Improving Medication Regimen Recommendation for Parkinson’s Disease Using Sensor Technology
Abstract
Parkinson’s disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson’s patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician’s initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson’s medication changes—clinically assessed by the MDS-Unified Parkinson’s Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients’ cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose—with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1more »
- Authors:
-
- Univ. of Tennessee, Knoxville, TN (United States). Dept. of Industrial and Systems Engineering
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Sciences (CNMS)
- Univ. of California, San Diego, La Jolla, CA (United States). Dept. of Neurosciences
- Donald and Barbara School of Medicine at Hofstra/Northwell, Hempstead, NY (United States). Dept. of Neurology
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC); USDOE Laboratory Directed Research and Development (LDRD) Program; Science Alliance; The Parkinson’s Alliance
- OSTI Identifier:
- 1815895
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Sensors
- Additional Journal Information:
- Journal Volume: 21; Journal Issue: 10; Journal ID: ISSN 1424-8220
- Publisher:
- MDPI AG
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 60 APPLIED LIFE SCIENCES; 59 BASIC BIOLOGICAL SCIENCES; Parkinson’s disease; wearable sensors; machine learning; levodopa; regimen; decision support tool; remote assessment; PKG; clustering
Citation Formats
Watts, Jeremy, Khojandi, Anahita, Vasudevan, Rama, Nahab, Fatta B., and Ramdhani, Ritesh A. Improving Medication Regimen Recommendation for Parkinson’s Disease Using Sensor Technology. United States: N. p., 2021.
Web. doi:10.3390/s21103553.
Watts, Jeremy, Khojandi, Anahita, Vasudevan, Rama, Nahab, Fatta B., & Ramdhani, Ritesh A. Improving Medication Regimen Recommendation for Parkinson’s Disease Using Sensor Technology. United States. https://doi.org/10.3390/s21103553
Watts, Jeremy, Khojandi, Anahita, Vasudevan, Rama, Nahab, Fatta B., and Ramdhani, Ritesh A. Thu .
"Improving Medication Regimen Recommendation for Parkinson’s Disease Using Sensor Technology". United States. https://doi.org/10.3390/s21103553. https://www.osti.gov/servlets/purl/1815895.
@article{osti_1815895,
title = {Improving Medication Regimen Recommendation for Parkinson’s Disease Using Sensor Technology},
author = {Watts, Jeremy and Khojandi, Anahita and Vasudevan, Rama and Nahab, Fatta B. and Ramdhani, Ritesh A.},
abstractNote = {Parkinson’s disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson’s patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician’s initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson’s medication changes—clinically assessed by the MDS-Unified Parkinson’s Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients’ cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose—with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.},
doi = {10.3390/s21103553},
journal = {Sensors},
number = 10,
volume = 21,
place = {United States},
year = {Thu May 20 00:00:00 EDT 2021},
month = {Thu May 20 00:00:00 EDT 2021}
}
Works referenced in this record:
Non-motor features of Parkinson disease
journal, June 2017
- Schapira, Anthony H. V.; Chaudhuri, K. Ray; Jenner, Peter
- Nature Reviews Neuroscience, Vol. 18, Issue 7
Global, regional, and national burden of neurological disorders during 1990–2015: a systematic analysis for the Global Burden of Disease Study 2015
journal, November 2017
- Feigin, Valery L.; Abajobir, Amanuel Alemu; Abate, Kalkidan Hassen
- The Lancet Neurology, Vol. 16, Issue 11
The coming crisis: Obtaining care for the growing burden of neurodegenerative conditions
journal, April 2013
- Dorsey, E. R.; George, B. P.; Leff, B.
- Neurology, Vol. 80, Issue 21
Parkinsonism death rates by race, sex, and geography
journal, October 1988
- Kurtzke, J. F.; Goldberg, I. D.
- Neurology, Vol. 38, Issue 10
The geographic distribution of Parkinson's disease mortality in the United States
journal, September 1997
- Lanska, Douglas J.
- Journal of the Neurological Sciences, Vol. 150, Issue 1
The Frequency of Idiopathic Parkinson's Disease by Age, Ethnic Group, and Sex in Northern Manhattan, 1988–1993
journal, October 1995
- Mayeux, Richard; Marder, Karen; Cote, Lucien J.
- American Journal of Epidemiology, Vol. 142, Issue 8
Randomized Controlled Clinical Trial of “Virtual House Calls” for Parkinson Disease
journal, May 2013
- Dorsey, E. Ray; Venkataraman, Vinayak; Grana, Matthew J.
- JAMA Neurology, Vol. 70, Issue 5
Neurologist care in Parkinson disease: A utilization, outcomes, and survival study
journal, August 2011
- Willis, A. W.; Schootman, M.; Evanoff, B. A.
- Neurology, Vol. 77, Issue 9
Delayed Parkinson’s Disease Diagnosis among African-Americans: The Role of Reporting of Disability
journal, January 2011
- Dahodwala, Nabila; Karlawish, Jason; Siderowf, Andrew
- Neuroepidemiology, Vol. 36, Issue 3
Diagnosis and Referral Delay in Women With Parkinson's Disease
journal, June 2011
- Saunders-Pullman, Rachel; Wang, Cuiling; Stanley, Kaili
- Gender Medicine, Vol. 8, Issue 3
Continuous dopamine-receptor treatment of Parkinson's disease: scientific rationale and clinical implications
journal, August 2006
- Olanow, C. Warren; Obeso, Jose A.; Stocchi, Fabrizio
- The Lancet Neurology, Vol. 5, Issue 8
Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS): Scale presentation and clinimetric testing results
journal, November 2008
- Goetz, Christopher G.; Tilley, Barbara C.; Shaftman, Stephanie R.
- Movement Disorders, Vol. 23, Issue 15
Patient Evaluation of a Home Diary to Assess Duration and Severity of Dyskinesia in Parkinson Disease
journal, January 2006
- Hauser, Robert A.; Russ, Hermann; Haeger, Doris-Anita
- Clinical Neuropharmacology, Vol. 29, Issue 6
Optimizing Clinical Assessments in Parkinson's Disease Through the Use of Wearable Sensors and Data Driven Modeling
journal, September 2018
- Ramdhani, Ritesh A.; Khojandi, Anahita; Shylo, Oleg
- Frontiers in Computational Neuroscience, Vol. 12
A clinical view on the development of technology-based tools in managing Parkinson's disease: Technology-Based Clinical PD Assessment
journal, June 2016
- Maetzler, Walter; Klucken, Jochen; Horne, Malcolm
- Movement Disorders, Vol. 31, Issue 9
Ambulatory motor assessment in Parkinson's disease
journal, January 2006
- Keijsers, Noël L. W.; Horstink, Martin W. I. M.; Gielen, Stan C. A. M.
- Movement Disorders, Vol. 21, Issue 1
Automated Assessment of Bradykinesia and Dyskinesia in Parkinson's Disease
journal, January 2012
- Griffiths, Robert I.; Kotschet, Katya; Arfon, Sian
- Journal of Parkinson's Disease, Vol. 2, Issue 1
Continuous Assessment of Levodopa Response in Parkinson's Disease Using Wearable Motion Sensors
journal, January 2018
- Pulliam, Christopher L.; Heldman, Dustin A.; Brokaw, Elizabeth B.
- IEEE Transactions on Biomedical Engineering, Vol. 65, Issue 1
Daytime sleep in Parkinson's disease measured by episodes of immobility
journal, June 2014
- Kotschet, K.; Johnson, W.; McGregor, S.
- Parkinsonism & Related Disorders, Vol. 20, Issue 6
An Objective Fluctuation Score for Parkinson's Disease
journal, April 2015
- Horne, Malcolm K.; McGregor, Sarah; Bergquist, Filip
- PLOS ONE, Vol. 10, Issue 4
An Ambulatory Tremor Score for Parkinson’s Disease
journal, October 2016
- Braybrook, Michelle; O’Connor, Sam; Churchward, Philip
- Journal of Parkinson's Disease, Vol. 6, Issue 4
Evaluation of Clinical Utility of the Personal KinetiGraph® in the Management of Parkinson Disease
journal, January 2019
- Nahab, Fatta B.; Abu-Hussain, Hamad; Moreno, Lissette
- Advances in Parkinson's Disease, Vol. 08, Issue 03
Therapy of Parkinson’s Disease Subtypes
journal, August 2020
- Marras, Connie; Chaudhuri, K. Ray; Titova, Nataliya
- Neurotherapeutics, Vol. 17, Issue 4
Therapeutic strategies for Parkinson disease: beyond dopaminergic drugs
journal, September 2018
- Charvin, Delphine; Medori, Rossella; Hauser, Robert A.
- Nature Reviews Drug Discovery, Vol. 17, Issue 11
The identification of Parkinson's disease subtypes using cluster analysis: A systematic review
journal, March 2010
- van Rooden, Stephanie M.; Heiser, Willem J.; Kok, Joost N.
- Movement Disorders, Vol. 25, Issue 8
Technical Note: Using k‐means clustering to determine the number and position of isocenters in MLC ‐based multiple target intracranial radiosurgery
journal, July 2017
- Yock, Adam D.; Kim, Gwe‐Ya
- Journal of Applied Clinical Medical Physics, Vol. 18, Issue 5
Role of the Personal KinetiGraph in the routine clinical assessment of Parkinson’s disease: recommendations from an expert panel
journal, July 2018
- Pahwa, Rajesh; Isaacson, Stuart H.; Torres-Russotto, Diego
- Expert Review of Neurotherapeutics, Vol. 18, Issue 8
Parkinson's Disease Subtypes Identified from Cluster Analysis of Motor and Non-motor Symptoms
journal, September 2017
- Mu, Jesse; Chaudhuri, Kallol R.; Bielza, Concha
- Frontiers in Aging Neuroscience, Vol. 9
Clinical clusters and dopaminergic dysfunction in de-novo Parkinson disease
journal, July 2016
- Erro, Roberto; Picillo, Marina; Vitale, Carmine
- Parkinsonism & Related Disorders, Vol. 28