RESUMO
Background: There has been a rapid increase in the number of Artificial Intelligence (AI) studies of cardiac MRI (CMR) segmentation aiming to automate image analysis. However, advancement and clinical translation in this field depend on researchers presenting their work in a transparent and reproducible manner. This systematic review aimed to evaluate the quality of reporting in AI studies involving CMR segmentation. Methods: MEDLINE and EMBASE were searched for AI CMR segmentation studies in April 2022. Any fully automated AI method for segmentation of cardiac chambers, myocardium or scar on CMR was considered for inclusion. For each study, compliance with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) was assessed. The CLAIM criteria were grouped into study, dataset, model and performance description domains. Results: 209 studies published between 2012 and 2022 were included in the analysis. Studies were mainly published in technical journals (58%), with the majority (57%) published since 2019. Studies were from 37 different countries, with most from China (26%), the United States (18%) and the United Kingdom (11%). Short axis CMR images were most frequently used (70%), with the left ventricle the most commonly segmented cardiac structure (49%). Median compliance of studies with CLAIM was 67% (IQR 59-73%). Median compliance was highest for the model description domain (100%, IQR 80-100%) and lower for the study (71%, IQR 63-86%), dataset (63%, IQR 50-67%) and performance (60%, IQR 50-70%) description domains. Conclusion: This systematic review highlights important gaps in the literature of CMR studies using AI. We identified key items missing-most strikingly poor description of patients included in the training and validation of AI models and inadequate model failure analysis-that limit the transparency, reproducibility and hence validity of published AI studies. This review may support closer adherence to established frameworks for reporting standards and presents recommendations for improving the quality of reporting in this field. Systematic Review Registration: [www.crd.york.ac.uk/prospero/], identifier [CRD42022279214].
RESUMO
BACKGROUND: Children born to high-risk pregnancies are more likely to experience adverse health outcomes later in life. As estimated, 15% of all pregnancies are at risk of various life-threatening conditions leading to adverse maternal and foetal outcomes. Millennium Development Goal resulted in the global reduction of maternal death from 390,000 to 275000 in 1990-2015). Similarly, to keep this momentum, the current United Nations Sustainable Development Goal (SDG: 3.1) aims at reducing the global maternal mortality ratio to less than 70 per 100,000 live births by 2030, and this can be achieved by addressing high-risk pregnancy contributing to significant mortality and morbidity. In India, gestational diabetes, gestational hypertension, and gestational hypothyroidism were identified as factors contributing to the high-risk pregnancy. This review summarises the commonly used approach for screening, diagnosis, and management of these conditions in the Asian population. It draws a comparison with the current protocols and guidelines in the Indian setting. METHODS: Electronic search in PubMed and Google Scholar, reference snowballing, and review of current guidelines and protocols were done between January 2010 to October 2019. Published studies reporting Screening, diagnosis, and management of these conditions were included. Articles selected were then screened, appraised for quality, extract relevant data, and synthesised. RESULTS: Screening, diagnosis, and management of these three conditions vary and no single universally accepted criteria for diagnosis and management exist to date. In India, national guidelines available have not been evaluated for feasibility of implementation at the community level. There are no national guidelines for PIH diagnosis and management despite the increasing burden and contribution to maternal and perinatal morbidity and mortality. Criteria for diagnosis and management of gestational diabetes, gestational hypertension, and gestational hypothyroidism varies but overall early screening for predicting risk, as reported from majority of the articles, were effective in minimizing maternal and foetal outcome. CONCLUSION: Existing National guidelines for Screening, Diagnosis, and Management of Gestational Diabetes Mellitus (2018) and Gestational Hypothyroidism (2014) need to be contextualized and modified based on the need of the local population for effective treatment. Findings from this review show that early screening for predicting risk to be an effective preventive strategy. However, reports related to a definitive diagnosis and medical management were heterogeneous.