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 40kgs and 85kgs had higher levels of depression than men who had weight between 39kgs and 102kgs. 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. ©

A comparative study of the quality and availability of health information used to facilitate cost burden analysis of diabetes and hypertension in the Caribbean / Estudio comparativo de la calidad y disponibilidad de la información sobre la salud usada para facilitar el análisis del nivel de costos de la diabetes y la hipertensión en el Caribe

OBJECTIVE: Non-communicable Diseases (NCDs) are leading threats to health and well-being in the Caribbean. A study was undertaken in the latter part of 2005 to compute the economic burden of diabetes mellitus and hypertension within the Caribbean Community and Common Market (CARICOM). This report critiques the quality and availability of health information which can be used to facilitate cost burden analysis of diabetes mellitus and hypertension. METHODS: A form was developed and disseminated to obtain epidemiological and health service utilization data. Subsequent visits were made to seven CARICOM member countries to collect the data. RESULTS: The results revealed (i) a number of deficiencies in the reliability and validity of the data received, in particular, those needed to facilitate the analysis of cost-specific complications such as ischaemic heart disease, cerebrovascular disease, chronic renal failure, hypertensive and diabetic retinopathy and peripheral circulatory complications; (ii) data management systems in hospitals were not linked to facilitate generation of cost-effectiveness estimates and other information required to compare options for health investment; (iii) despite repeated attempts by regional governments to develop/strengthen Health Information Systems within the Caribbean, sustainability has been significantly hampered by human, material and financial resource constraints and ongoing monitoring and evaluation is generally poor. CONCLUSION: There are deficiencies in the quality and availability of health information to facilitate cost burden analysis of hypertension and diabetes mellitus in the Caribbean. Strong commitment from CARICOM governments will be necessary to address these concerns if economic evaluations are to be undertaken more frequently as part of the effort to reduce the morbidity and mortality from these diseases.

OBJETIVO: Las enfermedades no comunicables (ENC) se cuentan entre las principales amenazas a la salud y el bienestar en el Caribe. Se llevó a cabo un estudio hacia finales de 2005, con el fin de computar la carga económica de la diabetes mellitus y la hipertensión dentro de la Comunidad y el Mercado Común del Caribe (CARICOM). Este reporte constituye un análisis crítico de la calidad y disponibilidad de información sobre la salud, que puede ser usada para facilitar el análisis del nivel de costos de la diabetes mellitus y la hipertensión. MÉTODOS: Se desarrolló y distribuyó un formulario para obtener datos acerca de la utilización de servicios de salud y servicios epidemiológicos. Posteriormente se realizaron visitas a siete países miembros de CARICOM con el propósito de recoger datos. RESULTADOS: Los resultados revelaron (i) algunas deficiencias en cuanto a la confiabilidad y la validez de los datos recibidos, en particular los necesarios para facilitar el análisis de las complicaciones costo-específicas, tales como la enfermedad cardíaca isquémica, la enfermedad cerebrovascular, el fallo renal crónico, la retinopatía hipertensiva y diabética, y las complicaciones circulatorias periféricas; (ii) los sistemas de administración de datos en los hospitales no estaban conectados para facilitar la producción de estimados de costo-efectividad y otras informaciones requeridas para comparar las opciones de inversión para la salud; (iii) a pesar de reiterados intentos de los gobiernos regionales por desarrollar y fortalecer los sistemas de información de salud en el área del Caribe, su sostenimiento ha sido obstaculizado significativamente a causa de restricciones en cuanto a recursos humanos, materiales y financieros, y por el hecho de que el monitoreo y la evaluación actuales son generalmente pobres. CONCLUSIÓN: Existen deficiencias en la calidad y disponibilidad de información sobre la salud, en cuanto a facilitar el análisis del nivel de la magnitud del costo de la hipertensión y la diabetes mellitus en el Caribe. Será necesario un fuerte compromiso por parte de los gobiernos del CARICOM para abordar estos problemas, si se ha de emprender evaluaciones económicas con mayor frecuencia, como parte del esfuerzo por reducir la morbilidad y la mortalidad por estas enfermedades.