A machine learning model exploring the relationship between chronic medication and COVID-19 clinical outcomes

Abstract

ACE inhibitors; ARBs; COVID-19; HMG-CoA reductase; Machine learning; Metformin; Mortality; Polypharmacy; Prediction models

Inhibidores de la ECA; ARA II; COVID-19; HMG-CoA reductasa; Aprendizaje automático; Metformina; Mortalidad; Polifarmacia; Modelos de predicción

Inhibidors de l'ECA; ARA II; COVID-19; HMG-CoA reductasa; Aprenentatge automàtic; Metformina; Mortalitat; Polifarmàcia; Models de predicció:ca_ES

The impact of chronic medication on COVID-19 outcomes has been a topic of ongoing debate since the onset of the pandemic. Investigating how specific long-term treatments influence infection severity and prognosis is essential for optimising patient management and care.

This study aimed to investigate the association between chronic medication and COVID-19 outcomes, using machine learning to identify key medication-related factors.

We analysed 137,835 COVID-19 patients in Catalonia (February-September 2020) using eXtreme Gradient Boosting to predict hospitalisation, ICU admission, and mortality. This was complemented by univariate logistic regression analyses and a sensitivity analysis focusing on diabetes, hypertension, and lipid disorders.

Participants had a mean age of 53 (SD 20) years, with 57% female. The best model predicted mortality risk in 18 to 65-year-olds (AUCROC 0.89, CI 0.85-0.92). Key features identified included the number of prescribed drugs, systemic corticoids, 3-hydroxy-3-methylglutaryl coenzyme A (HMG-CoA) reductase, and hypertension drugs. A sensitivity analysis identified that hypertensive participants over 65 taking angiotensin-converting enzyme (ACE) inhibitors or angiotensin II receptor blockers (ARBs) had lower mortality risk (OR 0.78 CI 0.68-0.92) compared to those on other antihypertensive medication (OR 0.8 CI 0.68-0.95). Treatment with inhibitors of dipeptidyl peptidase 4 was associated to higher mortality in participants aged 18-65, while metformin showed a protective effect in those over 65 (OR 0.79, 95% CI 0.68-0.92).

Machine learning models effectively distinguished COVID-19 outcomes. Patients under ACEi or ARBs or biguanides should continue their prescribed medications, which may offer protection over alternative treatments.

Funding Open Access Funding provided by Universitat Autonoma de Barcelona. This study was supported by the Spanish Foundation for Hospital Pharmacy (FEFH) and the Spanish Society of Hospital Pharmacy (SEFH) through the call for research grants 2022-2023. The Agency for Health Quality and Assessment of Catalonia (AQuaS) provided two data scientists for extracting, cleaning, merging and anonymizing the data from institutional databases for the development of this project. ASM is supported by a Juan Rodés (JR18/00022) postdoctoral fellowship from ISCIII. ASP is supported by the Spanish Ministerio de Ciencia e Innovación, grant PID2019-104830RB-I00, and by the Departament d’Economia i Coneixement de la Generalitat de Catalunya, grant 2021SGR01421 (GRBIO). The funding sources had no involvement in any aspect of this manuscript