{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:31:52Z","timestamp":1789475512278,"version":"build-2803163510"},"reference-count":23,"publisher":"BMJ","issue":"6","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"unspecified","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["IITP-2026-RS-2020-II201791"],"award-info":[{"award-number":["IITP-2026-RS-2020-II201791"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,6,16]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Periodic cognitive monitoring for mild cognitive impairment (MCI) is crucial. However, standard assessments like the Montreal Cognitive Assessment (MoCA) require in-person administration due to visual-based items, creating significant accessibility barriers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop and rigorously validate a machine learning model to accurately estimate total MoCA scores using only telephone-based (remote) items and demographic information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Data from three independent MCI cohorts (2022\u20132024) were used. Data from 2022 to 2023 (N=425) formed the training set; 2024 data (N=356) were the temporal test set. Models were trained to predict the 8-point visual-based score using 37 telephonic\/demographic features. Fivefold cross-validation (80% training\/20% validation per fold) was performed exclusively on the training set to compare three heterogeneous machine learning models. Random Forest, Linear Regression and XGBoost models were compared. The final score was reconstructed by summing actual telephonic scores with the predicted visual score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>\n                      In the fivefold cross-validation on the training set, the Random Forest model achieved the lowest mean Root Mean Squared Error (RMSE=1.2034) of 1.2034 points (SD=0.0407; 95%\u2009CI 1.1528 to 1.2540) for Visual Score prediction, though pairwise differences between models did not reach statistical significance, likely reflecting the limited power of fivefold comparisons. When applied to the 2024 temporal test set, the reconstructed total score showed high concordance with the actual total MoCA score (RMSE=1.29 points; mean absolute error=1.01 points; R\n                      <jats:sup>2<\/jats:sup>\n                      =0.9248). The most important features were education (28.7% importance) and age (13.8%), followed by sustained attention (4.1%).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our machine learning model accurately and reliably predicts total 30-point MoCA scores using only telephone-based information. The model demonstrated satisfactory generalisation performance on a temporally separated cohort, supporting its potential clinical applicability pending external validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-114046","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T13:32:45Z","timestamp":1782739965000},"page":"e114046","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Development and temporal validation of a machine learning model to estimate total MoCA scores from telephone-based items in patients with mild cognitive impairment"],"prefix":"10.1136","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0068-9904","authenticated-orcid":false,"given":"Chan-Young","family":"Kwon","sequence":"first","affiliation":[{"name":"Department of Oriental Neuropsychiatry, Dong-Eui University College of Korean Medicine, Busan, Korea (the Republic of)"},{"name":"Anti-Aging Research Center, Dong-Eui University, Busan, Korea (the Republic of)"},{"name":"Research Institute of Korean Medicine, Dong-Eui University, Busan, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"2026062906301640000_16.6.e114046.1","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.61.1.59"},{"key":"2026062906301640000_16.6.e114046.2","doi-asserted-by":"crossref","DOI":"10.1002\/dad2.70074","article-title":"The prognosis of mild cognitive impairment: A systematic review and meta-analysis","volume":"17","author":"Salemme","year":"2025","journal-title":"Alzheimers Dement (Amst)"},{"key":"2026062906301640000_16.6.e114046.3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2005.53221.x"},{"key":"2026062906301640000_16.6.e114046.4","doi-asserted-by":"crossref","DOI":"10.1093\/ageing\/afae051","article-title":"Strategies used during the cognitive evaluation of older adults with dual sensory impairment: a scoping review","volume":"53","author":"Dumassais","year":"2024","journal-title":"Age Ageing"},{"key":"2026062906301640000_16.6.e114046.5","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1176\/appi.neuropsych.20220154","article-title":"Telemedicine-Based Cognitive Examinations During COVID-19 and Beyond: Perspective of the Massachusetts General Hospital Behavioral Neurology & Neuropsychiatry Group","volume":"36","author":"Tanev","year":"2024","journal-title":"J Neuropsychiatry Clin Neurosci"},{"key":"2026062906301640000_16.6.e114046.6","doi-asserted-by":"publisher","DOI":"10.1001\/archneurol.2011.88"},{"key":"2026062906301640000_16.6.e114046.7","doi-asserted-by":"crossref","DOI":"10.1002\/dad2.12144","article-title":"T-MoCA: A valid phone screen for cognitive impairment in diverse community samples","volume":"13","author":"Katz","year":"2021","journal-title":"Alzheimers Dement (Amst)"},{"key":"2026062906301640000_16.6.e114046.8","doi-asserted-by":"crossref","DOI":"10.3389\/fneur.2024.1440111","article-title":"Effectiveness of Korean medicine treatments in improving cognitive function and prefrontal cortex activity in older individuals with mild cognitive impairment: retrospective observational study","volume":"15","author":"Choi","year":"2024","journal-title":"Front Neurol"},{"key":"2026062906301640000_16.6.e114046.9","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","year":"2024","journal-title":"BMJ"},{"key":"2026062906301640000_16.6.e114046.10","doi-asserted-by":"publisher","DOI":"10.1177\/0891988708316855"},{"key":"2026062906301640000_16.6.e114046.11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026062906301640000_16.6.e114046.12","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. San Francisco, California, USA: Association for Computing Machinery, 2016:785\u201394.","DOI":"10.1145\/2939672.2939785"},{"key":"2026062906301640000_16.6.e114046.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2026062906301640000_16.6.e114046.14","unstructured":"Lundberg SM , Lee S-I . A unified approach to interpreting model predictions. In: Advances in neural information processing systems. 2017."},{"key":"2026062906301640000_16.6.e114046.15","doi-asserted-by":"crossref","unstructured":"Harrell FE . Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. Springer International Publishing, 2015.","DOI":"10.1007\/978-3-319-19425-7"},{"key":"2026062906301640000_16.6.e114046.16","unstructured":"Tabachnick BG , Fidell LS . Using multivariate statistics. Pearson Education, 2013."},{"key":"2026062906301640000_16.6.e114046.17","doi-asserted-by":"crossref","first-page":"A9","DOI":"10.1016\/j.jss.2019.09.075","article-title":"Amplifying the Noise: The Dangers of Post Hoc Power Analyses","volume":"259","author":"Griffith","year":"2021","journal-title":"J Surg Res"},{"key":"2026062906301640000_16.6.e114046.18","doi-asserted-by":"crossref","DOI":"10.1002\/dad2.12516","article-title":"An explainable machine learning model of cognitive decline derived from speech","volume":"15","author":"Chandler","year":"2023","journal-title":"Alzheimers Dement (Amst)"},{"key":"2026062906301640000_16.6.e114046.19","doi-asserted-by":"crossref","first-page":"187","DOI":"10.12779\/dnd.2025.24.3.187","article-title":"Assessing the Equivalence of Telephone-MoCA and MoCA-22 in Healthy Adults","volume":"24","author":"Kim","year":"2025","journal-title":"Dement Neurocogn Disord"},{"key":"2026062906301640000_16.6.e114046.20","doi-asserted-by":"crossref","DOI":"10.1038\/s44271-025-00198-6","article-title":"Cognitive reserve is associated with education, social determinants, and cognitive outcomes among older American Indians in the Strong Heart Study","volume":"3","author":"Suchy-Dicey","year":"2025","journal-title":"Commun Psychol"},{"key":"2026062906301640000_16.6.e114046.21","doi-asserted-by":"publisher","DOI":"10.1006\/cogp.1999.0734"},{"key":"2026062906301640000_16.6.e114046.22","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"2026062906301640000_16.6.e114046.23","doi-asserted-by":"crossref","DOI":"10.3389\/fnagi.2016.00052","article-title":"The Differentiation of Amnestic Type MCI from the Non-Amnestic Types by Structural MRI","volume":"8","author":"Csukly","year":"2016","journal-title":"Front Aging Neurosci"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-114046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T13:32:53Z","timestamp":1782739973000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-114046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":23,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,29]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjopen-2025-114046"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-114046","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}