Search Results

Now showing 1 - 1 of 1

Predicting Birth Defects
(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Korkut Özer, Selen; Koç, Utku
Many couples are eager to have a healthy baby. For this reason, the pregnant woman is trying to take their baby through the steps of adjusting their lives during the pregnancy, such as healthy nutrition, organic life, avoiding cosmetics. Even though the woman can do it, health problems can be observed in the baby at the time of birth or after birth. The causes of these health problems may be factors such as genetic, the physiological characteristics of the mother, environmental. In this paper, we tried to answer the question whether the health problems that occur in babies after childbirth can be estimated before birth. This includes the birth records of the American Centers for Disease Control and Prevention (CDC). Approximately 3M data was analyzed and the prediction model worked on the baby dataset. Boosting, Random Forest, Neural Network, Logistic Regression and SVM models were used to estimate the babies who could have any disease at birth. Sick babies were estimated with an accuracy of 69.5%.

Yüksek Lisans Tezleri