Assessment of Severe Apnoea through Voice Analysis, Automatic Speech, and Speaker Recognition Techniques

This study is part of an ongoing collaborative effort between the medical and the signal processing communities to promote research on applying standard Automatic Speech Recognition (ASR) techniques for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based detection could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we describe an acoustic search for distinctive apnoea voice characteristics. We also study abnormal nasalization in OSA patients by modelling vowels in nasal and nonnasal phonetic contexts using Gaussian Mixture Model (GMM) pattern recognition on speech spectra. Finally, we present experimental findings regarding the discriminative power of GMMs applied to severe apnoea detection. We have achieved an 81% correct classification rate, which is very promising and underpins the interest in this line of inquiry.

Expectations, experiences and attitudes of patients and primary care health professionals regarding online psychotherapeutic interventions for depression: protocol for a qualitative study.

BACKGROUND In the year 2020, depression will cause the second highest amount of disability worldwide. One quarter of the population will suffer from depression symptoms at some point in their lives. Mental health services in Western countries are overburdened. Therefore, cost-effective interventions that do not involve mental health services, such as online psychotherapy programs, have been proposed. These programs demonstrate satisfactory outcomes, but the completion rate for patients is low. Health professionals' attitudes towards this type of psychotherapy are more negative than the attitudes of depressed patients themselves. The aim of this study is to describe the profile of depressed patients who would benefit most from online psychotherapy and to identify expectations, experiences, and attitudes about online psychotherapy among both patients and health professionals that can facilitate or hinder its effects. METHODS A parallel qualitative design will be used in a randomised controlled trial on the efficiency of online psychotherapeutic treatment for depression. Through interviews and focus groups, the experiences of treated patients, their reasons for abandoning the program, the expectations of untreated patients, and the attitudes of health professionals will be examined. Questions will be asked about training in new technologies, opinions of online psychotherapy, adjustment to therapy within the daily routine, the virtual and anonymous relationship with the therapist, the process of online communication, information necessary to make progress in therapy, process of working with the program, motivations and attitudes about treatment, expected consequences, normalisation of this type of therapy in primary care, changes in the physician-patient relationship, and resources and risks. A thematic content analysis from the grounded theory for interviews and an analysis of the discursive positions of participants based on the sociological model for focus groups will be performed. DISCUSSION Knowledge of the expectations, experiences, and attitudes of both patients and medical personnel regarding online interventions for depression can facilitate the implementation of this new psychotherapeutic tool. This qualitative investigation will provide thorough knowledge of the perceptions, beliefs, and values of patients and clinicians, which will be very useful for understanding how to implement this intervention method for depression.