{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T01:20:20Z","timestamp":1775784020976,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T00:00:00Z","timestamp":1600128000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T00:00:00Z","timestamp":1600128000000},"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":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Parkinson\u2019s Disease (PD) is a clinically diagnosed neurodegenerative disorder that affects both motor and non-motor neural circuits. Speech deterioration (hypokinetic dysarthria) is a common symptom, which often presents early in the disease course. Machine learning can help movement disorders specialists improve their diagnostic accuracy using non-invasive and inexpensive voice recordings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>We used \u201cParkinson Dataset with Replicated Acoustic Features Data Set\u201d from the UCI-Machine Learning repository. The dataset included 44 speech-test based acoustic features from patients with PD and controls. We analyzed the data using various machine learning algorithms including Light and Extreme Gradient Boosting, Random Forest, Support Vector Machines, K-nearest neighborhood, Least Absolute Shrinkage and Selection Operator Regression, as well as logistic regression. We also implemented a variable importance analysis to identify important variables classifying patients with PD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The cohort included a total of 80 subjects: 40 patients with PD (55% men) and 40 controls (67.5% men). Disease duration was 5\u2009years or less for all subjects, with a mean Unified Parkinson\u2019s Disease Rating Scale (UPDRS) score of 19.6 (SD 8.1), and none were taking PD medication. The mean age for PD subjects and controls was 69.6 (SD 7.8) and 66.4 (SD 8.4), respectively. Our best-performing model used Light Gradient Boosting to provide an AUC of 0.951 with 95% confidence interval 0.946\u20130.955 in 4-fold cross validation using only seven acoustic features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Machine learning can accurately detect Parkinson\u2019s disease using an inexpensive and non-invasive voice recording. Light Gradient Boosting outperformed other machine learning algorithms. Such approaches could be used to inexpensively screen large patient populations for Parkinson\u2019s disease.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-020-01250-7","type":"journal-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T10:03:53Z","timestamp":1600164233000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":70,"title":["Gradient boosting for Parkinson\u2019s disease diagnosis from voice recordings"],"prefix":"10.1186","volume":"20","author":[{"given":"Ibrahim","family":"Karabayir","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel M.","family":"Goldman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suguna","family":"Pappu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0313-9254","authenticated-orcid":false,"given":"Oguz","family":"Akbilgic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,15]]},"reference":[{"issue":"2","key":"1250_CR1","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/s0733-8619(05)70259-0","volume":"14","author":"CM Tanner","year":"1996","unstructured":"Tanner CM, Goldman SM. Epidemiology of Parkinson's disease. Neurol Clin. 1996;14(2):317\u201335. https:\/\/doi.org\/10.1016\/s0733-8619(05)70259-0.","journal-title":"Neurol Clin"},{"issue":"5","key":"1250_CR2","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1212\/01.wnl.0000247740.47667.03","volume":"68","author":"ER Dorsey","year":"2007","unstructured":"Dorsey ER, et al. Projected number of people with Parkinson disease in the most populous nations, 2005 through 2030. Neurology. 2007;68(5):384\u20136. https:\/\/doi.org\/10.1212\/01.wnl.0000247740.47667.03.","journal-title":"Neurology"},{"key":"1250_CR3","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1038\/s41531-018-0058-0","volume":"4","author":"C Marras","year":"2018","unstructured":"Marras C, et al. Prevalence of Parkinson's disease across North America. NPJ Parkinsons Dis. 2018;4:21. https:\/\/doi.org\/10.1038\/s41531-018-0058-0.","journal-title":"NPJ Parkinsons Dis"},{"issue":"Pt 5","key":"1250_CR4","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1093\/brain\/114.5.2283","volume":"114","author":"JM Fearnley","year":"1991","unstructured":"Fearnley JM, Lees AJ. Ageing and Parkinson's disease: substantia nigra regional selectivity. Brain. 1991;114(Pt 5):2283\u2013301. https:\/\/doi.org\/10.1093\/brain\/114.5.2283.","journal-title":"Brain"},{"issue":"Suppl 1","key":"1250_CR5","doi-asserted-by":"publisher","first-page":"S199","DOI":"10.1016\/s1353-8020(11)70062-1","volume":"18","author":"GW Ross","year":"2012","unstructured":"Ross GW, Abbott RD, Petrovitch H, Tanner CM, White LR. Pre-motor features of Parkinson's disease: the Honolulu-Asia Aging Study experience. Parkinsonism Relat Disord. 2012;18(Suppl 1):S199\u2013202. https:\/\/doi.org\/10.1016\/s1353-8020(11)70062-1.","journal-title":"Parkinsonism Relat Disord"},{"issue":"16","key":"1250_CR6","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1503\/cmaj.151179","volume":"188","author":"P Rizek","year":"2016","unstructured":"Rizek P, Kumar N, Jog MS. An update on the diagnosis and treatment of Parkinson disease. Cmaj. 2016;188(16):1157\u201365. https:\/\/doi.org\/10.1503\/cmaj.151179.","journal-title":"Cmaj"},{"issue":"7","key":"1250_CR7","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1212\/01.wnl.0000215437.80053.d0","volume":"66","author":"O Suchowersky","year":"2006","unstructured":"Suchowersky O, Reich S, Perlmutter J, Zesiewicz T, Gronseth G, Weiner WJ. Practice Parameter: diagnosis and prognosis of new onset Parkinson disease (an evidence-based review): report of the Quality Standards Subcommittee of the American Academy of Neurology. Neurology. 2006;66(7):968\u201375. https:\/\/doi.org\/10.1212\/01.wnl.0000215437.80053.d0.","journal-title":"Neurology"},{"issue":"16","key":"1250_CR8","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1056\/nejm199810153391607","volume":"339","author":"AE Lang","year":"1998","unstructured":"Lang AE, Lozano AM. Parkinson\u2019s disease. Second of two parts. N Engl J Med. 1998;339(16):1130\u201343. https:\/\/doi.org\/10.1056\/nejm199810153391607.","journal-title":"N Engl J Med"},{"issue":"3","key":"1250_CR9","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44(3):837\u201345.","journal-title":"Biometrics"},{"issue":"6","key":"1250_CR10","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1212\/wnl.0000000000002350","volume":"86","author":"G Rizzo","year":"2016","unstructured":"Rizzo G, Copetti M, Arcuti S, Martino D, Fontana A, Logroscino G. Accuracy of clinical diagnosis of Parkinson disease: A systematic review and meta-analysis. Neurology. 2016;86(6):566\u201376. https:\/\/doi.org\/10.1212\/wnl.0000000000002350.","journal-title":"Neurology"},{"issue":"4","key":"1250_CR11","doi-asserted-by":"publisher","first-page":"884","DOI":"10.1109\/tbme.2009.2036000","volume":"57","author":"A Tsanas","year":"2010","unstructured":"Tsanas A, Little MA, McSharry PE, Ramig LO. Accurate telemonitoring of Parkinson's disease progression by noninvasive speech tests. IEEE Trans Biomed Eng. 2010;57(4):884\u201393. https:\/\/doi.org\/10.1109\/tbme.2009.2036000.","journal-title":"IEEE Trans Biomed Eng"},{"issue":"5","key":"1250_CR12","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1136\/jnnp.73.5.529","volume":"73","author":"A Schrag","year":"2002","unstructured":"Schrag A, Ben-Shlomo Y, Quinn N. How valid is the clinical diagnosis of Parkinson's disease in the community? J Neurol Neurosurg Psychiatry. Nov 2002;73(5):529\u201334. https:\/\/doi.org\/10.1136\/jnnp.73.5.529.","journal-title":"J Neurol Neurosurg Psychiatry"},{"issue":"1","key":"1250_CR13","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.bandc.2004.05.002","volume":"56","author":"B Harel","year":"2004","unstructured":"Harel B, Cannizzaro M, Snyder PJ. Variability in fundamental frequency during speech in prodromal and incipient Parkinson's disease: a longitudinal case study. Brain Cogn. 2004;56(1):24\u20139. https:\/\/doi.org\/10.1016\/j.bandc.2004.05.002.","journal-title":"Brain Cogn"},{"issue":"12","key":"1250_CR14","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1016\/s1474-4422(09)70291-1","volume":"8","author":"W Maetzler","year":"2009","unstructured":"Maetzler W, Liepelt I, Berg D. Progression of Parkinson's disease in the clinical phase: potential markers. Lancet Neurol. 2009;8(12):1158\u201371. https:\/\/doi.org\/10.1016\/s1474-4422(09)70291-1.","journal-title":"Lancet Neurol"},{"issue":"2","key":"1250_CR15","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1586\/14737175.8.2.297","volume":"8","author":"LO Ramig","year":"2008","unstructured":"Ramig LO, Fox C, Sapir S. Speech treatment for Parkinson's disease. Expert Rev Neurother. 2008;8(2):297\u2013309. https:\/\/doi.org\/10.1586\/14737175.8.2.297.","journal-title":"Expert Rev Neurother"},{"key":"1250_CR16","doi-asserted-by":"publisher","first-page":"850596","DOI":"10.1155\/2012\/850596","volume":"2012","author":"S Skodda","year":"2012","unstructured":"Skodda S. \"effect of deep brain stimulation on speech performance in Parkinson's disease,\" (in eng). Parkinsons Dis. 2012;2012:850596. https:\/\/doi.org\/10.1155\/2012\/850596.","journal-title":"Parkinsons Dis"},{"issue":"3","key":"1250_CR17","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s11517-016-1512-y","volume":"55","author":"L Naranjo","year":"2017","unstructured":"Naranjo L, P\u00e9rez CJ, Mart\u00edn J. Addressing voice recording replications for tracking Parkinson's disease progression. Med Biol Eng Comput. 2017;55(3):365\u201373. https:\/\/doi.org\/10.1007\/s11517-016-1512-y.","journal-title":"Med Biol Eng Comput"},{"key":"1250_CR18","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.cmpb.2017.02.019","volume":"142","author":"L Naranjo","year":"2017","unstructured":"Naranjo L, P\u00e9rez CJ, Mart\u00edn J, Campos-Roca Y. \"A two-stage variable selection and classification approach for Parkinson's disease detection by using voice recording replications,\" (in eng). Comput Methods Prog Biomed. 2017;142:147\u201356. https:\/\/doi.org\/10.1016\/j.cmpb.2017.02.019.","journal-title":"Comput Methods Prog Biomed"},{"key":"1250_CR19","volume-title":"presented at the proceedings of the 31st international conference on neural information processing systems, Long Beach, California, USA","author":"G Ke","year":"2017","unstructured":"Ke G, et al. LightGBM: a highly efficient gradient boosting decision tree. In: presented at the proceedings of the 31st international conference on neural information processing systems, Long Beach, California, USA; 2017."},{"key":"1250_CR20","doi-asserted-by":"publisher","unstructured":"Friedman JH. Stochastic gradient boosting. Comput Stat Data Analysis. 38(4):367\u201378, 2002\/02\/28\/ 2002. https:\/\/doi.org\/10.1016\/S0167-9473(01)00065-2.","DOI":"10.1016\/S0167-9473(01)00065-2"},{"issue":"4","key":"1250_CR21","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1002\/mds.22379","volume":"24","author":"CG Goetz","year":"2009","unstructured":"Goetz CG, et al. Testing objective measures of motor impairment in early Parkinson's disease: Feasibility study of an at-home testing device. Mov Disord. 2009;24(4):551\u20136. https:\/\/doi.org\/10.1002\/mds.22379.","journal-title":"Mov Disord"},{"key":"1250_CR22","doi-asserted-by":"publisher","unstructured":"Shue YL, Keating P, Vicenik C. VOICESAUCE: A program for voice analysis. J Acoustical Soc Am. 126(4):2221, 2009\/10\/01 2009. https:\/\/doi.org\/10.1121\/1.3248865.","DOI":"10.1121\/1.3248865"},{"issue":"59","key":"1250_CR23","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1098\/rsif.2010.0456","volume":"8","author":"A Tsanas","year":"2011","unstructured":"Tsanas A, Little MA, McSharry PE, Ramig LO. Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity. J R Soc Interface. 2011;8(59):842\u201355. https:\/\/doi.org\/10.1098\/rsif.2010.0456.","journal-title":"J R Soc Interface"},{"key":"1250_CR24","doi-asserted-by":"publisher","first-page":"151193","DOI":"10.1016\/j.apnr.2019.151193","volume":"50","author":"MA Horning","year":"2019","unstructured":"Horning MA, Shin JY, DiFusco LA, Norton M, Habermann B. \"symptom progression in advanced Parkinson's disease: dyadic perspectives,\" (in eng). Appl Nurs Res. 2019;50:151193. https:\/\/doi.org\/10.1016\/j.apnr.2019.151193.","journal-title":"Appl Nurs Res"},{"key":"1250_CR25","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.parkreldis.2016.05.018","volume":"29","author":"I Rektorova","year":"2016","unstructured":"Rektorova I, et al. \"Speech prosody impairment predicts cognitive decline in Parkinson's disease,\" (in eng). Parkinsonism Relat Disord. 2016;29:90\u20135. https:\/\/doi.org\/10.1016\/j.parkreldis.2016.05.018.","journal-title":"Parkinsonism Relat Disord"},{"issue":"1","key":"1250_CR26","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/s00455-015-9671-9","volume":"31","author":"I Suttrup","year":"2016","unstructured":"Suttrup I, Warnecke T. Dysphagia in Parkinson's disease. Dysphagia. 2016;31(1):24\u201332. https:\/\/doi.org\/10.1007\/s00455-015-9671-9.","journal-title":"Dysphagia"},{"key":"1250_CR27","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.brainres.2013.06.030","volume":"1527","author":"X Chen","year":"2013","unstructured":"Chen X, et al. \"sensorimotor control of vocal pitch production in Parkinson's disease,\" (in eng). Brain Res. 2013;1527:99\u2013107. https:\/\/doi.org\/10.1016\/j.brainres.2013.06.030.","journal-title":"Brain Res"},{"issue":"3","key":"1250_CR28","first-page":"235","volume":"21","author":"LK Bowen","year":"2013","unstructured":"Bowen LK, Hands GL, Pradhan S, Stepp CE. Effects of Parkinson's disease on fundamental frequency variability in running speech. J Med Speech Lang Pathol. 2013;21(3):235\u201344.","journal-title":"J Med Speech Lang Pathol"},{"issue":"5","key":"1250_CR29","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH. Greedy Function Approximation: A Gradient Boosting Machine. Ann Stat. 2001;29(5):1189\u2013232 [Online]. Available: www.jstor.org\/stable\/2699986.","journal-title":"Ann Stat"},{"key":"1250_CR30","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/ICCVW.2009.5457451","volume-title":"2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops","author":"C Leistner","year":"2009","unstructured":"Leistner C, Saffari A, Roth PM, Bischof H. On robustness of on-line boosting - a competitive study. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops; 2009. p. 1362\u20139. https:\/\/doi.org\/10.1109\/ICCVW.2009.5457451."},{"key":"1250_CR31","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785","volume-title":"presented at the Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, USA","author":"T Chen","year":"2016","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: presented at the Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, USA; 2016. [Online]. Available. https:\/\/doi.org\/10.1145\/2939672.2939785."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01250-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-020-01250-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-01250-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,14]],"date-time":"2021-09-14T19:23:01Z","timestamp":1631647381000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-020-01250-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,15]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["1250"],"URL":"https:\/\/doi.org\/10.1186\/s12911-020-01250-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.2.20727\/v2","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.2.20727\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.21203\/rs.2.20727\/v3","asserted-by":"object"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,15]]},"assertion":[{"value":"3 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"NA. This manuscript is based on a publicly available de-identified data from UCI-Machine Learning Data Repository not including individual level identifiers.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors have approved this submission.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"No author has any conflict of interest to report.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"228"}}