An artificial intelligent diagnostic system with neural networks to determine genetical disorders and fetal health by using maternal serum markers

Objective: To develop an artificial intelligent diagnostic system with neural networks to determine genetical disorders and fetal health problems by using maternal serum markers ('Triple Test') and maternal age. Study Design. A total of 112 pregnant women were referred to Fetal Medicine Unit of Hacettepe University Hospital for fetal ultrasonography and chromosome analysis with different indications. All patients underwent genetic amniocentesis or fetal blood sampling under ultrasound guidance. Gross malformations and hydrops fetalis were detected in 15 and 5 fetuses, respectively. We have found chromosomal abnormality in 7 cases. 'Triple Test' is offered to all patients and serum levels of α-fetoprotein, human chorionic gonadotropin and unconjugated estriol were analyzed by radioimmunoassay. In this study, we have used supervised artificial neural network structure to develop a diagnostic system. Our system's input parameters are maternal age, gestational age and 'Triple Test' results. Our system consists of two different artificial neural network modules whose decision-making logics are different. One of them is designed to search genetical disorders while the other one is for the assessment of fetal well-being. Confusion matrix is used for statistical evaluation. The discriminatory power of the artificial neural network to search genetical disorders and fetal well-being is found to be highly significant (z = 10.583 and z = 10.424, respectively). This system brings objectivity to the evaluation of 'Triple Test' results and can be used both for the detection of genetical disorders and fetal well-being. Nevertheless, the analysis program's performance is limited to input information and knowledge and medical expert can not get more than he or she has donated the system.