Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease
Abstract Advanced metabolic-dysfunction-associated steatotic liver disease (MASLD) fibrosis (F3-4) predicts liver-related outcomes. Serum and elastography-based non-invasive tests (NIT) cannot yet reliably predict MASLD outcomes. The role of B-mode ultrasound (US) for outcome prediction is not yet k...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-09288-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849766628806361088 |
|---|---|
| author | Heather Mary-Kathleen Kosick Chris McIntosh Chinmay Bera Mina Fakhriyehasl Mohamed Shengir Oyedele Adeyi Leila Amiri Giada Sebastiani Kartik Jhaveri Keyur Patel |
| author_facet | Heather Mary-Kathleen Kosick Chris McIntosh Chinmay Bera Mina Fakhriyehasl Mohamed Shengir Oyedele Adeyi Leila Amiri Giada Sebastiani Kartik Jhaveri Keyur Patel |
| author_sort | Heather Mary-Kathleen Kosick |
| collection | DOAJ |
| description | Abstract Advanced metabolic-dysfunction-associated steatotic liver disease (MASLD) fibrosis (F3-4) predicts liver-related outcomes. Serum and elastography-based non-invasive tests (NIT) cannot yet reliably predict MASLD outcomes. The role of B-mode ultrasound (US) for outcome prediction is not yet known. We aimed to evaluate machine learning (ML) algorithms based on simple NIT and US for prediction of adverse liver-related outcomes in MASLD. Retrospective cohort study of adult MASLD patients biopsied between 2010–2021 at one of two Canadian tertiary care centers. Random forest was used to create predictive models for outcomes—hepatic decompensation, liver-related outcomes (decompensation, hepatocellular carcinoma (HCC), liver transplant, and liver-related mortality), HCC, liver-related mortality, F3-4, and fibrotic metabolic dysfunction-associated steatohepatitis (MASH). Diagnostic performance was assessed using area under the curve (AUC). 457 MASLD patients were included with 44.9% F3-4, diabetes prevalence 31.6%, 53.8% male, mean age 49.2 and BMI 32.8 kg/m2. 6.3% had an adverse liver-related outcome over mean 43 months follow-up. AUC for ML predictive models were—hepatic decompensation 0.90(0.79–0.98), liver-related outcomes 0.87(0.76–0.96), HCC 0.72(0.29–0.96), liver-related mortality 0.79(0.31–0.98), F3-4 0.83(0.76–0.87), and fibrotic MASH 0.74(0.65–0.85). Biochemical and clinical variables had greatest feature importance overall, compared to US parameters. FIB-4 and AST:ALT ratio were highest ranked biochemical variables, while age was the highest ranked clinical variable. ML models based on clinical, biochemical, and US-based variables accurately predict adverse MASLD outcomes in this multi-centre cohort. Overall, biochemical variables had greatest feature importance. US-based features were not substantial predictors of outcomes in this study. |
| format | Article |
| id | doaj-art-d0949afdf02e44bdb31b6748bdfdad16 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-d0949afdf02e44bdb31b6748bdfdad162025-08-20T03:04:30ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-09288-1Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver diseaseHeather Mary-Kathleen Kosick0Chris McIntosh1Chinmay Bera2Mina Fakhriyehasl3Mohamed Shengir4Oyedele Adeyi5Leila Amiri6Giada Sebastiani7Kartik Jhaveri8Keyur Patel9Division of Gastroenterology, University Health Network Toronto, Toronto General HospitalUniversity of TorontoDivision of Gastroenterology, University Health Network Toronto, Toronto General HospitalJoint Department of Medical Imaging, University Health Network, Mount Sinai Hospital, Women’s College HospitalDivision of Gastroenterology and Hepatology, McGill University Health CentreDepartment of Laboratory Medicine and Pathology, University of MinnesotaDivision of Gastroenterology, University Health Network Toronto, Toronto General HospitalDivision of Gastroenterology and Hepatology, McGill University Health CentreUniversity of TorontoDivision of Gastroenterology, University Health Network Toronto, Toronto General HospitalAbstract Advanced metabolic-dysfunction-associated steatotic liver disease (MASLD) fibrosis (F3-4) predicts liver-related outcomes. Serum and elastography-based non-invasive tests (NIT) cannot yet reliably predict MASLD outcomes. The role of B-mode ultrasound (US) for outcome prediction is not yet known. We aimed to evaluate machine learning (ML) algorithms based on simple NIT and US for prediction of adverse liver-related outcomes in MASLD. Retrospective cohort study of adult MASLD patients biopsied between 2010–2021 at one of two Canadian tertiary care centers. Random forest was used to create predictive models for outcomes—hepatic decompensation, liver-related outcomes (decompensation, hepatocellular carcinoma (HCC), liver transplant, and liver-related mortality), HCC, liver-related mortality, F3-4, and fibrotic metabolic dysfunction-associated steatohepatitis (MASH). Diagnostic performance was assessed using area under the curve (AUC). 457 MASLD patients were included with 44.9% F3-4, diabetes prevalence 31.6%, 53.8% male, mean age 49.2 and BMI 32.8 kg/m2. 6.3% had an adverse liver-related outcome over mean 43 months follow-up. AUC for ML predictive models were—hepatic decompensation 0.90(0.79–0.98), liver-related outcomes 0.87(0.76–0.96), HCC 0.72(0.29–0.96), liver-related mortality 0.79(0.31–0.98), F3-4 0.83(0.76–0.87), and fibrotic MASH 0.74(0.65–0.85). Biochemical and clinical variables had greatest feature importance overall, compared to US parameters. FIB-4 and AST:ALT ratio were highest ranked biochemical variables, while age was the highest ranked clinical variable. ML models based on clinical, biochemical, and US-based variables accurately predict adverse MASLD outcomes in this multi-centre cohort. Overall, biochemical variables had greatest feature importance. US-based features were not substantial predictors of outcomes in this study.https://doi.org/10.1038/s41598-025-09288-1SteatosisArtificial intelligenceFibrosisLiver biopsyHepatic decompensation |
| spellingShingle | Heather Mary-Kathleen Kosick Chris McIntosh Chinmay Bera Mina Fakhriyehasl Mohamed Shengir Oyedele Adeyi Leila Amiri Giada Sebastiani Kartik Jhaveri Keyur Patel Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease Scientific Reports Steatosis Artificial intelligence Fibrosis Liver biopsy Hepatic decompensation |
| title | Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease |
| title_full | Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease |
| title_fullStr | Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease |
| title_full_unstemmed | Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease |
| title_short | Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease |
| title_sort | machine learning models using non invasive tests b mode ultrasound to predict liver related outcomes in metabolic dysfunction associated steatotic liver disease |
| topic | Steatosis Artificial intelligence Fibrosis Liver biopsy Hepatic decompensation |
| url | https://doi.org/10.1038/s41598-025-09288-1 |
| work_keys_str_mv | AT heathermarykathleenkosick machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT chrismcintosh machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT chinmaybera machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT minafakhriyehasl machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT mohamedshengir machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT oyedeleadeyi machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT leilaamiri machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT giadasebastiani machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT kartikjhaveri machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease AT keyurpatel machinelearningmodelsusingnoninvasivetestsbmodeultrasoundtopredictliverrelatedoutcomesinmetabolicdysfunctionassociatedsteatoticliverdisease |