Application of machine learning in predicting hospital readmissions: a scoping review of the literature
Yinan Huang1, Ashna Talwar1, Satabdi Chatterjee1
1Department of Pharmaceutical Health Outcomes and Policy, College of Pharmacy, University of Houston, 4849 Calhoun Road, Health & Sciences Bldg 2, Houston, TX, 77204, USA.
Background:
Advances in machine learning (ML) provide great opportunities in the prediction of hospital readmission. This review synthesizes the literature on ML methods and their performance for predicting hospital readmission in the US.
Methods:
This review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) Statement. The extraction of items was also guided by the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS). Electronic databases PUBMED, MEDLINE, and EMBASE were systematically searched from January 1, 2015, through December 10, 2019. The articles were imported into COVIDENCE online software for title/abstract screening and full-text eligibility. Observational studies using ML techniques for hospital readmissions among US patients were eligible for inclusion. Articles without a full text available in the English language were excluded. A qualitative synthesis included study characteristics, ML algorithms utilized, and model validation, and quantitative analysis assessed model performance. Model performances in terms of Area Under the Curve (AUC) were analyzed using R software. Quality in Prognosis Studies (QUIPS) tool was used to assess the quality of the reviewed studies.
Results:
Of 522 citations reviewed, 43 studies met the inclusion criteria. A majority of the studies used electronic health records (24, 56%), followed by population-based data sources (15, 35%) and administrative claims data (4, 9%). The most common algorithms were tree-based methods (23, 53%), neural network (NN) (14, 33%), regularized logistic regression (12, 28%), and support vector machine (SVM) (10, 23%). Most of these studies (37, 85%) were of high quality. A majority of these studies (28, 65%) reported ML algorithms with an AUC above 0.70. There was a range of variability within AUC reported by these studies with a median of 0.68 (IQR: 0.64-0.76; range: 0.50-0.90).
Conclusions:
The ML algorithms involving tree-based methods, NN, regularized logistic regression, and SVM are commonly used to predict hospital readmission in the US. Further research is needed to compare the performance of ML algorithms for hospital readmission prediction.
Insights
Machine learning (ML) effectively predicts hospital readmissions in the US. Tree-based methods, neural networks, and logistic regression are common, with most models achieving an Area Under the Curve (AUC) above 0.70.
Area of Science:
- Health Informatics
- Artificial Intelligence in Medicine
- Predictive Analytics
Background:
- Machine learning (ML) offers significant potential for predicting hospital readmissions.
- This review synthesizes current literature on ML methods and their performance in US-based hospital readmission prediction.
Purpose of the Study:
- To review and synthesize the literature on machine learning methods used for predicting hospital readmission in the United States.
- To evaluate the performance of various ML algorithms in hospital readmission prediction models.
Main Methods:
- Systematic literature search of PubMed, MEDLINE, and EMBASE (2015-2019) following PRISMA-ScR guidelines.
- Inclusion of observational studies using ML for hospital readmissions in US patients; exclusion of non-English full-text articles.
- Qualitative synthesis of study characteristics, ML algorithms, and model validation; quantitative analysis of model performance using Area Under the Curve (AUC) and the QUIPS tool for quality assessment.
Main Results:
- 43 studies met inclusion criteria from 522 citations; most utilized electronic health records (56%).
- Commonly used ML algorithms included tree-based methods (53%), neural networks (33%), regularized logistic regression (28%), and support vector machines (23%).
- A majority of high-quality studies (85%) reported ML algorithms with an AUC > 0.70, with a median AUC of 0.68.
Conclusions:
- Tree-based methods, neural networks, regularized logistic regression, and SVM are prevalent for predicting US hospital readmissions.
- While many ML models show promising performance, further research is required for direct comparison of algorithm efficacy.
More Related Videos
05:16Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
Published on: June 10, 2025
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Related Concept Videos
01:18Steps in Outbreak Investigation
01:15Methods of Documentation VI: Case Management Model
For example, a patient with a chronic...
01:29Issues And Trends In Healthcare Delivery System
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
01:10Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
01:24Kaplan-Meier Approach