Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Considering internal conflict in the face of natural product biosynthesis and biosynthetic gene cluster evolution.

Essays in biochemistry·2026

Same author

Cervical Spine Immobilisation Following Stab Wounds to the Neck Is Unnecessary.

Emergency medicine Australasia : EMA·2026

Same author

The maternal health knowledge of pregnant women attending the antenatal clinics in the Western Cape: A cross-sectional study.

Journal of public health in Africa·2026

Same author

Utilisation of digital educational technology amongst undergraduate nursing students in the Western Cape.

Health SA = SA Gesondheid·2026

Same author

CT for Cervical Spine Clearance in the Obtunded Adult Blunt Trauma Patient is Appropriate in a Resource-Constrained Environment.

World journal of surgery·2026

Same author

Mob Assault in South Africa: The Public Health Consequences of a Failing Justice System.

World journal of surgery·2026

Search research articles

Related Experiment Video

Updated: May 13, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Using Machine Learning to Improve Readmission Risk in Surgical Patients in South Africa.

Umit Tokac¹, Jennifer Chipps², Petra Brysiewicz³

¹College of Nursing, University of Missouri-St. Louis, St. Louis, MO 63121, USA.

International Journal of Environmental Research and Public Health

|April 16, 2025

Summary

This summary is machine-generated.

This study developed a machine learning model to predict unplanned patient readmissions in South Africa using free-text electronic health records. The model improved prediction accuracy, identifying key factors for surgical and trauma readmissions.

Keywords:

South Africa machine learning surgery trauma unplanned readmissions

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Related Experiment Videos

Last Updated: May 13, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Area of Science:

Health Informatics
Machine Learning in Healthcare
Public Health

Background:

Unplanned 30-day readmissions pose a significant global and South African healthcare challenge.
Predicting readmissions is crucial for improving patient outcomes and optimizing resource allocation in public hospitals.

Purpose of the Study:

To develop and evaluate a machine learning model for predicting unplanned surgical and trauma readmissions.
To utilize unstructured text data from electronic health records for readmission prediction.

Main Methods:

Retrospective cohort analysis of patient records.
Application of random forest analysis combined with natural language processing (NLP) and sentiment analysis.
Extraction of insights from free-text data in an electronic registry.

Main Results:

Achieved Area Under the Curve (AUC) values ranging from 0.54 to 0.92, consistent with global benchmarks.
Identified the discharge plan score as the primary predictor for trauma readmissions.
Identified the problem score as the primary predictor for surgical readmissions.

Conclusions:

Machine learning and NLP techniques enhance the accuracy of predicting unplanned patient readmissions.
Specific predictor variables (discharge plan, problem score) are critical for different patient cohorts (trauma, surgical).
This approach offers a valuable tool for South African public hospitals to proactively manage readmission risks.