Objectives To identify stable cancer symptom clusters (CSCs) phenotypes and trajectories in patients with breast and ovarian cancer, examine associations with traditional Chinese medicine (TCM) syndromes and develop prediction models.Methods A multicentre, prospective, longitudinal real-world cohort will enrol 2000 patients with breast cancer and 1000 patients with ovarian cancer. Data include clinical characteristics, symptoms, TCM syndrome information and multiomics data from subgroups. CSCs will be identified using exploratory factor analysis with bootstrap resampling; associations and trajectories will be analysed using regression and mixed-effects models. Prediction models will use LASSO（least absolute shrinkage and selection operator）, random forest and XGBoost（extreme gradient boosting） with internal validation.Results Expected outcomes include stable CSCs phenotypes and clinically useful prediction models.Discussion This study integrates TCM syndrome differentiation to explore CSC heterogeneity and evolution in real-world settings.Conclusion Findings may support personalised symptom management and improve quality of life among patients with cancer.Trial registration number ChiCTR2500111873 (Approval time: 6 November 2025); ITMCTR2025001939 (registration time: 17 July 2025).
Objectives This review synthesised real-world patient safety evidence for artificial intelligence (AI)-enabled triage tools in primary care and mapped whether safety has been examined across sociodemographic groups.Methods PubMed, Embase, Web of Science and Scopus were searched (January 2015–November 2025) with citation searching. Prospective studies evaluating AI triage tools in real-world primary care settings were eligible. Quality was assessed using the Mixed Methods Appraisal Tool; equity dimensions were mapped using PROGRESS-Plus. Random-effects meta-analysis pooled comparable proportion-based outcomes.Results Four studies were included; all evaluated rule-based or decision-tree tools as no machine learning or generative AI system met the eligibility criteria. Safe triage rates ranged from 81% to 97.6%, under-triage rates ranged from 2% to 17.2% and over-triage rates ranged from 8% to 29%. An exploratory random-effects meta-analysis of three studies (n=1303) gave a pooled safe triage proportion of 0.908 (95% CI 0.319 to 0.995) with substantial heterogeneity (I²=97.0%); given incompatible outcome definitions across studies, these estimates are hypothesis-generating rather than summary measures. No study analysed differential triage accuracy by any sociodemographic factor despite available demographic data.Discussion Safety outcomes were confined to technical performance proxies rather than direct measures of harm, and the absence of equity-stratified analysis may reflect a systemic evidence gap.Conclusion To our knowledge, this is the first systematic review to examine both real-world patient safety and equity of AI-enabled triage in primary care; findings may not extend to machine learning or generative AI systems. A Safety-Equity Evidence Mapping (SEEM) matrix and an evidence maturity framing are proposed to characterise this evidence and inform emerging consensus on evidence thresholds.PROSPERO registration number CRD420251179046.
Objective Venous thromboembolism (VTE) is a major cause of morbidity and mortality, with combined oral contraceptives (COCPs) being a modifiable risk factor. Existing clinical tools have limited ability to capture complex predictor interactions. This study aimed to develop and evaluate machine learning (ML) models to predict VTE risk among COCP users.Methods This study was conducted using data from the Saudi Real-World Evidence Network (2016–2023). The primary outcome was the first VTE event within 2 years of COCP initiation. Following data partitioning, feature selection was performed on the training set. Elastic-net logistic regression, random forest (RF), extreme gradient boosting (XGBoost), one-class support vector machine and Isolation-Forest were trained on original and resampled datasets. Performance was evaluated using the area under the receiver operating characteristic curve (AUROC) and F1 score.Results The cohort included 24 518 treatment episodes (n=17 512, VTE events=52). After handling class imbalance, RF and XGBoost were the best-performing models (F1: 84.3% and 81.6%; AUROC: 59.6% and 69.2%, respectively), compared with other models (F1: 2.6%–55.3%, AUROC: 54.2%–68.4%). Key predictors included age, glucocorticoid use and rheumatic, renal and thyroid diseases.Discussion ML shows potential for VTE risk detection despite low event rate and class imbalance. However, findings suggest synthetic sample overfitting, and external validation is warranted before clinical deployment. Identified predictors reinforce the role of metabolic and inflammatory factors in VTE susceptibility among COCP users.Conclusion ML models, particularly XGBoost and RF, demonstrated moderate predictive ability for VTE among COCP users, supporting their use in individualised risk assessments, though external validation is warranted.
Objectives This systematic review examined the impact of digital health interventions on health beliefs and self-efficacy among adults living with chronic conditions.Methods Eight randomised controlled trials and one mixed-methods study involving adults aged 18 years or older with chronic conditions were included if they evaluated a digital health intervention and reported outcomes related to health beliefs and/or self-efficacy. PubMed, Embase and CINAHL were searched from database inception to 29 August 2025. Risk of bias was assessed using the Cochrane Risk of Bias 2 tool and the Mixed Methods Appraisal Tool.Results Nine studies were included comprising over 1500 adults with conditions including diabetes, heart failure, chronic kidney disease, chronic obstructive pulmonary disease and obesity. Most included studies reported improvements in self-efficacy following digital health interventions. Only two studies explicitly assessed health beliefs, both demonstrating favourable effects when interventions were theory informed. All randomised trials were rated as having a high risk of bias, primarily due to reliance on self-reported outcomes and lack of blinding.Discussion Digital health may support self-efficacy and to a lesser extent health beliefs in adults with chronic conditions, particularly when grounded in behavioural theory and supported by clinician engagement. However, methodological limitations and the under-representation of health belief outcomes restrict the strength of conclusions.Conclusion This review highlights that digital health interventions have the potential to improve self-efficacy and health beliefs when they are grounded in behavioural theory, personalised to users’ needs and culturally responsive. However, the certainty of these findings is limited by the consistently high risk of bias across the included studies.PROSPERO registration number CRD420251031784.
Health services are rapidly adopting digital systems, but health data remain unstandardised and segregated across separate healthcare providers. Allergy serves as a universally important use case since type I mediated reactions to medications, foods and environmental substances, impact a plethora of health services. Australia has among the highest rates of allergic diseases globally, with 30% of the population affected, costing $A18.9b and $A44.6b in health and non-financial impacts annually. A Commonwealth Parliamentary Inquiry into Allergy and Anaphylaxis (2020) delivered 24 recommendations that underpinned foundation of the National Allergy Council and National Allergy Centre of Excellence (2022). While our National Digital Health Strategy (2023–2028) guides integration of primary and tertiary health data for clinical decision support, secure health data access for research needs prioritisation. Here we consolidate regulatory, ethical, privacy and technical considerations for accessing, integrating and analysing health data for generation of new insights to inform health system improvement. We found through document tracking and sector knowledge as many as 77 national level documents relating to legislation, policy, strategy, roadmaps, standards, frameworks, guidelines and infrastructure, from 24 different national agencies linked to seven federal government departments. This perspective on the complex national landscape of digital health regulation identifies the challenges and suggests a GATEway framework to navigate fragmented health data, distributed responsibilities, and requirements of multiple stakeholders involved in guiding and governing ethical and secure access to large-scale health data assets for research analyses. With increasing allergy prevalence, expediting digital health analytical capabilities is a critical priority to drive evidence-based improvements in allergy care.
