AI Science Tracker
EN

Peripheral serum metabolomic profiles inform central cognitive impairment

University of Hawaii Cancer Center, 701 Ilalo Street, Honolulu, HI, 96813, USA; Department of Molecular Biosciences and Bioengineering, University of Hawaii at Manoa, Honolulu, HI, USA; Department of Psychiatry and Behavioral Sciences, Duke University, Durham, NC, USA; Institute of Computational Biology, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany; Duke Molecular Physiology Institute, Duke University, Durham, NC, USA; Rosa & Co LLC, San Carlos, CA, USA; University of Texas Health Science Center at San Antonio, San Antonio, TX, USA; Center for Translational & Computational Neuroimmunology, Columbia University College of Physicians and Surgeons Department of Neurology, New York, NY, USA; Rush Alzheimer's Disease Center, Rush University Medical Center, Chicago, IL, USA; Institute of Brain Sciences, Duke University, Durham, NC, USA; Department of Medicine, Duke University, Durham, NC, USA · 20 Aug 2020 · medicine

Discovery

Peripheral serum metabolomic profiles inform central cognitive impairment

Source check: Source checked. Not independent scientific confirmation.

Finding: Seven serum metabolites associated with cognitive impairment were identified; in baseline cognitively normal participants, the model predicted later conversion to MCI/AD (AUC 0.804; sensitivity 0.722; specificity 0.749). The paired pathway model had AUC 0.778. Retrospective ROS/MAP cohorts: 566 serum samples, 109 postmortem brain samples, and 446 baseline-normal participants (90 later converters). Internal repeated 70/30 splits (100 repetitions); no independent external cohort validation. The reported prediction is association/prognosis, not causal evidence.

Technology: Random-forest feature selection and classification used serum metabolite measurements plus age to predict later cognitive conversion from baseline normal cognition.

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

AI contribution
Random-forest feature selection and classification used serum metabolite measurements plus age to predict later cognitive conversion from baseline normal cognition.
Test and result
Seven serum metabolites associated with cognitive impairment were identified; in baseline cognitively normal participants, the model predicted later conversion to MCI/AD (AUC 0.804; sensitivity 0.722; specificity 0.749). The paired pathway model had AUC 0.778.
Limitation / still unknown
Retrospective ROS/MAP cohorts: 566 serum samples, 109 postmortem brain samples, and 446 baseline-normal participants (90 later converters). Internal repeated 70/30 splits (100 repetitions); no independent external cohort validation. The reported prediction is association/prognosis, not causal evidence.
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/PMC7441317/ · https://www.nature.com/articles/s41598-020-70703-w

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.