Automated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning.
Moritz GrossStefan P HaiderTal Ze'eviSteffen HuberSandeep AroraAhmet S KucukkayaSimon IsekeBernhard GebauerFlorian FleckensteinMarc DeweyAriel JaffeMario StrazzaboscoJulius ChapiroJohn A OnofreyPublished in: European radiology (2024)
• Machine learning enables hepatocellular carcinoma mortality risk prediction using standard-of-care clinical data and automated radiomic features from multiphasic contrast-enhanced MRI. • Automated mortality risk prediction achieved state-of-the-art performances for mortality risk quantification and outperformed conventional clinical staging systems. • Patients were stratified into low, intermediate, and high-risk groups with significantly different survival times, generalizable to an independent evaluation cohort.
Keyphrases
- contrast enhanced
- machine learning
- magnetic resonance imaging
- deep learning
- diffusion weighted
- computed tomography
- high throughput
- magnetic resonance
- end stage renal disease
- diffusion weighted imaging
- big data
- cardiovascular events
- healthcare
- artificial intelligence
- newly diagnosed
- chronic kidney disease
- risk factors
- peritoneal dialysis
- electronic health record
- quality improvement
- dual energy