Academic Journal
Resource-stratified machine learning framework for cognitive status classification and mild cognitive impairment to dementia progression prediction.
| Τίτλος: | Resource-stratified machine learning framework for cognitive status classification and mild cognitive impairment to dementia progression prediction. |
|---|---|
| Συγγραφείς: | Yang J; Department of Electrical & Computer Engineering, Division of Systems Engineering, Department of Biomedical Engineering, Boston University, 8 St. Mary's St, Boston, MA, 02215, USA., Ding H; Department of Anatomy & Neurobiology and Framingham Heart Study, Chobanian & Avedisian School of Medicine, Boston University, 72 E Concord St, Boston, MA, 02118, USA., Amini S; Department of Electrical & Computer Engineering, Division of Systems Engineering, Department of Biomedical Engineering, Boston University, 8 St. Mary's St, Boston, MA, 02215, USA., Hao B; Department of Electrical & Computer Engineering, Division of Systems Engineering, Department of Biomedical Engineering, Boston University, 8 St. Mary's St, Boston, MA, 02215, USA., Karjadi C; Department of Anatomy & Neurobiology and Framingham Heart Study, Chobanian & Avedisian School of Medicine, Boston University, 72 E Concord St, Boston, MA, 02118, USA., Au R; Department of Anatomy & Neurobiology and Framingham Heart Study, Chobanian & Avedisian School of Medicine, Boston University, 72 E Concord St, Boston, MA, 02118, USA.; Department of Neurology and Medicine, Chobanian & Avedisian School of Medicine, Boston University, 72 E Concord St, Boston, MA, 02118, USA.; Department of Epidemiology, School of Public Health, Boston University, 72 E Concord St, Boston, MA, 02118, USA., Paschalidis IC; Department of Electrical & Computer Engineering, Division of Systems Engineering, Department of Biomedical Engineering, Boston University, 8 St. Mary's St, Boston, MA, 02215, USA. yannisp@bu.edu.; Faculty of Computing & Data Sciences, Boston University, 665 Commonwealth Ave, Boston, MA, 02215, USA. yannisp@bu.edu. |
| Πηγή: | Alzheimer's research & therapy [Alzheimers Res Ther] 2026 Mar 07; Vol. 18 (1). Date of Electronic Publication: 2026 Mar 07. |
| Τύπος έκδοσης: | Journal Article; Research Support, N.I.H., Extramural; Research Support, U.S. Gov't, Non-P.H.S. |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: BioMed Central Ltd Country of Publication: England NLM ID: 101511643 Publication Model: Electronic Cited Medium: Internet ISSN: 1758-9193 (Electronic) NLM ISO Abbreviation: Alzheimers Res Ther Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: [London] : BioMed Central Ltd. |
| Ιατρικοί όροι (MeSH): | Cognitive Dysfunction*/diagnosis , Cognitive Dysfunction*/classification , Dementia*/diagnosis , Dementia*/classification , Disease Progression* , Machine Learning*, Humans ; Female ; Male ; Aged ; Predictive Learning Models ; Neuropsychological Tests ; Classification Algorithms ; Prognosis ; Aged, 80 and over ; Boosting Machine Learning Algorithms ; Prediction Algorithms |
| Περίληψη: | BACKGROUND: Widespread access to diagnosis of cognitive decline remains inadequate. Assessment tools rely on neuroimaging, biofluid markers, or lengthy neuropsychological batteries. This reliance limits their use in primary care and low-resource settings and contributes to healthcare disparities. We developed and validated a three-level, resource-stratified machine learning framework to provide scalable dementia screening and prognostic risk stratification across diverse healthcare settings. METHODS: We used data from 31,081 participants in the National Alzheimer’s Coordinating Center. We trained Gradient Boosted Tree models for multi-class detection (Cognitively Intact/Mild Cognitive Impairment [MCI]/Dementia) and 10-year risk stratification (MCI-to-dementia progression). The framework tiered inputs by resource intensity. The minimal-resource Level 1 included demographic and basic functional data. The moderate-resource Level 2 added standard cognitive tests. The high-resource Level 3 added comprehensive neuropsychological batteries. RESULTS: The Level 3 model achieved high classification performance (AUC: 93.98%), and the Level 1 model achieved comparable performance (AUC: 91.53%). For MCI-to-dementia progression, the framework showed strong prognostic performance. The Level 3 and Level 1 models achieved AUCs of 85.90% and 81.90% for predicting progression over a 2-year window, respectively. Key predictors remained consistent across all resource levels, such as difficulty managing finances and self-reported cognitive decline, and sociodemographic factors, including education level and Black race. CONCLUSIONS: The tiered system offers a scalable and accessible approach for dementia detection and prognostic stratification. It helps non-specialists conduct initial evaluations and identify high-risk individuals with minimal data. High-risk patients may then be triaged for specialized assessment. This resource-stratified framework offers a strategy to expand diagnostic capacity and reduce care inequities, especially in low-resource settings. |
| Competing Interests: | Declarations. Ethics approval and consent to participate: The data used in this study were obtained from the NACC database. All participants provided informed consent at their respective ADRCs prior to data collection and submission to NACC. As secondary users of de-identified data from the NACC database, consent was not necessary for the use of human subject data in this study. The use of NACC UDS data for this research was conducted in accordance with NACC data use agreements. Consent for publication: All authors have reviewed the manuscript and consented to its publication. Competing interests: The authors declare no competing interests. |
| References: | Int J Equity Health. 2025 Mar 17;24(1):74. (PMID: 40091013) J Alzheimers Dis. 2022;87(4):1627-1636. (PMID: 35491782) BMJ Glob Health. 2022 Apr;7(4):. (PMID: 35379735) Alzheimers Dement. 2023 Feb;19(2):477-486. (PMID: 35451562) Clin Interv Aging. 2007;2(4):631-6. (PMID: 18225464) Alzheimers Dement. 2013 Nov;9(6):657-65. (PMID: 23332672) Alzheimers Dement. 2023 Sep;19(9):4046-4060. (PMID: 37204054) Alzheimers Dement. 2018 Mar;14(3):263-270. (PMID: 29055814) Alzheimers Dement. 2024 Aug;20(8):5551-5560. (PMID: 38934297) Alzheimers Dement (N Y). 2024 Apr 24;10(2):e12465. (PMID: 38659717) Int J Mol Sci. 2022 Nov 12;23(22):. (PMID: 36430432) J Alzheimers Dis. 2021;83(2):581-589. (PMID: 34334396) JAMA Intern Med. 2024 May 1;184(5):563-572. (PMID: 38436963) BMC Med. 2025 Feb 21;23(1):98. (PMID: 39984949) Alzheimers Dement. 2024 Jun;20(6):4290-4314. (PMID: 38696263) Alzheimers Dement (N Y). 2022 Mar 24;8(1):e12271. (PMID: 35356741) Alzheimers Dement. 2024 Feb;20(2):769-782. (PMID: 37776210) Neuroimage. 2014 Nov 1;101:569-82. (PMID: 25042445) Alzheimers Res Ther. 2022 Mar 29;14(1):45. (PMID: 35351193) Life Sci. 2022 Oct 1;306:120861. (PMID: 35932841) J Med Syst. 2023 Feb 1;47(1):17. (PMID: 36720727) Alzheimers Dement. 2023 Dec;19(12):5885-5904. (PMID: 37563912) Lancet. 2015 Jun 6;385(9984):2255-63. (PMID: 25771249) JAMA. 2019 Oct 22;322(16):1589-1599. (PMID: 31638686) Alzheimer Dis Assoc Disord. 2009 Oct-Dec;23(4):306-14. (PMID: 19568149) J Prev Alzheimers Dis. 2023;10(2):301-313. (PMID: 36946457) Biomed Mater Devices. 2023 Apr 10;:1-17. (PMID: 37363136) Neuroimage Clin. 2014 Jan 04;4:461-72. (PMID: 24634832) Alzheimers Dement. 2024 May;20(5):3708-3821. (PMID: 38689398) BMC Fam Pract. 2010 Jul 01;11:52. (PMID: 20594302) EClinicalMedicine. 2024 Jul 12;74:102725. (PMID: 39764178) Alzheimers Res Ther. 2024 Jun 7;16(1):122. (PMID: 38849944) Alzheimer Dis Assoc Disord. 2018 Oct-Dec;32(4):351-358. (PMID: 30376508) Lancet. 2024 Aug 10;404(10452):572-628. (PMID: 39096926) J Alzheimers Dis. 2021;81(2):729-742. (PMID: 33814438) Transl Neurodegener. 2025 Jan 27;14(1):6. (PMID: 39865265) Alzheimers Dement. 2025 Jun;21(6):e14333. (PMID: 39713942) Front Neurosci. 2021 Feb 19;15:584641. (PMID: 33746695) Nat Commun. 2022 Jun 20;13(1):3404. (PMID: 35725739) Alzheimers Dement. 2024 Aug;20(8):5262-5270. (PMID: 38924662) Alzheimers Dement (Amst). 2025 Mar 12;17(1):e70074. (PMID: 40078377) Nat Med. 2024 Oct;30(10):2977-2989. (PMID: 38965435) Alzheimers Dement (N Y). 2021 Jul 27;7(1):e12200. (PMID: 34337138) J Alzheimers Dis. 2020;75(1):277-288. (PMID: 32250302) J Alzheimers Dis. 2022;87(1):83-100. (PMID: 35342092) BMC Fam Pract. 2021 Aug 11;22(1):166. (PMID: 34380424) Front Aging Neurosci. 2022 Jun 02;14:876202. (PMID: 35721012) Clin Gerontol. 2023 Mar-Apr;46(2):133-137. (PMID: 35672953) Biomedicines. 2019 Dec 09;7(4):. (PMID: 31835422) Nat Rev Neurol. 2018 Nov;14(11):653-666. (PMID: 30291317) Alzheimers Dement (Amst). 2023 Oct 29;15(4):e12494. (PMID: 37908438) Curr Med Imaging. 2023;19(8):855-864. (PMID: 36177618) J Gen Intern Med. 2007 Nov;22(11):1487-92. (PMID: 17823840) |
| Grant Information: | UL54 TR00413 United States GF NIH HHS; R03 AG095992 United States AG NIA NIH HHS; AG062109 United States AG NIA NIH HHS; DEB-2433726 Office of Inspector General; CCF-2200052 National Science Foundation, United States; R01 AG062109 United States AG NIA NIH HHS; U19 AG068753 United States AG NIA NIH HHS; R01 AG072654 United States AG NIA NIH HHS; R01 AG083735 United States AG NIA NIH HHS; P30 AG072959 United States AG NIA NIH HHS; P30 AG072958 United States AG NIA NIH HHS; P20 AG068082 United States AG NIA NIH HHS; P20 AG068077 United States AG NIA NIH HHS; P20 AG068053 United States AG NIA NIH HHS; P20 AG068024 United States AG NIA NIH HHS; P30 AG066546 United States AG NIA NIH HHS; P30 AG072931 United States AG NIA NIH HHS; P30 AG072947 United States AG NIA NIH HHS; P30 AG066515 United States AG NIA NIH HHS; P30 AG066508 United States AG NIA NIH HHS; P30 AG066506 United States AG NIA NIH HHS; P30 AG072973 United States AG NIA NIH HHS; P30 AG072946 United States AG NIA NIH HHS; P30 AG066511 United States AG NIA NIH HHS; P30 AG062422 United States AG NIA NIH HHS; P30 AG062677 United States AG NIA NIH HHS; P30 AG066519 United States AG NIA NIH HHS; P30 AG072977 United States AG NIA NIH HHS; U24 AG072122 United States AG NIA NIH HHS; P30 AG062429 United States AG NIA NIH HHS; P30 AG066468 United States AG NIA NIH HHS; P30 AG062421 United States AG NIA NIH HHS; P30 AG066509 United States AG NIA NIH HHS; P30 AG066514 United States AG NIA NIH HHS; P30 AG066530 United States AG NIA NIH HHS; P30 AG066507 United States AG NIA NIH HHS; P30 AG066444 United States AG NIA NIH HHS; P30 AG066518 United States AG NIA NIH HHS; P30 AG066512 United States AG NIA NIH HHS; P30 AG066462 United States AG NIA NIH HHS; P30 AG072979 United States AG NIA NIH HHS; P30 AG072972 United States AG NIA NIH HHS |
| Contributed Indexing: | Keywords: Cognitive Assessment; Healthcare Disparities; MCI-to-Dementia Progression; Machine Learning; National Alzheimer’s Coordinating Center Data; Resource-Stratified Screening |
| Entry Date(s): | Date Created: 20260307 Date Completed: 20260628 Latest Revision: 20260813 |
| Update Code: | 20260813 |
| PubMed Central ID: | PMC13081641 |
| DOI: | 10.1186/s13195-026-02006-7 |
| PMID: | 41794745 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!