Search

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. more...

Introduction Population ageing and increasing chronic illness burden have sparked interest in innovative care models. While self-management interventions (SMIs) are drawing increasing attention, evidence of their efficacy is mostly based on pairwise meta-analysis, generally derived from randomised controlled trials comparing interventions versus a control or no intervention. As such, relevant efficacy data for comparisons among different SMIs that can be applied to specific chronic conditions are missing. Therefore, the relevance of the available evidence for decision-making at clinical, organisational and policy levels is limited.Aim To identify, compare and rank the most effective and cost-effective SMIs for adults with four high-priority chronic conditions: type 2 diabetes, obesity, chronic obstructive pulmonary disease,and heart failure.Methods and analysis All activities will be conducted as part of the cost-effectiveness of self-management interventions in four high-priority chronic conditions in Europe(COMPAR-EU, Comparing effectiveness of self-management interventions in 4 high priority chronic diseases inEurope) Project, an European Union (EU)-funded project designed to bridge the gap between current knowledge and practice on SMIs. In the first phase of the project, we will develop and validate a taxonomy, and a Core Outcome Set for each condition. These activities will inform a series of systematic review and network meta-analysis about the effectiveness of SMIs. We will also perform a cost-effectiveness analysis of the most effective SMIs and an evaluation of contextual factors. We will finally develop tailored decision-making tools for the different relevant stakeholders.Ethics and dissemination Ethical approval was obtained from the local ethics committee (University Institute for Primary Care Research - IDIAP Jordi Gol). All patients and other stakeholders will provide informed consent prior to participation. This project has been funded by the EU Horizon 2020 research and innovation programme (grant agreement no. 754936). Results will be of interest to relevant stakeholder groups (patients, professionals, managers, policymakers and industry), and will be disseminated in a tailored multi-pronged approach that will include deployment of an interactive platform. more...