Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers.

BACKGROUND: Accurate estimates of gestational age (GA) at birth are important for preterm birth surveillance but can be challenging to obtain in low income countries. Our objective was to develop machine learning models to accurately estimate GA shortly after birth using clinical and metabolomic data. METHODS: We derived three GA estimation models using ELASTIC NET multivariable linear regression using metabolomic markers from heel-prick blood samples and clinical data from a retrospective cohort of newborns from Ontario, Canada. We conducted internal model validation in an independent cohort of Ontario newborns, and external validation in heel prick and cord blood sample data collected from newborns from prospective birth cohorts in Lusaka, Zambia and Matlab, Bangladesh. Model performance was measured by comparing model-derived estimates of GA to reference estimates from early pregnancy ultrasound. RESULTS: Samples were collected from 311 newborns from Zambia and 1176 from Bangladesh. The best-performing model accurately estimated GA within about 6 days of ultrasound estimates in both cohorts when applied to heel prick data (MAE 0.79 weeks (95% CI 0.69, 0.90) for Zambia; 0.81 weeks (0.75, 0.86) for Bangladesh), and within about 7 days when applied to cord blood data (1.02 weeks (0.90, 1.15) for Zambia; 0.95 weeks (0.90, 0.99) for Bangladesh). CONCLUSIONS: Algorithms developed in Canada provided accurate estimates of GA when applied to external cohorts from Zambia and Bangladesh. Model performance was superior in heel prick data as compared to cord blood data.

Validation of gestational age determination from ultrasound or a metabolic gestational age algorithm using exact date of conception in a cohort of newborns conceived using assisted reproduction technologies.

BACKGROUND: Accurate estimates of gestational age in pregnancy are important for the provision of optimal care. Although current guidelines generally recommend estimating gestational age via first-trimester ultrasound measurement of crown-rump length, error associated with this method can range from 3 to 8 days of gestation. In pregnancies resulting from assisted reproductive technology, estimated due date can be calculated on the basis of the age of the embryo and the date of embryo transfer, arguably providing the most accurate estimates possible. We have developed and extensively validated statistical models to estimate gestational age postnatally using metabolomic markers from blood samples in combination with clinical and demographic data. These models have shown high accuracy compared with first-trimester ultrasound, the recommended method for estimating gestational age in spontaneous pregnancies. We hypothesized that gestational age derived from date and stage of embryo at transfer in newborns conceived using assisted reproduction therapy would provide the most accurate reference standard possible to evaluate and compare the accuracy of both first-trimester ultrasound and metabolomic model-based gestational dating. OBJECTIVE: This study aimed to validate both first-trimester ultrasound dating and postnatal metabolomic gestational age estimation models against gestational age derived from date and stage of embryo at transfer in a cohort of newborns conceived via assisted reproductive technology, both overall and in important subgroups of interest (preterm birth, small for gestational age, and multiple birth). STUDY DESIGN: This was a retrospective cohort study of infants born in Ontario, Canada between 2015 and 2017 and captured in the provincial birth registry. Spontaneous conceptions were randomly partitioned into a model derivation sample (80%) and a test sample (20%) for model validation. A cohort of assisted conceptions resulting from fresh embryo transfers was derived to evaluate the accuracy of both ultrasound and model-based gestational dating. Postnatal gestational age estimation models were developed with multivariable linear regression using elastic-net regularization. Gestational age estimates from dating ultrasound and from postnatal metabolomic models were compared with date of embryo transfer reference gestational age in the independent test cohorts. Accuracy was quantified by calculating mean absolute error and the square root of mean squared error. RESULTS: Our model derivation cohort included 202,300 spontaneous conceptions, and the testing cohorts included 50,735 spontaneous conceptions and 1924 assisted conceptions. In the assisted conception cohort, first-trimester dating ultrasound was accurate to within approximately ±1.5 days compared with date of embryo transfer reference overall (mean absolute error, 0.21 [95% confidence interval, 0.20-0.23]). When compared with gestational age derived from date of embryo transfer, the metabolomic estimation models were accurate to within approximately ±5 days overall (0.79 [0.76-0.81] weeks). When ultrasound was used as the reference in validating the metabolomic model, the mean absolute error was slightly higher overall (0.81 [0.78-0.84] weeks). In general, the accuracy of gestational age estimates derived from ultrasound or metabolomic models was highest in term infants and lower in preterm and small-for-gestational-age newborns. CONCLUSION: Our findings support the accuracy of ultrasound as a gestational age dating tool. They also support the potential utility of metabolic gestational age dating algorithms in settings where ultrasound or other accurate methods of estimating gestational age are not available because of lack of infrastructure or specialized training (eg, low-income countries). However, the accuracy of metabolomic model-based dating was generally lower than that of ultrasound.

Universal interventions for suicide prevention in high-income Organisation for Economic Co-operation and Development (OECD) member countries: a systematic review.

INTRODUCTION: To examine the effectiveness of universal suicide prevention interventions on reducing suicide mortality in high-income Organisation for Economic Co-operation and Development (OECD) member countries. METHODS: We implemented a comprehensive search strategy across three electronic databases: MEDLINE (Ovid), PsycINFO (Ovid) and Embase (Ovid). All studies using time-series, retrospective, prospective, pre-post or cross-sectional study designs were included. Studies were required to examine suicide mortality as the outcome of interest. To help organise the results, studies were grouped into six broad categories of universal interventions consistent with the World Health Organization (WHO) Comprehensive Mental Health Action Plan. A narrative synthesis of results was used to describe the findings. RESULTS: Of the 15 641 studies identified through the search strategy, 100 studies were eligible in the following categories: law and regulation reforms (n=66), physical barriers (n=13), community-based interventions (n=9), communication strategies (n=4), mental health policies and strategies (n=7), and access to healthcare (n=1). Overall, 100% (13/13) of the included physical barrier interventions resulted in a significant reduction in suicide mortality. Although only 70% (46/66) of the law and regulation reform interventions had a significant impact on reducing suicide, they hold promise due to their extended reach. Universal suicide prevention interventions seem to be more effective at reducing suicide among males than females, identifying a need to stratify results by sex in future studies. CONCLUSIONS: These findings suggest that universal suicide prevention interventions hold promise in effectively reducing suicide mortality in high-income OECD countries.

Participatory model building for suicide prevention in Canada.

BACKGROUND: Suicide is a behaviour that results from a complex interplay of factors, including biological, psychological, social, cultural, and environmental factors, among others. A participatory model building workshop was conducted with fifteen employees working in suicide prevention at a federal public health organization to develop a conceptual model illustrating the interconnections between such factors. Through this process, knowledge emerged from participants and consensus building occurred, leading to the development of a conceptual model that is useful to organize and communicate the complex interrelationships between factors related to suicide. METHODS: A model building script was developed for the facilitators to lead the participants through a series of group and individual activities that were designed to elicit participants' implicit models of risk and protective factors for suicide in Canada. Participants were divided into three groups and tasked with drawing the relationships between factors associated with suicide over a simplified suicide process model. Participants were also tasked with listing prevention levers that are in use in Canada and/or described in the scientific literature. RESULTS: Through the workshop, risk and prevention factors and prevention levers were listed and a conceptual model was drafted. Several "lessons learned" which could improve future workshops were generated through reflection on the process. CONCLUSIONS: This workshop yielded a helpful conceptual model contextualising upstream factors that can be used to better understand suicide prevention efforts in Canada.

Differences in hospital length of stay between neonates exposed to buprenorphine versus methadone in utero: A retrospective chart review.

INTRODUCTION: Neonatal abstinence syndrome is a growing concern in neonatal intensive care units in rural and remote settings. METHODS: A retrospective chart review was conducted of 180 mother-infant dyads born with in utero exposure to buprenorphine (n=60), methadone (n=60) or to other opioids (n=60) to determine neonatal length of stay in hospital, number of days on morphine, day of life of initiation of morphine and the need for phenobarbital. RESULTS: The length of stay in hospital for neonates was 5.8 days shorter (95% confidence interval [CI] 6.1 to 8.5 days) for buprenorphine exposure in utero compared to methadone (P=0.001). For neonates requiring treatment for Neonatal abstinence syndrome, those with in utero exposure to buprenorphine required 6.1 fewer days (95% CI 2.5 to 9.7) of treatment with morphine then those exposed to methadone (P<0.0005). There were no statistically significant differences in day of life of initiation of morphine therapy for each of the study groups. The proportion of neonates requiring adjuvant therapy with phenobarbital was statistically significantly higher in neonates exposed to methadone in utero than either buprenorphine or illicit opioids (P<0.0005). CONCLUSIONS: Retrospective data suggest that neonates with in utero exposure to buprenorphine experience a shorter length of stay in hospital, fewer days of treatment with morphine for neonatal abstinence syndrome, and less use of phenobarbital than neonates exposed in utero to methadone. This suggests that Ontario provincial guidelines should be updated to recommend buprenorphine as first line for replacement therapy in pregnancy.

Opioid use in pregnancy and parenting: An Indigenous-based, collaborative framework for Northwestern Ontario.

Opioid use affects up to 30% of pregnancies in Northwestern Ontario. Health care providers in Northwestern Ontario have varying comfort levels providing care to substance-involved pregnant women. Furthermore, health care practitioners, social service agencies and community groups in Northwestern Ontario often work in isolation with little multidisciplinary communication and collaboration. This article describes two workshops that brought together health and social service providers, community organizations, as well as academic institutions and professional organizations involved in the care of substance-involved pregnant and parenting women. The initial workshop presented best practices and local experience in the management of opioid dependence in pregnancy while the second workshop asked participants to apply a local Indigenous worldview to the implementation of clinical, research and program priorities that were identified in the first workshop. Consensus statements developed by workshop participants identified improved transitions in care, facilitated access to buprenorphine treatment, stable funding models for addiction programs and a focus on Indigenous-led programming. Participants identified a critical need for a national strategy to address the effects of opioid use in pregnancy from a culturally safe, trauma-informed perspective that takes into account the health and well-being of the woman, her infant, her family and her community.