Machine Learning–Enhanced Frailty Assessment for High-Risk Older Patients Undergoing TAVR
2024
Machine Learning for Frailty Assessment in Older Patients
Sample size: 131
publication
Evidence: moderate
Author Information
Author(s): Mardini Mamoun, Bai Chen, Price Catherine, Manini Todd, Al-Ani Mohammad
Primary Institution: University of Florida
Hypothesis
Can machine learning improve frailty assessments for older patients undergoing TAVR?
Conclusion
Using machine learning to combine clinical notes and structured data significantly improves frailty assessment in older patients.
Supporting Evidence
- The study analyzed data from 131 TAVR patients collected over two years.
- Machine learning models achieved an AUC of 0.82 when combining clinical notes and structured data.
- Key frailty predictors included congestive heart failure management and back problems.
Takeaway
This study shows that using computers to analyze patient information can help doctors better understand how frail older patients are before heart surgery.
Methodology
The study used machine learning to analyze structured and unstructured data from clinical notes and electronic health records of TAVR patients.
Participant Demographics
Older patients undergoing TAVR.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website