The use of artificial intelligence (AI) is being integrated into infant health care and disease prediction, including for those with fetal and neonatal alloimmune thrombocytopenia (FNAIT), according to findings from a comprehensive analysis published in ECTI Transactions on Computer and Information Technology.
“The neonatal period is a crucial time in human life for a newborn to adapt to the current environment and several physiological adjustments essential for lifestyle,” the study researchers wrote.
Read more about FNAIT causes and risk factors
The authors stated that the use of preventive strategies should remain focused on maternal health care prior to birth and early disease detection. Newborns face the greatest risk to their health in their first 28 days of life. Such risks are usually attributable to harmful pathogenic disorders that are linked to conditions of poor immunity.
In order to devise specific treatments for each infant, prompt and accurate forms of medical information and diagnoses need to be provided for all health care professionals. The incorporation of AI into clinical domains and workflows, the authors stated, will pave the way toward improved patient safety, enhanced quality of care and decreased rates of human error.
Machine and deep learning to improve infant care
AI, which comprises both machine learning (ML) and deep learning (DL), plays an essential role in the medical industry in terms of predicting and classifying a range of infant disorders. The researchers of the current analysis sought to provide a comprehensive overview of the adaptation of ML and DL strategies for predicting infant health problems.
Regarding the use of ML in infant health care monitoring, the technique is being used for predicting such issues as gestational diabetes, sepsis in neonates, long-term pediatric conditions such as inflammatory bowel syndrome and respiratory syncytial virus. In addition, cardiotocograms are being utilized for the evaluation of fetal health and prevention of child mortality. Cardiotocography monitors the fetal heart rate and uterine contractions during pregnancy and labor.
With respect to the use of DL in infant health care, the suggested method involves cry detection among newborns. Cry, which is considered a primitive type of communication among infants, necessitates constant supervision and can be an effective strategy for monitoring this patient population.
Electroencephalography has been a critical part of infant monitoring for effective neurocritical care, which can be utilized in expediting early therapeutic decisions and predicting positive outcomes. Early identification of cerebral palsy via the use of DL is considered an essential task in early intervention of preventing injuries that occur in the brain.
To recap, the current analysis “identifies the research gaps and the future direction of the research in the current domain,” the authors noted. “A comprehensive form of analysis of the current landscapes involved in predicting infant health issues using AI is presented,” they concluded.
