{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T19:18:27Z","timestamp":1790536707629,"version":"4.1.0"},"reference-count":29,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T00:00:00Z","timestamp":1655856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003478","name":"Ministry of Health","doi-asserted-by":"publisher","award":["20FC1041"],"award-info":[{"award-number":["20FC1041"]}],"id":[{"id":"10.13039\/501100003478","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003478","name":"Ministry of Health","doi-asserted-by":"publisher","award":["201803011A"],"award-info":[{"award-number":["201803011A"]}],"id":[{"id":"10.13039\/501100003478","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Medical ICT and Artificial Intelligence","award":["20FC1041"],"award-info":[{"award-number":["20FC1041"]}]},{"name":"Medical ICT and Artificial Intelligence","award":["201803011A"],"award-info":[{"award-number":["201803011A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biology"],"abstract":"<jats:p>Multiple-system atrophy (MSA) is primarily an autonomic disorder with parkinsonism or cerebellar ataxia. Clinical diagnosis of MSA at an early stage is challenging because the symptoms change over the course of the disease. Recently, various artificial intelligence-based programs have been developed to improve the diagnostic accuracy of neurodegenerative diseases, but most are limited to the evaluation of diagnostic imaging. In this study, we examined the validity of diagnosis of MSA using a pointwise linear model (deep learning-based method). The goal of the study was to identify features associated with disease differentiation that were found to be important in deep learning. A total of 3377 registered MSA cases from FY2004 to FY2008 were used to train the model. The diagnostic probabilities of SND (striatonigral degeneration), SDS (Shy-Drager syndrome), and OPCA (olivopontocerebellar atrophy) were estimated to be 0.852 \u00b1 0.107, 0.650 \u00b1 0.235, and 0.858 \u00b1 0.270, respectively. In the pointwise linear model used to identify and visualize features involved in individual subtypes, autonomic dysfunction was found to be a more prominent component of SDS compared to SND and OPCA. Similarly, respiratory failure was identified as a characteristic of SDS, dysphagia was identified as a characteristic of SND, and brain-stem atrophy was identified as a characteristic of OPCA.<\/jats:p>","DOI":"10.3390\/biology11070951","type":"journal-article","created":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T21:31:06Z","timestamp":1655933466000},"page":"951","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving the Accuracy of Diagnosis for Multiple-System Atrophy Using Deep Learning-Based Method"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5790-4084","authenticated-orcid":false,"given":"Yasuhiro","family":"Kanatani","sequence":"first","affiliation":[{"name":"Department of Clinical Pharmacology, Tokai University School of Medicine, 143 Shimokasuya, Isehara City 259-1193, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8123-5191","authenticated-orcid":false,"given":"Yoko","family":"Sato","sequence":"additional","affiliation":[{"name":"Division of Clinical Biostatistics, Shizuoka Graduate University of Public Health, 4-27-1 Kitaando Aoi-ku, Shizuoka City 420-0881, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shota","family":"Nemoto","sequence":"additional","affiliation":[{"name":"Industrial & Digital Business Unit, Hitachi, Ltd., 1-5-2 Sotokanda, Chiyoda-ku, Tokyo 101-0021, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5943-516X","authenticated-orcid":false,"given":"Manabu","family":"Ichikawa","sequence":"additional","affiliation":[{"name":"Department of Planning, Architecture and Environmental Systems, Shibaura Institute of Technology, 307 Fukasaku, Minuma-ku, Saitama City 337-8570, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osamu","family":"Onodera","sequence":"additional","affiliation":[{"name":"Department of Neurology, Brain Research Institute, Niigata University, 1-757 Asahimachidori, Chuo-ku, Niigata City 951-8585, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1056\/NEJMra1311488","article-title":"Multiple-System Atrophy","volume":"372","author":"Fanciulli","year":"2015","journal-title":"N. Engl. J. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/S0022-510X(98)00304-9","article-title":"Consensus statement on the diagnosis of multiple system atrophy","volume":"163","author":"Gilman","year":"1999","journal-title":"J. Neurol. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1212\/01.wnl.0000324625.00404.15","article-title":"Second consensus statement on the diagnosis of multiple system atrophy","volume":"71","author":"Gilman","year":"2008","journal-title":"Neurology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1212\/WNL.0000000000001807","article-title":"PD, and PSP masquerade as MSA: An autopsy study of 134 patients","volume":"85","author":"Koga","year":"2015","journal-title":"Neurology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102081","DOI":"10.1016\/j.artmed.2021.102081","article-title":"Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques","volume":"117","author":"Ionescu","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.acra.2008.05.024","article-title":"Automated computer differential classification in Parkinsonian Syndromes via pattern analysis on MRI","volume":"16","author":"Duchesne","year":"2009","journal-title":"Acad. Radiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2813","DOI":"10.1093\/brain\/awz189","article-title":"Improving diagnostic accuracy of multiple system atrophy: A clinicopathological study","volume":"142","author":"Miki","year":"2019","journal-title":"Brain"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1038\/s41582-020-0377-8","article-title":"Applications of machine learning to diagnosis and treatment of neurodegenerative diseases","volume":"16","author":"Myszczynska","year":"2020","journal-title":"Nat. Rev. Neurol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1007\/s00415-019-09518-3","article-title":"Artificial intelligence as an emerging technology in the current care of neurological disorders","volume":"268","author":"Patel","year":"2021","journal-title":"J. Neurol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3923","DOI":"10.1038\/s41467-020-17419-7","article-title":"Improving the accuracy of medical diagnosis with causal machine learning","volume":"11","author":"Richens","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s10286-020-00682-5","article-title":"Diagnosing multiple system atrophy at the prodromal stage","volume":"30","author":"Xia","year":"2020","journal-title":"Clin. Auton. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1001\/archneur.64.2.256","article-title":"Early development of autonomic dysfunction may predict poor prognosis in patients with multiple system atrophy","volume":"64","author":"Tada","year":"2007","journal-title":"Arch. Neurol."},{"key":"ref_13","first-page":"1","article-title":"Machine learning in clinical and epidemiological research: Isn\u2019t it time for biostatisticians to work on it?","volume":"16","author":"Azzolina","year":"2019","journal-title":"Epidemiol. Biostat. Public Health"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1111\/jgh.15384","article-title":"Opening the black box of AI-Medicine","volume":"36","author":"Poon","year":"2021","journal-title":"J. Gastroenterol. Hepatol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Shibahara, T., Wada, C., Yamashita, Y., Fujita, K., Sato, M., Okamoto, A., and Ono, Y. (2021). Deep learning generates custom-made logistic regression models for explaining how breast cancer subtypes are classified. bioRxiv.","DOI":"10.21203\/rs.3.rs-598333\/v1"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1038\/s41590-020-0769-3","article-title":"The PD-1 expression balance between effector and regulatory T cells predicts the clinical efficacy of PD-1 blockade therapies","volume":"21","author":"Kumagai","year":"2020","journal-title":"Nat. Immunol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2176\/nmc.st.2016-0135","article-title":"National Registry of Designated Intractable Diseases in Japan: Present Status and Future Prospects","volume":"57","author":"Kanatani","year":"2017","journal-title":"Neurol. Med. Chir."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/S0022-510X(96)00231-6","article-title":"International Cooperative Ataxia Rating Scale for pharmacological assessment of the cerebellar syndrome. The Ataxia Neuropharmacology Committee of the World Federation of Neurology","volume":"145","author":"Trouillas","year":"1997","journal-title":"J. Neurol. Sci."},{"key":"ref_19","first-page":"153","article-title":"Members of the UPDRS Development Committee. The Unified Parkinson\u2019s Disease Rating Scale","volume":"Volume 2","author":"Fahn","year":"1987","journal-title":"Recent Developments in Parkinson\u2019s Disease"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.1002\/mds.20255","article-title":"Multiple System Atrophy Study Group. Development and validation of the Unified Multiple System Atrophy Rating Scale (UMSARS)","volume":"19","author":"Wenning","year":"2004","journal-title":"Mov. Disord."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/S1474-4422(06)70495-1","article-title":"Clinical interpretation and use of stroke scales","volume":"5","author":"Kasner","year":"2006","journal-title":"Lancet Neurol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Golas, S.B., Shibahara, T., Agboola, S., Otaki, H., Sato, J., Nakae, T., Hisamitsu, T., Kojima, G., Felsted, J., and Kakarmath, S. (2018). A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: A retrospective analysis of electronic medical records data. BMC Med. Inform. Decis. Mak., 18.","DOI":"10.1186\/s12911-018-0620-z"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1136\/jnnp-2017-315813","article-title":"Recent advances in neuropathology, biomarkers and therapeutic approach of multiple system atrophy","volume":"89","author":"Koga","year":"2018","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1007\/s00702-021-02406-z","article-title":"Current experimental disease-modifying therapeutics for multiple system atrophy","volume":"128","author":"Lemos","year":"2021","journal-title":"J. Neural Transm."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1959","DOI":"10.1093\/brain\/awx118","article-title":"Clinical criteria for subtyping Parkinson\u2019s disease: Biomarkers and longitudinal progression","volume":"140","author":"Fereshtehnejad","year":"2017","journal-title":"Brain"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Rajula, H.S.R., Verlato, G., Manchia, M., Antonucci, N., and Fanos, V. (2020). Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment. Medicina, 56.","DOI":"10.3390\/medicina56090455"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: An overview and application in radiology","volume":"9","author":"Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1001\/archneur.63.7.978","article-title":"Respiratory insufficiency as the primary presenting symptom of multiple-system atrophy","volume":"63","author":"Glass","year":"2006","journal-title":"Arch. Neurol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.parkreldis.2021.03.027","article-title":"Dysphagia in multiple system atrophy consensus statement on diagnosis, prognosis and treatment","volume":"86","author":"Alfonsi","year":"2021","journal-title":"Parkinsonism Relat. Disord."}],"container-title":["Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-7737\/11\/7\/951\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:37:42Z","timestamp":1760139462000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-7737\/11\/7\/951"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,22]]},"references-count":29,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["biology11070951"],"URL":"https:\/\/doi.org\/10.3390\/biology11070951","relation":{},"ISSN":["2079-7737"],"issn-type":[{"value":"2079-7737","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,22]]}}}