Personalized prescription of ACEI/ARBs for hypertensive COVID-19 patients

The COVID-19 pandemic has prompted an international effort to develop and repurpose medications and procedures to effectively combat the disease. Several groups have focused on the potential treatment utility of angiotensin-converting-enzyme inhibitors (ACEIs) and angiotensin-receptor blockers (ARBs) for hypertensive COVID-19 patients, with inconclusive evidence thus far. We couple electronic medical record (EMR) and registry data of 3,643 patients from Spain, Italy, Germany, Ecuador, and the US with a machine learning framework to personalize the prescription of ACEIs and ARBs to hypertensive COVID-19 patients. Our approach leverages clinical and demographic information to identify hospitalized individuals whose probability of mortality or morbidity can decrease by prescribing this class of drugs. In particular, the algorithm proposes increasing ACEI/ARBs prescriptions for patients with cardiovascular disease and decreasing prescriptions for those with low oxygen saturation at admission. We show that personalized recommendations can improve patient outcomes by 1.0% compared to the standard of care when applied to external populations. We develop an interactive interface for our algorithm, providing physicians with an actionable tool to easily assess treatment alternatives and inform clinical decisions. This work offers the first personalized recommendation system to accurately evaluate the efficacy and risks of prescribing ACEIs and ARBs to hypertensive COVID-19 patients.

[1]  N. Paneth,et al.  Seven Questions for Personalized Medicine. , 2015, JAMA.

[2]  D. Zeldin,et al.  Good or bad: Application of RAAS inhibitors in COVID-19 patients with cardiovascular comorbidities , 2020, Pharmacology & Therapeutics.

[3]  A. Troxel,et al.  Renin–Angiotensin–Aldosterone System Inhibitors and Risk of Covid-19 , 2020, The New England journal of medicine.

[4]  Harry Zhang,et al.  The Optimality of Naive Bayes , 2004, FLAIRS.

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[7]  Alfonso Valencia,et al.  Big data analytics for personalized medicine. , 2019, Current opinion in biotechnology.

[8]  Susan Athey,et al.  Recursive partitioning for heterogeneous causal effects , 2015, Proceedings of the National Academy of Sciences.

[9]  Jeffrey Dean,et al.  Machine Learning in Medicine , 2019, The New England journal of medicine.

[10]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[11]  T. Lumley,et al.  Antihypertensive treatment with ACE inhibitors or beta-blockers and risk of incident atrial fibrillation in a general hypertensive population. , 2009, American journal of hypertension.

[12]  Yan Zhao,et al.  Neutrophil-to-lymphocyte ratio as an independent risk factor for mortality in hospitalized patients with COVID-19 , 2020, Journal of Infection.

[13]  S. Murphy,et al.  PERFORMANCE GUARANTEES FOR INDIVIDUALIZED TREATMENT RULES. , 2011, Annals of statistics.

[14]  C. Granger,et al.  Continuing versus suspending angiotensin-converting enzyme inhibitors and angiotensin receptor blockers: Impact on adverse outcomes in hospitalized patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)--The BRACE CORONA Trial , 2020, American Heart Journal.

[15]  Dimitris Bertsimas,et al.  Optimal Prescriptive Trees , 2019, INFORMS J. Optim..

[16]  Stef van Buuren,et al.  MICE: Multivariate Imputation by Chained Equations in R , 2011 .

[17]  Erwan L'Her,et al.  Compassionate Use of Remdesivir for Patients with Severe Covid-19 , 2020, The New England journal of medicine.

[18]  Dimitris Bertsimas,et al.  Optimal classification trees , 2017, Machine Learning.

[19]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[20]  P. Austin.  An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies , 2011, Multivariate behavioral research.

[21]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[22]  C. Macaya,et al.  Health Outcome Predictive Evaluation for COVID 19 international registry (HOPE COVID-19), rationale and design , 2020, Contemporary Clinical Trials Communications.

[23]  Qiurong Ruan,et al.  Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan, China , 2020, Intensive Care Medicine.

[24]  F. Collins,et al.  The path to personalized medicine. , 2010, The New England journal of medicine.

[25]  Yi Wang,et al.  Remdesivir in adults with severe COVID-19: a randomised, double-blind, placebo-controlled, multicentre trial , 2020, The Lancet.

[26]  H. Rothan,et al.  The epidemiology and pathogenesis of coronavirus disease (COVID-19) outbreak , 2020, Journal of Autoimmunity.

[27]  Joshua D. Angrist,et al.  Identification of Causal Effects Using Instrumental Variables , 1993 .

[28]  Takuya Akiba,et al.  Optuna: A Next-generation Hyperparameter Optimization Framework , 2019, KDD.

[29]  C. E..  WHO Coronavirus Disease (COVID-19) Dashboard , 2020 .

[30]  D. Rubin.  Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[31]  D. Raoult,et al.  Hydroxychloroquine and azithromycin as a treatment of COVID-19: results of an open-label non-randomized clinical trial , 2020, International Journal of Antimicrobial Agents.

[32]  Yanbing Ding,et al.  The epidemiology, diagnosis and treatment of COVID-19 , 2020, International Journal of Antimicrobial Agents.

[33]  Dimitris Bertsimas,et al.  Personalized treatment for coronary artery disease patients: a machine learning approach , 2019, Health Care Management Science.

[34]  M. Esler,et al.  Can angiotensin receptor-blocking drugs perhaps be harmful in the COVID-19 pandemic? , 2020, Journal of hypertension.

[35]  T. Jodlowski,et al.  Pharmacologic Treatments for Coronavirus Disease 2019 (COVID-19): A Review. , 2020, JAMA.

[36]  L. Dodd,et al.  Remdesivir for the Treatment of Covid-19 — Final Report , 2020, The New England journal of medicine.

[37]  D. Bertsimas,et al.  Ensemble machine learning for personalized antihypertensive treatment , 2021, Naval Research Logistics (NRL).

[38]  Hugh Chen,et al.  From local explanations to global understanding with explainable AI for trees , 2020, Nature Machine Intelligence.

[39]  W. Liang,et al.  Risk Factors of Fatal Outcome in Hospitalized Subjects With Coronavirus Disease 2019 From a Nationwide Analysis in China , 2020, Chest.

[40]  Nathan Kallus,et al.  Recursive Partitioning for Personalization using Observational Data , 2016, ICML.

[41]  Juan Pablo Vielma,et al.  Building Representative Matched Samples With Multi-Valued Treatments in Large Observational Studies , 2018, Journal of Computational and Graphical Statistics.

[42]  Qingbo Xu,et al.  Association of Inpatient Use of Angiotensin-Converting Enzyme Inhibitors and Angiotensin II Receptor Blockers With Mortality Among Patients With Hypertension Hospitalized With COVID-19 , 2020, Circulation research.

[43]  G. Hripcsak,et al.  Observational Study of Hydroxychloroquine in Hospitalized Patients with Covid-19 , 2020, The New England journal of medicine.

[44]  Jing Shi,et al.  Risk factors for severity and mortality in adult COVID-19 inpatients in Wuhan , 2020, Journal of Allergy and Clinical Immunology.

[45]  Ying Daisy Zhuo,et al.  Personalized Diabetes Management Using Electronic Medical Records , 2016, Diabetes Care.

[46]  E. Schiffrin,et al.  Hypertension and COVID-19 , 2020, American journal of hypertension.

[47]  Emily G McDonald,et al.  A Randomized Trial of Hydroxychloroquine as Postexposure Prophylaxis for Covid-19 , 2020, The New England journal of medicine.

[48]  C. Lavie,et al.  Should atrial fibrillation be considered a cardiovascular risk factor for a worse prognosis in COVID-19 patients? , 2020, European heart journal.

[49]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[50]  S. Groshen,et al.  A multivariate analysis of genomic polymorphisms: prediction of clinical outcome to 5-FU/oxaliplatin combination chemotherapy in refractory colorectal cancer , 2004, British Journal of Cancer.

[51]  Stefan Wager,et al.  Estimation and Inference of Heterogeneous Treatment Effects using Random Forests , 2015, Journal of the American Statistical Association.

[52]  World Health Organisation.  COVID-19 and the use of angiotensin-converting enzyme inhibitors and receptor blockers. Scientific Brief , 2020, Pediatria i Medycyna Rodzinna.

[53]  M L Feldstein,et al.  A statistical model for predicting response of breast cancer patients to cytotoxic chemotherapy. , 1978, Cancer research.

[54]  G. Herrler,et al.  SARS-CoV-2 Cell Entry Depends on ACE2 and TMPRSS2 and Is Blocked by a Clinically Proven Protease Inhibitor , 2020, Cell.

[55]  Jian Chen,et al.  Association of Renin-Angiotensin System Inhibitors With Severity or Risk of Death in Patients With Hypertension Hospitalized for Coronavirus Disease 2019 (COVID-19) Infection in Wuhan, China. , 2020, JAMA cardiology.

[56]  Allan Schwartz,et al.  COVID-19 and Cardiovascular Disease , 2020, Circulation.

[57]  Harald H H W Schmidt,et al.  Gender differences in the effect of cardiovascular drugs: a position document of the Working Group on Pharmacology and Drug Therapy of the ESC. , 2015, European heart journal.

[58]  Jennifer L. Bell,et al.  Effect of Dexamethasone in Hospitalized Patients with COVID-19: Preliminary Report , 2020, medRxiv.

[59]  G. Mancia,et al.  Renin–Angiotensin–Aldosterone System Blockers and the Risk of Covid-19 , 2020, The New England journal of medicine.

[60]  D. Rubin.  [On the Application of Probability Theory to Agricultural Experiments. Essay on Principles. Section 9.] Comment: Neyman (1923) and Causal Inference in Experiments and Observational Studies , 1990 .

[61]  David B. Lewis,et al.  COVID-19 and cardiovascular disease: from basic mechanisms to clinical perspectives , 2020, Nature Reviews Cardiology.