Prevention and management of foot problems in diabetes: A summary guidance for daily practice 2015, based on the IWGDF Guidance Documents

In this 'Summary Guidance for Daily Practice', we describe the basic principles of prevention and management of foot problems in persons with diabetes. This summary is based on the International Working Group on the Diabetic Foot (IWGDF) Guidance 2015. There are five key elements that underpin prevention of foot problems: (1) identification of the at-risk foot; (2) regular inspection and examination of the at-risk foot; (3) education of patient, family and healthcare providers; (4) routine wearing of appropriate footwear, and; (5) treatment of pre-ulcerative signs. Healthcare providers should follow a standardized and consistent strategy for evaluating a foot wound, as this will guide further evaluation and therapy. The following items must be addressed: type, cause, site and depth, and signs of infection. There are seven key elements that underpin ulcer treatment: (1) relief of pressure and protection of the ulcer; (2) restoration of skin perfusion; (3) treatment of infection; (4) metabolic control and treatment of co-morbidity; (5) local wound care; (6) education for patient and relatives, and; (7) prevention of recurrence. Finally, successful efforts to prevent and manage foot problems in diabetes depend upon a well-organized team, using a holistic approach in which the ulcer is seen as a sign of multi-organ disease, and integrating the various disciplines involved.

Elliptical summary randomisation for sensor-based human activity recognition

Many conventional statistical machine learning al- gorithms generalise poorly if distribution bias ex- ists in the datasets. For example, distribution bias arises in the context of domain generalisation, where knowledge acquired from multiple source domains need to be used in a previously unseen target domains. We propose Elliptical Summary Randomisation (ESRand), an efficient domain generalisation approach that comprises of a randomised kernel and elliptical data summarisation. ESRand learns a domain interdependent projection to a la- tent subspace that minimises the existing biases to the data while maintaining the functional relationship between domains. In the latent subspace, ellipsoidal summaries replace the samples to enhance the generalisation by further removing bias and noise in the data. Moreover, the summarisation enables large-scale data processing by significantly reducing the size of the data. Through comprehensive analysis, we show that our subspace-based approach outperforms state-of-the-art results on several activity recognition benchmark datasets, while keeping the computational complexity significantly low.