Developing Measures of Cognitive Impairment in the Real World from Consumer-Grade Multimodal Sensor Streams

The ubiquity and remarkable technological progress of wearable consumer devices and mobile-computing platforms (smart phone, smart watch, tablet), along with the multitude of sensor modalities available, have enabled continuous monitoring of patients and their daily activities. Such rich, longitudinal information can be mined for physiological and behavioral signatures of cognitive impairment and provide new avenues for detecting MCI in a timely and cost-effective manner. In this work, we present a platform for remote and unobtrusive monitoring of symptoms related to cognitive impairment using several consumer-grade smart devices. We demonstrate how the platform has been used to collect a total of 16TB of data during the Lilly Exploratory Digital Assessment Study, a 12-week feasibility study which monitored 31 people with cognitive impairment and 82 without cognitive impairment in free living conditions. We describe how careful data unification, time-alignment, and imputation techniques can handle missing data rates inherent in real-world settings and ultimately show utility of these disparate data in differentiating symptomatics from healthy controls based on features computed purely from device data.

[1]  Timnit Gebru,et al.  Datasheets for datasets , 2018, Commun. ACM.

[2]  D. Howieson.  Current limitations of neuropsychological tests and assessment procedures , 2019, The Clinical neuropsychologist.

[3]  Stephen P. Boyd,et al.  Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data , 2017, KDD.

[4]  Oliver B. Regele,et al.  Digital biomarkers for Alzheimer’s disease: the mobile/wearable devices opportunity , 2019, npj Digital Medicine.

[5]  S. Folstein,et al.  "Mini-mental state". A practical method for grading the cognitive state of patients for the clinician. , 1975, Journal of psychiatric research.

[6]  B. Cuthbert,et al.  The PRISM project: Social withdrawal from an RDoC perspective , 2019, Neuroscience & Biobehavioral Reviews.

[7]  A. Siderowf,et al.  Validity of the MoCA and MMSE in the detection of MCI and dementia in Parkinson disease , 2009, Neurology.

[8]  A Sutcliffe,et al.  Can you detect early dementia from an email? A proof of principle study of daily computer use to detect cognitive and functional decline , 2018, International journal of geriatric psychiatry.

[9]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[10]  Reynold Xin,et al.  Apache Spark , 2016 .

[11]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[12]  Camarin E. Rolle,et al.  Video game training enhances cognitive control in older adults , 2013, Nature.

[13]  Yan Liu,et al.  Recurrent Neural Networks for Multivariate Time Series with Missing Values , 2016, Scientific Reports.

[14]  M. Albert,et al.  Introduction to the recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease , 2011, Alzheimer's & Dementia.

[15]  Aleksey Boyko,et al.  Detecting Cancer Metastases on Gigapixel Pathology Images , 2017, ArXiv.

[16]  Luca Foschini,et al.  Collecting and Analyzing Millions of mHealth Data Streams , 2017, KDD.

[17]  P. Snyder,et al.  Validity of the CogState brief battery: relationship to standardized tests and sensitivity to cognitive impairment in mild traumatic brain injury, schizophrenia, and AIDS dementia complex. , 2009, Archives of clinical neuropsychology : the official journal of the National Academy of Neuropsychologists.

[18]  M. McConnell,et al.  The Use of Smartphones for Health Research. , 2017, Academic medicine : journal of the Association of American Medical Colleges.

[19]  Grant L Iverson,et al.  Computerized Neuropsychological Assessment Devices: Joint Position Paper of the American Academy of Clinical Neuropsychology and the National Academy of Neuropsychology , 2012, The Clinical neuropsychologist.

[20]  David Sontag,et al.  Why Is My Classifier Discriminatory? , 2018, NeurIPS.

[21]  Rumona Dickson,et al.  A systematic review of the diagnostic accuracy of automated tests for cognitive impairment , 2018, International journal of geriatric psychiatry.

[22]  Hardeep Singh,et al.  Missed and Delayed Diagnosis of Dementia in Primary Care: Prevalence and Contributing Factors , 2009, Alzheimer disease and associated disorders.

[23]  M. Pavel,et al.  Intelligent Systems For Assessing Aging Changes: home-based, unobtrusive, and continuous assessment of aging. , 2011, The journals of gerontology. Series B, Psychological sciences and social sciences.

[24]  Ervin Sejdic,et al.  Association of Dual-Task Gait With Incident Dementia in Mild Cognitive Impairment: Results From the Gait and Brain Study , 2017, JAMA neurology.

[25]  J. Cummings,et al.  The Montreal Cognitive Assessment, MoCA: A Brief Screening Tool For Mild Cognitive Impairment , 2005, Journal of the American Geriatrics Society.

[26]  Philip D. Harvey,et al.  Practice effects due to serial cognitive assessment: Implications for preclinical Alzheimer's disease randomized controlled trials , 2015, Alzheimer's & dementia.

[27]  Jure Leskovec,et al.  Modeling Individual Cyclic Variation in Human Behavior , 2017, WWW.

[28]  Hong Cheng,et al.  TATC: Predicting Alzheimer's Disease with Actigraphy Data , 2018, KDD.

[29]  David D. Cox,et al.  Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms , 2013, SciPy.

[30]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[31]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.