Predicting prenatal depression and assessing model bias using machine learning models DOI Creative Commons
Yongchao Huang, Suzanne Alvernaz,

Sage J. Kim

et al.

Biological Psychiatry Global Open Science, Journal Year: 2024, Volume and Issue: 4(6), P. 100376 - 100376

Published: Aug. 14, 2024

Perinatal depression is one of the most common medical complications during pregnancy and postpartum period, affecting 10% to 20% pregnant individuals, with higher rates among Black Latina women who are also less likely be diagnosed treated. Machine learning (ML) models based on electronic records (EMRs) have effectively predicted in middle-class White but rarely included sufficient proportions racial/ethnic minorities, which has contributed biases ML models. Our goal determine whether could predict early minority by leveraging EMR data.

Language: Английский

Artificial intelligence in perinatal mental health research: A scoping review DOI Creative Commons

Wai Hang Kwok,

Yuanpeng Zhang, Guanjin Wang

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 177, P. 108685 - 108685

Published: June 3, 2024

The intersection of Artificial Intelligence (AI) and perinatal mental health research presents promising avenues, yet uncovers significant challenges for innovation. This review explicitly focuses on this multidisciplinary field undertakes a comprehensive exploration existing therein. Through scoping guided by the Preferred Reporting Items Systematic Reviews Meta-Analyses (PRISMA) framework, we searched relevant literature spanning decade (2013-2023) selected fourteen studies our analysis. We first provide an overview main AI techniques their development, including traditional methods across different categories, as well recent emerging in field. Then, through analysis literature, summarize predominant ML adopted applications studies, such identifying risk factors, predicting disorders, voice assistants, Q&A chatbots. also discuss limitations potential that hinder technologies from improving outcomes, suggest several directions future to meet real needs facilitate translation into clinical settings.

Language: Английский

Citations

6
Sensing and Artificial Intelligent Maternal-Infant Health Care Systems: A Review DOI Creative Commons
Saima Gulzar Ahmad, Tassawar Iqbal, Anam Javaid

et al.

Sensors, Journal Year: 2022, Volume and Issue: 22(12), P. 4362 - 4362

Published: June 9, 2022

Currently, information and communication technology (ICT) allows health institutions to reach disadvantaged groups in rural areas using sensing artificial intelligence (AI) technologies. Applications of these technologies are even more essential for maternal infant health, since is vital a healthy society. Over the last few years, researchers have delved into artificially intelligent healthcare systems health. Sensors exploited gauge parameters, machine learning techniques investigated predict conditions patients assist medical practitioners. Since deal with large amounts data, significant development also noted computing platforms. The relevant literature reports potential impact ICT-enabled improving This article reviews wearable sensors AI algorithms based on existing designed risk factors during after pregnancy both mothers infants. review covers used analyzes each approach its features, outcomes, novel aspects chronological order. It includes discussion datasets extends challenges as well future work directions researchers.

Language: Английский

Citations

26
On AI Approaches for Promoting Maternal and Neonatal Health in Low Resource Settings: A Review DOI Creative Commons

Misaal Khan,

Mahapara Khurshid, Mayank Vatsa

et al.

Frontiers in Public Health, Journal Year: 2022, Volume and Issue: 10

Published: Sept. 30, 2022

A significant challenge for hospitals and medical practitioners in low- middle-income nations is the lack of sufficient health care facilities timely diagnosis chronic deadly diseases. Particularly, maternal neonatal morbidity due to various non-communicable nutrition related diseases a serious public issue that leads several deaths every year. These affecting either mother or child can be hospital-acquired, contracted during pregnancy delivery, postpartum even growth development. Many these conditions are challenging detect at their early stages, which puts patient risk developing severe over time. Therefore, there need screening, detection diagnosis, could reduce mortality. With advent Artificial Intelligence (AI), digital technologies have emerged as practical assistive tools different healthcare sectors but still nascent stages when applied health. This review article presents an in-depth examination solutions proposed low resource settings discusses open problems well future research directions.

Language: Английский

Citations

24
An optimization for postpartum depression risk assessment and preventive intervention strategy based machine learning approaches DOI
Hao Liu, Anran Dai, Zhou Zhou

et al.

Journal of Affective Disorders, Journal Year: 2023, Volume and Issue: 328, P. 163 - 174

Published: Feb. 8, 2023

Language: Английский

Citations

15
Predicting prenatal depression and assessing model bias using machine learning models DOI Creative Commons
Yongchao Huang, Suzanne Alvernaz,

Sage J. Kim

et al.

Biological Psychiatry Global Open Science, Journal Year: 2024, Volume and Issue: 4(6), P. 100376 - 100376

Published: Aug. 14, 2024

Perinatal depression is one of the most common medical complications during pregnancy and postpartum period, affecting 10% to 20% pregnant individuals, with higher rates among Black Latina women who are also less likely be diagnosed treated. Machine learning (ML) models based on electronic records (EMRs) have effectively predicted in middle-class White but rarely included sufficient proportions racial/ethnic minorities, which has contributed biases ML models. Our goal determine whether could predict early minority by leveraging EMR data.

Language: Английский

Citations

5