Touchscreen typing-pattern analysis for detecting fine motor skills decline in early-stage Parkinson\u2019s disease

Dimitrios Iakovakis,Zoe Katsarou,Sevasti Bostantzopoulou,Leontios J Hadjileontiadis,Stelios Hadjidimitriou,Vasileios Charisis

doi:10.1038/s41598-018-25999-0

Abstract

Parkinson’s disease (PD) is a degenerative movement disorder causing progressive disability that severely affects patients’ quality of life. While early treatment can produce significant benefits for patients, the mildness of many early signs combined with the lack of accessible high-frequency monitoring tools may delay clinical diagnosis. To meet this need, user interaction data from consumer technologies have recently been exploited towards unsupervised screening for PD symptoms in daily life. Similarly, this work proposes a method for detecting fine motor skills decline in early PD patients via analysis of patterns emerging from finger interaction with touchscreen smartphones during natural typing. Our approach relies on low-/higher-order statistical features of keystrokes timing and pressure variables, computed from short typing sessions. Features are fed into a two-stage multi-model classification pipeline that reaches a decision on the subject’s status (PD patient/control) by gradually fusing prediction probabilities obtained for individual typing sessions and keystroke variables. This method achieved an AUC = 0.92 and 0.82/0.81 sensitivity/specificity (matched groups of 18 early PD patients/15 controls) with discriminant features plausibly correlating with clinical scores of relevant PD motor symptoms. These findings suggest an improvement over similar approaches, thereby constituting a further step towards unobtrusive early PD detection from routine activities.

Highlights

Parkinson’s disease (PD) is a common progressive neurodegenerative disorder[1], characterised primarily by motor symptoms that contribute to significant disability[2,3]
Subsequence, the first- up to fourth-order statistical moments of the elements are computed; (3) The probability density function (PDF) f i(x) of each subsequence is estimated through kernel density estimation (KDE) and the matrix of sample covariance C(i, j) between the
Feature vector set {vP} serves as input to a Logistic Regression classifier CLR that outputs the final classification probabilities {Pf} denoting whether each typing session belongs to a PD patient or a healthy control

Summary

Introduction

Parkinson’s disease (PD) is a common progressive neurodegenerative disorder[1], characterised primarily by motor symptoms that contribute to significant disability[2,3]. Motor status in particular, is often assessed by an expert based on the individual scoring and aggregated score of UPDRS Part III items[10], which cover a broad range of PD motor symptoms, including among others, tremor (resting and action), rigidity, and bradykinesia The latter examination, as is the case with other scales/questionnaires, requires a movement disorders specialist and the presence of the subject at the clinic. With higher sampling rate can lead to timely diagnosis and consequent improvement of the prospective patient’s quality of life via early therapeutic interventions[12] To this end, data captured from electronic sensors have been used by works targeting objective PD symptoms monitoring, such as microphone-captured speech signals for voice impairment recognition[13] and inertial measurement unit (IMU) data for hand tremor assessment[14] or freezing of gait detection[15], among others[16], with real-life transferability potential. Both studies included tasks of continuous typing for more than five minutes

Methods

Results

Conclusion