Related Experiment Video
Updated: Jul 11, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Machine Learning Enables Single-Score Assessment of MASLD Presence and Severity
Robert Chen1,2,3, Ben Omega Petrazzini1,2,4, Girish Nadkarni1,2
1The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Abstract:
Metabolic dysfunction-associated steatotic liver disease (MASLD) affects 30% of the global population but is often underdiagnosed. To fill this diagnostic gap, we developed a digital score reflecting presence and severity of MASLD. We fitted a machine learning model to electronic health records from 37,212 UK Biobank participants with proton density fat fraction measurements and/or a MASLD diagnosis to generate a "MASLD score". In holdout testing, our model achieved areas under the receiver-operating curve of 0.83-0.84 for MASLD diagnosis and 0.90-0.91 for identifying MASLD-associated advanced fibrosis. MASLD score was significantly associated with MASLD risk factors, progression to cirrhosis, and mortality. External testing in 252,725 diverse American participants demonstrated consistent results, and hepatologist chart review showed MASLD score identified probable MASLD underdiagnosis. The MASLD score could improve early diagnosis and intervention of chronic liver disease by providing a non-invasive, low-cost method for population-wide screening of MASLD.
Insights
A new digital MASLD score aids early detection of metabolic dysfunction-associated steatotic liver disease. This non-invasive tool helps identify underdiagnosed cases, improving chronic liver disease management.
Area of Science:
- Hepatology and Digital Health
Background:
- Metabolic dysfunction-associated steatotic liver disease (MASLD) impacts 30% of the global population, yet remains frequently underdiagnosed.
- A significant diagnostic gap exists for MASLD, hindering timely intervention and management of chronic liver disease.
Approach:
- Developed a machine learning model using UK Biobank data (37,212 participants) to create a predictive 'MASLD score'.
- Validated the MASLD score using proton density fat fraction measurements and/or MASLD diagnoses.
- Externally validated the score in a diverse cohort of 252,725 American participants.
Key Points:
- The MASLD score demonstrated high accuracy (AUC 0.83-0.84) for diagnosing MASLD and identifying advanced fibrosis (AUC 0.90-0.91).
- The score correlated significantly with MASLD risk factors, disease progression (cirrhosis), and mortality.
- External validation confirmed consistent performance, and chart review indicated the score's ability to detect probable underdiagnosis.
Conclusions:
- The developed MASLD score offers a non-invasive, low-cost method for population-wide screening.
- This digital tool has the potential to enhance early diagnosis and intervention for MASLD, a prevalent chronic liver disease.
Related Concept Videos
01:19MALDI-TOF Mass Spectrometry
Matrix-assisted laser desorption ionization (MALDI) is a commonly...
01:08Matrix-Assisted Laser Desorption Ionization (MALDI)
The analyte of interest, a biomolecule or a mixture of biomolecules, is mixed with a suitable matrix material. The...