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

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

In COVID-19 clinical symptoms can persist even after negativization also in individuals who have had mild or moderate disease. We here investigated the biomarkers that define the post-COVID-19 clinical state analyzing the exhaled breath condensate (EBC) of 38 post COVID-19 patients and 38 sex and age-matched healthy controls via nuclear magnetic resonance (NMR)-based metabolomics. Predicted gene-modulated microRNAs (miRNAs) related to COVID-19 were quantified from EBC of 10 patients and 10 controls. Finally, clinical parameters from all post-COVID-19 patients were correlated with metabolomic data. Post-COVID-19 patients and controls showed different metabolic phenotype ("metabotype"). From the metabolites, by using enrichment analysis we identified miRNAs that resulted up-regulated (hsa-miR146a-5p) and down-regulated (hsa-miR-126-3p and hsa-miR-223-3p) in post-COVID-19. Taken together, our multiomics data indicate that post-COVID-19 patients before rehabilitation are characterized by persistent inflammation, dysregulation of liver, endovascular thrombotic and pulmonary processes, and physical impairment, which should be the primary clinical targets to contrast the post-acute sequelae of COVID-19.

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

Background

Post-COVID-19 syndrome (PCS) has been increasingly recognized as an emerging problem: 50% of patients report ongoing symptoms 1 year after acute infection, with most typical manifestations (fatigue, dyspnea, psychiatric and neurological symptoms) having potentially debilitating effect. Early identification of high-risk candidates for PCS development would facilitate the optimal use of resources directed to rehabilitation of COVID-19 convalescents.

Objective

To study the in-hospital clinical characteristics of COVID-19 survivors presenting with self-reported PCS at 3 months and to identify the early predictors of its development.

Methods

221 hospitalized COVID-19 patients underwent symptoms assessment, 6-min walk test, and echocardiography pre-discharge and at 1 month; presence of PCS was assessed 3 months after discharge. Unsupervised machine learning was used to build a SANN-based binary classification model of PCS development.

Results

PCS at 3 months has been detected in 75% patients. Higher symptoms level in the PCS group was not associated with worse physical functional recovery or significant echocardiographic changes. Despite identification of a set of pre-discharge predictors, inclusion of parameters obtained at 1 month proved necessary to obtain a high accuracy model of PCS development, with inputs list including age, sex, in-hospital levels of CRP, eGFR and need for oxygen supplementation, and level of post-exertional symptoms at 1 month after discharge (fatigue and dyspnea in 6MWT and MRC Dyspnea score).

Conclusion

Hospitalized COVID-19 survivors at 3 months were characterized by 75% prevalence of PCS, the development of which could be predicted with an 89% accuracy using the derived neural network-based classification model.