1818-1859
September 1, 2021Pearse Keane
September 1, 2021News Obstetrics
Artificial Intelligence along with the judgment of obstetrician-gynecologists, prevent morbidity and mortality in pregnant women...
Cognitive Care develops an AI-based platform for maternal & child healthcare
AI-Enhanced women’s health ultrasound with industry-first auto recognition tools to help improve efficiency.
GE Healthcare launched Voluson SWIFT, a novel ultrasound system to help women’s health clinicians expand diagnostic modalities and improve patient outcomes. The Voluson SWIFT ultrasound system offers an embedded artificial intelligence platform that includes the new SonoLyst application, the company’s first AI-incorporated tool.
The new ultrasound has redefined one of the essential evaluation tools used by obstetrics and gynecology clinicians. Some benefits include delivering a contemporary design, intuitive user interface, and AI-supported workflow.(2)
GE Healthcare launched Voluson SWIFT, a novel ultrasound system to help women’s health clinicians expand diagnostic modalities and improve patient outcomes. The Voluson SWIFT ultrasound system offers an embedded artificial intelligence platform that includes the new SonoLyst application, the company’s first AI-incorporated tool.
The new ultrasound has redefined one of the essential evaluation tools used by obstetrics and gynecology clinicians. Some benefits include delivering a contemporary design, intuitive user interface, and AI-supported workflow.(2)
Machine learning can predict health risks of future pregnancies.
A machine learning tool can evaluate and predict future pregnancies’ health risks by recognizing specific characteristics in the placentas. This machine learning method can analyze placenta slides and inform women of their health risks in succeeding pregnancies, leading to diminished healthcare costs and better ends. Providers examine placentas to search for a type of blood vessel lesion named decidual vasculopathy (DV).(3)
Machine learning can predict health risks of future pregnancies.
A machine learning tool can evaluate and predict future pregnancies’ health risks by recognizing specific characteristics in the placentas. This machine learning method can analyze placenta slides and inform women of their health risks in succeeding pregnancies, leading to diminished healthcare costs and better ends. Providers examine placentas to search for a type of blood vessel lesion named decidual vasculopathy (DV).(3)
The future of AI in OB/GYN ultrasound.
Large data sets are crucial to generate a successful deep learning application. One of the most distinguished players in the AI field is the UK-based business Intelligent Ultrasound. The company acquired over 1 million high-quality pictures from actual obstetric scans to create algorithms for the software ScanNav.
The purpose of ScanNav is to provide real-time guidance to sonographers by automatically capturing the six images recommended by the UK fetal anomaly screening program. Additionally, it supplies evidence for audits of appropriate image gathering. This platform adds a layer of quality improvement to guarantee optimal patient care delivery.(4)
Large data sets are crucial to generate a successful deep learning application. One of the most distinguished players in the AI field is the UK-based business Intelligent Ultrasound. The company acquired over 1 million high-quality pictures from actual obstetric scans to create algorithms for the software ScanNav.
The purpose of ScanNav is to provide real-time guidance to sonographers by automatically capturing the six images recommended by the UK fetal anomaly screening program. Additionally, it supplies evidence for audits of appropriate image gathering. This platform adds a layer of quality improvement to guarantee optimal patient care delivery.(4)
Can AI improve embryo selection for in vitro fertilization (IVF)?
A group of investigators at Weill Cornell Medicine and New York-Presbyterian is trying to accurately determine the likelihood of an in vitro fertilized human embryo progressing to a successful pregnancy. This new AI used thousands of authentic images to develop algorithms, determine appropriate embryonic landmarks, and perform precise measurements.
Such information is thoroughly analyzed in layers of increasing complexity using deep learning algorithms. The outcome is expected to display a significantly more precise embryo selection.(5)
A group of investigators at Weill Cornell Medicine and New York-Presbyterian is trying to accurately determine the likelihood of an in vitro fertilized human embryo progressing to a successful pregnancy. This new AI used thousands of authentic images to develop algorithms, determine appropriate embryonic landmarks, and perform precise measurements.
Such information is thoroughly analyzed in layers of increasing complexity using deep learning algorithms. The outcome is expected to display a significantly more precise embryo selection.(5)
This software is helping find once-hidden features of congenital heart defects.
Dr. Greggory DeVore is a maternal-fetal medicine specialist and a clinical professor in the David Geffen School of Medicine at the University of California, Los Angeles. DeVore was inspired by software that evaluates heart activity in children and adults. The tool, entitled speckle tracking analysis, monitored the movement of the walls of the ventricles in the heart and made him question the chances of using something similar for the fetus.
Clinicians can now use this tool to simultaneously examine the fetal heart’s size, shape, and contractility. As a result, diagnoses that were difficult or impossible in the past are now feasible.(6)
Dr. Greggory DeVore is a maternal-fetal medicine specialist and a clinical professor in the David Geffen School of Medicine at the University of California, Los Angeles. DeVore was inspired by software that evaluates heart activity in children and adults. The tool, entitled speckle tracking analysis, monitored the movement of the walls of the ventricles in the heart and made him question the chances of using something similar for the fetus.
Clinicians can now use this tool to simultaneously examine the fetal heart’s size, shape, and contractility. As a result, diagnoses that were difficult or impossible in the past are now feasible.(6)
How AI could help doctors reduce maternal mortality
A group of investigators at Massachusetts General Hospital found that machine-learning algorithms using data from electronic health records could predict obstetrical complications. The device automatically inputs vital signs at triage into the patients’ electronic records. Technology embedded in the system then compares the vital signs with all the pregnant women’s records, identifies high-risk patients, and alerts the staff about the likely complication. Obstetric patients at risk of life-threatening complications, such as hemorrhaging, are more likely identified and surveyed to receive appropriate care in a timely fashion.(7)
A group of investigators at Massachusetts General Hospital found that machine-learning algorithms using data from electronic health records could predict obstetrical complications. The device automatically inputs vital signs at triage into the patients’ electronic records. Technology embedded in the system then compares the vital signs with all the pregnant women’s records, identifies high-risk patients, and alerts the staff about the likely complication.
Obstetric patients at risk of life-threatening complications, such as hemorrhaging, are more likely identified and surveyed to receive appropriate care in a timely fashion.(7)
AI, 30 second MRI scan predict pregnancy complications
Combining artificial intelligence with a 30 second MRI scan can predict placental health and identify associated complications. Researchers from King’s College London unveiled the tool; it automates manual segmentation of placenta images. The information released through “APPLAUSE: Automatic Prediction of Placental health via U-net Segmentation and statistical Evaluation,” revealed the machine learning pathways run close to real-time and, when deployed in clinical settings, have the potential to become a diagnostic cornerstone for placental insufficiency.(8)
