A review of dynamic Bayesian network techniques with applications in healthcare risk modelling

Coping with an ageing population is a major concern for healthcare organisations around the world. The average cost of hospital care is higher than social care for older and terminally ill patients. Moreover, the average cost of social care increases with the age of the patient. Therefore, it is important to make efficient and fair capacity planning which also incorporates patient centred outcomes. Predictive models can provide predictions which their accuracy can be understood and quantified. Predictive modelling can help patients and carers to get the appropriate support services, and allow clinical decision-makers to improve care quality and reduce the cost of inappropriate hospital and Accident and Emergency admissions. The aim of this study is to provide a review of modelling techniques and frameworks for predictive risk modelling of patients in hospital, based on routinely collected data such as the Hospital Episode Statistics database. A number of sub-problems can be considered such as Length-of-Stay and End-of-Life predictive modelling. The methodologies in the literature are mainly focused on addressing the problems using regression methods and Markov models, and the majority lack generalisability. In some cases, the robustness, accuracy and re-usability of predictive risk models have been shown to be improved using Machine Learning methods. Dynamic Bayesian Network techniques can represent complex correlations models and include small probabilities into the solution. The main focus of this study is to provide a review of major time-varying Dynamic Bayesian Network techniques with applications in healthcare predictive risk modelling.

Who gets to play? Investigating equity in musical instrument instruction in Scottish primary schools

There is a widely held view that learning to play a musical instrument is a valuable experience for all children in terms of their personal growth and development. Although there is no statutory obligation for instrumental music provision in Scottish primary schools, there are well-established Instrumental Music Services in Local Education Authorities that have been developed to provide this facility for pupils. This article presents the findings of a study that was aimed at investigating the extent to which the opportunity to undertake instrumental instruction in Scottish primary schools is equitable. The study employed a mixed-methods approach. Data were gathered from 21 Scottish primary schools, a total pupil population of 5122 pupils of whom 323 pupils were receiving instrumental instruction. The analysis involved an investigation of the academic profile of this group, the representation of children with additional support needs (ASN) and the nature of their ASN. A qualitative analysis of policy and guideline documents and interviews with Heads of Instrumental Services, headteachers and instrumental instructors served to explain and illuminate the quantitative data. The findings showed that particular groups of children with ASN were significantly under-represented and offer explanations of the processes by which this occurs.

Graded Exercise Therapy Guided Self-Help Trial for Patients with Chronic Fatigue Syndrome (GETSET): Protocol for a Randomized Controlled Trial and Interview Study

Background: Chronic fatigue syndrome, also known as myalgic encephalomyelitis (CFS/ME), is characterized by chronic disabling fatigue and other symptoms, which are not explained by an alternative diagnosis. Previous trials have suggested that graded exercise therapy (GET) is an effective and safe treatment. GET itself is therapist-intensive with limited availability. Objective: While guided self-help based on cognitive behavior therapy appears helpful to patients, Guided graded Exercise Self-help (GES) is yet to be tested. Methods: This pragmatic randomized controlled trial is set within 2 specialist CFS/ME services in the South of England. Adults attending secondary care clinics with National Institute for Health and Clinical Excellence (NICE)-defined CFS/ME (N=218) will be randomly allocated to specialist medical care (SMC) or SMC plus GES while on a waiting list for therapist-delivered rehabilitation. GES will consist of a structured booklet describing a 6-step graded exercise program, supported by up to 4 face-to-face/telephone/Skype™ consultations with a GES-trained physiotherapist (no more than 90 minutes in total) over 8 weeks. The primary outcomes at 12-weeks after randomization will be physical function (SF-36 physical functioning subscale) and fatigue (Chalder Fatigue Questionnaire). Secondary outcomes will include healthcare costs, adverse outcomes, and self-rated global impression change scores. We will follow up all participants until 1 year after randomization. We will also undertake qualitative interviews of a sample of participants who received GES, looking at perceptions and experiences of those who improved and worsened. Results: The project was funded in 2011 and enrolment was completed in December 2014, with follow-up completed in March 2016. Data analysis is currently underway and the first results are expected to be submitted soon. Conclusions: This study will indicate whether adding GES to SMC will benefit patients who often spend many months waiting for rehabilitative therapy with little or no improvement being made during that time. The study will indicate whether this type of guided self-management is cost-effective and safe. If this trial shows GES to be acceptable, safe, and comparatively effective, the GES booklet could be made available on the Internet as a practitioner and therapist resource for clinics to recommend, with the caveat that patients also be supported with guidance from a trained physiotherapist. The pragmatic approach in this trial means that GES findings will be generalizable to usual National Health Service (NHS) practice.