A Comprehensive Multifunctional Approach for Measuring Parkinson's Disease Severity

Abstract

Objectives This research study aims to advance the staging of Parkinson's disease (PD) by incorporating machine learning to assess and include a broader multifunctional spectrum of neurocognitive symptoms in the staging schemes beyond motor-centric assessments. Specifically, we provide a novel framework to modernize and personalize PD staging more objectively by proposing a hybrid feature scoring approach.

Methods We recruited 37 individuals diagnosed with PD, each of whom completed a series of tablet-based neurocognitive tests assessing motor, memory, speech, executive functions, and tasks ranging in complexity from single to multifunctional. Then, the collected data were used to develop a hybrid feature scoring system to calculate a weighted vector for each function. We evaluated the current PD staging schemes and developed a new approach based on the features selected and extracted using random forest and principal component analysis.

Results Our findings indicate a substantial bias in current PD staging systems toward fine motor skills, that is, other neurological functions (memory, speech, executive function, etc.) do not map into current PD stages as well as fine motor skills do. The results demonstrate that a more accurate and personalized assessment of PD severity could be achieved by including a more exhaustive range of neurocognitive functions in the staging systems either by involving multiple functions in a unified staging score or by designing a function-specific staging system.

Conclusion The proposed hybrid feature score approach provides a comprehensive understanding of PD by highlighting the need for a staging system that covers various neurocognitive functions. This approach could potentially lead to more effective, objective, and personalized treatment strategies. Further, this proposed methodology could be adapted to other neurodegenerative conditions such as Alzheimer's disease or amyotrophic lateral sclerosis.

Keywords

machine learning - Parkinson's disease - disease staging - digital health - neurocognitive disorder

Protection of Human and Animal Subjects

This study was conducted in compliance with the World Medical Association Declaration of Helsinki on Ethical Principles for Medical Research Involving Human Subjects, and it was reviewed by the University of Notre Dame Institutional Review Board. No human subjects were harmed during the study.

Publication History

Received: 22 May 2024

Accepted: 20 September 2024

Accepted Manuscript online:
23 September 2024

Article published online:
01 January 2025

• References

• 1 Solti D, Zhai H. Predicting breast cancer patient survival using machine learning. Paper presented at: 2013 ACM Conference on Bioinformatics, Computational Biology and Biomedical Informatics, ACM-BCB 2013; September 22–25, 2013; Washington, DC
• 2 Templeton JM, Poellabauer C, Schneider S. Classification of Parkinson's disease and its stages using machine learning. Sci Rep 2022; 12 (01) 14036
• 3 Seeley M, Clement M, Giraud-Carrier C, Snell Q, Bodily P, Fujimoto S. et al. A structured approach to ensemble learning for Alzheimer's disease prediction. Paper presented at: ACM BCB 2014: 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics; September 20–23, 2014; Newport Beach, CA
• 4 Tabl AA, ElMaraghy W, Alkhateeb A, Ngom A. Machine learning model for identifying gene biomarkers for breast cancer treatment survival. Paper presented at: ACM-BCB 2017: Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics; August 20–23, 2017; Boston, MA
• 5 Templeton JM, Poellabauer C, Schneider S. Design of a neurocognitive digital health system (NDHS) for neurodegenerative diseases. Paper presented at: DigiBiom 2021: Proceedings of the 2021 Future of Digital Biomarkers; June 25, 2021; Virtual Event, Wisconsin
• 6 Hamzehei S, Akbarzadeh O, Attar H, Rezaee K, Fasihihour N, Khosravi MR. Predicting the total Unified Parkinson's Disease Rating Scale (UPDRS) based on ML techniques and cloud-based update. J Cloud Comput (Heidelb) 2023; 12: 1-16
• 7 Qayyum A, Qadir J, Bilal M, Al-Fuqaha A. Secure and robust machine learning for healthcare: a survey. IEEE Rev Biomed Eng 2021; 14: 156-180
• 8 Rehman RZU, Buckley C, Mico-Amigo ME. et al. Accelerometry-based digital gait characteristics for classification of Parkinson's disease: what counts?. IEEE Open J Eng Med Biol 2020; 1: 65-73
• 9 Bhidayasiri R, Tarsy D, Bhidayasiri R, Tarsy D. Parkinson's disease: Hoehn and Yahr Scale. Curr Clin Neurol 2012; 36: 4-5
• 10 Templeton JM, Poellabauer C, Schneider S. Design of a mobile-based neurological assessment tool for aging populations. Lect Notes Inst Comput Sci Soc Telecommun Eng 2021; 362: 166-185
• 11 Templeton JM, Poellabauer C, Schneider S. The case for symptom-specific neurological digital biomarkers. Lect Notes Inst Comput Sci Soc Telecommun Eng 2022; 440: 235-255
• 12 Harb H, Makhoul A, Tawbi S, Couturier R. Comparison of different data aggregation techniques in distributed sensor networks. IEEE Access 2017; 5: 4250-4263
• 13 Enders CK, Baraldi AN. Missing data handling methods. In: Irwing P, Booth T, Hughes DJ. eds. The Wiley Handbook of Psychometric Testing: A Multidisciplinary Reference on Survey, Scale and Test Development. Vols. 1–2. Hoboken, NJ: John Wiley & Sons, Ltd; 2017: 139-185
• 14 Singh D, Singh B. Investigating the impact of data normalization on classification performance. Appl Soft Comput 2020; 97: 105524
• 15 Gajera V, Shubham Shubham, Gupta R, Jana PK. An effective multi-objective task scheduling algorithm using min-max normalization in cloud computing. Paper presented at: Proceedings of the 2016 2nd International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT); July 21–23, 2016; Bangalore, India
• 16 Fryer D, Strümke I, Nguyen H. Shapley values for feature selection: the good, the bad, and the axioms. IEEE Access 2021; 9: 144352-144360
• 17 Qi Y. Random forest for bioinformatics. In: Zhang C, Ma Y. eds. Ensemble Machine Learning. New York, NY: Springer; 2012: 307-323
• 18 Moorthy U, Gandhi UD. A novel optimal feature selection technique for medical data classification using ANOVA based whale optimization. J Ambient Intell Humaniz Comput 2021; 12: 3527-3538
• 19 Urbanowicz RJ, Meeker M, La Cava W, Olson RS, Moore JH. Relief-based feature selection: introduction and review. J Biomed Inform 2018; 85: 189-203
• 20 Jin X, Xu A, Bie R, Guo P. Machine learning techniques and chi-square feature selection for cancer classification using SAGE gene expression profiles. In: Li J, Yang Q, Tan AH. eds. Data Mining for Biomedical Applications. Lecture Notes in Computer Science. Vol. 3916. Berlin: Springer; 2006: 106-115
• 21 Ali Khan S, Hussain A, Basit A, Akram S. Kruskal-Wallis-based computationally efficient feature selection for face recognition. ScientificWorldJournal 2014; 2014: 672630
• 22 Rouah FD. Pearson correlation coefficient. In: Gregoriou GN. ed. Encyclopedia of Alternative Investments. New York, NY: Chapman and Hall/CRC; 2008: 353-354
• 23 Picasso P. Principal component analysis why principal component analysis?. IEEE Signal Process Lett 2002; 9: 40-42
• 24 Rahimi M, Al Masry Z, Templeton JM, Schneider S, Poellabauer C. Beyond motor symptoms: toward a comprehensive grading of Parkinson's disease severity. Paper presented at: ACM-BCB 2023: Proceedings of the 14th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics; September 3–6, 2023; Houston, TX
• 25 van Wamelen DJ, Sringean J, Trivedi D. et al; International Parkinson and Movement Disorder Society Non Motor Parkinson's Disease Study Group. Digital health technology for non-motor symptoms in people with Parkinson's disease: futile or future?. Parkinsonism Relat Disord 2021; 89: 186-194
• 26 Mughal H, Javed AR, Rizwan M, Almadhor AS, Kryvinska N. Parkinson's disease management via wearable sensors: a systematic review. IEEE Access 2022; 10: 35219-35237
• 27 Goetz CC. Movement Disorder Society Task Force on Rating Scales for Parkinson's Disease. The Unified Parkinson's Disease Rating Scale (UPDRS): status and recommendations. Mov Disord 2003; 18 (07) 738-750
• 28 Zhao YJ, Wee HL, Chan YH. et al. Progression of Parkinson's disease as evaluated by Hoehn and Yahr stage transition times. Mov Disord 2010; 25 (06) 710-716
• 29 Martínez-Martín P, Rodríguez-Blázquez C, Mario Alvarez Mario Alvarez. et al. Parkinson's disease severity levels and MDS-Unified Parkinson's Disease Rating Scale. Parkinsonism Relat Disord 2015; 21 (01) 50-54
• 30 van Wamelen DJ, Rota S, Schrag A. et al. Characterization of non-motor fluctuations using the Movement Disorder Society non-motor rating scale. Mov Disord Clin Pract 2022; 9 (07) 932-940
• 31 Ellis TD, Earhart GM. Digital therapeutics in Parkinson's disease: practical applications and future potential. J Parkinsons Dis 2021; 11 (s1): S95-S101
• 32 Meng J, Huo X, Zhao H. et al. Multi-modal biological feature selection for Parkinson's disease staging based on binary PSO with broad learning. Biomed Signal Process Control 2024; 94: 106234
• 33 Cardoso F, Goetz CG, Mestre TA. et al. A statement of the MDS on biological definition, staging, and classification of Parkinson's Disease. Mov Disord 2024; 39 (02) 259-266
• 34 Soni R, Mathur K, Shah J. An update on new-age potential biomarkers for Parkinson's disease. Ageing Res Rev 2024; 94: 102208
• 35 Piro NE, Baumann L, Tengler M, Piro L, Blechschmidt-Trapp R. Telemonitoring of patients with Parkinson's disease using inertia sensors. Appl Clin Inform 2014; 5 (02) 503-511
• 36 Lu TC, Fu CM, Ma MHM, Fang CC, Turner AM. Healthcare applications of smart watches: a systematic review. Appl Clin Inform 2016; 7 (03) 850-869
• 37 Martinez-Martin P, Rojo-Abuín JM, Weintraub D. et al. Factor analysis and clustering of the Movement Disorder Society: non-motor rating scale. Mov Disord 2020; 35 (06) 969-975
• 38 Scarpina F, Tagini S. The Stroop color and word test. Front Psychol 2017; 8: 557