{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/98336"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/98336","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Use of wearable ambulatory monitor in the classification of movement states in Parkinson's disease","abstract":"For Parkinson's patients to function at their best, their medications need to be optimally adjusted to the diurnal variation of symptoms. For this to occur, it is important for the managing clinician to have an accurate picture of how the patient's bradykinesia/hypokinesia and dyskinesia fluctuate throughout the normal daily activities. This thesis proposes the use of wearable accelerometers coupled with machine learning and statistical techniques in order to classify the movement states of Parkinson's patients and to provide a timeline of how the patients fluctuate throughout the day. A pilot study was performed using 2 patients with the goal of assessing the ability to classify dyskinesia and bradykinesia/hypokinesia based on accelerometric data. The patients were observed and videotaped. Clinical observations of bradykinesia/hypokinesia and dyskinesia were noted every minute. Neural networks were able to classify better than classification trees with an average c-index (equivalent to the area under the ROC curve) of 0.905 for bradykinesia/hypokinesia and 0.926 for dyskinesia. A separate group of 5 patients were observed with the additional goal of building models that can classify the movement of a patient without requiring clinically annotated training data for the same patient. An enhanced protocol was used in the final study. Dichotomized linear regression was found to classify well with an average c-index of 0.8219 for body bradykinesia/hypokinesia and 0.8799 using as the gold-standard the patient's diary. Dyskinesia was classified at a c-index of 0.7522. Neural networks did not perform as well, possibly because of restrictions placed on adjusting parameters. The two most clinically important problems: predicting","abstract_html":"For Parkinson's patients to function at their best, their medications need to be optimally adjusted to the diurnal variation of symptoms. For this to occur, it is important for the managing clinician to have an accurate picture of how the patient's bradykinesia/hypokinesia and dyskinesia fluctuate throughout the normal daily activities. This thesis proposes the use of wearable accelerometers coupled with machine learning and statistical techniques in order to classify the movement states of Parkinson's patients and to provide a timeline of how the patients fluctuate throughout the day. A pilot study was performed using 2 patients with the goal of assessing the ability to classify dyskinesia and bradykinesia/hypokinesia based on accelerometric data. The patients were observed and videotaped. Clinical observations of bradykinesia/hypokinesia and dyskinesia were noted every minute. Neural networks were able to classify better than classification trees with an average c-index (equivalent to the area under the ROC curve) of 0.905 for bradykinesia/hypokinesia and 0.926 for dyskinesia. A separate group of 5 patients were observed with the additional goal of building models that can classify the movement of a patient without requiring clinically annotated training data for the same patient. An enhanced protocol was used in the final study. Dichotomized linear regression was found to classify well with an average c-index of 0.8219 for body bradykinesia/hypokinesia and 0.8799 using as the gold-standard the patient's diary. Dyskinesia was classified at a c-index of 0.7522. Neural networks did not perform as well, possibly because of restrictions placed on adjusting parameters. The two most clinically important problems: predicting","abstract_has_math":false,"creators":["Klapper, David A. (David Asher), 1966-"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Harvard University--MIT Division of Health Sciences and Technology.","school":null,"contributors":[],"advisors":["Lucila Ohno-Machado."],"committee_chairs":[],"committee_members":[],"year":2003,"date_issued":"2003","date_published":"2003","updated_at":"2026-07-22T22:21:53Z","subjects":["Harvard University--MIT Division of Health Sciences and Technology."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/98336","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lucila Ohno-Machado."]},{"key":"dc:contributor.department","label":"Department","values":["Harvard University--MIT Division of Health Sciences and Technology."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Harvard University--MIT Division of Health Sciences and Technology."]},{"key":"dc:creator","label":"Author","values":["Klapper, David A. (David Asher), 1966-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2015-09-02T15:28:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2015-09-02T15:28:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2003"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Harvard University--MIT Division of Health Sciences and Technology."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/98336"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (S.M.)--Harvard-MIT Division of Health Sciences and Technology, September 2003.","\"August 2003.\"","Includes bibliographical references (p. 54-57)."]},{"key":"dc:description.abstract","label":"Abstract","values":["For Parkinson's patients to function at their best, their medications need to be optimally adjusted to the diurnal variation of symptoms. For this to occur, it is important for the managing clinician to have an accurate picture of how the patient's bradykinesia/hypokinesia and dyskinesia fluctuate throughout the normal daily activities. This thesis proposes the use of wearable accelerometers coupled with machine learning and statistical techniques in order to classify the movement states of Parkinson's patients and to provide a timeline of how the patients fluctuate throughout the day. A pilot study was performed using 2 patients with the goal of assessing the ability to classify dyskinesia and bradykinesia/hypokinesia based on accelerometric data. The patients were observed and videotaped. Clinical observations of bradykinesia/hypokinesia and dyskinesia were noted every minute. Neural networks were able to classify better than classification trees with an average c-index (equivalent to the area under the ROC curve) of 0.905 for bradykinesia/hypokinesia and 0.926 for dyskinesia. A separate group of 5 patients were observed with the additional goal of building models that can classify the movement of a patient without requiring clinically annotated training data for the same patient. An enhanced protocol was used in the final study. Dichotomized linear regression was found to classify well with an average c-index of 0.8219 for body bradykinesia/hypokinesia and 0.8799 using as the gold-standard the patient's diary. Dyskinesia was classified at a c-index of 0.7522. Neural networks did not perform as well, possibly because of restrictions placed on adjusting parameters. The two most clinically important problems: predicting","(cont.) when the patient feels he/she is \"off' or when he/she has \"troublesome dyskinesia\" were discriminated with c-indices of 0.96 and 1.0 respectively. The good result of the models despite the small number of patients is promising. Further studies with larger number of patients are therefore justified."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Use of wearable ambulatory monitor in the classification of movement states in Parkinson's disease"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lucila Ohno-Machado."],"dc:contributor.department":["Harvard University--MIT Division of Health Sciences and Technology."],"dc:contributor.other":["Harvard University--MIT Division of Health Sciences and Technology."],"dc:creator":["Klapper, David A. (David Asher), 1966-"],"dc:date.accessioned":["2015-09-02T15:28:22Z"],"dc:date.available":["2015-09-02T15:28:22Z"],"dc:date.issued":["2003"],"dc:description":["Thesis (S.M.)--Harvard-MIT Division of Health Sciences and Technology, September 2003.","\"August 2003.\"","Includes bibliographical references (p. 54-57)."],"dc:description.abstract":["For Parkinson's patients to function at their best, their medications need to be optimally adjusted to the diurnal variation of symptoms. For this to occur, it is important for the managing clinician to have an accurate picture of how the patient's bradykinesia/hypokinesia and dyskinesia fluctuate throughout the normal daily activities. This thesis proposes the use of wearable accelerometers coupled with machine learning and statistical techniques in order to classify the movement states of Parkinson's patients and to provide a timeline of how the patients fluctuate throughout the day. A pilot study was performed using 2 patients with the goal of assessing the ability to classify dyskinesia and bradykinesia/hypokinesia based on accelerometric data. The patients were observed and videotaped. Clinical observations of bradykinesia/hypokinesia and dyskinesia were noted every minute. Neural networks were able to classify better than classification trees with an average c-index (equivalent to the area under the ROC curve) of 0.905 for bradykinesia/hypokinesia and 0.926 for dyskinesia. A separate group of 5 patients were observed with the additional goal of building models that can classify the movement of a patient without requiring clinically annotated training data for the same patient. An enhanced protocol was used in the final study. Dichotomized linear regression was found to classify well with an average c-index of 0.8219 for body bradykinesia/hypokinesia and 0.8799 using as the gold-standard the patient's diary. Dyskinesia was classified at a c-index of 0.7522. Neural networks did not perform as well, possibly because of restrictions placed on adjusting parameters. The two most clinically important problems: predicting","(cont.) when the patient feels he/she is \"off' or when he/she has \"troublesome dyskinesia\" were discriminated with c-indices of 0.96 and 1.0 respectively. The good result of the models despite the small number of patients is promising. Further studies with larger number of patients are therefore justified."],"dc:description.degree":["S.M."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/98336"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Harvard University--MIT Division of Health Sciences and Technology."],"dc:title":["Use of wearable ambulatory monitor in the classification of movement states in Parkinson's disease"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:53Z"}