An intelligent diagnostic system for the assessment of gestational age based on ultrasonic fetal head measurements.

The object of this study is the assessment of gestational age by using fetal biparietal diameter and head circumference based on automated image analysis and artificial neural networks. Standard ultrasonic measurements were made in 143 normal fetuses between 14 and 40 weeks' gestation. Six hundred and thirteen fetal head images were transferred to a microcomputer environment by means of a frame grabber and spatial software. Biparietal diameter and head circumference measurements were made by automated image processing and analysis techniques. In the next stage, these two fetal parameters were used to determine the gestational age by using an unsupervised artificial neural network. Back propagation learning algorithm was trained by 552 fetal head images and the system was tested with the remaining 61 images. It has been demonstrated that 98% of gestational weeks were estimated correctly by our system.

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 alpha-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. RESULTS: 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). CONCLUSION: This system brings objectively 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 expert can not get more than he or she has donated the system.

Prenatal diagnosis of sickle cell anemia using PCR and restriction enzyme Dde I.

Prenatal diagnosis of sickle cell anemia was carried out in four fetuses using DNA technology. Fetal chorionic villus specimen were obtained at the 10th week of pregnancy from women at risk of giving birth to children with sickle cell anemia. Whole cellular DNA was obtained and the part of the DNA presumed to have a mutation increased after PCR was performed. After the application of Dde I restriction enzyme, mini gel electrophoresis was performed. The study of the electrophoretic patterns of the DNA indicated that one of the four fetuses was unaffected, one was a carrier and the remaining two were affected.

The validation of a computerized system for the interpretation of the antepartum fetal heart rate tracings (version 89/2.34).

We have developed a knowledge-based system for the interpretation of the antepartum fetal heart rate tracings. This study consists of four groups of patient: (1) 49 normal pregnancies with a normal perinatal outcome; (2) 13 normal pregnancies with abnormal perinatal outcome; (3) 33 high-risk pregnancies with abnormal perinatal outcome; and (4) 16 high-risk pregnancies with normal perinatal outcome. The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of our expert system (version 89/2.34) were estimated to be 60.0, 85.7, 75.0 and 75.0%, respectively. When the normal pregnancies with abnormal outcome and the high-risk pregnancies with normal outcome were excluded from the population, sensitivity, specificity, PPV and NPV were calculated to be 57.7, 82.9, 68.2 and 75.6%, respectively (corrected values). The prevalance of abnormal outcome for this study was 41.7%.

Computerized analysis of antepartum fetal heart rate tracings in normal pregnancies (version 88/2.29).

A computerized system is developed for the interpretation of antepartum fetal heart-rate monitoring. Various parameters are described to define the cardiotocograms. The pattern of the tracing is defined as saltatory, undulatory, reduced undulatory or silent according to the results of the spectrum analysis. Three different baselines including simple average baseline, real baseline and basecurve are described for each tracing. Spontaneous and fetal movement related accelerations and decelerations are also defined. Tracings from 33 normal pregnancies with normal outcome were studied and the distribution of parameters for each gestational week (28th to 40th) was defined. The real baseline of fetal heart rate was 141.5 +/- 8.5 between the 28th and 40th gestational week. 75% of the cardiotocograms were found to obtain fetal movement. It has also been observed that in normal pregnancies the general pattern of the tracings is undulatory or undulatory/saltatory.

Development and application of a simple expert system for the interpretation of the antepartum fetal heart rate tracings (version 88/2.29).

A simple expert system is developed for the interpretation of antepartum fetal heart rate tracings. The perinatal expert chose to use the phrase 'Fetal Reserve' to describe what the cardiotocogram is indirectly measuring. Our analysis program gives numerical values to each CTG such as 5, 4, 3, 2.5, 2 and 1 corresponding to the fetal reserve conditions of good, satisfactory, probably satisfactory with uncertainty, borderline, decreased, and critical respectively. This study consists of 33 normal pregnancies with normal outcome. Each patient is followed by our computerized system biweekly from the 28th to the 38th gestational week and weekly there after. The expert system's decision for 28th, 30th, 32nd, 34th, 36th, 38th, 39th and 40th gestational weeks were 3.3 +/- 1.0, 3.8 +/- 0.7, 3.8 +/- 1.0, 4.1 +/- 0.9, 4.1 +/- 0.7, 3.6 +/- 1.0, 4.2 +/- 1.0, 3.8 +/- 0.9 and 3.4 +/- 1.2, respectively. In this study, we have used confusion matrix to determine the normal, security, and danger zones according to the perinatal expert and the expert system and the discriminatory power of the system is found to be highly significant statistically (Q = 221). We also showed that the passive test (non-stress test) in normal pregnancies has demonstrated false positive results in 4.2 and 9.3% of the cases according to the evaluations of the perinatal expert and the expert system, respectively.