Back to all available

Predicting readmission and mortality in hospitalized older adults in Taiwan: A machine learning approach integrating electronic health records with functional assessments

algorithms-and-analysis-of-algorithms
artificial-intelligence
data-mining-and-machine-learning
data-science
neural-networks

Abstract

Background

The population of Taiwan is aging rapidly, leading to a higher prevalence of hospital readmission and mortality among older adults. Identifying patients at high risk of adverse outcomes is essential to optimize healthcare resource allocation and for better patient outcomes. Here, we aimed to develop machine learning models combining electronic health records (EHRs) and comprehensive geriatric assessments (CGAs) to predict hospital readmission and mortality in older adults.

Methods

In this retrospective cohort study, we analyzed data of 1,565 hospitalized older adults in Taiwan, as recorded between 2012 and 2018. Data preprocessing included imputation for missing values, selecting variables, and correcting for class imbalance using the synthetic minority oversampling technique (SMOTE). Three machine learning models — XGBoost, Random Forest, and Logistic Regression — were trained and optimized through grid search with cross-validation. Model performance was compared based on metrics like accuracy, F1 score, and area under the receiver operating characteristic curve(AUC).

Results

We found that the XGBoost model had outperformed the other two models, achieving an AUC of 0.77 for mortality prediction and 0.81 for readmission prediction after applying SMOTE. Key predictors included readmission history, nutritional status, and functional assessments. Incorporating CGA data with EHRs, instead of using EHR data alone, further improved the model accuracy.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].