active field of research. Delayed feedback control (DFC), a popular method used to control chaotic systems, has been proposed as a closed-loop technique for desynchronisation of neuronal populations but, so far, was only tested in computational studies. We implement DFC for the first time in neuronal populations and access its efficacy in disrupting unwanted neuronal oscillations. To analyse in detail the performance of this activity control algorithm, we used specialised in vitro platforms with high spatiotemporal monitoring/stimulating capabilities. We show that the conventional DFC in fact worsens the neuronal population oscillatory behaviour, which was never reported before. Conversely, we present an improved control algorithm, adaptive DFC (aDFC), which monitors the ongoing oscillation periodicity and self-tunes accordingly. aDFC effectively disrupts collective neuronal oscillations restoring a more physiological state. Overall, these results support aDFC as a better candidate for therapeutic closed-loop brain stimulation.