Impact of socio-demographic factors, lifestyle and health status on nutritional status among the elderly in Taiwan.

BACKGROUND/OBJECTIVES: Aging is an imperative problem for many countries in this century, and presents several challenges for the maintenance of good nutritional status. This study aims to assess the impact of socio-demographic factors, lifestyle and health status on the nutritional status among the elderly in Taiwan. SUBJECTS/METHODS: A cross-sectional study was carried out in Taiwan. Data were obtained from the Mei Jau Health Management Institution, which is a private health evaluation provider with multiple health screening centers in Taiwan and Asia. This study included 7947 adults aged 65 years or above. The data were extracted between 2001 to 2010. Nutritional status was assessed using anthropometric data, biochemical data and dietary intake information. RESULTS: Among the 7947 participants with mean age of 70.1 (SD = 4.5) years, 20.2%, 6.6%, 10.5% and 52.5% experienced underweight, protein malnutrition, anemia and inadequate dietary intake in the past month, respectively. Age was negatively correlated with body weight (r = -0.19, P = 0.02), body mass index (r = -0.41, P < 0.001), albumin level (r = -0.93, P < 0.001) and hemoglobin level (r = -0.30, P = 0.008). Age above 70 years, gender, unmarried status, retirement, lack of education, low family income, smoking, alcohol drinking, sleep duration of 6-8 hours, vegetarian diet, multiple medications, comorbidity and dysphagia were positively associated with malnutrition in older adults. CONCLUSIONS: Underweight and inadequate dietary intake are prevalent among the elderly in Taiwan. Vegetarian diet, multiple medications, comorbidity, dysphagia and lifestyle factors such as smoking, alcohol drinking and sleep duration of 6-8 hours are risk factors for undernutrition in older adults.

A Cloud Based Potentially Inappropriate Medication Management System Using Patient Owned Personal Health Records.

Taiwan has been confronted with a serious problem of aging in recent years. The prevalence of the chronic diseases caused by aging is increased continuously, which has led to a high percentage of comorbidity and polypharmacy. The proportion of the elderly people with polypharmacy (over three to five kinds of drugs) is 81%. Under the situation of high comorbidity, the potentially inappropriate drug for the elderly have become a series problem. However, in order to promote personal health management, Taiwan's Ministry of Health and Welfare has released a service of "My Health Bank", which contains all the personal medical information issued by the National Health Insurance Department and can be downloaded by any individual person. This study designs a cloud-based personal health management platform to parse and store the information of "My Health Bank", establishes two databases, one for the health insurance drug table and one for the inappropriate medications. A warning of inappropriate personal medication will be generated based on a checking process. We expect that the application will enhance the safety of medication and improve the self-health management of the elderly.

Development of a web-based liver cancer prediction model for type II diabetes patients by using an artificial neural network.

BACKGROUND: Diabetes mellitus is associated with an increased risk of liver cancer, and these two diseases are among the most common and important causes of morbidity and mortality in Taiwan. PURPOSE: To use data mining techniques to develop a model for predicting the development of liver cancer within 6 years of diagnosis with type II diabetes. METHODS: Data were obtained from the National Health Insurance Research Database (NHIRD) of Taiwan, which covers approximately 22 million people. In this study, we selected patients who were newly diagnosed with type II diabetes during the 2000-2003 periods, with no prior cancer diagnosis. We then used encrypted personal ID to perform data linkage with the cancer registry database to identify whether these patients were diagnosed with liver cancer. Finally, we identified 2060 cases and assigned them to a case group (patients diagnosed with liver cancer after diabetes) and a control group (patients with diabetes but no liver cancer). The risk factors were identified from the literature review and physicians' suggestion, then, chi-square test was conducted on each independent variable (or potential risk factor) for a comparison between patients with liver cancer and those without, those found to be significant were selected as the factors. We subsequently performed data training and testing to construct artificial neural network (ANN) and logistic regression (LR) prediction models. The dataset was randomly divided into 2 groups: a training group and a test group. The training group consisted of 1442 cases (70% of the entire dataset), and the prediction model was developed on the basis of the training group. The remaining 30% (618 cases) were assigned to the test group for model validation. RESULTS: The following 10 variables were used to develop the ANN and LR models: sex, age, alcoholic cirrhosis, nonalcoholic cirrhosis, alcoholic hepatitis, viral hepatitis, other types of chronic hepatitis, alcoholic fatty liver disease, other types of fatty liver disease, and hyperlipidemia. The performance of the ANN was superior to that of LR, according to the sensitivity (0.757), specificity (0.755), and the area under the receiver operating characteristic curve (0.873). After developing the optimal prediction model, we base on this model to construct a web-based application system for liver cancer prediction, which can provide support to physicians during consults with diabetes patients. CONCLUSION: In the original dataset (n=2060), 33% of diabetes patients were diagnosed with liver cancer (n=515). After using 70% of the original data to training the model and other 30% for testing, the sensitivity and specificity of our model were 0.757 and 0.755, respectively; this means that 75.7% of diabetes patients can be predicted correctly to receive a future liver cancer diagnosis, and 75.5% can be predicted correctly to not be diagnosed with liver cancer. These results reveal that this model can be used as effective predictors of liver cancer for diabetes patients, after discussion with physicians; they also agreed that model can assist physicians to advise potential liver cancer patients and also helpful to decrease the future cost incurred upon cancer treatment.