MétaCan
Menu
Back to cohort
Record W4225504827 · doi:10.2196/36997

Noninvasive Diagnosis of Nonalcoholic Steatohepatitis and Advanced Liver Fibrosis Using Machine Learning Methods: Comparative Study With Existing Quantitative Risk Scores

2022· article· en· W4225504827 on OpenAlexvenueno aff
Yonghui Wu, Xi Yang, Heather Morris, Matthew J. Gurka, Elizabeth Shenkman, Kenneth Cusi, Fernando Bril, William T. Donahoo

Bibliographic record

VenueJMIR Medical Informatics · 2022
Typearticle
Languageen
FieldMedicine
TopicLiver Disease Diagnosis and Treatment
Canadian institutionsnot available
FundersNational Center for Advancing Translational Sciences
KeywordsCirrhosisNonalcoholic fatty liver diseaseMedicineInternal medicineFibrosisSteatosisLiver biopsyHepatocellular carcinomaSteatohepatitisFatty liverGastroenterologyAlanine transaminaseMachine learningAlgorithmBiopsyArtificial intelligenceComputer scienceDisease

Abstract

fetched live from OpenAlex

Background Nonalcoholic steatohepatitis (NASH), advanced fibrosis, and subsequent cirrhosis and hepatocellular carcinoma are becoming the most common etiology for liver failure and liver transplantation; however, they can only be diagnosed at these potentially reversible stages with a liver biopsy, which is associated with various complications and high expenses. Knowing the difference between the more benign isolated steatosis and the more severe NASH and cirrhosis informs the physician regarding the need for more aggressive management. Objective We intend to explore the feasibility of using machine learning methods for noninvasive diagnosis of NASH and advanced liver fibrosis and compare machine learning methods with existing quantitative risk scores. Methods We conducted a retrospective analysis of clinical data from a cohort of 492 patients with biopsy-proven nonalcoholic fatty liver disease (NAFLD), NASH, or advanced fibrosis. We systematically compared 5 widely used machine learning algorithms for the prediction of NAFLD, NASH, and fibrosis using 2 variable encoding strategies. Then, we compared the machine learning methods with 3 existing quantitative scores and identified the important features for prediction using the SHapley Additive exPlanations method. Results The best machine learning method, gradient boosting (GB), achieved the best area under the curve scores of 0.9043, 0.8166, and 0.8360 for NAFLD, NASH, and advanced fibrosis, respectively. GB also outperformed 3 existing risk scores for fibrosis. Among the variables, alanine aminotransferase (ALT), triglyceride (TG), and BMI were the important risk factors for the prediction of NAFLD, whereas aspartate transaminase (AST), ALT, and TG were the important variables for the prediction of NASH, and AST, hyperglycemia (A1c), and high-density lipoprotein were the important variables for predicting advanced fibrosis. Conclusions It is feasible to use machine learning methods for predicting NAFLD, NASH, and advanced fibrosis using routine clinical data, which potentially can be used to better identify patients who still need liver biopsy. Additionally, understanding the relative importance and differences in predictors could lead to improved understanding of the disease process as well as support for identifying novel treatment options.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.015
metaresearch head score (Gemma)0.027
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.015
Threshold uncertainty score0.081

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0150.027
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.001
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0000.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.071
GPT teacher head0.396
Teacher spread0.325 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations16
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Medical InformaticsSame topicLiver Disease Diagnosis and TreatmentFrench-language works237,207