The lack of standardized techniques for processing complex health data from COVID-19 patients hinders the development of accurate predictive models in healthcare. To address this, we present a protocol for utilizing real-world multivariate time-series electronic health records of COVID-19 patients. We describe steps for covering the necessary setup, data standardization, and formatting. We then provide detailed instructions for creating datasets and for training and evaluating AI models designed to predict two key outcomes: in-hospital mortality and length of stay. For complete details on the use and execution of this protocol, please refer to Gao et al..

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.xpro.2025.103669DOI Listing

Publication Analysis

Top Keywords

covid-19 patients
12
multivariate time-series
8
time-series electronic
8
electronic health
8
health records
8
records covid-19
8
protocol processing
4
processing multivariate
4
patients lack
4
lack standardized
4

Similar Publications

Background: Telenursing has become prevalent in providing care to diverse populations experiencing different health conditions both in Israel and globally. The nurse-patient relationship aims to improve the condition of individuals requiring health services.

Objectives: This study aims to evaluate nursing graduates' skills and knowledge regarding remote nursing care prior to and following a simulation-based telenursing training program in an undergraduate nursing degree.

View Article and Find Full Text PDF

Assessment of patient safety from their perspective during the COVID-19 pandemic.

Rev Gaucha Enferm

March 2025

Universidade Federal de São Paulo (UNIFESP), Escola Paulista de Enfermagem. Departamento de Administração em Serviços de Saúde e Enfermagem. São Paulo, São Paulo, Brasil.

Objective: to assess patient safety, from their own perspective, during hospitalization for COVID-19 in a university hospital.

Method: cross-sectional study conducted in a university hospital in São Paulo, Brazil, involving patients hospitalized due to COVID-19. The sample included 129 participants hospitalized between March 2020 and June 2021 who responded to the Patient Measure of Safety instrument.

View Article and Find Full Text PDF

Prevalence and Factors Associated With Hepatitis C Virus in Riyadh, Saudi Arabia: A Large Cross-Sectional Study.

J Epidemiol Glob Health

March 2025

Department of Public Health, College of Public Health and Health Informatics, King Saud Bin Abdulaziz University for Health Sciences, Riyadh, Saudi Arabia.

Introduction: Viral hepatitis stands accountable for approximately 1.34 million deaths worldwide, with the number of fatalities steadily growing with time. This is partly due to the various genotypes of hepatitis C virus and having no vaccination developed yet.

View Article and Find Full Text PDF

Unlabelled: Coronavirus disease 2019 (COVID-19) and COVID-19-related multisystem inflammatory syndrome in children (MIS-C) is known to be a life-threatening health problem worldwide. The study investigates the potential relationship between asymmetric dimethylarginine (ADMA) levels and disease severity in such conditions. We conducted an observational, prospective study between July 2021 and January 2022.

View Article and Find Full Text PDF

Importance: Exercise intervention studies have shown benefits for patients with lung cancer undergoing surgery, yet most interventions to date have been resource intensive and have followed a one-size-fits-all approach.

Objective: To determine whether a personalized, clinic-aligned perioperative exercise program with remote monitoring and instructions can improve physical function and fatigue among patients undergoing surgery for lung cancer.

Design, Setting, And Participants: The Precision-Exercise-Prescription (PEP) randomized clinical trial is a single-center phase 3 trial.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!