Related Experiment Video
Updated: Aug 9, 2026
06:55
Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Can the US minimum data set be used for predicting admissions to acute care facilities?
P A Abbott1, S Quirolgico, D Candidate
1University of Maryland School of Nursing, Department of EAHPI, Baltimore 21201, USA. abbott@gl.umbc.edu
Studies in Health Technology and Informatics
|June 29, 1999
Summary
This study explores using the Minimum Data Set (MDS) and data mining to predict long-term care residents
Area of Science:
- Healthcare Informatics
- Data Mining
- Gerontology
Background:
- Healthcare facilities face pressure to improve efficiency and patient outcomes.
- Large datasets, such as the Minimum Data Set (MDS), are underutilized in healthcare.
- The MDS is a mandatory resident assessment tool in US long-term care facilities.
Purpose of the Study:
- To develop an approach using MDS data and Knowledge Discovery in Large Datasets (KDD) to predict acute care admissions.
- To demonstrate the value of MDS data for improving patient outcomes and reducing healthcare costs.
- To explore the predictive potential of MDS data for describing patient outcomes.
Main Methods:
- Utilizing Knowledge Discovery in Large Datasets (KDD) principles.
- Applying classification algorithms to MDS data.
- Developing a predictive model for hospital readmissions from long-term care.
Main Results:
- Preliminary study design focusing on methodology.
- The potential to identify high-risk patients for acute care transfer.
- Demonstrates the feasibility of using MDS data for predictive analytics.
Conclusions:
- MDS data holds significant value for improving patient outcomes in long-term care.
- KDD and data mining can effectively predict negative health outcomes, such as acute care admissions.
- Further research is warranted to validate the predictive model and its clinical utility.