MACHINE LEARNING-BASED CLINICAL DECISION SUPPORT SYSTEM FOR PREDICTING FETAL HYPOXEMIA DURING NON-STRESS TEST    

Authors : 1. Sajal Baxi, Student, IIHMR University ; 2. Dr. Anoop Khanna, Professor, IIHMR University

Publishing Date : 2024

DOI : https://doi.org/10.52458/9788197040887.2024.eb.ch-17

ISBN : 978-81-970408-1-8

Pages : 76-79

Chapter id : IIHMR/NSP/EB/SAHHE/2024/Ch-17

Abstract : In the fiscal year 2019-2020, India reported 824,000 under-five deaths. Neonatal deaths, with almost 24 out of 1000 attributed to fetal hypoxia associated with metabolic acidosis (45%), constitute a significant concern. Other leading causes of neonatal mortality include complications from preterm birth (35%), intrapartum events (25%), and infections (10%) [1].

Keywords :

Cite : Baxi, S., & Khanna, A. (2024). Machine Learning-Based Clinical Decision Support System For Predicting Fetal Hypoxemia During Non-Stress Test (1st ed., pp. 76-79). Noble Science Press. https://doi.org/10.52458/9788197040887.2024.eb.ch-17

References :
  1. Low, J. A., Lindsay, B. G., & Derrick, E. J. (1997). Threshold of metabolic acidosis associated with newborn complications. American journal of obstetrics and gynecology, 177(6), 1391-1394.
  2. Maslova, M. V., Maklakova, A. S., Sokolova, N. A., Ashmarin, I. P., Goncharenko, E. N., & Krushinskaya, Y. V. (2003). The effects of ante-and postnatal hypoxia on the central nervous system and their correction with peptide hormones. Neuroscience and behavioral physiology, 33, 607-611.
  3. Preboth, M. (2000). ACOG guidelines on antepartum fetal surveillance. American family physician, 62(5), 1184-1188.