AI Science Tracker
EN

Leukemia can be Effectively Early Predicted in Routine Physical Examination with the Assistance of Machine Learning Models

Department of Hematology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China. · 24 Nov 2022 · medicine

Discovery

Leukemia can be Effectively Early Predicted in Routine Physical Examination with the Assistance of Machine Learning Models

Source check: Source checked. Not independent scientific confirmation.

Finding: Random forest and XGBoost applied to routine examination/lab data distinguished newly diagnosed leukemia cases from healthy controls and identified influential blood measures.

Technology: Random forest and XGBoost classify leukemia cases from routine examination and laboratory measurements.

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

AI contribution
Random forest and XGBoost classify leukemia cases from routine examination and laboratory measurements.
Test and result
The study reports accuracy above 0.9 and highlights RBC, hematocrit, and WBC measures in a specific early-detection task.
Limitation / still unknown
Internal train/test data from one hospital with selected cases and healthy controls; no independent external cohort, so performance may not transfer to screening populations.
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/PMC9715329/ · https://pmc.ncbi.nlm.nih.gov/articles/PMC9715329/#methods · https://pmc.ncbi.nlm.nih.gov/articles/PMC9715329/#results · https://pubmed.ncbi.nlm.nih.gov/36465253/

Source checked · editorial details

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

Source type: paper. Paper: linked separately.

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

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.