Machine Learning as a Precision-Medicine Approach to Prescribing COVID-19 Pharmacotherapy with Remdesivir or Corticosteroids

Abstract

Purpose : Coronavirus Disease 2019 ( COVID-19) continues to be a global threat and remains a significant cause of hospitalizations. Recent clinical guidelines have supported the use of corticosteroids and remdesivir in the treatment of COVID-19. However, uncertainty remains about which patients are most likely to benefit from treatment with either drug; such knowledge is crucial for avoiding preventable side effects, minimizing costs, and effectively allocating resources. This study presents a machine learning system capable of identifying patients for whom treatment with corticosteroids or remdesivir is associated with improved survival time. Methods : Gradient boosted decision tree models to predict treatment benefit were trained and tested on data from patients hospitalized at 10 hospitals in the United States between December 18, 2019 and October 18, 2020. 893 patients were treated with remdesivir, and 1,471 were treated with corticosteroids. Models were evaluated for their ability to identify patients that exhibited longer survival times when treated with corticosteroids or remdesivir. Fine and Gray models for the proportional hazard were evaluated comparing treated and untreated patients in the full COVID-19 population, in patients receiving supplemental oxygen, and in patients identified by the algorithm. Inverse probability of treatment weights were used to adjust for confounding. Models for each treatment were trained and tested separately. Findings : .Adult patients (age ≥ 18) were included in this study, with men comprising slightly more than 50% of the sample. After adjusting for confounding, neither corticosteroids nor remdesivir were associated with increased survival time in the full hospitalized COVID-19 population or in the population receiving supplemental oxygen. However, in the populations identified by the algorithms, both corticosteroids and remdesivir were significantly associated with an increase in survival time, with hazard ratios of 0.56 (p = 0.04) and 0.40 (p = 0.04), respectively Implications : Machine learning methods are capable of identifying hospitalized COVID-19 patients for whom treatment with corticosteroids or remdesivir is associated with an increase in survival time. These methods may help improve patient outcomes and allocate resources during the COVID-19 crisis.

Machine Learning for Real-World Evidence Analysis of COVID-19 Pharmacotherapy

“…For remdesivir and tocilizumab, the only models where survival analysis yielded statistically significant results in the test set and were trusted after the futility analysis, the AUC degraded from 0.83 to 0.74 from validation to test set. Nonetheless, the ML model performance for Remdesivir was higher than the previously reported AUC of 0.57 [Lam et al, 2021], even if the AUCs obtained on the present study, 0.83 and 0.73 in validation and test set respectively, still did not reach the commonly accepted threshold of an AUC > 0.85 considered as reasonable decision making. For both drugs studied by Lam et al [2021], Remdesivir and Corticosteroids the direction and magnitude of treatment effects as well as the behaviour after model adjustment was similar, strengthening the evidence for the robustness of this ML-approach as well as the replicability of results.…”

“…[2021] using a binomial logistic objective that defined a positive class (improved disease if treated vs worsened disease if not treated) and a negative class (worsened disease if treated vs improved disease if not treated). Lam et al [2021] defined improved disease as a last recorded oxygen saturation of >= 95%, or survival (i.e. discharged alive), and worsened disease was defined as a last recorded oxygen saturation of < 95%, or death.…”

“…On this study, we aim to 1) contribute to the validation of RCTs on the effectiveness of most common COVID-19 pharmacotherapy, helping to identify the patient profiles based on their responsiveness to treatment using readily available data derived from electronic health records (EHRs), 2) follow a methodology widely accepted and successfully applied in a prior study on RWE of COVID-19 therapies Lam et al [2021] to investigate if their results on the effectiveness of remdesivir and corticosteroids are reproducible in a different population 3) apply the same methods to extend the RWE on other common COVID-19 pharmacotherapy and 4) enrich those experimental approaches in terms of explainability, futility and additive testing and negative treatment effect.…”

CT Diagnosis of COVID-19: A View through the PICOTS Lens

“…The availability and widespread initial distribution of an effective vaccine less than one year after the emergence of the pathogen have been a triumph of modern science. Refinements to the diagnosis and management of COVID-19 have substantially improved outcomes for hospitalized patients since disease surges overtook healthcare delivery systems in New York, Wuhan, and Northern Italy in the late winter of 2020 (2,3).…”

Personalized Preventive Corticosteroid Medication Recommendation System for Postacute COVID-19 Treatment

“…It is the goal of several works that have focused on predicting the benefits of CS treatment. Work [12] proposes a machine learning-based approach which identifies patients for whom treatment with a CS or remdesivir will increase survival time. The method is based on the Gradient-boosted decisiontree model.…”