Development and Validation of a Machine Learning–Based Screening Algorithm to Predict High-Risk Hepatitis C Infection - Summary - MDSpire

Development and Validation of a Machine Learning–Based Screening Algorithm to Predict High-Risk Hepatitis C Infection

  • By

  • Suk-Chan Jang

  • Wei-Hsuan Lo-Ciganic

  • Pilar Hernandez-Con

  • Chanakan Jenjai

  • James Huang

  • Ashley Stultz

  • Shunhua Yan

  • Debbie L Wilson

  • Ashley Norse

  • Faheem W Guirgis

  • Robert L Cook

  • Christine Gage

  • Khoa A Nguyen

  • Patrick Hornes

  • Yonghui Wu

  • David R Nelson

  • Haesuk Park

  • August 15, 2025

  • 0 min

Share

Objective:

To develop and validate a machine learning-based algorithm specifically for screening individuals at high risk of HCV infection.

Key Findings:
  • Out of 445,624 individuals, 11,823 (2.65%) tested positive for HCV.
  • The gradient boosting machine model outperformed others with a C statistic of 0.916.
  • GBM achieved 79.39% sensitivity (95% CI: X) and 89.08% specificity (95% CI: Y), identifying 1 positive case per 6 tests.
Interpretation:

Machine learning algorithms effectively predicted and stratified HCV infection risk, providing a promising tool for targeted screening in clinical settings, which could enhance patient outcomes.

Limitations:
  • Study limited to a specific geographic area (Florida), which may affect generalizability.
  • Potential biases in electronic health record data, such as incomplete records or misclassification.
Conclusion:

The developed ML algorithm offers a sustainable approach to enhance targeted screening for HCV, addressing the challenges of universal screening.

Original Source(s)

Related Content