The ANTICIPATE-NASH Models Stratify Better the Risk of Clinical Events Than Histology in Metabolic Dysfunction-Associated Steatotic Liver Disease Patients With Advanced Chronic Liver Disease
Bibliographic record
Abstract
BACKGROUND & AIMS: The reference for risk stratification and clinical trial selection of metabolic dysfunction-associated steatotic liver disease (MASLD) patients is fibrosis degree by histology. The noninvasive ANTICIPATE-NASH models have been validated for risk prediction of clinically significant portal hypertension (CSPH) and liver-related events (LRE). We assessed whether these models provide better risk stratification of events than histology. METHODS: A multicenter cohort 1, including 699 biopsy specimen-proven F3-F4 patients with MASLD was evaluated. The end point was LRE (hepatic decompensation, hepatocellular carcinoma, transplantation, or liver-related death). We assessed (Cox regression) whether histology provided added value to ANTICIPATE-NASH and whether model predictions differed in F3/F4 patients. Results were validated in cohort 2 (1396 F3-F4 patients) from 4 clinical trials using the clinical regulatory end point. RESULTS: In cohort 1, F3 and F4 were equally distributed. There were 56 LREs (8.0%) during follow-up, concentrated in F4 (51 LREs). The ANTICIPATE-NASH model showed excellent discrimination (C statistic, 0.93) for LRE, higher than histology (C statistic, 0.67). Model calibration was excellent. Adding histology did not improve model prediction. Thresholds of ANTICIPATE-NASH above which F3 patients developed LREs and below which F4 patients did not were identified. Results were reproduced in cohort 2 with the regulatory end point, with higher model discrimination (C statistic, 0.84) compared with histology (C statistic, 0.64). CONCLUSIONS: In MASLD patients with F3/F4, the noninvasive ANTICIPATE-NASH models provide better risk stratification of clinical events than histologic classification. These models could be very useful for clinical trials by selecting patients at risk of clinical events and patients with higher chances of observed cirrhosis regression.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".