Postpartum hemorrhage (PPH) remains a significant contributor to maternal mortality and morbidity worldwide, with approximately 14 million women affected annually and 70,000 resulting deaths. Despite advances in health care, PPH continues to pose challenges even in developed settings. Apart from mortality, PPH leads to various adverse outcomes and morbidity. Recently, there has been a surge in interest in using artificial intelligence (AI), including machine learning and deep learning, across many areas of health care. This article explores the application of AI in tackling PPH, including predictive modeling and risk stratification. Some studies have shown promising results in predicting PPH. However, external validation of these models is crucial and frequently lacking, with barriers including differences in cohort characteristics and variations in outcome measurement methods. Most of the existing research has taken place in well-resourced health care settings, and there is a lack of models applicable to resource-limited settings where the need is arguably greatest. Incorporating uterine contractility metrics and radiomics into predictive models offers new avenues for enhancing prediction accuracy. Beyond risk prediction, AI has also been explored in other aspects of PPH management, including blood product management and early detection using wearable devices. In conclusion, while AI presents exciting opportunities for PPH prediction and management, challenges such as model validation, clinical translation, and applicability in diverse health care settings remain. Further research, particularly in low-and middle-income countries, is necessary to realize the full potential of AI for addressing the global burden of PPH.

Postpartum hemorrhage (PPH) remains a significant contributor to maternal mortality and morbidity worldwide, with approximately 14 million women affected annually and 70,000 resulting deaths. Despite advances in health care, PPH continues to pose challenges even in developed settings. Apart from mortality, PPH leads to various adverse outcomes and morbidity. Recently, there has been a surge in interest in using artificial intelligence (AI), including machine learning and deep learning, across many areas of health care. This article explores the application of AI in tackling PPH, including predictive modeling and risk stratification. Some studies have shown promising results in predicting PPH. However, external validation of these models is crucial and frequently lacking, with barriers including differences in cohort characteristics and variations in outcome measurement methods. Most of the existing research has taken place in well-resourced health care settings, and there is a lack of models applicable to resource-limited settings where the need is arguably greatest. Incorporating uterine contractility metrics and radiomics into predictive models offers new avenues for enhancing prediction accuracy. Beyond risk prediction, AI has also been explored in other aspects of PPH management, including blood product management and early detection using wearable devices. In conclusion, while AI presents exciting opportunities for PPH prediction and management, challenges such as model validation, clinical translation, and applicability in diverse health care settings remain. Further research, particularly in low-and middle-income countries, is necessary to realize the full potential of AI for addressing the global burden of PPH.

Pigbel remains a likely significant cause of morbidity and mortality in the highlands of Papua New Guinea (PNG), two decades after the administration of pigbel vaccination ceased. There is a need for an effective surveillance program for pigbel to better understand the disease burden and to target communities for preventive strategies. This paper reviews the epidemiology, pathogenesis, recent history and current data on the burden of pigbel in PNG. We propose a surveillance program based on clinical recognition of likely cases and laboratory confirmation using an ELISA assay for Clostridium perfringens type C beta-toxin. Research aimed at validating this approach in the clinical setting is outlined.
Clostridium Infections/epidemiology/*microbiology/*prevention & control ; Clostridium perfringens/pathogenicity ; Enteritis/epidemiology/*microbiology/*prevention & control ; Health Services Needs and Demand ; Humans ; Incidence ; Papua New Guinea/epidemiology ; Population Surveillance

Child, Preschool ; Emollients ; therapeutic use ; Exanthema ; diagnosis ; drug therapy ; immunology ; virology ; Female ; Histamine Antagonists ; therapeutic use ; Humans