AI Science Tracker
EN

Chongqing Research Institute of Big Data, Peking University, Chongqing, China

1 discovery from 2023

Discoveries

A dynamic machine learning model for prediction of NAFLD in a health checkup population: A longitudinal study.

Source check: Source checked. Not independent scientific confirmation.

Finding: An LSTM updated with successive health-check records predicted later NAFLD in retrospective cohorts, with AUROC .818 internally and .792 externally after five checkups; this does not show prospective clinical benefit. The reviewed source supports this bounded result; external generalization, causal effects, and sustained operational impact remain unestablished where the source reports retrospective or internal evaluation.

Technology: LSTM consumes successively updated records; L1-penalized logistic regression selected features and SHAP explained predictions.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
LSTM consumes successively updated records; L1-penalized logistic regression selected features and SHAP explained predictions.
Test and result
In 10,493 retrospective participants, internal AUROC rose .729 to .818; external cohort of 1,728 had .700 to .792.
Limitation / still unknown
Training-set five-fold tuning and separate internal/external validation assessed discrimination and calibration; no prospective deployment or clinical benefit was tested.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC10412833/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.