Gestational Diabetes Mellitus (GDM):
Current screening for gestational diabetes mellitus is costly and a
burden for pregnant women. AI can assist in finding ways to replace the
current standard. Current screening guidelines according to the US
Preventive Services Task Force consist of a 50g of oral glucose
challenge test performed after 24-week gestation, followed by a second
diagnostic test. They found insufficient evidence to screen before
24-week gestation [11,12]. Screening for GDM is important to prevent
complications, such as hypoglycemia in the neonate, large for
gestational age, increased number of cesarean births, amongst others.
GDM also results in more expensive outcomes due to increased cesarean
deliveries, which could be decreased if a more convenient screening test
was available. Polak and Mendyk created a study to evaluate the use of
an AI calculator to screen for GDM that would be more cost-efficient and
less inconvenient for the patient than current guidelines [11]. They
proposed the use of an online calculator that a physician and patient
can use for screening. The calculator is based on an artificial neuronal
network (ANN) which was adapted to a Java applet and published online
[12]. The model they used to create the AI system is called
multi-layer perceptrons, which can send information back and forth,
hence its denomination as an algorithm-back propagation (BP). Risk
factors such as high blood pressure, hyperlipidemia, smoking, weight,
low-fat diet, and ethnicity are used to create the calculator. The
authors concluded that despite AI having lower-efficacy than the
standard screening test, the current ANN model on the website will
continue to progress and learn as it continues to be exposed to more
cases; with the finality of eventually helping to lower health costs
[13]. An additional benefit is that it is user-friendly, which makes
it practical for daily use.