Related Experiment Video
Updated: Jul 5, 2026
11:19
Dorsal Column Steerability with Dual Parallel Leads using Dedicated Power Sources: A Computational Model
Published on: February 10, 2011
12.0K
Improving Spinal Cord Stimulation Patient Triage: Random Forest Model with Custom Evaluation Functions
Chen-Ta Lin1, Wei-Lin Chao1, Yu-Li Huang2
1Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C.
Studies in Health Technology and Informatics
|August 8, 2025
Summary
This study optimized a Random Forest classifier to accurately recreate healthcare referral notes and identify patients needing Spinal Cord Stimulation. The model achieved 0.74 accuracy, improving timely patient scheduling.
Area of Science:
- Healthcare informatics
- Machine learning in medicine
- Neurosurgery
Background:
- Healthcare referral triage is complex, often delayed by inefficient note processing.
- Timely extraction of referral notes is critical for patient scheduling and care coordination.
Purpose of the Study:
- To develop an optimized Random Forest classifier for reconstructing referral note content.
- To accurately identify patients eligible for Spinal Cord Stimulation (SCS) procedures.
Main Methods:
- An optimized Random Forest classifier was developed and tuned.
- A performance index was introduced to enhance classification accuracy.
- A consistency index was implemented to mitigate overfitting.
Main Results:
- The optimized classifier achieved an accuracy of 0.74.
- Optimal parameters included 5 trees and a tree depth of 4.
- The model demonstrated reliability and effectiveness with a lower standard deviation.
Conclusions:
- The optimized Random Forest classifier effectively recreates referral note content and identifies SCS candidates.
- This approach can improve the efficiency of healthcare referral triage and patient scheduling.
