Screening patients for risk of sleep apnea using facial photographs.

We investigated using frontal and profile facial photographic images for screening patients for risk of sleep apnea. A 180 image pairs were used from patients who were diagnosed using an attended overnight polysomnogram test into controls (AHI<;10/h) and sleep apnea (AHI≥10/h). A series of 35 landmarks and 71 features motivated by craniofacial structure pertinent to upper airway physiology were identified on the photographs. After reducing the dimension of the feature set using recursive feature selection, the features were processed by a Support Vector Machine (SVM). Classification was performed using linear kernel SVM. The accuracy and area under Receiver Operating Curve (ROC) improved when the number of features reduced from 71 to eight top-ranked features. Further improvement was achieved by adding clinical measurements to the selected features resulting in the accuracy of 80% and the area under ROC of 0.83.

Do large-scale hospital- and system-wide interventions improve patient outcomes: a systematic review.

BACKGROUND: While health care services are beginning to implement system-wide patient safety interventions, evidence on the efficacy of these interventions is sparse. We know that uptake can be variable, but we do not know the factors that affect uptake or how the interventions establish change and, in particular, whether they influence patient outcomes. We conducted a systematic review to identify how organisational and cultural factors mediate or are mediated by hospital-wide interventions, and to assess the effects of those factors on patient outcomes. METHODS: A systematic review was conducted and reported in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Database searches were conducted using MEDLINE from 1946, CINAHL from 1991, EMBASE from 1947, Web of Science from 1934, PsycINFO from 1967, and Global Health from 1910 to September 2012. The Lancet, JAMA, BMJ, BMJ Quality and Safety, The New England Journal of Medicine and Implementation Science were also hand searched for relevant studies published over the last 5 years. Eligible studies were required to focus on organisational determinants of hospital- and system-wide interventions, and to provide patient outcome data before and after implementation of the intervention. Empirical, peer-reviewed studies reporting randomised and non-randomised controlled trials, observational, and controlled before and after studies were included in the review. RESULTS: Six studies met the inclusion criteria. Improved outcomes were observed for studies where outcomes were measured at least two years after the intervention. Associations between organisational factors, intervention success and patient outcomes were undetermined: organisational culture and patient outcomes were rarely measured together, and measures for culture and outcome were not standardised. CONCLUSIONS: Common findings show the difficulty of introducing large-scale interventions, and that effective leadership and clinical champions, adequate financial and educational resources, and dedicated promotional activities appear to be common factors in successful system-wide change.The protocol has been registered in the international prospective register of systematic reviews, PROSPERO (Registration No. CRD42103003050).

The role of organisational and cultural factors in the implementation of system-wide interventions in acute hospitals to improve patient outcomes: protocol for a systematic literature review.

INTRODUCTION: Little is known about the role of the organisational culture in the success and sustainability of the hospital-wide interventions, and how local culture affects patient outcomes in acute hospitals. METHODS AND ANALYSIS: A systematic literature review will be conducted to identify organisational factors influencing hospital-wide interventions and patient outcomes. A search of English language articles will be performed in MEDLINE, CINAHL, EMBASE, Web of Science, PsychInfo and Global Health databases using Medical Subject Headings and keywords. Randomised controlled trials, quasi-randomised trials, controlled before and after design studies and interrupted time-series analysis studies will be included. 'Grey literature' will be excluded, however peer-reviewed journals that are likely to publish relevant studies (JAMA, BMJ, BMJ Quality and Safety, Lancet and New England Journal of Medicine and Implementation Science) will be hand searched for the last 5 years. Two reviewers will independently undertake a title and abstract review using inclusion and exclusion criteria. Studies will be excluded only after discussion between at least two reviewers, who will assess and agree on the inclusion, risk of bias and quality rating of the studies. One author will extract summary descriptive data from these studies; the other author will review this documentation for accuracy and completeness. RESULTS: It is likely that the studies will be heterogeneous in nature, therefore a narrative synthesis of the findings will be conducted. CONCLUSIONS: We will discuss characteristics of the studies and stratify the results according to the type of hospital-wide interventions, organisational factors associated with them and outcomes measured.