Abstract
The purpose of this research is to identify optimal combinations of data modes and variables to predict the severity of Parkinson’s Disease (PD) from Fox Insight, a large-scale online prospective cohort study.
We applied 7 machine learning models on the Fox Insight Telemedicine Verification Sub-Study (FIVE), to compute the baseline accuracy for predicting 3 common severity measures, Hoehn and Yahr Scale (HY), Clinical Global Impression Severity (CGI-S) and Schwab and England Activities of Daily Living Scale (SE-ADL). We then removed all clinician reported outcomes (CROs), which are only shared by 232 (0.5%) respondents, to rebuild scalable models based on common patient reported outcomes (PROs), which are shared across over 30,000 (58%) respondents. A total of 59 information categories, including genetics, were examined from both cross-sectional and longitudinal studies, to take into account the widest range of factors and modes available.
Our highest performing model, based on Neural Network (NN) and Extremely Randomized Trees (ERT), yields F1 weighted scores of 0.93, 0.86 and 0.91 for predicting HY, CGI-S and SE-ADL, an improvement of 21%, 32% and 52% compared with the baselines. Applying machine learning on the multi-modal PROs and genetic information proves to predict PD severity consistent with clinical assessment.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Data Exploration Network, A Fox Insight research tool, author = The Michael J. Fox Foundation, howpublished. https://foxden.michaeljfox.org/insight/explore/insight.jsp. Accessed 2022
Busner, J., Targum, S.D.: The clinical global impressions scale: applying a research tool in clinical practice. Psychiatry (Edgmont) 4(7), 28 (2007)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)
International Parkinson’s Disease Genomics Consortium: Imputation of sequence variants for identification of genetic risks for Parkinson’s disease: a meta-analysis of genome-wide association studies. Lancet 377(9766), 641–649 (2011)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Do, C.B., et al.: Web-based genome-wide association study identifies two novel loci and a substantial genetic component for Parkinson’s disease. PLoS Genet. 7(6), e1002141 (2011)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 1189–1232 (2001)
Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006)
Hinton, G., Vinyals, O., Dean, J., et al.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, vol. 2, no. 7 (2015)
Ho, T.K.: Random decision forests. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 1, pp. 278–282. IEEE (1995)
Hoehn, M.M., Yahr, M.D., et al.: Parkinsonism: onset, progression, and mortality. Neurology 50(2), 318–318 (1998)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Martínez-Martín, P., et al.: Parkinson’s disease severity levels and MDS-unified Parkinson’s disease rating scale. Parkinsonism Relat. Disord. 21(1), 50–54 (2015)
Martínez-Martín, P., et al.: Analysis of four scales for global severity evaluation in Parkinson’s disease. NPJ Parkinson’s Dis. 2(1), 1–6 (2016)
Mohaghegh, M., Gascon, J.: IEEE Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (2021)
Myers, T.L., et al.: Video-based Parkinson’s disease assessments in a nationwide cohort of fox insight participants. Clin. Parkinsonism Relat. Disord. 4, 100094 (2021)
Smolensky, L., et al.: Fox insight collects online, longitudinal patient-reported outcomes and genetic data on Parkinson’s disease. Sci. Data 7(1), 1–9 (2020)
Acknowledgements
This research program is funded by the Auckland University of Technology. We wish to thank Michael J. Fox Foundation for designing robust study instruments and making the large-scale integrated Fox Insight data accessible for research. This work is funded by the Summer Research Scholarships of Auckland University of Technology.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mohaghegh, M., Peng, N. (2023). Predicting Parkinson’s Disease Severity Using Patient-Reported Outcomes and Genetic Information. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1792. Springer, Singapore. https://doi.org/10.1007/978-981-99-1642-9_49
Download citation
DOI: https://doi.org/10.1007/978-981-99-1642-9_49
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1641-2
Online ISBN: 978-981-99-1642-9
eBook Packages: Computer ScienceComputer Science (R0)