Non-alcoholic fatty liver disease (NAFLD) affects 20%-40% of the general population in developed countries and is an increasingly important cause of hepatocellular carcinoma.
Electronic medical records facilitate large-scale epidemiological studies, existing NAFLD scores often require clinical and anthropometric parameters that may not be captured in those databases.
Dr Wong and colleagues from Hong Kong developed and validated a laboratory parameter-based machine learning model to detect NAFLD for the general population.
The team randomly divided 922 subjects from a population screening study into training and validation groups.
|The NAFLD ridge score achieved an AUROC of 0.87 in the training groups|
|Alimentary Pharmacology & Therapeutics|
The researchers diagnosed NAFLD by proton-magnetic resonance spectroscopy.
On the basis of machine learning from 23 routine clinical and laboratory parameters after elastic net regulation, the researchers evaluated the logistic regression, ridge regression, AdaBoost and decision tree models.
The areas under receiver-operating characteristic curve (AUROC) of models in validation group were compared.
The research team selected 6 predictors including alanine aminotransferase, high-density lipoprotein cholesterol, triglyceride, haemoglobin A1c, white blood cell count and the presence of hypertension.
The research team found that the NAFLD ridge score achieved AUROC of 0.87 and 0.88 in the training and validation groups, respectively.
Using dual cut-offs of 0.24 and 0.44, NAFLD ridge score achieved 92% sensitivity and 90% specificity with corresponding negative and positive predictive values of 96% and 69%, and 87% of overall accuracy among 70% of classifiable subjects in the validation group; 30% of subjects remained indeterminate.
Dr Wong's team comments, "NAFLD ridge score is a simple and robust reference comparable to existing NAFLD scores to exclude NAFLD patients in epidemiological studies."