Evidence map›Paper›PMID 41310166›Full record

ArticleNPJ digital medicine2025

Fair positive unlabeled learning for predicting undiagnosed Alzheimer's disease in diverse electronic health records.

Thai Tran, Mingzhou Fu, Jessica Fung, Sriram Sankararaman, David A Elashoff, Keith Vossel, Timothy S Chang

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in NPJ digital medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers.

0numbers the graph read from it
0cells of the map it votes in
3citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

3 citing papers in PubMed.

  1. Adaptive cascading artificial intelligence for Alzheimer's disease assessment: a clinically oriented narrative review and implementation framework.Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology · 2026
    Review
  2. Review
  3. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

7 authors.

Thai TranDepartment of Neurology, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
Mingzhou FuDepartment of Neurology, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
Jessica FungDepartment of Neurology, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
Sriram SankararamanComputational Medicine, University of California, Los Angeles, CA, USA.
David A ElashoffComputational Medicine, University of California, Los Angeles, CA, USA.
Keith VosselDepartment of Neurology, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
Timothy S ChangDepartment of Neurology, David Geffen School of Medicine, University of California, Los Angeles, CA, USA. timothychang@mednet.ucla.edu.

Funding

The National Institute on Aging (NIA) Late Onset of Alzheimer's Disease (LOAD) Family-Based Study (FBS)U24AG056270 · NIA · COLUMBIA UNIVERSITY HEALTH SCIENCES · PI Gary Wayne Beecham, TATIANA M. FOROUD · 2017 to 2026
$31.4M
Uncovering the Genetic Mechanisms of the Chromosome 17q21.31 Tau Haplotype on Neurodegeneration Risk in FTD and PSPU54NS123746 · NINDS · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI GESCHWIND, DANIEL H, GOATE, ALISON M · 2021 to 2025
$9.4M
IN VIVO STUDIES OF THE EPILEPTIC HIPPOCAMPUSR01NS033310 · NINDS · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI JEROME NONE ENGEL, Richard Staba · 1994 to 2026
$7.5M
Astrocyte and neuron brain-region and compartment-specific proteome dynamics in aging and Alzheimer’s diseaseR01AG075955 · NIA · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI KHAKH, BALJIT, VOSSEL, KEITH ALAN · 2021 to 2025
$5.2M
MAEVE: Microbiota mediated flavonoid metabolites for cognitive healthR01AG081768 · NIA · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI ARPANA CHURCH, Emeran A Mayer · 2024 to 2026
$4.6M
Network-targeted theta-burst stimulation for episodic memory improvement in mild cognitive impairmentR01AG068317 · NIA · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI LEUCHTER, ANDREW F · 2020 to 2024
$3.4M
Novel Imaging and Biofluid Biomarkers of Small Vessel Cerebrovascular DiseaseU01NS100608 · NINDS · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · PI KRAMER, JOEL H · 2023 to 2025
$3.2M
Leveraging the Electronic Health Record and Integrating Social and Biological Data to Expand Dementia Research in Understudied Populations in Los Angeles CountyUH3AG083254 · NIA · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI Keith Alan Vossel · 2025 to 2026
$2.3M
Identifying Undiagnosed Alzheimer’s Disease in Understudied PopulationsR01AG085518 · NIA · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI Timothy S Chang · 2024 to 2026
$2.3M
Biomedical Data Science Training Program for Precision Health EquityT15LM013976 · NLM · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI ALEX BUI · 2022 to 2026
$1.9M
Preventing Seizures and Associated Memory Loss in Alzheimer's Disease by Blocking Tau Interactions with SH3-containing Proteins.R01AG058820 · NIA · UNIVERSITY OF MINNESOTA · PI VOSSEL, KEITH ALAN · 2019 to 2023
$1.9M
Leveraging the Electronic Health Record and Integrating Social and Biological Data to Expand Dementia Research in Understudied Populations in Los Angeles CountyUH2AG083254 · NIA · UNIVERSITY OF CALIFORNIA LOS ANGELES · PI VOSSEL, KEITH ALAN · 2023 to 2024
$1.1M
California Department of Public Health, Chronic Disease Control Branch, Alzheimer's Disease Program Contract #22-10079National Institute of Aging R01AG085518-01A1National Science Foundation CAREER-1943497NIA NIH HHS K08 AG065519NIA NIH HHS R01 AG058820NIA NIH HHS R01 AG068317NIA NIH HHS R01 AG075955NIA NIH HHS R01 AG081768NIA NIH HHS R01 AG085518NIA NIH HHS U24 AG056270NIA NIH HHS UH2 AG083254NIA NIH HHS UH3 AG083254NIGMS NIH HHS R35 GM153406NIH HHS R01AG081768ANIH HHS R35GM153406NINDS NIH HHS R01 NS033310NINDS NIH HHS U01 NS100608NINDS NIH HHS U54 NS123746NINDS NIH HHS U54NS123746NLM NIH HHS T15 LM013976
6 · The paper itself

Abstract

Alzheimer's Disease (AD), the most common neurodegenerative disease, is underdiagnosed and more prominent in underrepresented groups. We performed semi-supervised positive unlabeled learning (SSPUL) coupled with racial bias mitigation for equitable prediction of undiagnosed AD from diverse populations at UCLA Health using electronic health records. SSPUL achieved superior sensitivity (0.77-0.81) and area under the precision recall curve (AUCPR) (0.81-0.87) across non-Hispanic white, non-Hispanic African American, Hispanic Latino, and East Asian groups compared to supervised baseline models (sensitivity: 0.39-0.53; AUCPR: 0.3-0.7). SSPUL also exhibited superior fairness as evidenced by the lowest cumulative parity loss. We identified top shared and distinct features among labeled and unlabeled AD patients, including those that are neurological (e.g., memory loss) and non-neurological (e.g., decubitus ulcer). We validated our results using polygenic risk scores, which were higher in labeled and predicted positives than in predicted negatives among non-Hispanic white, Hispanic Latino, and East Asian groups (p < 0.001).

Identifiers

PMID41310166
PMCPMC12661022

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.