• T. Palaniappan
• Vidya P Janaki
• T.Rajendra Prasad
• S. Samaya Naveen

Children are the future of the world. It is important to make sure that they are delivered safely to this world. One of the complicated prenatal and neonatal problems faced by pregnant woman and new born infants is fetal distress. It is a condition where the fetus does not receive enough oxygen for respiration, which results in an unhealthy and dangerous condition in the fetus. If left untreated fetal distress may result in stillbirth. The fetal distress can be diagnosed by monitoring the heartbeat of the baby. Any abnormal spike or deceleration in the fetus’ heartbeat is the indication of the problem. The main objective is to use machine learning algorithm to predict the condition of fetal distress from the test results of a cardiotocogram. The decision tree classifier algorithm has been used to predict the abnormal fetus. Various parameters such as light decelerations, severe deceleration, prolonged deceleration, repetitive deceleration, baseline value, fetal movements and uterine contraction are analysed and the fetal distress is predicted by the algorithm in decision tree classifier. The main purpose of this decision tree classification method is to classify and determine the fetal state class code consisting of normal, suspicious or pathologic. The histogram means median, mode and standard deviations for those parameters and effectively is calculated and used in the algorithm to get high accuracy. Totally 2126 measurements and classifications of fetal heart rate (FHR) signal output were analyzed to predict the fetal distress. 80% of data is given as train dataset and 20% as test dataset. The algorithm also have predicts the suitable food to be taken by the women during the time of her pregnancy by giving the input as the total number of her pregnancy month. Thus using ML (machine learning) algorithm the possibility of fetal distress in pregnant women is predicted.

- Decision tree classifier, histogram mean, median, mode and standard deviations, normal, suspicious, pathologic.

"Fetal Distress Classification based on Cardiotocography using Machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.199-204, May-2019, Available :http://www.jetir.org/papers/JETIR1905I31.pdf

"Fetal Distress Classification based on Cardiotocography using Machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp199-204, May-2019, Available at : http://www.jetir.org/papers/JETIR1905I31.pdf