Background Suicidal behaviour is difficult to detect in the general practice. Machine learning (ML) algorithms using routinely collected data might support General Practitioners (GPs) in the detection of suicidal behaviour. In this paper, we applied machine learning techniques to support GPs recognizing suicidal behaviour in primary care patients using routinely collected general practice data. Methods This case-control study used data from a national representative primary care database including over 1.5 million patients (Nivel Primary Care Database). Patients with a suicide (attempt) in 2017 were selected as cases (N = 574) and an at risk control group (N = 207,308) was selected from patients with psychological vulnerability but without a suicide attempt in 2017. RandomForest was trained on a small subsample of the data (training set), and evaluated on unseen data (test set). Results Almost two-third (65%) of the cases visited their GP within the last 30 days before the suicide (attempt). RandomForest showed a positive predictive value (PPV) of 0.05 (0.04–0.06), with a sensitivity of 0.39 (0.32–0.47) and area under the curve (AUC) of 0.85 (0.81–0.88). Almost all controls were accurately labeled as controls (specificity = 0.98 (0.97–0.98)). Among a sample of 650 at-risk primary care patients, the algorithm would label 20 patients as high-risk. Of those, one would be an actual case and additionally, one case would be missed. Conclusion In this study, we applied machine learning to predict suicidal behaviour using general practice data. Our results showed that these techniques can be used as a complementary step in the identification and stratification of patients at risk of suicidal behaviour. The results are encouraging and provide a first step to use automated screening directly in clinical practice. Additional data from different social domains, such as employment and education, might improve accuracy.
Self-management interventions (SMIs) may improve outcomes in Chronic Obstructive Pulmonary Disease (COPD). However, accurate comparisons of their relative effectiveness are challenging, partly due to a lack of clarity and detail regarding the intervention content being evaluated. This study systematically describes intervention components and characteristics in randomized controlled trials (RCTs) related to COPD self-management using the COMPAR-EU taxonomy as a framework, identifying components that are insufficiently incorporated into the design of the intervention or insufficiently reported. Overall, 235 RCTs published between 2010 and 2018, from a systematic review were coded using the taxonomy, which includes 132 components across four domains: intervention characteristics, expected patient (or caregiver) self-management behaviours, patient relevant outcomes, and target population characteristics. Risk of bias was also assessed. Interventions mainly focused on physical activity (67.4%), and condition-specific behaviours like breathing exercise (63.5%), self-monitoring (50.8%), and medication use (33.9%). Support techniques like education and skills-training, self-monitoring, and goal setting (over 35% of the RCTs) were mostly used for this. Emotional-based techniques, problem-solving, and shared decision-making were less frequently reported (less than 15% of the studies). Numerous SMIs components were insufficiently incorporated into the design of COPD SMIs or insufficiently reported. Characteristics like mode of delivery, intensity, location, and providers involved were often not described. Only 8% of the interventions were tailored to the target population’s characteristics. Outcomes that are considered important by patients were hardly taken into account. There is still a lot to improve in both the design and description of SMIs for COPD. Using a framework such as the COMPAR-EU SMI taxonomy may contribute to better reporting and to better informing of replication efforts. In addition, prospective use of the taxonomy for developing and reporting intervention content would further aid in building a cumulative science of effective SMIs in COPD.
Objectives To identify and describe the most relevant contextual factors (CFs) from the literature that influence the successful implementation of self-management interventions (SMIs) for patients living with type 2 diabetes mellitus, obesity, COPD and/or heart failure. Methods We conducted a qualitative review of reviews. Four databases were searched, 929 reviews were identified, 460 screened and 61 reviews met the inclusion criteria. CFs in this paper are categorized according to the Tailored Implementation for Chronic Diseases framework. Results A great variety of CFs was identified on several levels, across all four chronic diseases. Most CFs were on the level of the patient, the professional and the interaction level, while less CFs were obtained on the level of the intervention, organization, setting and national level. No differences in main themes of CFs across all four diseases were found. Discussion For the successful implementation of SMIs, it is crucial to take CFs on several levels into account simultaneously. Person-centered care, by tailoring SMIs to patients’ needs and circumstances, may increase the successful uptake, application and implementation of SMIs in real-life practice. The next step will be to identify the most important CFs according to various stakeholders through a group consensus process.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.