TY - JOUR
T1 - Machine learning models predict liver steatosis but not liver fibrosis in a prospective cohort study
AU - Mamandipoor, Behrooz
AU - Wernly, Sarah
AU - Semmler, Georg
AU - Flamm, Maria
AU - Jung, Christian
AU - Aigner, Elmar
AU - Datz, Christian
AU - Wernly, Bernhard
AU - Osmani, Venet
N1 - Lehr-KH Oberndorf;
Wernly S, Datz, Wernly B: Department of Internal Medicine, General Hospital Oberndorf, Teaching Hospital of the Paracelsus Medical University, Salzburg, Austria; Flamm: Institute of general practice, family medicine and preventive medicine, Paracelsus Medical University, Salzburg, Austria; Aigner: Clinic I for Internal Medicine, University Hospital Salzburg, Paracelsus Medical University, Salzburg, Austria
PY - 2023/8
Y1 - 2023/8
N2 - 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.
AB - 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.
KW - Humans
KW - Male
KW - Female
KW - Middle Aged
KW - Aged
KW - Prospective Studies
KW - Liver Cirrhosis/diagnostic imaging
KW - Fatty Liver
KW - Fibrosis
KW - Elasticity Imaging Techniques/methods
KW - Machine Learning
KW - Non-alcoholic Fatty Liver Disease
U2 - 10.1016/j.clinre.2023.102181
DO - 10.1016/j.clinre.2023.102181
M3 - Original Article
C2 - 37467893
SN - 2210-7401
VL - 47
SP - 102181
JO - CLINICS AND RESEARCH IN HEPATOLOGY AND GASTROENTEROLOGY
JF - CLINICS AND RESEARCH IN HEPATOLOGY AND GASTROENTEROLOGY
IS - 7
ER -