Validation of the first-trimester machine learning model for predicting pre-eclampsia in an Asian population.

OBJECTIVES: To evaluate the performance of an artificial intelligence (AI) and machine learning (ML) model for first-trimester screening for pre-eclampsia in a large Asian population. METHODS: This was a secondary analysis of a multicenter prospective cohort study in 10 935 participants with singleton pregnancies attending for routine pregnancy care at 11-13+6 weeks of gestation in seven regions in Asia between December 2016 and June 2018. We applied the AI+ML model for the first-trimester prediction of preterm pre-eclampsia (<37 weeks), term pre-eclampsia (≥37 weeks), and any pre-eclampsia, which was derived and tested in a cohort of pregnant participants in the UK (Model 1). This model comprises maternal factors with measurements of mean arterial pressure, uterine artery pulsatility index, and serum placental growth factor (PlGF). The model was further retrained with adjustments for analyzers used for biochemical testing (Model 2). Discrimination was assessed by area under the receiver operating characteristic curve (AUC). The Delong test was used to compare the AUC of Model 1, Model 2, and the Fetal Medicine Foundation (FMF) competing risk model. RESULTS: The predictive performance of Model 1 was significantly lower than that of the FMF competing risk model in the prediction of preterm pre-eclampsia (0.82, 95% confidence interval [CI] 0.77-0.87 vs. 0.86, 95% CI 0.811-0.91, P = 0.019), term pre-eclampsia (0.75, 95% CI 0.71-0.80 vs. 0.79, 95% CI 0.75-0.83, P = 0.006), and any pre-eclampsia (0.78, 95% CI 0.74-0.81 vs. 0.82, 95% CI 0.79-0.84, P < 0.001). Following the retraining of the data with adjustments for the PlGF analyzers, the performance of Model 2 for predicting preterm pre-eclampsia, term pre-eclampsia, and any pre-eclampsia was improved with the AUC values increased to 0.84 (95% CI 0.80-0.89), 0.77 (95% CI 0.73-0.81), and 0.80 (95% CI 0.76-0.83), respectively. There were no differences in AUCs between Model 2 and the FMF competing risk model in the prediction of preterm pre-eclampsia (P = 0.135) and term pre-eclampsia (P = 0.084). However, Model 2 was inferior to the FMF competing risk model in predicting any pre-eclampsia (P = 0.024). CONCLUSION: This study has demonstrated that following adjustment for the biochemical marker analyzers, the predictive performance of the AI+ML prediction model for pre-eclampsia in the first trimester was comparable to that of the FMF competing risk model in an Asian population.

The employment of art therapy to develop empathy and foster wellbeing for junior doctors in a palliative medicine rotation - a qualitative exploratory study on acceptability.

BACKGROUND: The interdisciplinary realm of medical humanities explores narratives and experiences that can enhance medical education for physicians through perspective-taking and reflective practice. However, there is a gap in comprehension regarding its appropriateness at the postgraduate level, especially when utilising art therapists as faculty. This study aims to assess the acceptability of an innovative art therapy-focused educational initiative among junior doctors during a palliative care rotation, with the goal of cultivating empathy and promoting well-being. METHODS: A qualitative research project was conducted at the Division of Supportive and Palliative Care (DSPC) in the National Cancer Centre Singapore (NCCS). The study involved the recruitment of junior doctors who had successfully completed a three-month palliative care rotation program, spanning from January 2020 to April 2021. In a single small-group session lasting 1.5 h, with 3 to 4 participants each time, the individuals participated in activities such as collage making, group reflection, and sharing of artistic creations. These sessions were facilitated by an accredited art therapist and a clinical psychologist, focusing on themes related to empathy and wellbeing. To assess the acceptability of the program, two individual interviews were conducted three months apart with each participant. An independent research assistant utilised a semi-structured question guide that considered affective attitude, burden, perceived effectiveness, coherence, and self-efficacy. Thematic analysis of the transcribed data was then employed to scrutinise the participants' experiences. RESULTS: A total of 20 individual interviews were completed with 11 participants. The three themes identified were lack of pre-existing knowledge of the humanities, promotors, and barriers to program acceptability. CONCLUSIONS: The participants have mixed perceptions of the program's acceptability. While all completed the program in its entirety, the acceptability of the program is impeded by wider systemic factors such as service and manpower needs. It is vital to address these structural limitations as failing to do so risks skewing current ambivalence towards outright rejection of future endeavours to integrate humanities programs into medical education.

Preferences for a non-invasive prenatal test as first-line screening for Down Syndrome: A discrete choice experiment.

OBJECTIVE: To investigate preferences of pregnant women for the characteristics of prenatal testing, and to quantify their willingness-to-pay (WTP) for non-invasive prenatal testing (NIPT) as first-line screening for Down Syndrome. METHOD: A cross-sectional discrete choice experiment survey including five testing attributes was administered to 192 pregnant women (≤14 weeks' gestation) who were aged ≥21 years in Singapore. We calculated marginal WTP for improvements in testing characteristics and NIPT. RESULTS: We identified two groups of women with distinct preferences for prenatal testing. Women aged ≥35 years, with at least a university education, and with intention to terminate pregnancy of an affected fetus were more likely to be in the group with higher WTP for improvements in test characteristics. While participants valued increased detection rate and lower screen positive rate associated with NIPT, they also valued no risk of test failure and ability to test for birth defects using standard testing. The participants, on average, were not willing to pay for NIPT over the standard testing as a first-line screening test. CONCLUSIONS: As a first-line screening, NIPT was not preferred over standard testing. The prenatal consultations should focus on each testing characteristic equally as our findings show diverse preferences for testing characteristics.

Prospective Evaluation of International Prediction of Pregnancy Complications Collaborative Network Models for Prediction of Preeclampsia: Role of Serum sFlt-1 at 11-13 Weeks' Gestation.

The study aimed to investigate whether serum sFlt-1 (soluble fms-like tyrosine kinase-1) at 11-13 weeks' gestation in pregnancies that subsequently developed preeclampsia was different from those without preeclampsia and compare screening performance of the International Prediction of Pregnancy Complications (IPPIC) reported models, which include various combinations of maternal factors, systolic blood pressure, diastolic blood pressure, PlGF (placental growth factor) and sFlt-1 and the competing risk (CR) models, which include various combinations of maternal factors, mean arterial pressure (MAP) and PlGF for predicting any-onset, early-onset, and late-onset preeclampsia. This was a prospective multicenter study in 7877 singleton pregnancies. The differences of the predictive performance between the IPPIC and CR models were compared. There were 141 women (1.79%) who developed preeclampsia, including 13 cases (0.17%) of early-onset preeclampsia and 128 cases (1.62%) of late-onset preeclampsia. In pregnancies that developed preeclampsia compared to unaffected pregnancies, median serum sFlt-1 levels and its MoMs were not significantly different (p>0.05). There was no significant association between gestational age at delivery and log10 sFlt-1 and log10 sFlt-1 MoM (p>0.05). The areas under the curve of CR models were significantly higher than the IPPIC models for the prediction of any-onset and late-onset preeclampsia but not for early-onset preeclampsia. In conclusion, there are no significant differences in the maternal serum sFlt-1 levels at 11-13 weeks' gestation between women who subsequently develop preeclampsia and those who do not. Moreover, the CR models for the prediction of any-onset and late-onset preeclampsia perform better than the IPPIC reported model.

Unexpected case of postnatal pancreatitis: first presentation of autoimmune diabetes.

Gestational diabetes mellitus (GDM) is defined as the first onset of glucose intolerance in pregnancy without prior known diabetes. While it is commonly associated with metabolic risk factors such as obesity and hypertension, a small percentage of women with GDM have underlying autoimmune causes, with presence of islet-cell antibodies resulting in autoimmune-mediated destruction of the pancreas. We present a case of idiopathic postpartum pancreatitis precipitating fulminant diabetic ketoacidosis in a patient with otherwise well-controlled GDM during pregnancy, and subsequent findings of positive anti-glutamic acid decarboxylase antibody. This is the first presentation of autoimmune diabetes diagnosed postnatally in a woman who has no previous medical or family history.

DORSCON Orange: An Approach to Challenges in a Busy Antenatal Diagnostic Centre in the Midst of a Global Pandemic.

The WHO declared the coronavirus disease 2019 (COVID-19) a global pandemic on 11 March 2020. Lessons from SARS epidemic led Singapore to develop stringent infection control protocols in preparation for future pandemics. However, unlike SARS, COVID-19 appears to be more transmissible and is predicted to continue for longer. As of 14 June 2020, there have been 40,197 positive cases with 26 deaths in Singapore, and KK Women's and Children's Hospital (KKH) has managed a total of 73 cases. Obstetrics ultrasound is an indispensable medical service and must continue to operate during a pandemic. A key balance must be struck between keeping patients and healthcare workers safe while being able to provide quality and prompt obstetric care. Our Antenatal Diagnostic Centre (ADC) in KKH developed new strategies to adapt to the pandemic when the national Disease Outbreak Response System Condition (DORSCON) was raised from yellow to orange on 7 February 2020. In this paper, we discuss our clinical workflow to reduce the risk of transmission amongst patients and staff while minimising disruption to our services.

A meta-analysis of the effectiveness of yoga-based interventions for maternal depression during pregnancy.

Prompt and effective treatment of maternal depression during pregnancy is important as it is an independent predictor of negative maternal and fetal outcomes. Yoga is an increasingly popular non-pharmacological modality. This study thus aimed to undertake a meta-analysis of the efficacy of yoga-based interventions for maternal depression during pregnancy. A total of 8 clinical studies were systematically reviewed, and 6 studies with a total of 405 pregnant mothers were included in the final meta-analysis. Applying per-protocol analysis and a random-effects model, the pooled standardized mean difference (SMD) from baseline depressive score was -0.452 (95% CI: -0.816 to -0.880, P = 0.015), supporting a statistically significant beneficial effect of yoga-based interventions on mood. Overall, yoga-based interventions are a promising non-pharmacological option, however, most trials examined were preliminary, recruited only participants with mild depression, did not blind study participants and had relatively small sample sizes. Larger randomized, controlled trials should be encouraged.

Selective Serotonin Reuptake Inhibitors and Persistent Pulmonary Hypertension of the Newborn: An Update Meta-Analysis.

BACKGROUND: Persistent pulmonary hypertension of the newborn (PPHN) is a serious condition associated with substantial mortality and morbidity. Previous studies have suggested a possible link between maternal selective serotonin reuptake inhibitor (SSRI) use and the risk of PPHN. This study aimed to provide an up-to-date review and meta-analysis of the topic. METHODS: Using the search terms [SSRI OR SSRIs OR selective serotonin reuptake inhibitors OR antidepressant OR Prozac OR fluoxetine OR Lexapro OR escitalopram] AND [pregnancy OR maternal OR newborn OR persistent pulmonary hypertension OR PPHN OR neonat* OR fet*], a preliminary search on the PubMed, Medline, EMBASE, Web of Science, and Google Scholar database yielded 7327 articles published in English between January 1, 1960 and October 1, 2017. RESULTS: A total of 9 cohort and case-control studies, with a total of 7,540,265 subjects were systematically reviewed. Random-effects meta-analysis of eight studies revealed a significantly increased risk of PPHN with maternal SSRI use during pregnancy, with a pooled OR of 1.516 (95% confidence interval: 1.035-1.997, p < 0.001). Overall, the absolute increase in risk of PPHN with SSRI use appears small, with an absolute risk difference of 0.619 per 1000 livebirths and a number needed to harm of 1615 women. CONCLUSIONS: Current evidence suggests that there were significantly greater odds of PPHN with SSRI use during pregnancy. However, the clinical significance of this association remains modest and likely outweighed by the potential benefits of treatment of perinatal depression. The risk of PPHN associated with SSRI therapy might not warrant the recommendation to withdraw antidepressant therapy, as evidence from other studies show that untreated perinatal depression presents additional adverse maternal and fetal outcomes. Given the increasing prevalence of maternal depression and consequent use of antidepressant medications, further research with robust longitudinal or randomized, controlled studies and mechanistic investigations are needed.