Outcomes and use of healthcare resources after an intervention for chronic limb-threatening ischaemia.

BACKGROUND: The fate of patients with chronic limb-threatening ischaemia undergoing revascularization or a primary amputation is unclear. The aim of this study was to assess the postoperative outcomes and post-procedural healthcare resource use/costs over 1 year after revascularization or a primary amputation for chronic limb-threatening ischaemia. METHODS: The UK Kent Integrated Dataset, which links primary, community, and secondary care for 1.6 million people, was interrogated. All patients with a new diagnosis of chronic limb-threatening ischaemia undergoing revascularization or a major amputation between January 2016 and January 2019 (3 years) were identified. Postoperative events across all healthcare settings and post-procedure healthcare resource use were analysed over 1 year (until the end of 2019). RESULTS: Overall, 4252 patients with a new diagnosis of chronic limb-threatening ischaemia were identified (65 per cent were male and the mean age was 73 years) between January 2016 and January 2019, of whom 579 (14 per cent) underwent an intervention (studied population); 296 (7 per cent) had an angioplasty, 75 (2 per cent) had bypass surgery, 141 (3 per cent) had a primary major lower limb amputation, 11 had a thrombo-embolectomy (0.3 per cent), and 56 had an endarterectomy (1.3 per cent). Readmissions (median of 2) were similar amongst different procedures within 1 year; bypass surgery was associated with more hospital appointments (median of 4 versus 2; P = 0.002). Patients undergoing a primary amputation had the highest number of cardiovascular events and 1-year mortality. In a linear regression model, index procedure type and Charlson co-morbidity index score were not predictors of appointments in primary/secondary care, community care visits, or readmissions after discharge. There were no statistically significant differences regarding post-procedural healthcare costs between procedures over 1 year. CONCLUSION: Revascularization is not associated with more hospital, primary/community care appointments or increased post-procedural healthcare costs over 1 year when compared with primary amputation, in people with chronic limb-threatening ischaemia.

Assessment of machine learning algorithms in national data to classify the risk of self-harm among young adults in hospital: A retrospective study.

BACKGROUND: Self-harm is one of the most common presentations at accident and emergency departments in the UK and is a strong predictor of suicide risk. The UK Government has prioritised identifying risk factors and developing preventative strategies for self-harm. Machine learning offers a potential method to identify complex patterns with predictive value for the risk of self-harm. METHODS: National data in the UK Mental Health Services Data Set were isolated for patients aged 18-30 years who started a mental health hospital admission between Aug 1, 2020 and Aug 1, 2021, and had been discharged by Jan 1, 2022. Data were obtained on age group, gender, ethnicity, employment status, marital status, accommodation status and source of admission to hospital and used to construct seven machine learning models that were used individually and as an ensemble to predict hospital stays that would be associated with a risk of self-harm. OUTCOMES: The training dataset included 23 808 items (including 1081 episodes of self-harm) and the testing dataset 5951 items (including 270 episodes of self-harm). The best performing algorithms were the random forest model (AUC-ROC 0.70, 95%CI:0.66-0.74) and the ensemble model (AUC-ROC 0.77 95%CI:0.75-0.79). INTERPRETATION: Machine learning algorithms could predict hospital stays with a high risk of self-harm based on readily available data that are routinely collected by health providers and recorded in the Mental Health Services Data Set. The findings should be validated externally with other real-world, prospective data. FUNDING: This study was supported by the Midlands and Lancashire Commissioning Support Unit.