In one paragraphArticle in medRxiv : the preprint server for health sciences, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
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 registryThe 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 literatureWho cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
4 · The recordCorrections and comments
5 · Who and what moneyAuthors and funding
8 authors.
An ZhaoUCL Hawkes Institute, University College London, London, WC1E 6BT, UK.
Phoebe ImmsLeonard Davis School of Gerontology, University of Southern California, 3715 McClintock Ave, Los Angeles, CA, 90089, USA.ORCID 0000-0002-7205-4177 Andrei IrimiaLeonard Davis School of Gerontology, University of Southern California, 3715 McClintock Ave, Los Angeles, CA, 90089, USA.ORCID 0000-0002-9254-9388 Alzheimer’s Disease Neuroimaging Initiative
Funding
Project 1U19AG024904 · NIA · NORTHERN CALIFORNIA INSTITUTE/RES/EDU · PI MONICA G. RIVERA-MINDT · 2016 to 2026
$226.7MSmartphone-Based "Burst" Cognitive AssessmentsP01AG003991 · NIA · WASHINGTON UNIVERSITY · PI JOHN MORRIS · 1985 to 2026
$69.5MNational Alzheimer's Coordinating CenterU24AG072122 · NIA · UNIVERSITY OF WASHINGTON · PI STEPHENS, KARI A · 2021 to 2025
$45.8MResearch Education ComponentP30AG062422 · NIA · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · PI Katherine P Rankin · 2019 to 2026
$36.9MResearch Education ComponentP30AG062421 · NIA · MASSACHUSETTS GENERAL HOSPITAL · PI Christine S Ritchie · 2019 to 2026
$36.5MUCSD Shiley-Marcos Alzheimer's Disease Research Center P30P30AG062429 · NIA · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI DOUGLAS R GALASKO · 2019 to 2026
$34.9MWisconsin Alzheimer's Disease Research CenterP30AG062715 · NIA · UNIVERSITY OF WISCONSIN-MADISON · PI Sanjay Asthana · 2019 to 2026
$34.5MResearch Education ComponentP30AG062677 · NIA · MAYO CLINIC ROCHESTER · PI KEJAL KANTARCI · 2019 to 2026
$33.5MResearch Education ComponentP30AG066514 · NIA · ICAHN SCHOOL OF MEDICINE AT MOUNT SINAI · PI Margaret Sewell · 2020 to 2026
$31.0MYale Alzheimer Disease Research CenterP30AG066508 · NIA · YALE UNIVERSITY · PI STEPHEN M STRITTMATTER · 2020 to 2026
$30.2MResearch Education CoreP30AG066462 · NIA · COLUMBIA UNIVERSITY HEALTH SCIENCES · PI PHILIP L DE JAGER · 2020 to 2026
$30.1MResearch Education ComponentP30AG066468 · NIA · UNIVERSITY OF PITTSBURGH AT PITTSBURGH · PI C. Elizabeth Shaaban · 2020 to 2026
$29.4MNIA NIH HHS P01 AG003991NIA NIH HHS P20 AG068082NIA NIH HHS P30 AG017265NIA NIH HHS P30 AG062421NIA NIH HHS P30 AG062422NIA NIH HHS P30 AG062429NIA NIH HHS P30 AG062677NIA NIH HHS P30 AG062715NIA NIH HHS P30 AG066444NIA NIH HHS P30 AG066462NIA NIH HHS P30 AG066468NIA NIH HHS P30 AG066506NIA NIH HHS P30 AG066507NIA NIH HHS P30 AG066508NIA NIH HHS P30 AG066509NIA NIH HHS P30 AG066511NIA NIH HHS P30 AG066512NIA NIH HHS P30 AG066514NIA NIH HHS P30 AG066515NIA NIH HHS P30 AG066518NIA NIH HHS P30 AG066519NIA NIH HHS P30 AG066530NIA NIH HHS P30 AG066546NIA NIH HHS P30 AG072931NIA NIH HHS P30 AG072946NIA NIH HHS P30 AG072947NIA NIH HHS P30 AG072958NIA NIH HHS P30 AG072959NIA NIH HHS P30 AG072972NIA NIH HHS P30 AG072973NIA NIH HHS P30 AG072975NIA NIH HHS P30 AG072976NIA NIH HHS P30 AG072977NIA NIH HHS P30 AG072978NIA NIH HHS P30 AG072979NIA NIH HHS P30 AG086401NIA NIH HHS P30 AG086404NIA NIH HHS R01 AG079280NIA NIH HHS R01 AG079957NIA NIH HHS RF1 AG082201NIA NIH HHS T32 AG000037NIA NIH HHS U19 AG024904NIA NIH HHS U24 AG072122NINDS NIH HHS R01 NS100973
6 · The paper itselfAbstract
introductionArtificial intelligence and neuroimaging enable accurate dementia prediction, but 'black box' models can be difficult to trust. Explainable artificial intelligence (XAI) describes techniques to understand model behaviour and the influence of features, however deciding which method is most appropriate is non-trivial. Vision transformers (ViT) have also gained popularity, providing a self-explainable, alternative to traditional convolutional neural networks (CNN).
methodsWe used T1-weighted MRI to train models on two tasks: Alzheimer's disease (AD) classification (diagnosis) and predicting conversion from mild-cognitive impairment (MCI) to AD (prognosis). We compared ten XAI methods across CNN and ViT architectures.
resultsModels achieved balanced accuracies of 81% and 67% for diagnosis and prognosis. XAI outputs highlighted brain regions relevant to AD and contained useful information for MCI prognosis. DISCUSSION: XAI can be used to verify that models are utilising relevant features and to generate valuable measures for further analysis.
Identifiers
PMID39867413
PMCPMC11759246
What Socratic holds
Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390