Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : In face of the current SARS-COV-2 pandemic, the timely prediction of upcoming medical needs for infected individuals enables a better and quicker care provision when necessary and management decisions within health care systems.

OBJECTIVE : This work aims to predict medical needs (hospitalizations, ICU admission, respiratory assistance) and survivability of individuals testing SARS-CoV-2 positive using a retrospective cohort with 38.545 infected individuals in Portugal during 2020.

METHODS : Predictions of medical needs are performed using state-of-the-art machine learning approaches at various stages of a patient's cycle, namely: testing time (pre-hospitalization), post-hospitalization, and post-intensive care. A thorough optimization of state-of-the-art predictors is undertaken to assess the ability to anticipate medical needs and infection outcomes using demographic and comorbidity variables, as well as onset date of symptoms, test and hospitalization.

RESULTS : For the target cohort, 75% of hospitalization needs can be identified at the SARS-CoV-2 testing time and over 60% respiratory needs at hospitalization time, both with >50% precision.

CONCLUSIONS : The conducted study pinpoints the relevance of the proposed predictive models as good candidates to support medical decisions for the Portuguese population, including both monitoring and in-hospital care decisions. A clinical decision support system (CDSS) is further provided to this end.

CLINICALTRIAL :

Patrício André, Costa Rafael S, Henriques Rui

2021-Mar-18