Artificial intelligence (AI) is growing exponentially in various fields, including medicine. This paper reviews the pertinent aspects of AI in obstetrics and gynecology (OB/GYN) and how these can be applied to improve patient outcomes and reduce the healthcare costs and workload for clinicians. Herein, we will address current AI uses in OB/GYN, and the use of AI as a tool to interpret fetal heart rate (FHR) and cardiotocography (CTG) to aid in the detection of preterm labor, pregnancy complications, and review discrepancies in its interpretation between clinicians to reduce maternal and infant morbidity and mortality. AI systems can be used as tools to create algorithms identifying asymptomatic women with short cervical length who are at risk of preterm birth. Additionally, the benefits of using the vast data capacity of AI storage can assist in determining the risk factors for preterm labor using multiomics and extensive genomic data. In the field of gynecological surgery, the use of augmented reality helps surgeons detect vital structures, thus decreasing complications, reducing operative time, and helping surgeons in training to practice in a realistic setting. Using three-dimensional (3D) printers can provide materials that mimic real tissues and also helps trainees to practice on a realistic model. Furthermore, 3D imaging allows better depth perception than its two-dimensional (2D) counterpart, allowing the surgeon to create preoperative plans according to tissue depth and dimensions. Although AI has some limitations, this new technology can improve the prognosis and management of patients, reduce healthcare costs, and help OB/GYN practitioners to reduce their workload and increase their efficiency and accuracy by incorporating AI systems into their daily practice. AI has the potential to guide practitioners in decision-making, reaching a diagnosis, and improving case management. It can reduce healthcare costs by decreasing medical errors and providing more dependable predictions. AI systems can accurately provide information on the large array of patients in clinical settings, although more robust data is required.
Copyright © 2020, Iftikhar et al.

Author