In health systems with strongly developed primary care, such as in the Netherlands, effectively engaging primary care professionals (PCPs) in suicide prevention is a key strategy. As part of the national Suicide Prevention Action Network (SUPRANET), a program was offered to PCPs in six regions in the Netherlands in 2017–2018 to more effectively engage them in suicide prevention. This implementation study aimed to evaluate to what extent SUPRANET was helpful in supporting PCPs to apply suicide prevention practices. From March to May 2018, 21 semi-structured interviews have been carried out with PCPs and other non-clinical professionals from SUPRANET regions in the Netherlands. Verbatim transcripts were analysed using the grounded theory approach. Data was structured using the Consolidated Framework for Implementation Research, which enabled identifying facilitating and challenging factors for PCPs to carry out suicide prevention practices. An important challenge included difficulties in assessing suicide risk (intervention characteristics) due to PCPs’ self-perceived incompetence, burdensomeness of suicide and limited time and heavy workload of PCPs. Another important limitation was collaboration with mental health care (outer setting), whereas mental health nurses (inner setting) and SUPRANET (implementation process) were facilitating factors for applying suicide prevention practices. With regard to SUPRANET, especially the training was positively evaluated by PCPs. PCPs expressed a strong need for improving collaboration with specialized mental health care, which was not provided by SUPRANET. Educating PCPs on suicide prevention seems beneficial, but is not sufficient to improve care for suicidal patients. Effective suicide prevention also requires improved liaison between mental health services and primary care, and should therefore be the focus of future suicide prevention strategies aimed at primary care.

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.

No abstract

No abstract