ABSTRACT
INTRODUCTION: Health inequities are defined as unfair and avoidable differences in health between groups within a population. Most health research is conducted through observational studies, which are able to offer real-world insights about etiology, healthcare policy/programme effectiveness and the impacts of socioeconomic factors. However, most published reports of observational studies do not address how their findings relate to health equity. Our team seeks to develop equity-relevant reporting guidance as an extension of the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement. This scoping review will inform the development of candidate items for the STROBE-Equity extension. We will operationalise equity-seeking populations using the PROGRESS-Plus framework of sociodemographic factors. As part of a parallel stream of the STROBE-Equity project, the relevance of candidate guideline items to Indigenous research will be led by Indigenous coinvestigators on the team. METHODS AND ANALYSIS: We will follow the Joanna Briggs Institute method for conducting scoping reviews. We will evaluate the extent to which the identified guidance supports or refutes our preliminary candidate items for reporting equity in observational studies. These candidate items were developed based on items from equity-reporting guidelines for randomised trials and systematic reviews, developed by members of this team. We will consult with our knowledge users, patients/public partners and Indigenous research steering committee to invite suggestions for relevant guidance documents and interpretation of findings. If the identified guidance suggests the need for additional candidate items, they will be developed through inductive thematic analysis. ETHICS AND DISSEMINATION: We will follow a principled approach that promotes ethical codevelopment with our community partners, based on principles of cultural safety, authentic partnerships, addressing colonial structures in knowledge production and the shared ownership, interpretation, and dissemination of research. All products of this research will be published as open access.
Subject(s)
Health Equity , Humans , Population Groups , Research Design , Research Report , Review Literature as Topic , Socioeconomic FactorsABSTRACT
OBJECTIVES: We aimed at identifying the important variables for labour induction intervention and assessing the predictive performance of machine learning algorithms. SETTING: We analysed the birth registry data from a referral hospital in northern Tanzania. Since July 2000, every birth at this facility has been recorded in a specific database. PARTICIPANTS: 21 578 deliveries between 2000 and 2015 were included. Deliveries that lacked information regarding the labour induction status were excluded. PRIMARY OUTCOME: Deliveries involving labour induction intervention. RESULTS: Parity, maternal age, body mass index, gestational age and birth weight were all found to be important predictors of labour induction. Boosting method demonstrated the best discriminative performance (area under curve, AUC=0.75: 95% CI (0.73 to 0.76)) while logistic regression presented the least (AUC=0.71: 95% CI (0.70 to 0.73)). Random forest and boosting algorithms showed the highest net-benefits as per the decision curve analysis. CONCLUSION: All of the machine learning algorithms performed well in predicting the likelihood of labour induction intervention. Further optimisation of these classifiers through hyperparameter tuning may result in an improved performance. Extensive research into the performance of other classifier algorithms is warranted.
