AI Science Tracker
EN

Combining metabolome and clinical indicators with machine learning provides some promising diagnostic markers to precisely detect smear-positive/negative pulmonary tuberculosis

State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Respiratory Medicine, First Affiliated Hospital of Xinjiang Medical University, Urumqi, 830000, Xinjiang, China; Department of Respiratory Medicine, First Affiliated Hospital of Xinjiang Medical University, Urumqi, 830011, Xinjiang, China; CAS Key Laboratory of Genome Sciences and Information, Beijing Institute of Genomics, Chinese Academy of Sciences and China National Center for Bioinformation, Beijing, 100101, China; University of Chinese Academy of Sciences, Beijing, 100049, China; Department of Respiratory Medicine, Second Affiliated Hospital of Xinjiang Medical University, Urumqi, 830063, Xinjiang, China; State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Urumqi, 830011, Xinjiang, China; Key Laboratory of Molecular Virology and Immunology, Unit of Pathogenic Fungal Infection and Host Immunity, Institute Pasteur of Shanghai, Chinese Academy of Sciences, Shanghai, 20003, China; Department of Respiratory Medicine, Second Affiliated Hospital of Hainan Medical University Haikou, Hainan, 570100, China · 25 Aug 2022 · medicine

Discovery

Combining metabolome and clinical indicators with machine learning provides some promising diagnostic markers to precisely detect smear-positive/negative pulmonary tuberculosis

Source check: Source checked. Not independent scientific confirmation.

Finding: The study reports altered fatty-acid and amino-acid metabolite patterns and candidate marker combinations for three TB/control groups; this is a small retrospective biomarker result, not established clinical utility. Primary Methods/Results report 27 smear-positive cases, 37 smear-negative cases and 36 controls; RF performance is checked with SVM and MLP on the same study cohort. Independent external validation is not reported.

Technology: Random forest selects metabolite/clinical feature combinations from plasma metabolomics for smear-positive, smear-negative and control classification.

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

AI contribution
Random forest selects metabolite/clinical feature combinations from plasma metabolomics for smear-positive, smear-negative and control classification.
Test and result
The study reports altered fatty-acid and amino-acid metabolite patterns and candidate marker combinations for three TB/control groups; this is a small retrospective biomarker result, not established clinical utility.
Limitation / still unknown
Primary Methods/Results report 27 smear-positive cases, 37 smear-negative cases and 36 controls; RF performance is checked with SVM and MLP on the same study cohort. Independent external validation is not reported.
Evidence sources and annotation context

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

Evidence sources: https://link.springer.com/article/10.1186/s12879-022-07694-8

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 source full text Methods and Results; version/date checked against bibliographic record..

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