Search

Predicting emergence from prolonged disorders of consciousness (PDOC) is important for planning care and treatment. We used machine learning to examine which variables from routine clinical data on admission to specialist rehabilitation units best predict emergence by discharge. A multicentre national cohort analysis of prospectively collected clinical data from the UK Rehabilitation Outcomes (UKROC) database 2010–2018. Patients (n = 1170) were operationally defined as "still in PDOC" or "emerged" by their total UK Functional Assessment Measure (FIM + FAM) discharge score. Variables included: Age, aetiology, length of stay, time since onset, and all items of the Neurological Impairment Scale, Rehabilitation Complexity Scale, Northwick Park Dependency Scale, and the Patient Categorisation Tool. After filtering, prediction of emergence was explored using four techniques: binary logistic regression, linear discriminant analysis, artificial neural networks, and rule induction. Triangulation through these techniques consistently identified characteristics associated with emergence from PDOC. More severe motor impairment, complex disability, medical and behavioural instability, and anoxic aetiology were predictive of non-emergence, whereas those with less severe motor impairment, agitated behaviour and complex disability were predictive of emergence. This initial exploration demonstrates the potential opportunities to enhance prediction of outcome using machine learning techniques to explore routinely collected clinical data. Predicting emergence from prolonged disorders of consciousness is important for planning care and treatment. Few evidence-based criteria exist for aiding clinical decision-making and existing criteria are mostly based upon acute admission data. Whilst acknowledging the limitations of using proxy data for diagnosis of emergence, this study suggests that key items from the UKROC dataset, routinely collected on admission to specialist rehabilitation some months post injury, may help to predict those patients who are more (or less) likely to regain consciousness. Machine learning can help to enhance our understanding of the best predictors of outcome and thus assist with clinical decision-making in PDOC. [ABSTRACT FROM AUTHOR]

The present study aimed to assess: (1) whether a more active involvement of patients is associated with an improvement of clinical symptoms, global functioning, and quality-of-life; and (2) how patients' satisfaction with clinical decisions can lead to better outcome after 1 year. Data were collected as part of the study 'Clinical decision-making and outcome in routine care for people with severe mental illness (CEDAR)', a longitudinal observational study, funded by the European Commission and carried out in six European countries. Patients' inclusion criteria were: (a) aged between 18 and 60 years; (b) diagnosis of a severe mental illness of any kind according to the Threshold Assessment Grid (TAG) ≥ 5 and duration of illness ≥ 2 years; (c) expected contact with the local mental health service during the 12-month observation period; (d) adequate skills in the language of the host countries; and (e) the ability to provide written informed consent. The clinical decision-making styles of clinicians and the patient satisfaction with decisions were assessed using the Clinical Decision Making Style and the Clinical Decision Making Involvement and Satisfaction scales, respectively. Patients were assessed at baseline and 1 year after the recruitment. The sample consisted of 588 patients with severe mental illness, mainly female, with a mean age of 41.69 (±10.74) and a mean duration of illness of 12.5 (±9.27) years. The majority of patients were diagnosed with psychotic (45.75%) or affective disorders (34.01%). At baseline, a shared CDM style was preferred by 70.6% of clinicians and about 40% of patients indicated a high level of satisfaction with the decision and 31% a medium level of satisfaction. Higher participation in clinical decisions was associated with improved social functioning and quality-of-life, and reduced interpersonal conflicts, sense of loneliness, feelings of inadequacy, and withdrawal in friendships after 1 year (p < 0.05). Moreover, a higher satisfaction with decisions was associated with a better quality-of-life (p < 0.0001), reduced symptom severity (p < 0.0001), and a significantly lower illness burden associated with symptoms of distress (p < 0.0001), interpersonal difficulties (p < 0.0001), and problems in social roles (p < 0.05). Our findings clearly show that a higher involvement in and satisfaction of patients with clinical decision-making was associated with better outcomes. More efforts have to be made to increase the involvement of patients in clinical decision-making in routine care settings. [ABSTRACT FROM AUTHOR]

Existing research suggests the provision of communication aids for children with complex communication needs can have significant positive impacts on health and quality-of-life. The process of clinical decision-making related to the recommendation of high-tech communication aids is not well documented or evaluated, and research evidence related to the provision of these aids remains limited. This study aimed to understand the factors that specialized AAC professionals in the UK consider when recommending high-tech communication aids. Purposive sampling was used to recruit teams to six focus groups, each of which centred on a team's recent recommendation process (i.e. a discussion following a real-time assessment session, where the team attempted to arrive at an agreed recommendation for a specific child). Thematic network analysis was used to interpret data from the focus group discussions. Participants identified a wide range of child characteristics, access features, and communication aid attributes in weighing up decisions for individual children. Findings suggest that specialized AAC professionals in the UK prioritize access features over language considerations in their communication aid recommendations. An explanatory model was developed to illustrate the interaction effect that several competing considerations may have on decision-making. Implications for clinical practice and future research are discussed. [ABSTRACT FROM AUTHOR]

The choice of which AAC device to provide for a child can have long lasting consequences, but little is known about the decision-making of AAC professionals who make recommendations in this context. A survey was conducted with AAC professionals using best–worst scaling methodology examining what characteristics of children and attributes of AAC devices are considered most important in decision-making. A total of 19 child characteristics and 18 device attributes were selected by the authors from lists generated from literature reviews and from focus groups with AAC professionals, people who use AAC, and other stakeholders. The characteristics and attributes were used to develop two best–worst scaling surveys that were administered to 93 AAC professionals based in the UK. The relative importance of characteristics/attributes was estimated using statistical modelling. Child characteristics related to language and communication, cognitive and learning abilities, and personality traits were generally found to be more important than physical features. Communication, language, and interface-related AAC device attributes were generally more important than hardware and physical attributes. Respondent demographics (e.g., experience, professional background) did not seem to influence the importance assigned to device characteristics or attributes. Findings may inform both future quantitative research into decision-making and efforts to improve decision-making in practice. [ABSTRACT FROM AUTHOR]

Objective:The Any Qualified Provider framework in the National Health Service has changed the way adult audiology services are offered in England. Under the new rules, patients are being offered a choice in geographical location and audiology provider. This study aimed to explore how choices in treatment are presented and to identify what information patients need when they are seeking help with hearing loss.Design:This study adopted qualitative methods of ethnographic observations and focus group interviews to identify information needed prior to, and during, help-seeking. Observational data and focus group data were analysed using the constant comparison method of grounded theory.Study sample:Participants were recruited from a community Health and Social Care Trust in the west of England. This service incorporates both an Audiology and a Hearing Therapy service. Twenty seven participants were involved in focus groups or interviews.Results:Participants receive little information beyond the detail of hearing aids. Participants report little information that was not directly related to uptake of hearing aids.Conclusions:Participant preferences were not explored and limited information resulted in decisions that were clinician-led. The gaps in information reflect previous data on clinician communication and highlight the need for consistent information on a range of interventions to manage hearing loss. [ABSTRACT FROM AUTHOR]