Andreas Neocleous

First Trimester Noninvasive Prenatal Diagnosis: A Computational Intelligence Approach

The objective of this study is to examine the potential value of using machine learning techniques such as artificial neural network (ANN) schemes for the noninvasive estimation, at 11-13 weeks of gestation, the risk for euploidy, trisomy 21 (T21), and other chromosomal aneuploidies (O.C.A.), from suitable sonographic, biochemical markers, and other relevant data. A database1 consisted of 51,208 singleton pregnancy cases, while undergoing first trimester screening for aneuploidies has been used for the building, training, and verification of the proposed method. From all the data collected for each case from the mother and the fetus, the following 9 are considered by the collaborating obstetricians as the most relevant to the problem in question: maternal age, previous pregnancy with T21, fetal crown-rump length, serum free β-hCG in multiples of the median (MoM), pregnancy-associated plasma protein-A in MoM, nuchal translucency thickness, nasal bone, tricuspid flow, and ductus venosus flow. The dataset was randomly divided into a training set that was used to guide the development of various ANN schemes, support vector machines, and k-nearest neighbor models. An evaluation set used to determine the performance of the developed systems. The evaluation set, totally unknown to the proposed system, contained 16,898 cases of euploidy fetuses, 129 cases of T21, and 76 cases of O.C.A. The best results were obtained by the ANN system, which identified correctly all T21 cases, i.e., 0% false negative rate (FNR) and 96.1% of euploidies, i.e., 3.9% false positive rate (FPR), meaning that no child would have been born with T21 if only that 3.9% of all pregnancies had been sent for invasive testing. The aim of this work is to produce a practical tool for the obstetrician which will ideally provide 0% FNR and to recommend the minimum possible number of cases for further testing such as invasive. In conclusion, it was demonstrated that ANN schemes can provide an effective early screening for fetal aneuploidies at a low FPR with results that compare favorably to those of existing systems.

Prenatal Diagnosis of Aneuploidy Using Artificial Neural Networks in Relation to Health Economics

RASimAs (Regional Anaesthesia Simulator and Assistant) is a EU FP7 project that aims at increasing the application, the effectiveness and the success rates of regional anaesthesia by developing two independent but complementary systems, one system for training by using patient-specific computer models, and one for guidance in the assistance of nerve’s location during the actual intervention. In this context, the present document focuses on the training system, which will be deployed in multiple participating hospitals that will be connected to a central information system. In particular, this paper deals with the software architecture of the aforementioned integrated environment and the components that constitute it. We present indicative key components and functionalities such as the user authentication and authorization service, the user profile and performance metrics management service, the role based access control system, the VPH (Virtual Physiological Human) library, and the synchronization between the training centres and the central information system.

Marker selection for the detection of trisomy 21 using generalized matrix learning vector quantization

In this work we explore the relevance of markers that are used for the early detection of fetal chromosomal abnormalities. For medical applications, it is important to optimize the number of used markers with respect to the number of necessary clinical examinations. We use the Generalized Matrix Learning Vector Quantization (GMLVQ) method to identify the most relevant markers from a set of 18 clinical examinations. We cross-validated our results using ten different training and test sets and we repeated our experiments using different parameters of GMLVQ. We identified the seven most relevant markers and we found that with these seven markers we obtain results that are comparable with the results that can be achieved with the full set of 18 markers. The results are in line with previous work that is found in the literature.

Filter-Based Approach for Ornamentation Detection and Recognition in Singing Folk Music

Ornamentations in music play a significant role for the emotion whi1ch a performer or a composer aims to create. The automated identification of ornamentations enhances the understanding of music, which can be used as a feature for tasks such as performer identification or mood classification. Existing methods rely on a pre-processing step that performs note segmentation. We propose an alternative method by adapting the existing two-dimensional COSFIRE filter approach to one-dimension (1D) for the automatic identification of ornamentations in monophonic folk songs. We construct a set of 1D COSFIRE filters that are selective for the 12 notes of the Western music theory. The response of a 1D COSFIRE filter is computed as the geometric mean of the differences between the fundamental frequency values in a local neighbourhood and the preferred values at the corresponding positions. We apply the proposed 1D COSFIRE filters to the pitch tracks of a song at every position along the entire signal, which in turn give response values in the range [0,1]. The 1D COSFIRE filters that we propose are effective to recognize meaningful musical information which can be transformed into symbolic representations and used for further analysis. We demonstrate the effectiveness of the proposed methodology in a new data set that we introduce, which comprises five monophonic Cypriot folk tunes consisting of 428 ornamentations. The proposed method is effective for the detection and recognition of ornamentations in singing folk music.

Artificial Neural Networks to Investigate the Importance and the Sensitivity to Various Parameters Used for the Prediction of Chromosomal Abnormalities

A selection of artificial neural network models were built and implemented for systematically study the contribution and the sensitivity of the main influencing parameters as important contributing factors for the non-invasive prediction of chromosomal abnormalities. The parameters that had been investigated are: the previous medical history of the pregnant mother, the nasal bone, the tricuspid flow, the ductus venosus flow, the PAPP-A value, the b-hCG value, the crown rump length (CRL), the changes in nuchal translucency (deltaNT) and the mother’s age. The main conclusions drawn are: 1) The deltaNT is the most significant factor for the overall prediction, while the CRL the least significant. 2) The previous medical history of the pregnant mother is not a significant factor for the prediction of the abnormal cases. 3) The nasal bone, the tricuspid flow and the ductus venosus flow contribute significantly in the prediction of trisomy 21 but not in the prediction of the “normal” cases. 4) The PAPP-A, the b-hCG and the mother’s age are of intermediate importance. Also, a sensitivity analysis of the attributes PAPP-A, b-hCG, CRL, deltaNT and of the mother’s age was done. This analysis showed that the CRL and deltaNT are more sensitive when their values are decreased, the PAPP-A is more sensitive when its values are increased and the b-hCG is insensitive to variations in its values.

Artificial neural networks to investigate the significance of PAPPA and b-hCG for the prediction of chromosomal abnormalities

A systematic approach has been done, to investigate different neural network structures for the appraisal of the significance of the free b-human chorionic gonadotrophin (b-hCG) and the pregnancy associated plasma protein-A (PAP-PA) as important parameters for the prediction of the existence of chromosomal abnormalities in fetuses.