Predictions of coronary artery stenosis by artificial neural network

Prediction and causal inference of cardiovascular and cerebrovascular diseases based on lifestyle questionnaires

Cardiovascular and cerebrovascular diseases (CCVD) are prominent mortality causes in Japan, necessitating effective preventative measures, early diagnosis, and treatment to mitigate their impact. A diagnostic model was developed to identify patients with ischemic heart disease (IHD), stroke, or both, using specific health examination data. Lifestyle habits affecting CCVD development were analyzed using five causal inference methods. This study included 473,734 patients aged ≥ 40 years who underwent specific health examinations in Kanazawa, Japan between 2009 and 2018 to collect data on basic physical information, lifestyle habits, and laboratory parameters such as diabetes, lipid metabolism, renal function, and liver function. Four machine learning algorithms were used: Random Forest, Logistic regression, Light Gradient Boosting Machine, and eXtreme-Gradient-Boosting (XGBoost). The XGBoost model exhibited superior area under the curve (AUC), with mean values of 0.770 (± 0.003), 0.758 (± 0.003), and 0.845 (± 0.005) for stroke, IHD, and CCVD, respectively. The results of the five causal inference analyses were summarized, and lifestyle behavior changes were observed after the onset of CCVD. A causal relationship from 'reduced mastication' to 'weight gain' was found for all causal species theory methods. This prediction algorithm can screen for asymptomatic myocardial ischemia and stroke. By selecting high-risk patients suspected of having CCVD, resources can be used more efficiently for secondary testing.

Deep learning-based prediction of coronary artery stenosis resistance

Coronary artery stenosis resistance (SR) is a key factor for noninvasive calculations of fractional flow reserve derived from coronary CT angiography (FFR_CT). Existing computational fluid dynamics (CFD) methods, including three-dimensional (3-D) computational and zero-dimensional (0-D) analytical models, are usually limited by high calculation cost or low precision. In this study, we have developed a multi-input back-propagation neural network (BPNN) that can rapidly and accurately predict coronary SR. A training data set including 3,028 idealized anatomic coronary artery stenosis models was constructed for 3-D CFD calculation of SR with specific blood flow boundaries. Based on 3-D calculation results, we established a BPNN whose input is geometric parameters and blood flow, whereas output is SR. Then, a test set (324 cases) was constructed to evaluate the performance of the BPNN model. To verify the validity and practicability of the network, BPNN prediction results were compared with 3-D CFD and 0-D analytical model results from patient-specific models. For test set, the mean square error (MSE) between CFD and prediction results was 2.97%, linear regression analysis indicating a good correlation between the two (P < 0.001). For 30 patient-specific models, the MSE of BPNN and the 0-D model were 3.26 and 9.7%, respectively. The calculation time for BPNN and the 3-D CFD model for 30 cases was about 2.15 s and 2 h, respectively. The present results demonstrate the practicability of using deep learning methods for fast and accurate predictions of coronary artery SR. Our study represents an advance in noninvasive calculations of FFR_CT.NEW & NOTEWORTHY This study developed a multi-input back-propagation neural network (BPNN) that can be used to predict coronary artery stenosis resistance by inputting vascular geometric parameters and blood flow. Compared with previous studies, the network developed in this study can accurately and rapidly predict coronary artery stenosis resistance, which can not only meet clinical requirements but also reduce the cost of calculation duration. This study contributes to the noninvasive methods for the numerical calculation of fractional flow reserve derived from coronary CT angiography (FFRCT) and indicates that this technique can potentially be used for evaluating myocardial ischemia.

Predicting cardiac disease from interactions of simultaneously-acquired hemodynamic and cardiac signals

BACKGROUND AND OBJECTIVE

Coronary artery disease (CAD) and heart failure are the most common cardiovascular diseases. Non-invasive diagnostic testing for CAD requires radiation, heart rate acceleration, and imaging infrastructure. Early detection of left ventricular dysfunction is critical in heart failure management, the best measure of which is an elevated left ventricular end-diastolic pressure (LVEDP) that can only be measured using invasive cardiac catheterization. There exists a need for non-invasive, safe, and fast diagnostic testing for CAD and elevated LVEDP. This research employs nonlinear dynamics to assess for significant CAD and elevated LVEDP using non-invasively acquired photoplethysmographic (PPG) and three-dimensional orthogonal voltage gradient (OVG) signals. PPG (variations of the blood volume perfusing the tissue) and OVG (mechano-electrical activity of the heart) signals represent the dynamics of the cardiovascular system.

METHODS

PPG and OVG were simultaneously acquired from two cohorts, (i) symptomatic subjects that underwent invasive cardiac catheterization, the gold standard test (408 CAD positive with stenosis≥ 70% and 186 with LVEDP≥ 20 mmHg) and (ii) asymptomatic healthy controls (676). A set of Poincaré-based synchrony features were developed to characterize the interactions between the OVG and PPG signals. The extracted features were employed to train machine learning models for CAD and LVEDP. Five-fold cross-validation was used and the best model was selected based on the average area under the receiver operating characteristic curve (AUC) across 100 runs, then assessed using a hold-out test set.

RESULTS

The Elastic Net model developed on the synchrony features can effectively classify CAD positive subjects from healthy controls with an average validation AUC=0.90±0.03 and an AUC= 0.89 on the test set. The developed model for LVEDP can discriminate subjects with elevated LVEDP from healthy controls with an average validation AUC=0.89±0.03 and an AUC=0.89 on the test set. The feature contributions results showed that the selection of a proper registration point for Poincaré analysis is essential for the development of predictive models for different disease targets.

CONCLUSIONS

Nonlinear features from simultaneously-acquired signals used as inputs to machine learning can assess CAD and LVEDP safely and accurately with an easy-to-use, portable device, utilized at the point-of-care without radiation, contrast, or patient preparation.

A new non-invasive diagnostic tool in coronary artery disease: artificial intelligence as an essential element of predictive, preventive, and personalized medicine

Background

Known coronary artery disease (CAD) risk scores (e.g., Framingham) estimate the CAD-related event risk rather than presence/absence of CAD. Artificial intelligence (AI) is rarely used in this context.

Aims

This study aims to evaluate the diagnostic power of AI (memetic pattern-based algorithm (MPA)) in CAD and to expand its applicability to a broader patient population.

Methods and results

Nine hundred eighty-seven patients of the Ludwigshafen Risk and Cardiovascular Health Study (LURIC) were divided into a training (n = 493) and a test population (n = 494). They were evaluated by the Basel MPA. The "training population" was further used to expand and optimize the Basel MPA, and after modifications, a final validation was carried out on the "test population." The results were compared with the Framingham Risk Score (FRS) using receiver operating curves (ROC; area-under-the-curve (AUC)). Of the 987 LURIC patients, 71% were male, age 62 ± 11 years and 68% had documented CAD. AUC of Framingham and BASEL MPA to diagnose CAD in "LURIC training" were 0.69 and 0.80, respectively. AUC of the optimized MPA in the training and test cohort were 0.88 and 0.87, respectively. The positive predictive values (PPV) of the optimized MPA for exclusion of CAD in "training" and "test" were 98 and 95%, respectively. The PPV of MPA for identification of CAD was 93 and 94%, respectively.

Conclusions

The successful use of the MPA approach has been demonstrated in a broad-risk spectrum of patients undergoing CAD evaluation, as an element of predictive, preventive, personalized medicine, and may be used instead of further non-invasive diagnostic procedures.

Preventive Healthcare: A Neural Network Analysis of Behavioral Habits and Chronic Diseases

The research aims to explore the association between behavioral habits and chronic diseases, and to identify a portfolio of risk factors for preventive healthcare. The data is taken from the Behavioral Risk Factor Surveillance System (BRFSS) database of the Centers for Disease Control and Prevention, for the year 2012. Using SPSS Modeler, we deploy neural networks to identify strong positive and negative associations between certain chronic diseases and behavioral habits. The data for 475,687 records from BRFS database included behavioral habit variables of consumption of soda and fruits/vegetables, alcohol, smoking, weekly working hours, and exercise; chronic disease variables of heart attack, stroke, asthma, and diabetes; and demographic variables of marital status, income, and age. Our findings indicate that with chronic conditions, behavioral habits of physical activity and fruit and vegetable consumption are negatively associated; soda, alcohol, and smoking are positively associated; and income and age are positively associated. We contribute to individual and national preventive healthcare by offering a portfolio of significant behavioral risk factors that enable individuals to make lifestyle changes and governments to frame campaigns and policies countering chronic conditions and promoting public health.

A clinical decision support system for femoral peripheral arterial disease treatment

One of the major challenges of providing reliable healthcare services is to diagnose and treat diseases in an accurate and timely manner. Recently, many researchers have successfully used artificial neural networks as a diagnostic assessment tool. In this study, the validation of such an assessment tool has been developed for treatment of the femoral peripheral arterial disease using a radial basis function neural network (RBFNN). A data set for training the RBFNN has been prepared by analyzing records of patients who had been treated by the thoracic and cardiovascular surgery clinic of a university hospital. The data set includes 186 patient records having 16 characteristic features associated with a binary treatment decision, namely, being a medical or a surgical one. K-means clustering algorithm has been used to determine the parameters of radial basis functions and the number of hidden nodes of the RBFNN is determined experimentally. For performance evaluation, the proposed RBFNN was compared to three different multilayer perceptron models having Pareto optimal hidden layer combinations using various performance indicators. Results of comparison indicate that the RBFNN can be used as an effective assessment tool for femoral peripheral arterial disease treatment.

Nonlinear Survival Regression Using Artificial Neural Network

Survival analysis methods deal with a type of data, which is waiting time till occurrence of an event. One common method to analyze this sort of data is Cox regression. Sometimes, the underlying assumptions of the model are not true, such as nonproportionality for the Cox model. In model building, choosing an appropriate model depends on complexity and the characteristics of the data that effect the appropriateness of the model. One strategy, which is used nowadays frequently, is artificial neural network (ANN) model which needs a minimal assumption. This study aimed to compare predictions of the ANN and Cox models by simulated data sets, which the average censoring rate were considered 20% to 80% in both simple and complex model. All simulations and comparisons were performed by R 2.14.1.

Image processing and machine learning for fully automated probabilistic evaluation of medical images

The paper presents results of our long-term study on using image processing and data mining methods in a medical imaging. Since evaluation of modern medical images is becoming increasingly complex, advanced analytical and decision support tools are involved in integration of partial diagnostic results. Such partial results, frequently obtained from tests with substantial imperfections, are integrated into ultimate diagnostic conclusion about the probability of disease for a given patient. We study various topics such as improving the predictive power of clinical tests by utilizing pre-test and post-test probabilities, texture representation, multi-resolution feature extraction, feature construction and data mining algorithms that significantly outperform medical practice. Our long-term study reveals three significant milestones. The first improvement was achieved by significantly increasing post-test diagnostic probabilities with respect to expert physicians. The second, even more significant improvement utilizes multi-resolution image parametrization. Machine learning methods in conjunction with the feature subset selection on these parameters significantly improve diagnostic performance. However, further feature construction with the principle component analysis on these features elevates results to an even higher accuracy level that represents the third milestone. With the proposed approach clinical results are significantly improved throughout the study. The most significant result of our study is improvement in the diagnostic power of the whole diagnostic process. Our compound approach aids, but does not replace, the physician's judgment and may assist in decisions on cost effectiveness of tests.

Comparison of artificial neural networks with logistic regression for detection of obesity

Obesity is a common problem in nutrition, both in the developed and developing countries. The aim of this study was to classify obesity by artificial neural networks and logistic regression. This cross-sectional study comprised of 414 healthy military personnel in southern Iran. All subjects completed questionnaires on their socio-economic status and their anthropometric measures were measured by a trained nurse. Classification of obesity was done by artificial neural networks and logistic regression. The mean age±SD of participants was 34.4 ± 7.5 years. A total of 187 (45.2%) were obese. In regard to logistic regression and neural networks the respective values were 80.2% and 81.2% when correctly classified, 80.2 and 79.7 for sensitivity and 81.9 and 83.7 for specificity; while the area under Receiver-Operating Characteristic (ROC) curve were 0.888 and 0.884 and the Kappa statistic were 0.600 and 0.629 for logistic regression and neural networks model respectively. We conclude that the neural networks and logistic regression both were good classifier for obesity detection but they were not significantly different in classification.

Decision support systems for clinical radiological practice -- towards the next generation

The huge amount of information that needs to be assimilated in order to keep pace with the continued advances in modern medical practice can form an insurmountable obstacle to the individual clinician. Within radiology, the recent development of quantitative imaging techniques, such as perfusion imaging, and the development of imaging-based biomarkers in modern therapeutic assessment has highlighted the need for computer systems to provide the radiological community with support for academic as well as clinical/translational applications. This article provides an overview of the underlying design and functionality of radiological decision support systems with examples tracing the development and evolution of such systems over the past 40 years. More importantly, we discuss the specific design, performance and usage characteristics that previous systems have highlighted as being necessary for clinical uptake and routine use. Additionally, we have identified particular failings in our current methodologies for data dissemination within the medical domain that must be overcome if the next generation of decision support systems is to be implemented successfully.

Recurrent neural networks for diagnosis of carpal tunnel syndrome using electrophysiologic findings

This paper presents the use of recurrent neural networks (RNNs) for diagnosis of carpal tunnel syndrome (CTS) (normal, right CTS, left CTS, bilateral CTS). The RNN is trained with the Levenberg-Marquardt algorithm. The RNN is trained on the features of CTS (right median motor latency, left median motor latency, right median sensory latency, left median sensory latency). The multilayer perceptron neural network (MLPNN) is also implemented for comparison the performance of the classifiers on the same diagnosis problem. The total classification accuracy of the RNN is significantly high (94.80%). The obtained results confirmed the validity of the RNNs to help in clinical decision-making.

The association forecasting of 13 variants within seven asthma susceptibility genes on 3 serum IgE groups in Taiwanese population by integrating of adaptive neuro-fuzzy inference system (ANFIS) and classification analysis methods

Asthma is one of the most common chronic diseases in children. It is caused by complicated coactions between various genetic factors and environmental allergens. The study aims to integrate the concept of implementing adaptive neuro-fuzzy inference system (ANFIS) and classification analysis methods for forecasting the association of asthma susceptibility genes on 3 serum IgE groups. The ANFIS model was trained and tested with data sets obtained from 425 asthmatic subjects and 483 non-asthma subjects from the Taiwanese population. We assessed 13 single-nucleotide polymorphisms (SNPs) in seven well-known asthma susceptibility genes; firstly, the proposed ANFIS model learned to reduce input features from the 13 SNPs. And secondly, the classification will be used to classify the serum IgE groups from the simulated SNPs results. The performance of the ANFIS model, classification accuracies and the results confirmed that the integration of ANFIS and classified analysis has potential in association discovery.

Adaptive neuro-fuzzy inference systems for automatic detection of breast cancer

This paper intends to an integrated view of implementing adaptive neuro-fuzzy inference system (ANFIS) for breast cancer detection. The Wisconsin breast cancer database contained records of patients with known diagnosis. The ANFIS classifiers learned how to differentiate a new case in the domain by given a training set of such records. The ANFIS classifier was used to detect the breast cancer when nine features defining breast cancer indications were used as inputs. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the impacts of features on the detection of breast cancer were obtained through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of training performances and classification accuracies and the results confirmed that the proposed ANFIS model has potential in detecting the breast cancer.

The classification of obesity disease in logistic regression and neural network methods

The aim of this study is to establish an automated system to recognize and to follow-up obesity. In this study, the areas affected from obesity were examined with a classification considering the divergent arteries and body mass index of 30 healthy and 52 obese people by using two different mathematical models such as the traditional statistical method based on logistic regression and a multilayer perception (MLP) neural network, and then classifying performances of logistic regression and neural network were compared. As a result of this comparison, it is observed that the classifying performance of neural network is better than logistic regression; also the reasons of this result were examined. Furthermore, after these classifications it is observed that in obesity the body mass index is more affected than the divergent arteries.

The use of artificial neural networks to stratify the length of stay of cardiac patients based on preoperative and initial postoperative factors

BACKGROUND

The limitations of current prognostic models in identifying postoperative cardiac patients at risk of experiencing morbidity and subsequently an extended intensive care unit length of stay (ICU LOS) is well recognized. This coupled with the desire for risk stratification in order to prioritize medical intervention has lead to the need for the development of a system that can accurately predict individual patient outcome based on both preoperative and immediate postoperative clinical factors. The usefulness of artificial neural networks (ANNs) as an outcome prediction tool in the critical care environment has been previously demonstrated for medical intensive care unit (ICU) patients and it is the aim of this study to apply this methodology to postoperative cardiac patients.

METHODS

A review of contemporary literature revealed 15 preoperative risk factors and 17 operative and postoperative variables that have a determining effect on LOS. An integrated, multi-functional software package was developed to automate the ANN development process. The efficacy of the resultant individual ANNs as well as groupings or ensembles of ANNs were measured by calculating sensitivity and specificity estimates as well as the area under the receiver operating curve (AUC) when the ANN is applied to an independent test dataset.

RESULTS

The individual ANN with the highest discriminating ability produced an AUC of 0.819. The use of the ensembles of networks technique significantly improved the classification accuracy. Consolidating the output of three ANNs improved the AUC to 0.90.

CONCLUSIONS

This study demonstrates the suitability of ANNs, in particular ensembles of ANNs, to outcome prediction tasks in postoperative cardiac patients.

Prediction of minor head injured patients using logistic regression and MLP neural network

In this study it is aimed to assess the posttraumatic cerebral hemodynamia in minor head injured patients. Eighty patients with minor head injury (Group 1) evaluated in the early 8 h of posttraumatic period between July 2003 and February 2004. The control group (Group 2) has composed of 32 healthy people. Bilateral blood flow velocities of middle cerebral arteries (MCA) had measured using transtemporal technique while internal carotid arteries were evaluated by submandibular examination. Two different mathematical models such as the traditional statistical method on the basis of logistic regression and a multi-layer perceptron (MLP) neural network are used to classify the age, sex, velocitiy parameters of MCA, mean velocity of extracranial ICAs and V(MCA)/ V(ICA) ratios. The neural network was trained, cross-validated and tested with subject's transcranial Doppler signals. As a result of these classifications, we found the success rate of logistic regression, the success rate of MLP neural network is 88.2 and 89.1%, respectively. The classification results show that MLP neural network is offering the best results in the case of diagnosis.

Forecasting the Prognosis of Choroidal Melanoma with an Artificial Neural Network

PURPOSE

To develop an artificial neural network (ANN) that will forecast the 5-year mortality from choroidal melanoma.

DESIGN

Retrospective, comparative, observational cohort study.

PARTICIPANTS

One hundred fifty-three eyes of 153 consecutive patients with choroidal melanoma (age, 58.4+/-14.6 years) who were treated with ruthenium 106 brachytherapy between 1988 and 1998 at the Department of Ophthalmology, Hadassah University Hospital, Jerusalem, Israel.

METHODS

Patients were observed clinically and ultrasonographically (A- and B-mode standardized ultrasonography). Metastatic screening included liver function tests and liver imaging. Backpropagation ANNs composed of 3 or 4 layers of neurons with various types of transfer functions and training protocols were assessed for their ability to predict the 5-year mortality. The ANNs were trained on 77 randomly selected patients and tested on a different set of 76 patients. Artificial neural networks were compared based on their sensitivity, specificity, forecasting accuracy, area under the receiver operating curves, and likelihood ratios (LRs). The best ANN was compared with the results of logistic regression and the performance of an ocular oncologist.

MAIN OUTCOME

The ability of the ANNs to forecast the 5-year mortality from choroidal melanoma.

RESULTS

Thirty-one patients died during the follow-up period of metastatic choroidal melanoma. The best ANN (one hidden layer of 16 neurons) had 84% forecasting accuracy and an LR of 31.5. The number of hidden neurons significantly influenced the ANNs' performance (P<0.001). The performance of the ANNs was not significantly influenced by the training protocol, the number of hidden layers, or the type of transfer function. In comparison, logistic regression reached 86% forecasting accuracy, with a very low LR (0.8), whereas the human expert forecasting ability was <70% (LR, 1.85).

CONCLUSIONS

Artificial neural networks can be used for forecasting the prognosis of choroidal melanoma and may support decision-making in treating this malignancy.

Examination of the Effects of Degeneration on Vertebral Artery by Using Neural Network in Cases With Cervical Spondylosis

The scope of this study is to diagnose vertebral arterial inefficiency by using Doppler measurements from both right and left vertebral arterials. Total of 96 patients' Doppler measurements, consisting of 42 of healthy, 30 of spondylosis, and 24 of clinically proven vertebrobasillary insufficiency (VBI), were examined. Patients' age and sex information as well as RPSN, RPSVN, LPSN, LPSVN, and TOTALVOL medical parameters obtained from vertebral arterials were classified by neural networks, and the performance of said classification reached up to 93.75% in healthy, 83.33% in spondylosis, and 97.22% in VBI cases. The area under ROC curve, which is a direct indication of repeating success ratio, is calculated as 92.3%, and the correlation coefficient of the classification groups is 0.9234. It is also demonstrated that those medical parameters of age and systolic velocity, which were applied into the neural networks, were more effective in developing vertebral deficiency.

Detection of ophthalmic arterial doppler signals with Behcet disease using multilayer perceptron neural network

Doppler ultrasound is known as a reliable technique, which demonstrates the flow characteristics and resistance of ophthalmic arteries. In this study, ophthalmic arterial Doppler signals were obtained from 106 subjects, 54 of whom suffered from ocular Behcet disease while the rest were healthy subjects. Multilayer perceptron neural network (MLPNN) employing delta-bar-delta training algorithm was used to detect the presence of ocular Behcet disease. Spectral analysis of the ophthalmic arterial Doppler signals was performed by least squares (LS) autoregressive (AR) method for determining the MLPNN inputs. The MLPNN was trained with training set, cross validated with cross validation set and tested with testing set. All these data sets were obtained from ophthalmic arteries of healthy subjects and subjects suffering from ocular Behcet disease. Performance indicators and statistical measures were used for evaluating the MLPNN. The correct classification rate was 96.43% for healthy subjects and 93.75% for unhealthy subjects suffering from ocular Behcet disease. The classification results showed that the MLPNN employing delta-bar-delta training algorithm was effective to detect the ophthalmic arterial Doppler signals with Behcet disease.

Neural network predictions of significant coronary artery stenosis in men

OBJECTIVE

A neural network system was designed to predict whether coronary arteriography on a given patient would reveal any occurrence of significant coronary stenosis (>50%), a degree of stenosis which often leads to coronary intervention.

METHODOLOGY

A dataset of 2004 records from male cardiology patients was derived from a national cardiac catheterization database. The catheterizations selected for analysis from the database were first-time and elective, and they were precipitated by chest pain. Eleven patient variables were used as inputs in an artificial neural network system. The network was trained on the earliest 902 records in the dataset. The next 902 records formed a cross-validation file, which was used to optimize the training. A third file composed of the next 100 records facilitated the choice of a cutoff number between 0 and 1. The cutoff number was applied to the last 100 records, which comprised a test file.

RESULTS

When a cutoff of 0.25 was compared to the network outputs of all 100 records in the test file, 12 of 46 (specificity=26%) patients without significant stenosis had outputs<or=0.25, but all patients with significant stenosis had outputs>0.25 (sensitivity=100%). Therefore, the network identified a fraction of the patients in the test file who did not have significant coronary artery stenosis, while at the same time the network identified all of the patients in the test file who had significant stenosis capable of causing chest pain.

CONCLUSION

Artificial neural networks may be helpful in reducing unnecessary cardiac catheterizations.

Classification of carotid artery stenosis of patients with diabetes by neural network and logistic regression

The blood flow hemodynamics of carotid arteries were obtained from carotid arteries of 168 individuals with diabetes using the 7.5 MHz ultrasound Doppler M-unit. Fast Fourier Transform (FFT) methods were used for feature extraction from the Doppler signals on the time-frequency domain. The parameters, obtained from the Doppler sonograms, were applied to the mathematical models that were constituted to analyze the effect of diabetes on internal carotid artery (ICA) stenosis. In this study, two different mathematical models such as the traditional statistical method based on logistic regression and a Multi-Layer Perceptron (MLP) neural network were used to classify the Doppler parameters. The correct classification of these data was performed by an expert radiologist using angiograpy before they were executed by logistic regression and MLP neural networks. We classified the carotid artery stenosis into two categories such as non-stenosis and stenosis and we achieved similar results (correctly classified (CC) = 92.8%) in both mathematical models. But, as the degree of stenosis had been increased to 4 (0-39%, 40-59%, 60-79% and 80-99% diameter stenosis), it was found that the neural network (CC = 73.9%) became more efficient than the logistic regression analysis (CC = 67.7%). These outcomes indicate that the Doppler sonograms taken from the carotid arteries may be classified successfully by neural network.

Detection of ophthalmic artery stenosis by least-mean squares backpropagation neural network

Doppler ultrasound is a noninvasive technique that allows the examination of the direction, velocity, and volume of blood flow. In this study, ophthalmic artery Doppler signals were obtained from 105 subjects, 48 of whom had suffered from ophthalmic artery stenosis. A least-mean squares backpropagation neural network was used to detect the presence or absence of ophthalmic artery stenosis. Spectral analysis of ophthalmic artery Doppler signals was done by the Welch method for determining the neural network inputs. The network was trained, cross validated and tested with subject records from the database. Performance indicators and statistical measures were used for evaluating the neural network. Ophthalmic artery Doppler signals were classified with the accuracy varying from 88.9% to 90.6%.

Prediction of survival in surgical unresectable lung cancer by artificial neural networks including genetic polymorphisms and clinical parameters

Lung cancer, a common malignancy in Taiwan, involves multiple factors, including genetics and environmental factors. The survival time is very short once cancer is diagnosed as being in advanced stage and surgically unresectable. Therefore, a good model of prediction of disease outcome is important for a treatment plan. We investigated the survival time in advanced lung cancer by using computer science from the genetic polymorphism of the p21 and p53 genes in conjunction with patients' general data. We studied 75 advanced and surgical unresectable lung cancer patients. The prediction of survival time was made by comparing real data obtained from follow-up periods with data generated by an artificial neural network (ANN). The most important input variable was the clinical staging of lung cancer patients. The second and third most important variables were pathological type and responsiveness to treatment, respectively. There were 25 neurons in the input layer, four neurons in the hidden layer-1, and one neuron in the output layer. The predicted accuracy was 86.2%. The average survival time was 12.44 +/- 7.95 months according to real data and 13.16 +/- 1.77 months based on the ANN results. ANN provides good prediction results when clinical parameters and genetic polymorphisms are considered in the model. It is possible to use computer science to integrate the genetic polymorphisms and clinical parameters in the prediction of disease outcome. Data mining provides a promising approach to the study of genetic markers for advanced lung cancer.

Evaluation of inherent performance of intelligent medical decision support systems: utilising neural networks as an example

Researchers who design intelligent systems for medical decision support, are aware of the need for response to real clinical issues, in particular the need to address the specific ethical problems that the medical domain has in using black boxes. This means such intelligent systems have to be thoroughly evaluated, for acceptability. Attempts at compliance, however, are hampered by lack of guidelines. This paper addresses the issue of inherent performance evaluation, which researchers have addressed in part, but a Medline search, using neural networks as an example of intelligent systems, indicated that only about 12.5% evaluated inherent performance adequately. This paper aims to address this issue by concentrating on the possible evaluation methodology, giving a framework and specific suggestions for each type of classification problem. This should allow the developers of intelligent systems to produce evidence of a sufficiency of output performance evaluation.

Implementation of intelligent decision support systems in health care

The full implementation of any intelligent system in health care, which is designed for decision support, has several stages, from initial problem identification through development and, finally, cost-benefit analysis. Central to this is formal objectivist evaluation with its core component of inherent performance of the outputs from these systems. A Medline survey of one type of intelligent system is presented, which demonstrates that this issue is not being addressed adequately. Lack of criteria for dealing with the outputs from these "black box" systems to prescribe adequate levels of inherent performance may be preventing their being accepted by those in the health-care domain and, thus, their being applied widely in the field.