Transformation of Temperature Timeseries into Features that Characterize Patients with Diabetic Autonomic Nerve Disorder

Diabetic foot syndrome is a frequent and serious complication occurring among patients with diabetes. In this study, we investigate the potential of intelligent wearables that monitor temperature changes of the foot surface through temperature sensors. In particular, we are interested in identifying differences between the temperature variations recorded on patients with the disorder and healthy people during an experiment. To this purpose, we propose a method that encompasses shapelet-based timeseries classification and shapelet ranking on predictiveness. We report on our results for an experiment consisting of stance and rest periods of increasing duration.

[1]  E. Boyko,et al.  Skin temperature in the neuropathic diabetic foot. , 2001, Journal of diabetes and its complications.

[2]  George C. Runger,et al.  A time series forest for classification and feature extraction , 2013, Inf. Sci..

[3]  C. M. Agrawal,et al.  Home monitoring of foot skin temperatures to prevent ulceration. , 2004, Diabetes care.

[4]  A. Anguera,et al.  Applying data mining techniques to medical time series: an empirical case study in electroencephalography and stabilometry , 2016, Computational and structural biotechnology journal.

[5]  Jason Lines,et al.  A shapelet transform for time series classification , 2012, KDD.

[6]  Li Wei,et al.  Semi-supervised time series classification , 2006, KDD '06.

[7]  Ralf Lobmann,et al.  Neuropathy and Diabetic Foot Syndrome , 2016, International journal of molecular sciences.

[8]  George Manis,et al.  Heartbeat Time Series Classification With Support Vector Machines , 2009, IEEE Transactions on Information Technology in Biomedicine.

[9]  Eamonn J. Keogh,et al.  Time series shapelets: a novel technique that allows accurate, interpretable and fast classification , 2010, Data Mining and Knowledge Discovery.

[10]  S. Pendsey.  Understanding diabetic foot , 2010, International journal of diabetes in developing countries.

[11]  David George Lindsay,et al.  Effective Probability Forecasting for Time Series Data Using Standard Machine Learning Techniques , 2005, ICAPR.

[12]  Roy Tranberg,et al.  An innovative sealed shoe to off-load and heal diabetic forefoot ulcers – a feasibility study , 2017, Diabetic foot & ankle.

[13]  E. Fernholz.  Stochastic Portfolio Theory , 2002 .

[14]  Myra Spiliopoulou,et al.  Comparative Clustering of Plantar Pressure Distributions in Diabetics with Polyneuropathy May Be Applied to Reveal Inappropriate Biomechanical Stress , 2016, PloS one.

[15]  Panagiotis Papapetrou,et al.  Forests of Randomized Shapelet Trees , 2015, SLDS.

[16]  Francisco-J Renero-C,et al.  The thermoregulation of healthy individuals, overweight–obese, and diabetic from the plantar skin thermogram: a clue to predict the diabetic foot , 2017, Diabetic foot & ankle.

[17]  Hui Ding,et al.  Querying and mining of time series data: experimental comparison of representations and distance measures , 2008, Proc. VLDB Endow..