Application of Interpretable Machine Learning Models Based on Ultrasonic Radiomics for Predicting the Risk of Fibrosis Progression in Diabetic Patients with Nonalcoholic Fatty Liver Disease
Fei Meng, Qin Wu, Wei Zhang, Shirong Hou · 2023
Read Application of Interpretable Machine Learning Models Based on Ultrasonic Radiomics for Predicting the Risk of Fibrosis Progression in Diabetic Patients with Nonalcoholic Fatty Liver Disease by Fei Meng, Qin Wu, Wei Zhang, Shirong Hou (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10700041.txt.
Description
Fei Meng and three colleagues predict which diabetic patients with fatty livers will slide toward scarring, in a 2023 study. Stiffness scans can rule out advanced scarring, but they say little about who will progress from a clean start.
Records and ultrasound image features from six hundred eighteen patients fed several machine learning models. About eighteen percent already showed stiffness in the risk zone. Twenty-five image features carried the signal, and a support vector machine performed best in both internal and external checks. An explanation tool ranked five key features, three from elasticity imaging and two from standard scans. The authors say such models could trigger earlier, targeted treatment.
Catalog record
| CREATOR | Fei Meng, Qin Wu, Wei Zhang, Shirong Hou |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |