Abstract— Innovations in digital health and machine learning are changing the path of clinical health and care. People from many different geographies and cultures can benefit from the mobility of wearable devices and smartphones to monitor their health in a ubiquitous manner. This paper focuses on reviewing the digital health and machine learning technologies used in gestational diabetes ̵̶  a subtype of diabetes that occurs during pregnancy. Despite a large number of patients with gestational diabetes, only a handful of digital health applications have been deployed in clinical practice. This paper reviews sensor technologies in blood glucose monitoring devices and machine learning fused digital health innovations for gestational diabetes monitoring and management in both clinical and commercial settings. It is one of the first comprehensive reviews in this area to the best of our knowledge. In conclusion, there is a need to (1) develop digital health technologies and clinically interpretable machine learning methods for patients with gestational diabetes, assisting health professionals with treatment monitoring and planning; (2) adapt and develop clinically proven devices for patient self-management of health and well-being at the hospital and home settings thereby facilitating timely intervention; and (3) ensure innovations are affordable and sustainable for women everywhere. Data statement: this is a review manuscript that have not generated any new data. The views expressed are those of the authors and not necessarily those of InnoHK. This research was supported by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR or the Department of Health.

Objective To validate a serum biomarker developed in the USA for preterm birth (PTB) risk stratification in Viet Nam. Design Case-cohort study Setting Tu Du Hospital, Ho Chi Minh City, Viet Nam Population Women with a viable singleton pregnancy (n=5000). Methods Maternal serum was collected between 19 +0-22 +6 weeks’ gestation and participants followed to neonatal discharge. Relative insulin-like growth factor binding protein 4 (IGFBP4) and sex hormone binding globulin (SHBG) abundances were measured by mass spectrometry and their ratio compared between PTB cases and term controls. Discrimination (area under the receiver operating characteristic curve, AUC) and calibration for PTB <37 and <34 weeks were tested, with model tuning using clinical factors. Main outcomes measures All PTBs (any birth ≤37 weeks’ gestation) and spontaneous PTBs (birth ≤37 weeks’ gestation with clinical signs of initiation of parturition). Results Complete data were available for 4984 (99.7%), cohort PTB rate=6.7%; n=335. We observed an inverse association between IGFBP4/SHBG ratio and gestational age at birth (p=0.017); AUC 0.60 (95% CI, 0.53-0.68). Including previous PTB (multiparous women) or prior miscarriage (primiparous women) improved performance (AUC 0.65 and 0.70, respectively, for PTB <37 and <34 weeks’ gestation). Optimal performance (AUC 0.74) was between 19-20 weeks’ gestation, for BMI >21kg/m 2 and age 20-35 years. Conclusions We have validated a novel serum biomarker for PTB risk stratification in a very different setting to the original study. Further research is required to determine appropriate ratio thresholds based on the prevalence of risk factors and the availability of resources and preventative therapies.

Exposure to extreme heat in pregnancy increases the risk of stillbirth. Progress in reducing stillbirth rates has stalled, and populations are increasingly exposed to high temperatures and climate events that may further undermine health strategies. This narrative review summaries the current clinical and epidemiological evidence of the impact of maternal heat exposure on stillbirth risk. 19 out of 20 studies found an association between heat and stillbirth risk. Recent studies based in low- middle- income countries and tropical settings add to the existing literature to demonstrate that all populations are at risk. Additionally, both short-term heat exposure and whole-pregnancy heat exposure increase the risk of stillbirth. A definitive threshold of effect has not been identified, as most studies define exposure as > 90 th percentile of the usual temperature for that population. Therefore, the association between heat and stillbirth has been found with exposures from as low as >12.64°C up to >46.4°C. The pathophysiological pathways by which maternal heat exposure may lead to stillbirth, based on human and animal studies, include both placental and embryonic or fetal impacts. Although evidence gaps remain and further research is needed to characterise these mechanistic pathways in more detail, preliminary evidence suggests epigenetic changes, alteration in imprinted genes, congenital abnormalities, reduction in placental blood flow, size and function all play a part. Finally, we explore this topic from a public health perspective; we discuss and evaluate the current public health guidance on minimising the risk of extreme heat in the community. There is limited pregnancy specific guidance within heatwave planning, and no evidence-based interventions have been established to prevent poor pregnancy outcomes. We highlight priority research questions to move forward in the field and specifically note the urgent need for evidence-based interventions that are sustainable.