A Machine Learning Approach to Predict the Rehabilitation Outcome in Convalescent COVID-19 Patients

Abstract

Background: After the acute disease, convalescent coronavirus disease 2019 (COVID-19) patients may experience several persistent manifestations that require multidisciplinary pulmonary rehabilitation (PR). By using a machine learning (ML) approach, we aimed to evaluate the clinical characteristics predicting the effectiveness of PR, expressed by an improved performance at the 6-min walking test (6MWT). Methods: Convalescent COVID-19 patients referring to a Pulmonary Rehabilitation Unit were consecutively screened. The 6MWT performance was partitioned into three classes, corresponding to different degrees of improvement (low, medium, and high) following PR. A multiclass supervised classification learning was performed with random forest (RF), adaptive boosting (ADA-B), and gradient boosting (GB), as well as tree-based and k-nearest neighbors (KNN) as instance-based algorithms. Results: To train and validate our model, we included 189 convalescent COVID-19 patients (74.1% males, mean age 59.7 years). RF obtained the best results in terms of accuracy (83.7%), sensitivity (84.0%), and area under the ROC curve (94.5%), while ADA-B reached the highest specificity (92.7%). Conclusions: Our model enables a good performance in predicting the rehabilitation outcome in convalescent COVID-19 patients.

A prognostic model and pre-discharge predictors of post-COVID-19 syndrome after hospitalization for SARS-CoV-2 infection

“…The difficulties in predicting the development of post-COVID-19 syndrome might be related to the heterogenous underlying mechanisms, differences in vaccination status at the population level, and the constantly changing landscape of temporarily and locally prevailing SARS-CoV-2 variants. The literature search has allowed us to identify several finished studies proposing tools for predicting the outcomes of the acute phase of disease ( 43 ), effects of post COVID-19 rehabilitation ( 44 ), development of post-acute cardiovascular complications ( 45 ), and dynamics of the radiological recovery ( 46 ). Additionally, we have identified a published protocol of the study directed at solving the problem of predicting the development of the long COVID syndrome ( 47 ).…”

The biomarkers’ landscape of post-COVID-19 patients can suggest selective clinical interventions

“…The rehabilitation (a 5-week exercise-based program of 6 sessions/week (30 sessions)) protocol followed the official ATS/ERS guidelines (Supplementary Information) 86 . In brief, patients undertook a 5-week exercise-based program of 6 sessions/week (30 sessions).…”