Conectar
Digital therapeutics (DTx) show promise in bridging mental healthcare gaps. However, treatment selection often relies on availability and trial-and-error, prolonging suffering and increasing costs. Personalised prediction models could help identify individuals benefiting most from specific DTx.
The aim of this secondary analysis was to establish a machine learning-based prediction model for positive treatment outcomes in patients with depressive or anxiety symptoms after 8 weeks of internet-delivered cognitive behavioural therapy (iCBT).
We analysed a large real-world dataset of patients from the online therapy unit iCBT programme in Saskatchewan, Canada (2013–2021). Clinically significant changes in depressive symptoms or anxiety were measured using the Patient Health Questionnaire-9 (PHQ-9) and the Generalised Anxiety Disorder-7 (GAD-7). We trained six prediction models using sociodemographic and mental health-related factors at baseline, compared model performances and calculated Shapley values for feature importance.
Data from 4175 patients using 34 features for prediction, identified by least absolute shrinkage and selection operator regression, showed the Gradient Boosted Model (gbm) and logistic regression (log) performed best, with balanced accuracies of 0.76, 95% CI (0.70 to 0.83) and 0.70, 95% CI (0.63 to 0.77). Shapley values indicated GAD-7 scores at baseline as the most important predictor of clinically significant improvement, along with mental health history and sociodemographic variables.
The gbm and log models achieved comparable accuracy in predicting clinically significant improvement after iCBT, supporting the use of simpler, interpretable methods in clinical practice.
These findings could help improve mental health treatment selection, iCBT assignment, enhance effectiveness and optimise treatment for patients.
A pressure ulcer is an injury to the skin and underlying tissues caused by pressure, shear or a combination of the two. In Europe, the mean prevalence rate of pressure ulcers is 10.8%, in Ireland, it is less than 12%. Using systematic review methodology, original research studies written in English were included, employing pre- and post-studies, quality improvement initiatives or projects, randomised controlled trials and experimental studies. Data was extracted using a pre-designed data extraction tool and quality appraisal was undertaken using the Evidence-Based Librarianship (EBL) tool. Where appropriate, a meta-analysis was undertaken using RevMan. The study protocol was pre-registered with the International Prospective Register of Systematic Reviews (PROSPERO CRD42023442711). Following the search, 628 records were returned, of which 25 met the inclusion criteria. The studies were conducted in a variety of acute healthcare settings. Of the included studies, 16 presented data on incidence and 12 presented data on prevalence of pressure ulcers post-implementation of a care bundle. A meta-analysis of 10 studies discussing incidence indicates the RR of PU is 0.40 (95% CI: 0.21–0.78; p = 0.007), supporting the use of a care bundle. A meta-analysis of seven studies discussing prevalence indicates the RR of PU is 0.34 (95% CI: 0.21–0.56; p = 0.0001), demonstrating the reduction in the RR of PU development in favour of the care bundle group. A variety of care bundle elements were found in the studies. Although results indicated the use of a care bundle was advantageous in preventing a pressure ulcer in the acute care setting, it was unclear which of these elements were most effective.
To gain a greater understanding of how compression therapy affects quality of life, this systematic review appraised existing published studies measuring the impact of compression therapy on health quality of life (HRQoL), and pain, among people with venous leg ulcers (VLU).
Five databases were searched, and two authors extracted data and appraised the quality of selected papers using the RevMan risk of bias tool. Due to heterogeneity in the types of compression and instruments used to evaluate HRQoL, meta-analysis was not appropriate; thus, a narrative synthesis of findings was undertaken.
Ten studies were included, 9 RCTs and one before-after study. The studies employed nine different HRQoL tools to measure the impact of a variety of compression therapy systems, with or without an additional exercise programme, versus other compression systems or usual care, and the results are mixed. With the use of the Cardiff Cardiff Wound Impact Schedule, the SF-8 and the SF-12, study authors found no differences in QoL scores between the study groups. This is similar to one study using QUALYs (Iglesias et al., 2004). Conversely, for studies using EuroQol-5D, VEINES-QOL, SF-36 and CIVIQ-20 differences in QoL scores between the study groups were noted, in favour of the study intervention groups. Two further studies using QUALYs found results that favoured a two-layer cohesive compression bandage and the TLCCB group, respectively. Results for the five studies that assessed pain are also mixed, with one study finding no difference between study groups, one finding that pain increased over the study period and three studies finding that pain reduced in the intervention groups. All studies were assessed as being at risk of bias in one or more domains.
Results were varied, reflecting uncertainty in determining the impact of compression therapy on quality of life and pain among people with a venous leg ulcer. The heterogeneity of the compression systems and the measures used to evaluate HRQoL make it a challenge to interpret the overall evidence. Further studies should strive for homogeneity in design, interventions and comparators to enhance both internal and external validity.
FreshRSS