Weakly-supervised learning for Parkinson's Disease tremor detection

Continuous, automated monitoring of Parkinsons Disease (PD) symptoms would provide clinicians with more information to understand their patients' disease progression and adjust treatment protocols, thereby improving PD care. Collecting precisely labeled data for Parkinson's symptoms, such as tremor, is difficult. Therefore, algorithms for monitoring should only require weakly-labeled training data. In this paper, we evaluate five standard weakly-supervised algorithms and propose a “stratified” version of three of the algorithms, which take advantage of knowing the approximate amount of tremor within each segment. In particular, we analyze PD tremor detection performance as training segments increase in length from 30 seconds to 10 minutes, and labels thereby become less precise. As segment length increases to 10 minutes, standard algorithms are not able to discriminate tremor from non-tremor. However, our stratified algorithms, which can make use of more nuanced labels, show little decrease in performance as segment length increases.

[1]  Michael Montgomery,et al.  A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinson's Diease Motor Symptoms , 2014, 2014 IEEE International Conference on Bioinformatics and Bioengineering.

[2]  Nando de Freitas,et al.  Learning about Individuals from Group Statistics , 2005, UAI.

[3]  Alexander J. Smola,et al.  Estimating Labels from Label Proportions , 2009, J. Mach. Learn. Res..

[4]  Thomas Hofmann,et al.  Support Vector Machines for Multiple-Instance Learning , 2002, NIPS.

[5]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[6]  Max A. Little,et al.  Detecting and monitoring the symptoms of Parkinson's disease using smartphones: A pilot study. , 2015, Parkinsonism & related disorders.

[7]  Iñaki Inza,et al.  Learning Bayesian network classifiers from label proportions , 2013, Pattern Recognit..

[8]  Jaume Amores,et al.  Multiple instance classification: Review, taxonomy and comparative study , 2013, Artif. Intell..

[9]  T. Ploetz,et al.  Unsupervised home monitoring of Parkinson's disease motor symptoms using body-worn accelerometers. , 2016, Parkinsonism & related disorders.

[10]  Qi Zhang,et al.  EM-DD: An Improved Multiple-Instance Learning Technique , 2001, NIPS.

[11]  Max A. Little,et al.  High-accuracy discrimination of Parkinson’s Disease participants from healthy controls using smartphones , 2013 .

[12]  Jessica K. Hodgins,et al.  Detecting Parkinsons' symptoms in uncontrolled home environments: A multiple instance learning approach , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Paolo Bonato,et al.  Monitoring Motor Fluctuations in Patients With Parkinson's Disease Using Wearable Sensors , 2009, IEEE Transactions on Information Technology in Biomedicine.

[14]  Paola Pierleoni,et al.  A real-time system to aid clinical classification and quantification of tremor in Parkinson's disease , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[15]  Kamiar Aminian,et al.  Quantification of Tremor and Bradykinesia in Parkinson's Disease Using a Novel Ambulatory Monitoring System , 2007, IEEE Transactions on Biomedical Engineering.

[16]  J. Jankovic,et al.  Movement Disorder Society‐sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS‐UPDRS): Scale presentation and clinimetric testing results , 2008, Movement disorders : official journal of the Movement Disorder Society.

[17]  Zhi-Hua Zhou,et al.  Neural Networks for Multi-Instance Learning , 2002 .

[18]  Serge H. Roy,et al.  Dynamical Learning and Tracking of Tremor and Dyskinesia From Wearable Sensors , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.