A Hybrid Model-Based Recursive Partitioning Framework for Subgroup Analysis Using Semiparametric and Non-Parametric Competing Risk Models in Covid-19 Hospitalizations Publisher



Rezaei Ghahroodi Z ; Eftekhari Mahabadi S ; Momeni Roochi E ; Arashi M ; Mansourian M
Source: Statistics in Biosciences Published:2026

Abstract

Hospital medications can significantly influence patient recovery and length of stay (LoS) in COVID-19, highlighting the need to understand drug effects in diverse patient subgroups. Therefore, identifying drug interactions and the types of medications administered during hospitalization is crucial, as it can be associated with LoS, and reducing the length of hospitalization can lead to improved hospital service delivery. We analyzed a prospective cohort of 1998 COVID-19 patients hospitalized at Khorshid Hospital, Iran (February 2020–February 2021), using an innovative hybrid modeling approach. Our framework combines model-based recursive partitioning (MOB trees) with (1) semiparametric Fine–Gray (FG) models for interpretable covariate effect estimation and (2) non-parametric Generalized Additive Models for competing risks (GAM-CR) to model complex nonlinear medication effects. This dual modeling strategy, building upon rigorous feature selection, successfully identified clinically meaningful patient subgroups with differential treatment responses, enabling personalized assessment of LoS based on individual medication regimens and clinical characteristics. The results indicate that the hospital LoS among severe patients is about 3 days, significantly higher than in non-severe patients (p-value < 0.05). Moreover, the effect of average daily medication dosage on LoS varies notably across four clinical subgroups. MOB tree analysis using FG model (FG-MOB) indicated that older age consistently prolonged hospitalization across all patient subgroups, reducing the probability of discharge by approximately 1–1.3% per year. The use of potent medications, including antibiotics such as linezolid and vancomycin, and the antiviral caltera, was a key predictor of delayed discharge, reflecting treatment intensity in more severe cases. Notably, in severe patients without underlying disease, average daily dosage of doxycycline was associated with a 22% higher probability of discharge, suggesting a potentially favorable response. Non-linear GAM-CR using the MOB tree (GAM-MOB-CR) analyses revealed that medication effects on LoS were highly context-dependent: intermediate to high doses of vancomycin, methylprednisolone, and interferon B were associated with longer stays, whereas higher doses of heparin and ceftriaxone corresponded to shorter hospitalization. These patterns predominantly reflect underlying patient severity and clinical complexity rather than direct pharmacological effects, particularly for medications reserved for critically ill patients or those with complicated infections. Overall, observed drug dosing patterns serve as robust proxies for disease severity and clinical context, underscoring the importance of accounting for confounding by indication when interpreting observational treatment outcomes. These findings advocate for tailored treatment strategies to optimize hospital stays and resource use, with direct implications for pandemic preparedness. © The Author(s) under exclusive licence to International Chinese Statistical Association 2026.