Machine learning models predict liver steatosis but not liver fibrosis in a prospective cohort study - 11/08/23
Highlights |
• | Liver steatosis risk can be estimated by AI models, using routinely collected clinical data, paving the way towards a wide-scale screening instrument. |
• | Routinely collected clinical data is not sufficient for a high-performance estimation of liver fibrosis. |
• | Patient-reported outcomes, such as nutrition and lifestyle, do not contribute to risk estimation neither for liver steatosis nor fibrosis. |
• | Male and female subjects should be treated differently as there are significant differences in estimating risk of liver steatosis and fibrosis, between genders. |
Abstract |
Introduction |
Screening for liver fibrosis continues to rely on laboratory panels and non-invasive tests such as FIB-4-score and transient elastography. In this study, we evaluated the potential of machine learning (ML) methods to predict liver steatosis on abdominal ultrasound and liver fibrosis, namely the intermediate-high risk of advanced fibrosis, in individuals participating in a screening program for colorectal cancer.
Methods |
We performed ultrasound on 5834 patients admitted between 2006 and 2020, and transient elastography on a subset of 1240 patients. Steatosis on ultrasound was diagnosed if liver areas showed a significantly increased echogenicity compared to the renal parenchyma. Liver fibrosis was defined as a liver stiffness measurement ≥8 kPa in transient elastography. We evaluated the performance of three algorithms, namely Extreme Gradient Boosting, Feed-Forward neural network and Logistic Regression, deriving the models using data from patients admitted from January 2007 up to January 2016 and prospectively evaluating on the data of patients admitted from January 2016 up to March 2020. We also performed a performance comparison with the standard clinical test based on Fibrosis-4 Index (FIB-4).
Results |
The mean age was 58±9 years with 3036 males (52%). Modelling laboratory parameters, clinical parameters, and data on eight food types/dietary patterns, we achieved high performance in predicting liver steatosis on ultrasound with AUC of 0.87 (95% CI [0.87–0.87]), and moderate performance in predicting liver fibrosis with AUC of 0.75 (95% CI [0.74–0.75]) using XGBoost machine learning algorithm. Patient-reported variables did not significantly improve predictive performance. Gender-specific analyses showed significantly higher performance in males with AUC of 0.74 (95% CI [0.73–0.74]) in comparison to female patients with AUC of 0.66 (95% CI [0.65–0.66]) in prediction of liver fibrosis. This difference was significantly smaller in prediction of steatosis with AUC of 0.85 (95% CI [0.83–0.87]) in female patients, in comparison to male patients with AUC of 0.82 (95% CI [0.80–0.84]).
Conclusion |
ML based on point-prevalence laboratory and clinical information predicts liver steatosis with high accuracy and liver fibrosis with moderate accuracy. The observed gender differences suggest the need to develop gender-specific models.
Le texte complet de cet article est disponible en PDF.Keywords : Steatosis, Liver fibrosis, Machine learning, Predictive modelling, Gender differences, Patient self-reported outcomes
Plan
Vol 47 - N° 7
Article 102181- août 2023 Retour au numéro
Article précédent
- Effects of saroglitazar in the treatment of non-alcoholic fatty liver disease or non-alcoholic steatohepatitis: A systematic review and meta-analysis
- Sanjay Bandyopadhyay, Shambo Samrat Samajdar, Saibal Das
- Factors associated with discordance in the assessment of fibrosis stage between transient elastography and liver biopsy in NAFLD patients
- Meng Lu, Mingyu Zhu, Hu Li, Qingling Wang, Yuting Qian, Mingjie Wang, Li Chen
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?