Machine learning approaches for risk prediction after percutaneous coronary intervention: a systematic review and meta-analysis.

Aims: Accurate prediction of clinical outcomes following percutaneous coronary intervention (PCI) is essential for mitigating risk and peri-procedural planning. Traditional risk models have demonstrated a modest predictive value. Machine learning (ML) models offer an alternative risk stratification that may provide improved predictive accuracy.

Delayed return of bowel function after general surgery in South Australia.

Introduction: Reference ranges for determining pathological versus normal postoperative return of bowel function are not well characterised for general surgery patients. This study aimed to characterise time to first postoperative passage of stool after general surgery; determine associations between clinical factors and delayed time to first postoperative stool; and evaluate the association between delay to first postoperative stool and prolonged length of hospital stay.

Methods: This study included consecutive admissions at two tertiary hospitals across a two-year period whom underwent a range of general surgery operations.

Emergency laparotomy preoperative risk assessment tool performance: A systematic review.

Background: Preoperative assessment of risk for emergency laparotomy may enhance decision making with regards to urgency or perioperative critical care admission and promote a more informed consent process for patients. Accordingly, we aimed to assess the performance of risk assessment tools in predicting mortality after emergency laparotomy.

Methods: PubMed, Embase, the Cochrane Library and CINAHL were searched to 12 February 2022 for observational studies reporting expected mortality based on a preoperative risk assessment and actual mortality after emergency laparotomy.

Association between direct oral anticoagulant concentrations and clinical outcomes: A systematic review and meta-analysis.

Introduction: Current guidelines suggest preoperative direct oral anticoagulant levels of < 30-50 ng/ml. However, there is limited evidence to guide this expert consensus. Reviewing assay titres and clinical outcomes may be able to inform perioperative care of the anticoagulated patient.

Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis.

Background: Accurate mortality prediction following transcatheter aortic valve implantation (TAVI) is essential for mitigating risk, shared decision-making and periprocedural planning. Surgical risk models have demonstrated modest discriminative value for patients undergoing TAVI and are typically poorly calibrated, with incremental improvements seen in TAVI-specific models. Machine learning (ML) models offer an alternative risk stratification that may offer improved predictive accuracy.