Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information. McTeer, M., Applegate, D., Mesenbrink, P., Ratziu, V., Schattenberg, J. M., Bugianesi, E., Geier, A., Romero Gomez, M., Dufour, J., Ekstedt, M., Francque, S., Yki-Jarvinen, H., Allison, M., Valenti, L., Miele, L., Pavlides, M., Cobbold, J., Papatheodoridis, G., Holleboom, A. G., Tiniakos, D., Brass, C., Anstee, Q. M., Missier, P., & investigators , o. b. o. t. L. C. PLOS ONE, 19(2):1–17, February, 2024. Publisher: Public Library of Science
Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information [link]Paper  doi  abstract   bibtex   
Aims Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints. Methods Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable. Results Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance. Conclusions This study developed a series of ML models of accuracy ranging from 71.9—99.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.
@article{mcteer_machine_2024,
	title = {Machine learning approaches to enhance diagnosis and staging of patients with {MASLD} using routinely available clinical information},
	volume = {19},
	url = {https://doi.org/10.1371/journal.pone.0299487},
	doi = {10.1371/journal.pone.0299487},
	abstract = {Aims Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints. Methods Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable. Results Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance. Conclusions This study developed a series of ML models of accuracy ranging from 71.9—99.4\% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.},
	number = {2},
	journal = {PLOS ONE},
	author = {McTeer, Matthew and Applegate, Douglas and Mesenbrink, Peter and Ratziu, Vlad and Schattenberg, Jörn M. and Bugianesi, Elisabetta and Geier, Andreas and Romero Gomez, Manuel and Dufour, Jean-Francois and Ekstedt, Mattias and Francque, Sven and Yki-Jarvinen, Hannele and Allison, Michael and Valenti, Luca and Miele, Luca and Pavlides, Michael and Cobbold, Jeremy and Papatheodoridis, Georgios and Holleboom, Adriaan G. and Tiniakos, Dina and Brass, Clifford and Anstee, Quentin M. and Missier, Paolo and investigators, on behalf of the LITMUS Consortium},
	month = feb,
	year = {2024},
	note = {Publisher: Public Library of Science},
	pages = {1--17},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021