A clinical decision support system using multilayer perceptron neural network to assess well being in diabetes.

BACKGROUND: Diabetes mellitus is an increasingly common life-style disorder whose management outcomes are measured in symptomatic, biochemical as well as psychological areas. Well being as an outcome of treatment is being increasingly recognized as a crucial component of treatment. There is little published literature on psychosocial outcomes and the factors influencing them. Therefore we have developed a neural network system which is trained to predict the well being in diabetes, using data generated in real life. MATERIAL AND METHODS: We developed a Multi Layer Perceptron Neural Network model, which had been trained by back propagation algorithm. Data was used from a cohort of 241 individuals with diabetes. We used age, gender, weight, fasting plasma glucose as a set of inputs and predicted measures of well-being (depression, anxiety, energy and positive well-being). RESULTS: It was observed that female patients report significantly higher levels of depression than their male counter parts. Some slight high or no significant differences are observed between males and female patients with regard to the number of persons with whom they share their anxieties and fears regarding diabetes. There is not much difference has been observed in energy levels of both males and females. Also, Males have higher pwb value when compared with the female counterparts. Also, this may be due to women tend to react more emotionally to disease and hence experience more difficulty in coping with it. The present sample of women being predominantly house wives may be worrying more about their health and its problems. Also, it is observed that, gender differences are significant with regard to total general well-being. With five inputs (age, sex, weight, fasting plasma glucose, bias), four outputs are four (depression, anxiety, energy and positive well-being) the momentum rate was 0.9, the learning rate 0.7, using a sample of 50. the maximum individual error is 0.001 when the number of iterations were 500, number of hidden layers is 1 and the number of units in the hidden layer are 6, the normalized system error was 470.57. With input samples of 100, 150 and 200, keeping the other variables constant, the normalized system error was 419.61, 359.67 and 332.32 respectively. Similar values are found for the normalized system error when the number of units in the hidden layer have been increased to 7, 8 and 9 respectively. With two hidden layers, and with each hidden layer containing 6,7 ,8, 9, 10, 11 units for the samples 50, 100, 150, and 200, the same values of normalized system error was found. Women having weight between 40 kgs and 85kgs had higher levels of depression than men who had weight between 39kgs and 102 kgs. CONCLUSION: We have developed a prototype neural network model to predict the psychosocial well-being in diabetes, when biological or biographical variables are given as inputs. When greater data was fed to the system, the normalized system error can be reduced.

Reliability of phase-encode mapping in the presence of spatial non-stationarity of response latency.

Phase-encode mapping has been used as the primary functional magnetic resonance imaging (fMRI) technique to reveal spatial variation of response properties in both visual and auditory cortex (e.g., retinotopy and tonotopy). Spatial variation in the time of response produces a map of cortical sensitivity to a time-varying property of the presented stimulus. Inherently, this technique assumes that response latency is invariant across cortex. However, the latency of the fMRI response has been found to exhibit both temporal and spatial non-stationarity, with variance across cortex increasing with longer stimulus duration--a critical concern given the typically long duration (e.g., 48-64 s) of stimuli presented in phase-encode mapping experiments. This study addresses two issues--assessment of error rates caused by latency variance and reliability of maps identified using phase-encode mapping. Our findings suggest that the latency variance was found to have a greater effect on the type II error (missed detection) rate than on the type I error (false alarm) rate, with the size of the cortical map controlling the type I error rate. Moreover, empirical determination of false alarm rates provides the first approximation of the statistical significance (i.e., P values) of observed maps in both retinotopic and tonotopic studies, with maps as short as three voxels in length achieving the P < 0.05 significance level for a single subject.

Anticardiolipin antibodies in eclampsia.

Twenty patients with eclampsia were studied for the presence of anticardiolipin antibodies by the standard microflocculation test (quantitative) used in the VDRL. Four out of 20 patients (20%) were positive for anticardiolipin antibodies. Anticardiolipin antibodies which are antiphospholipid antibodies by decreasing the prostacyclin production may damage the vascular endothelium and cause thrombosis in the vessels. Hence, the presence of anticardiolipin antibody in eclampsia may have association with antiphospholipid antibody syndrome described by Harris et al. (Lancet ii: 1211, 1983) and its central nervous system sequelae.

Influence of material properties on the mechanical behaviour of the L5-S1 intervertebral disc in compression: a nonlinear finite element study.

A simple finite element model of the L5-S1 intervertebral disc body has been constructed; it is circular and symmetrical about the sagittal plane. The annulus fibrosus of the model was idealized as an inhomogeneous composite of an isotropic ground substance, reinforced by helically oriented collagen fibres so that the model has six different structural components namely: cortical bone, cancellous bone, cartilaginous endplates, nucleus pulposus, ground substance and collagen fibres. A sensitivity analysis of the material properties of each structural component was carried out by varying those properties for one structural component at a time and evaluating the changes in the biomechanical response to compressive displacements. Experimentally available relations between the applied compressive force and the vertical displacements, the nucleus pulposus pressure increase and the disc lateral bulge were used to evaluate the biomechanical responses for each set of material properties. Results showed that both the Poisson's ratio and the Young's modulus of the ground substance play an important role in the prediction of the biomechanical response.

Redox substoichiometric determination of thallium.

A method for the redox substoichiometric determination of thallium employing chlorate as an oxidant has been developed. The substoichiometric amount of Tl(III) formed was isolated by extraction with isoamyl acetate. 5-50 micrograms of thallium can be determined with an accuracy of +/- 1.3%.