Back to all papers

A precision-constrained framework for evaluating noninvasive biomarkers in MASLD and beyond.

July 20, 2026pubmed logopapers

Authors

Zhang G,Wang X,Ozturk A,Cheah E,Guo P,Martin M,Shih A,Bhan AK,Obuchowski N,Asgharpour A,Sanyal AJ,Telfer BA,Pierce TT,Samir AE

Affiliations (7)

  • Center for Ultrasound Research & Translation, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Faculty of Neurology, The Saul R. Korey Department of Neurology, Albert Einstein College of Medicine, Bronx, NY, USA.
  • Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Quantitative Health Sciences, Cleveland Clinic, Cleveland, OH, USA.
  • Stravitz-Sanyal Institute for Liver Disease and Metabolic Health and Division of Gastroenterology, Hepatology and Nutrition, Virginia Commonwealth University School of Medicine, Richmond, VA, USA.
  • Lincoln Laboratory, Massachusetts Institute of Technology, Lexington, MA, USA.
  • Center for Ultrasound Research & Translation, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA. [email protected].

Abstract

In patients with Metabolic Dysfunction-associated Steatotic Liver Disease (MASLD), accurate and low-cost non-invasive risk stratification remains a major unmet need. We developed a clinical records-based neural network integrating patient history, routine laboratory tests, and ultrasound imaging features. Here we show that in an internal test set (n = 209), the model achieved receiver operating characteristic area under the curve (ROC-AUC) values of 0.85 vs 0.82 (F ≥2), 0.90 vs 0.86 (F ≥3), 0.96 vs 0.89 (F  = 4) compared with Fibrosis-4 (FIB-4). To address limitations of ROC-AUC, we applied RP-AUC<sub>0.5-0.7</sub>, a recall-precision metric focused on clinically relevant precision range, showing improved performance over FIB-4. External validation (n = 194) shows reduced liver biopsy failure rate from 86.6% to 50.0% for at-risk metabolic dysfunction-associated steatohepatitis (MASH) prediction. Our work presents a low-cost neural network improving FIB-4, introduces RP-AUC<sub>0.5-0.7</sub> for biomarker comparison, and provides a generalizable framework for evaluating screening biomarkers in clinical care and drug trials.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.