Pregnancy

Foundation versus Domain-Specific Models for Left Ventricular Segmentation on Cardiac Ultrasound

The Segment Anything Model (SAM) was fine-tuned on the EchoNet-Dynamic dataset and evaluated on external transthoracic echocardiography (TTE) and Point-of-Care Ultrasound (POCUS) datasets from CAMUS (University Hospital of St Etienne) and Mayo Clinic (99 patients: 58 TTE, 41 POCUS). Fine-tuned SAM was superior or comparable to MedSAM. The fine-tuned SAM also outperformed EchoNet and U-Net models, ...

Machine learning for the prediction of spontaneous preterm birth using early second and third trimester maternal blood gene expression: A Cautionary Tale

Spontaneous preterm birth (sPTB) remains a significant global health challenge and a leading cause of neonatal mortality and morbidity. Despite advancements in neonatal care, the prediction of sPTB remains elusive, in part due to complex etiologies and heterogeneous patient populations. This study aimed to validate and extend information on gene expression biomarkers previously described for predi...

Leveraging neighborhood-level Information to Improve Model Fairness in Predicting Prenatal Depression

Perinatal depression (PND) affects 10-20% of pregnant women, with significant racial disparities in prevalence, screening, and treatment. Neighborhood...

Step-by-Step Approach to Design Image Classifiers in AI: An Exemplary Application of the CNN Architecture for Breast Cancer Diagnosis

In recent years, different Convolutional Neural Networks (CNNs) approaches have been applied for image classification in general and specific problems...

COVID-19 modulates pregnancy outcomes

The COVID-19 pandemic exposed many pregnant individuals to SARS-CoV-2. Literature suggests a link between gestational COVID-19 and adverse gestational...

Synthetic Ultrasound Image Generation for Breast Cancer Diagnosis Using cVAE-WGAN Models: An Approach Based on Generative Artificial Intelligence

The scarcity and imbalance of medical image datasets hinder the development of robust computer-aided diagnosis (CAD) systems for breast cancer. This s...

Barriers and Facilitators to the Implementation of Artificial Intelligence Enabled Diabetes Interventions in Lower-Middle-Income Countries: A Systematic Review Protocol

Diabetes represents an emerging global health crisis, with lower-middle-income countries experiencing a fast growth in prevalence. Diabetes care in th...

Advancing the Safe Motherhood Initiative: a qualitative and sentiment analysis of local physician’s perspectives on antibiotic self-medication during pregnancy in a low- and middle-income country

Although the Safe Motherhood Initiative is currently a global priority, the implications of maternal self-medication for meeting Safe Motherhood and S...

Towards automated multi-regional lung parcellation for 0.55-3T 3D T2w fetal MRI

Fetal MRI is increasingly being employed in the diagnosis of fetal lung anomalies and segmentation-derived total fetal lung volumes are used as one of...

CLIF-Net: Intersection-guided Cross-view Fusion Network for Infection Detection from Cranial Ultrasound

This paper addresses the problem of detecting possible serious bacterial infection (pSBI) of infancy, i.e. a clinical presentation consistent with bac...

Predicting Utilization of Emergency Contraceptive Usage in Ethiopia and Identifying Its Predictors Using Machine Learning

Despite policy support, inappropriate use of emergency contraception (EC) in Ethiopia contributes to high rates of unintended pregnancy and maternal m...

Development of an AI-enabled predictive model to identify the ‘sick child’ at a pediatric telemedicine and medication delivery service in Haiti

One of the most difficult challenges in pediatric telemedicine is to accurately discriminate between the ‘sick’ and ‘not sick’ child, especially in re...

Privacy Protection for Chinese Electronic Medical Records Using Large Language Models: Effectiveness Evaluation and Application of LLM Models in Medical Data Tasks

The privacy protection of medical patients has remained a critical concern in healthcare information management during the digital era. Conventional a...

Integrating Machine Learning for Propensity Score Matching and Causal Inference: A Causal Forest Approach to Assessing the Impact of Maternal Education on Antenatal Care Utilization

While maternal education is linked to antenatal care (ANC) use, its causal effect remains uncertain. This study applies a machine learning approach, C...

Differential Predictability of Preterm Birth Types: Strong Signals for Indicated Cases versus Limited Success in Spontaneous Preterm Birth

Preterm birth, defined as birth occurring before 37 weeks of gestation, poses a significant and enduring public health challenge, with substantial emo...

Artificial intelligence in prenatal ultrasound: A systematic review of diagnostic tools for detecting congenital anomalies

Artificial intelligence (AI) has potentially shown promise in interpreting ultrasound imaging through flexible pattern recognition and algorithmic lea...

Large Language Models Improve Coding Accuracy and Reimbursement in a Neonatal Intensive Care Unit

Diagnosis coding is essential for clinical care, research validity, and hospital reimbursement. In neonatal settings, manual coding is frequently erro...

External Validation of a Machine Learning Model to Predict Postpartum Hemorrhage in a US Northeastern Healthcare System

Postpartum hemorrhage (PPH) is a major cause of maternal morbidity and mortality. Timely prediction may prevent adverse maternal outcomes, and efforts...

The African Breast Imaging Dataset for Equitable Cancer Care: Protocol for an Open Mammogram and Ultrasound Breast Cancer Detection Dataset

Breast cancer is one of the most common cancers globally. Its incidence in Africa has increased sharply, surpassing that in high-income countries. Mor...

Association between zidovudine and adverse pregnancy outcomes/congenital malformations: A pharmacovigilance study using FAERS data

Zidovudine (AZT), a key antiretroviral drug used for HIV treatment and preventing mother-to-child transmission, has insufficient post-marketing pharma...