{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:21:48Z","timestamp":1792790508773,"version":"4.5.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Alzheimer\u2019s disease (AD) accounts for 60\u201370% of the population with dementia. Mild cognitive impairment (MCI) is a diagnostic entity defined as an intermediate stage between subjective cognitive decline and dementia, and about 10\u201315% of people annually convert to AD. We aimed to investigate the most robust model and modality combination by combining multi-modality image features based on demographic characteristics in six machine learning models. A total of 196 subjects were enrolled from four hospitals and the Alzheimer\u2019s Disease Neuroimaging Initiative dataset. During the four-year follow-up period, 47 (24%) patients progressed from MCI to AD. Volumes of the regions of interest, white matter hyperintensity, and regional Standardized Uptake Value Ratio (SUVR) were analyzed using T1, T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRIs, and amyloid PET (\u03b1PET), along with automatically provided hippocampal occupancy scores (HOC) and Fazekas scales. As a result of testing the robustness of the model, the GBM model was the most stable, and in modality combination, model performance was further improved in the absence of T2-FLAIR image features. Our study predicts the probability of AD conversion in MCI patients, which is expected to be useful information for clinician\u2019s early diagnosis and treatment plan design.<\/jats:p>","DOI":"10.1038\/s41598-024-60134-2","type":"journal-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:02:14Z","timestamp":1716940934000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["A multimodal machine learning model for predicting dementia conversion in Alzheimer\u2019s disease"],"prefix":"10.1038","volume":"14","author":[{"given":"Min-Woo","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hye Weon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeong Sim","family":"Choe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeon Sik","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyeon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyunji","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jung Hyeon","family":"Yong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghyeon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong Woo","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"So Yeon","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Joon","family":"Son","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Min","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyug-Gi","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Regina E. Y.","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Kook","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"60134_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12929-019-0609-7","volume":"27","author":"LK Huang","year":"2020","unstructured":"Huang, L. K., Chao, S. P. & Hu, C. J. Clinical trials of new drugs for alzheimer disease. J. Biomed. Sci. 27, 1\u201313 (2020).","journal-title":"J. Biomed. Sci."},{"key":"60134_CR2","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1111\/joim.12190","volume":"275","author":"RC Petersen","year":"2014","unstructured":"Petersen, R. C. et al. Mild cognitive impairment: A concept in evolution. J. Internal Med. 275, 214\u2013228 (2014).","journal-title":"J. Internal Med."},{"key":"60134_CR3","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.1016\/j.neurobiolaging.2010.05.023","volume":"32","author":"C Davatzikos","year":"2011","unstructured":"Davatzikos, C., Bhatt, P., Shaw, L. M., Batmanghelich, K. N. & Trojanowski, J. Q. Prediction of mci to ad conversion, via mri, csf biomarkers, and pattern classification. Neurobiol. Aging 32, 2322-e19 (2011).","journal-title":"Neurobiol. Aging"},{"key":"60134_CR4","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1001\/archneur.56.3.303","volume":"56","author":"RC Petersen","year":"1999","unstructured":"Petersen, R. C. et al. Mild cognitive impairment: clinical characterization and outcome. Arch. Neurol. 56, 303\u2013308 (1999).","journal-title":"Arch. Neurol."},{"key":"60134_CR5","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1001\/archneurol.2009.106","volume":"66","author":"ST Farias","year":"2009","unstructured":"Farias, S. T., Mungas, D., Reed, B. R., Harvey, D. & DeCarli, C. Progression of mild cognitive impairment to dementia in clinic-vs community-based cohorts. Arch. Neurol. 66, 1151\u20131157 (2009).","journal-title":"Arch. Neurol."},{"key":"60134_CR6","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.exger.2006.05.016","volume":"42","author":"L Mosconi","year":"2007","unstructured":"Mosconi, L. et al. Early detection of alzheimer\u2019s disease using neuroimaging. Exp. Gerontol. 42, 129\u2013138 (2007).","journal-title":"Exp. Gerontol."},{"key":"60134_CR7","doi-asserted-by":"publisher","first-page":"221","DOI":"10.3233\/JAD-2010-1220","volume":"19","author":"WR Markesbery","year":"2010","unstructured":"Markesbery, W. R. Neuropathologic alterations in mild cognitive impairment: A review. J. Alzheimer\u2019s Dis. 19, 221\u2013228 (2010).","journal-title":"J. Alzheimer\u2019s Dis."},{"key":"60134_CR8","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1016\/j.neuroimage.2014.10.002","volume":"104","author":"E Moradi","year":"2015","unstructured":"Moradi, E. et al. Machine learning framework for early mri-based alzheimer\u2019s conversion prediction in mci subjects. Neuroimage 104, 398\u2013412 (2015).","journal-title":"Neuroimage"},{"key":"60134_CR9","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1016\/j.neuroimage.2008.10.031","volume":"44","author":"C Misra","year":"2009","unstructured":"Misra, C., Fan, Y. & Davatzikos, C. Baseline and longitudinal patterns of brain atrophy in mci patients, and their use in prediction of short-term conversion to ad: results from adni. Neuroimage 44, 1415\u20131422 (2009).","journal-title":"Neuroimage"},{"issue":"10","key":"60134_CR10","first-page":"755","volume":"1","author":"CC Luk","year":"2018","unstructured":"Luk, C. C. et al. Alzheimer\u2019s disease neuroimaging initiative. Alzheimer\u2019s disease 3-dimensional MRI texture for prediction of conversion from mild cognitive impairment. Alzheimer\u2019s Dementia Diagnosis Assess. Dis. Monit. 1(10), 755\u201363 (2018).","journal-title":"Alzheimer's Dementia Diagnosis Assess. Dis. Monit."},{"key":"60134_CR11","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.mri.2018.03.003","volume":"50","author":"M Gomez-Sancho","year":"2018","unstructured":"Gomez-Sancho, M. et al. Comparison of feature representations in mri-based mci-to-ad conversion prediction. Magn. Resonance Imaging 50, 84\u201395 (2018).","journal-title":"Magn. Resonance Imaging"},{"key":"60134_CR12","doi-asserted-by":"publisher","first-page":"944","DOI":"10.3174\/ajnr.A0949","volume":"29","author":"G Karas","year":"2008","unstructured":"Karas, G. et al. Amnestic mild cognitive impairment: Structural mr imaging findings predictive of conversion to Alzheimer disease. Am. J. Neuroradiol. 29, 944\u2013949 (2008).","journal-title":"Am. J. Neuroradiol."},{"key":"60134_CR13","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1016\/j.neurobiolaging.2010.04.029","volume":"31","author":"SL Risacher","year":"2010","unstructured":"Risacher, S. L. et al. Longitudinal mri atrophy biomarkers: Relationship to conversion in the adni cohort. Neurobiol. Aging 31, 1401\u20131418 (2010).","journal-title":"Neurobiol. Aging"},{"key":"60134_CR14","doi-asserted-by":"publisher","first-page":"4758","DOI":"10.1002\/hbm.22926","volume":"36","author":"P Coupe","year":"2015","unstructured":"Coupe, P. et al. Detection of alzheimer\u2019s disease signature in mr images seven years before conversion to dementia: Toward an early individual prognosis Hum. Brain Map. 36, 4758\u20134770 (2015).","journal-title":"Brain Map."},{"key":"60134_CR15","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1212\/WNL.0b013e3182343314","volume":"77","author":"D Heister","year":"2011","unstructured":"Heister, D. et al. Predicting mci outcome with clinically available mri and csf biomarkers. Neurology 77, 1619\u20131628 (2011).","journal-title":"Neurology"},{"key":"60134_CR16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13195-018-0453-0","volume":"11","author":"C Puzo","year":"2019","unstructured":"Puzo, C. et al. Independent effects of white matter hyperintensities on cognitive, neuropsychiatric, and functional decline: a longitudinal investigation using the national alzheimer\u2019s coordinating center uniform data set. Alzheimer\u2019s Res. Therapy 11, 1\u201313 (2019).","journal-title":"Alzheimer\u2019s Res. Therapy"},{"key":"60134_CR17","doi-asserted-by":"publisher","first-page":"170","DOI":"10.3390\/brainsci9070170","volume":"9","author":"OM Al-Janabi","year":"2019","unstructured":"Al-Janabi, O. M. et al. White matter hyperintensity regression: comparison of brain atrophy and cognitive profiles with progression and stable groups. Brain Sci. 9, 170 (2019).","journal-title":"Brain Sci."},{"key":"60134_CR18","first-page":"421","volume":"8","author":"F Fazekas","year":"1987","unstructured":"Fazekas, F., Chawluk, J. B., Alavi, A., Hurtig, H. I. & Zimmerman, R. A. Mr signal abnormalities at 1.5 t in alzheimer\u2019s dementia and normal aging. Am. J. Neuroradiol. 8, 421\u2013426 (1987).","journal-title":"Am. J. Neuroradiol."},{"key":"60134_CR19","doi-asserted-by":"publisher","first-page":"765","DOI":"10.3233\/JAD-161074","volume":"57","author":"S Hatashita","year":"2017","unstructured":"Hatashita, S. & Wakebe, D. Amyloid-\u03b2 deposition and long-term progression in mild cognitive impairment due to alzheimer\u2019s disease defined with amyloid pet imaging. J. Alzheimer\u2019s Dis. 57, 765\u2013773 (2017).","journal-title":"J. Alzheimer\u2019s Dis."},{"key":"60134_CR20","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1097\/MNM.0000000000000953","volume":"40","author":"Y Yan","year":"2019","unstructured":"Yan, Y., Somer, E. & Grau, V. Classification of amyloid pet images using novel features for early diagnosis of alzheimer\u2019s disease and mild cognitive impairment conversion. Nucl. Med. Commun. 40, 242\u2013248 (2019).","journal-title":"Nucl. Med. Commun."},{"key":"60134_CR21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0154406","volume":"11","author":"X Chen","year":"2016","unstructured":"Chen, X. et al. Potential clinical value of multiparametric pet in the prediction of alzheimer\u2019s disease progression. PLoS One 11, e0154406 (2016).","journal-title":"PLoS One"},{"key":"60134_CR22","doi-asserted-by":"crossref","unstructured":"Blazhenets, G., Soerensen, A., Schiller, F., Frings, L. & Meyer, P. Predictive value of quantitative f-18-florbetapir and f-18-fdg pet for conversion from mci to ad (2019).","DOI":"10.1055\/s-0039-1683502"},{"key":"60134_CR23","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1007\/s11682-015-9356-x","volume":"9","author":"B Cheng","year":"2015","unstructured":"Cheng, B., Liu, M., Suk, H.-I., Shen, D. & Zhang, D. Multimodal manifold-regularized transfer learning for mci conversion prediction. Brain Imaging Behavior 9, 913\u2013926 (2015).","journal-title":"Brain Imaging Behavior"},{"key":"60134_CR24","doi-asserted-by":"crossref","unstructured":"Rana, S.S., Ma, X., Pang, W. & Wolverson, E. A multi-modal deep learning approach to the early prediction of mild cognitive impairment conversion to alzheimer\u2019s disease. In 2020 IEEE\/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT), 9\u201318 (IEEE, 2020).","DOI":"10.1109\/BDCAT50828.2020.00013"},{"key":"60134_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/6628036","volume":"2021","author":"S Minhas","year":"2021","unstructured":"Minhas, S. et al. Early mci-to-ad conversion prediction using future value forecasting of multimodal features. Comput. Intell. Neurosci. 2021, 1\u201312 (2021).","journal-title":"Comput. Intell. Neurosci."},{"key":"60134_CR26","doi-asserted-by":"publisher","first-page":"674","DOI":"10.3390\/brainsci11060674","volume":"11","author":"H-T Li","year":"2021","unstructured":"Li, H.-T., Yuan, S.-X., Wu, J.-S., Gu, Y. & Sun, X. Predicting conversion from mci to ad combining multi-modality data and based on molecular subtype. Brain sciences 11, 674 (2021).","journal-title":"Brain sciences"},{"key":"60134_CR27","doi-asserted-by":"publisher","first-page":"974","DOI":"10.3390\/brainsci10120974","volume":"10","author":"M Lee","year":"2020","unstructured":"Lee, M. et al. Split-attention u-net: a fully convolutional network for robust multi-label segmentation from brain mri. Brain Sci. 10, 974 (2020).","journal-title":"Brain Sci."},{"key":"60134_CR28","doi-asserted-by":"publisher","first-page":"237","DOI":"10.13104\/imri.2022.26.4.237","volume":"26","author":"SY Jeong","year":"2022","unstructured":"Jeong, S. Y., Suh, C. H., Heo, H., Shim, W. H. & Kim, S. J. Current updates and unmet needs of brain mri-based artificial intelligence software for patients with neurodegenerative diseases in the republic of korea. Investig. Magn. Reson. Imaging 26, 237\u2013245 (2022).","journal-title":"Investig. Magn. Reson. Imaging"},{"key":"60134_CR29","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1016\/j.neuroimage.2004.06.018","volume":"23","author":"RL Buckner","year":"2004","unstructured":"Buckner, R. L. et al. A unified approach for morphometric and functional data analysis in young, old, and demented adults using automated atlas-based head size normalization: Reliability and validation against manual measurement of total intracranial volume. Neuroimage 23, 724\u2013738 (2004).","journal-title":"Neuroimage"},{"key":"60134_CR30","doi-asserted-by":"publisher","first-page":"2130","DOI":"10.3174\/ajnr.A7358","volume":"42","author":"S Bash","year":"2021","unstructured":"Bash, S. et al. Deep learning enables 60% accelerated volumetric brain mri while preserving quantitative performance: a prospective, multicenter, multireader trial. Am. J. Neuroradiol. 42, 2130\u20132137 (2021).","journal-title":"Am. J. Neuroradiol."},{"key":"60134_CR31","doi-asserted-by":"publisher","first-page":"57","DOI":"10.31083\/j.jin2203057","volume":"22","author":"Z Rieu","year":"2023","unstructured":"Rieu, Z. et al. A fully automated visual grading system for white matter hyperintensities of t2-fluid attenuated inversion recovery magnetic resonance imaging. J. Integr. Neurosci. 22, 57 (2023).","journal-title":"J. Integr. Neurosci."},{"key":"60134_CR32","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"1","author":"ER DeLong","year":"1988","unstructured":"DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics. 1, 837\u201345 (1988).","journal-title":"Biometrics."},{"key":"60134_CR33","first-page":"836510","volume":"11","author":"J Orozco-Sanchez","year":"2019","unstructured":"Orozco-Sanchez, J., Trevino, V., Martinez-Ledesma, E., Farber, J. & Tamez-Pe\u00f1a, J. Exploring survival models associated with mci to ad conversion: A machine learning approach. BioRxiv. 11, 836510 (2019).","journal-title":"BioRxiv."},{"key":"60134_CR34","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1016\/j.neuroimage.2010.10.081","volume":"55","author":"C Hinrichs","year":"2011","unstructured":"Hinrichs, C. et al. Predictive markers for ad in a multi-modality framework: An analysis of mci progression in the adni population. Neuroimage 55, 574\u2013589 (2011).","journal-title":"Neuroimage"},{"key":"60134_CR35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0033182","volume":"7","author":"D Zhang","year":"2012","unstructured":"Zhang, D., Shen, D. & Initiative, A. D. N. Predicting future clinical changes of mci patients using longitudinal and multimodal biomarkers. PloS one 7, e33182 (2012).","journal-title":"PloS one"},{"key":"60134_CR36","doi-asserted-by":"publisher","first-page":"688926","DOI":"10.3389\/fnagi.2021.688926","volume":"13","author":"T Zhang","year":"2021","unstructured":"Zhang, T. et al. Predicting mci to ad conversation using integrated smri and rs-fmri: machine learning and graph theory approach. Front. Aging Neurosci. 13, 688926 (2021).","journal-title":"Front. Aging Neurosci."},{"key":"60134_CR37","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.neuroscience.2023.01.029","volume":"514","author":"R Franciotti","year":"2023","unstructured":"Franciotti, R. et al. Comparison of machine learning-based approaches to predict the conversion to alzheimer\u2019s disease from mild cognitive impairment. Neuroscience 514, 143\u2013152 (2023).","journal-title":"Neuroscience"},{"key":"60134_CR38","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3389\/fnagi.2020.00077","volume":"12","author":"W Lin","year":"2020","unstructured":"Lin, W. et al. Predicting alzheimer\u2019s disease conversion from mild cognitive impairment using an extreme learning machine-based grading method with multimodal data. Front. Aging Neurosci. 12, 77 (2020).","journal-title":"Front. Aging Neurosci."},{"key":"60134_CR39","doi-asserted-by":"publisher","first-page":"877","DOI":"10.3233\/JAD-201451","volume":"80","author":"K Hirao","year":"2021","unstructured":"Hirao, K. et al. Association of white matter hyperintensity progression with cognitive decline in patients with amnestic mild cognitive impairment. J. Alzheimer\u2019s Dis. 80, 877\u2013883 (2021).","journal-title":"J. Alzheimer\u2019s Dis."},{"key":"60134_CR40","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.neurobiolaging.2018.12.004","volume":"76","author":"M Dadar","year":"2019","unstructured":"Dadar, M. et al. White matter in different regions evolves differently during progression to dementia. Neurobiol. Aging 76, 71\u201379 (2019).","journal-title":"Neurobiol. Aging"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-60134-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-60134-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-60134-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:02:23Z","timestamp":1716940943000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-60134-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["60134"],"URL":"https:\/\/doi.org\/10.1038\/s41598-024-60134-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,29]]},"assertion":[{"value":"7 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"12276"}}