[CLSTR]
< Back to situations

Monitor this situation.

[SITUATION] · [QUIET] · [HEALTH]

2 clusters · 4 sources · 5 days · First seen · Last updated

AI and machine learning in fatty liver disease research

Overview

Researchers are increasingly employing artificial intelligence and machine learning to address the global fatty liver disease crisis. Early efforts have focused on using AI models to analyze electronic medical records, blood biomarkers, and routine chest X-rays to identify high-risk patients. One study noted that AI could identify fatty liver with 82% accuracy using standard X-ray images, while the LiverPRO algorithm has demonstrated predictive capabilities for severe liver disease.

Subsequent developments have expanded these technological applications. Machine learning is being used to identify high-fat dietary patterns through electronic health records by analyzing demographics and laboratory results. Additionally, new noninvasive detection methods using MRI radiomics and TabPFN classifiers have achieved an accuracy of 95.65% in classifying nonalcoholic fatty liver disease (NAFLD). Complementary research in Hong Kong has also explored herbal interventions, such as capsules containing milk thistle and bitter melon, to manage liver indicators and obesity markers.

Entities

Osaka Metropolitan University · Royal Medic · National Health and Nutrition Examination Survey · Evido · Roche

Timeline

  1. 20 days ago

    [HEALTH] 2 sources
    Machine learning advances dietary and liver disease detection

    New machine learning models are improving medical diagnostics by inferring high-fat dietary patterns from electronic health records and detecting nonalcoholic fatty liver disease via MRI radiomics.

  2. 25 days ago

    [HEALTH] 2 sources
    AI and herbal research target global fatty liver crisis

    With fatty liver disease affecting 1 billion people globally, AI is emerging as a vital screening tool to detect risks through blood data and X-rays, while new herbal research offers supplementary management.

Sources

digitalcommons.library.tmc.edu · finance.technews.tw · jdc.jefferson.edu · medicalinspire.com