☆ 4.7 Review

Predicting COVID-19 severity: Challenges in reproducibility and deployment of machine learning methods

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS (2023)

Related references

Note: Only part of the references are listed.

Letter Infectious Diseases

Random forest method for the recognition of susceptibility and resistance patterns in antibiograms

Nicolas Ayala-Aldana et al.

REVISTA CHILENA DE INFECTOLOGIA (2023)

Add to Collection

Article Surgery

Development and validation of a simple web-based tool for early prediction of COVID-19-associated death in kidney transplant recipients

Luis Gustavo Modelli de Andrade et al.

Summary: This study used data from the Brazilian kidney transplant COVID-19 study to develop a prediction score for stratifying COVID-19 risk in kidney transplant recipients. The prediction score included factors such as age, hypertension, cardiovascular disease, body mass index, symptoms, and medication use.

AMERICAN JOURNAL OF TRANSPLANTATION (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A standardized analytics pipeline for reliable and rapid development and validation of prediction models using observational health data

Sara Khalid et al.

Summary: The paper presents the OHDSI analytics pipeline as a standardized approach for rapid and reliable development and validation of prediction models. By following this pipeline and using open-source software tools, researchers can efficiently address important prediction questions while limiting potential causes of bias.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Add to Collection

Article Multidisciplinary Sciences

SARS2 simplified scores to estimate risk of hospitalization and death among patients with COVID-19

Hesam Dashti et al.

Summary: Simplified models were examined for estimating the risk of hospitalization and mortality in COVID-19 patients, revealing that older age, male sex, Black ethnicity, lower socioeconomic status, and smoking status were associated with higher risk. These models can help in predicting absolute risks and making individualized decisions in the absence of detailed medical history.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Critical Care Medicine

Predicting 90-day survival of patients with COVID-19: Survival of Severely Ill COVID (SOSIC) scores

Matthieu Schmidt et al.

Summary: This study developed predictive survival models for COVID-19 patients in ICU after 1-2 weeks, using machine learning to predict 90-day mortality by collecting ICU data on D1, D7 or D14. It found that cardiovascular, renal, and pulmonary functions were crucial variables for prediction, with SOSIC-7 showing slightly higher predictive accuracy compared to SOSIC-1 and SOSIC-14.

ANNALS OF INTENSIVE CARE (2021)

Add to Collection

Article Health Care Sciences & Services

Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study

Bumjo Oh et al.

Summary: This study aimed to develop and validate machine learning models based on clinical features to assess the risk of severe disease and triage for COVID-19 patients upon hospital admission. The study identified risk factors for predicting critical patients and developed prediction models with high predictive power, along with a web-based nomogram, to aid in the assessment of severe and critical illness onset among COVID-19 patients.

JOURNAL OF MEDICAL INTERNET RESEARCH (2021)

Add to Collection

Article Health Care Sciences & Services

An Early Warning Risk Prediction Tool (RECAP-V1) for Patients Diagnosed With COVID-19: Protocol for a Statistical Analysis Plan

Francesca Fiorentino et al.

Summary: The RECAP study aims to develop accurate predictive models to assess the risk of hospitalization, deterioration, and death of COVID-19 patients. Through statistical analysis and the development of the RECAP-V1 prediction model, clinicians will have a robust tool to prioritize COVID-19 patients.

JMIR RESEARCH PROTOCOLS (2021)

Add to Collection

Article Health Policy & Services

Personalized stratification of hospitalization risk amidst COVID-19: A machine learning approach

Carson Lam et al.

Summary: In response to COVID-19, the U.S. developed a three-stage plan to determine when states could reopen businesses and ease travel restrictions, but these guidelines may have limitations in accurately identifying high-risk populations. This study evaluated a machine learning algorithm using inpatient data to predict serious illness from COVID-19. The algorithm outperformed government guidelines by identifying 80% of patients at risk for hospitalization with a high specificity of 95%.

HEALTH POLICY AND TECHNOLOGY (2021)

Add to Collection

Review Health Care Sciences & Services

COVID Mortality Prediction with Machine Learning Methods: A Systematic Review and Critical Appraisal

Francesca Bottino et al.

Summary: This study found that machine learning techniques are playing an increasingly important role in predicting COVID mortality. The use of machine learning models for mortality prediction can help with clinical decision-making, especially for COVID patients at imminent risk of death.

JOURNAL OF PERSONALIZED MEDICINE (2021)

Add to Collection

Article Critical Care Medicine

Machine-learning-based COVID-19 mortality prediction model and identification of patients at low and high risk of dying

Mohammad M. Banoei et al.

Summary: The study utilized a SIMPLS-based model to analyze clinical features and comorbidities of COVID-19 patients, identifying important predictors for predicting hospital mortality, such as coronary artery disease and diabetes. By using machine learning methods, clustering analysis was performed to classify high- and low-risk patients among COVID-19 survivors.

CRITICAL CARE (2021)

Add to Collection

Article Critical Care Medicine

Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort

Harry Magunia et al.

Summary: This study aimed to develop a machine learning model to stratify patient risk and predict ICU survival and outcomes for COVID-19 patients. By using Explainable Boosting Machine analysis, the study identified predictive factors such as age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission. These findings can assist in the treatment and management of critically ill COVID-19 patients.

CRITICAL CARE (2021)

Add to Collection

Article Computer Science, Information Systems

Understanding Demographic Risk Factors for Adverse Outcomes in COVID-19 Patients: Explanation of a Deep Learning Model

Yijun Shao et al.

Summary: The study aims to understand how age, gender, and race impact adverse outcomes in patients with COVID-19, with older age and African American race associated with higher risks, while female gender associated with lower risks. Individual-level impact scores of age show age as a more impactful risk factor in younger patients and older patients with fewer comorbidities. Gender and race variables have impact scores covering both positive and negative values.

JOURNAL OF HEALTHCARE INFORMATICS RESEARCH (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Predicting the Disease Outcome in COVID-19 Positive Patients Through Machine Learning: A Retrospective Cohort Study With Brazilian Data

Fernanda Sumika Hojo De Souza et al.

Summary: The first case of COVID-19 in Brazil was on February 26, 2020, and since then, there have been over 672,000 confirmed cases and at least 36,000 reported deaths by June 2020. Accurate diagnosis is crucial for proper treatment and to prevent healthcare system overload. Machine learning using demographic and clinical data can assist in predicting disease outcomes and supporting physician decision-making, contributing to a more effective response and preventing healthcare overload.

FRONTIERS IN ARTIFICIAL INTELLIGENCE (2021)

Add to Collection

Article Medicine, General & Internal

Diagnosis and Treatment Protocol for Novel Coronavirus Pneumonia (Trial Version 7)

Pei-Fang Wei

CHINESE MEDICAL JOURNAL (2020)

Add to Collection

Editorial Material Cardiac & Cardiovascular Systems

COVID-19 illness in native and immunosuppressed states: A clinical?therapeutic staging proposal

Hasan K. Siddiqi et al.

JOURNAL OF HEART AND LUNG TRANSPLANTATION (2020)

Add to Collection

Review Health Care Sciences & Services

Artificial Intelligence in the Fight Against COVID-19: Scoping Review

Alaa Abd-Alrazaq et al.

JOURNAL OF MEDICAL INTERNET RESEARCH (2020)

Add to Collection

Article Biotechnology & Applied Microbiology

A biomarker based severity progression indicator for COVID-19: the Kuwait prognosis indicator score

Mohammad H. Jamal et al.

BIOMARKERS (2020)

Add to Collection

Article Respiratory System

Systematic evaluation and external validation of 22 prognostic models among hospitalised adults with COVID-19: an observational cohort study

Rishi K. Gupta et al.

EUROPEAN RESPIRATORY JOURNAL (2020)

Add to Collection

Article Multidisciplinary Sciences

Identification of risk factors for mortality associated with COVID-19

Yuetian Yu et al.

PEERJ (2020)

Add to Collection

Article Critical Care Medicine

Diagnosis and Treatment of Adults with Community-acquired Pneumonia An Official Clinical Practice Guideline of the American Thoracic Society and Infectious Diseases Society of America

Joshua P. Metlay et al.

AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE (2019)

Add to Collection

Editorial Material Medicine, General & Internal

Predicting the Future - Big Data, Machine Learning, and Clinical Medicine

Ziad Obermeyer et al.

NEW ENGLAND JOURNAL OF MEDICINE (2016)

Add to Collection

© Peeref 2019-2024. All rights reserved.