Development of the Joint Commission of Taiwan's Smart Healthcare Standard.

It is well known that information technology (IT) can play a pivotal role in enhancing healthcare quality and patient safety. The use of computational science to enhance the capabilities of hospital information systems helps deliver enhanced healthcare quality. "Smart healthcare" has become a popular term, reflecting the level of IT involvement in healthcare services. However, each hospital has a different level of IT development, and no clear definition of smart healthcare exists. In this study, we aimed to develop and validate a survey standard to evaluate the level of IT involvement in hospitals. The quality improvement task force of the Joint Commission of Taiwan (QITF-JCT) conducted a systematic literature review to identify the key elements of major healthcare IT functions. The modified Delphi technique was used to review the importance and appropriateness of these elements through an expert panel, and the JCT Smart Healthcare Standard version 1.0 (JCT-SHS 1.0) was drafted. A total of 40 healthcare quality improvement campaign (HQIC) application projects in 2018 were selected for evaluating nine key dimensions of hospital functions: security, digitization, automation, interconnection, connectivity, interoperability, mobility, computation, and artificial intelligence. The standard can be used smart hospital evaluation and executed by two experts by on-site evaluation and rating as three-level scale (norm, excellent, and innovative). The internal consistency and inter-rater reliability were investigated using Cronbach's α and kappa statistics, respectively. This standard was evaluated by using 40 HQIC application projects. The Cronbach's α values were in the range of 0.74-0.92, indicating the good internal consistency of the JCT-SHS 1.0 among the nine IT dimensions. The kappa correlation coefficients were 0.68 for security (p = 0.027), 0.47 for digitization (p = 0.042), 0.21 for automation (p = 0.048), 0.82 for interconnection (p = 0.014), 0.35 for connectivity (p = 0.036), 0.28 for interoperability (p = 0.042), 0.71 for mobility (p = 0.016), 0.47 for computation (p = 0.029), and 0.34 for artificial intelligence (p = 0.033), revealing moderate inter-rater reliability. The validation data indicated that the JCT-SHS 1.0 is a consistent and reliable instrument for evaluating the levels of IT development in the hospitals. Healthcare providers, external accreditation bodies, and policymakers may use the JCT-SHS 1.0 to assess and plan their organizational and system-wise IT strategy.

Comparing two methods for deriving dietary patterns associated with risk of metabolic syndrome among middle-aged and elderly Taiwanese adults with impaired kidney function.

BACKGROUND: Dietary patterns were associated with the risk of chronic disease development and outcome-related diseases. In this study, we aimed to compare the correlation between dietary patterns and metabolic syndrome (MetS) using two methods for identifying dietary patterns. METHODS: The participants (n = 25,569) aged ≥40 years with impaired kidney function were retrieved from Mei Jau (MJ) Health Screening database from 2008 to 2010. Dietary patterns were identified by principal component analysis (PCA) and reduced rank regression (RRR) from twenty-two food groups using PROC FACTOR and PROC PLS functions. RESULTS: We identified two similar dietary pattern characteristics (high intakes of deep fried foods, preserved or processed foods, dipping sauce, meat, sugary drinks, organ meats, jam/honey, fried rice/flour products, instant noodles and eggs) derived by PCA and RRR. Logistic regression analysis revealed that RRR-derived dietary pattern scores were positively associated with an odds ratio (OR = 1.70, 95% CI: 1.56, 1.86) of having MetS than PCA-derived dietary pattern scores (OR = 1.38, 95% CI: 1.27, 1.51). The correlations between RRR-derived dietary pattern scores and elevated systolic and diastolic blood pressure (OR = 1.30 for both) or low high density lipoprotein cholesterol in women (OR = 1.32) were statistically significant but not significant in PCA-derived dietary pattern scores. CONCLUSIONS: Our findings suggest that RRR gives better results when studying behavior related dietary patterns in association with MetS. RRR may be more preferable to provide dietary information for developing dietary guidelines among people with MetS. Further studies with prospective measurements are needed to verify whether RRR is a useful analytic tool for the association between dietary patterns and other chronic diseases.

Dietary patterns in relation to testosterone levels and severity of impaired kidney function among middle-aged and elderly men in Taiwan: a cross-sectional study.

BACKGROUND: Chronic Kidney Disease (CKD), characterized by an impaired kidney function, is associated with low testosterone levels. This study investigated the association between dietary patterns, testosterone levels, and severity of impaired kidney function among middle-aged and elderly men. METHODS: This cross-sectional study used the database from a private health-screening institute in Taiwan between 2008 and 2010. Men aged 40 years old and older (n = 21,376) with estimated glomerular filtration rate (eGFR) < 90 mL/min/1.73 m2 and proteinuria were selected. Among 21,376 men, 256 men had available measurements of testosterone levels. Dietary assessment was conducted using a food frequency questionnaire and three dietary patterns (fried-processed, vege-seafood, and dairy-grain dietary patterns) were identified using principal component analysis. RESULTS: Men in the lower tertiles (T1 and T2) of eGFR had significantly decreased testosterone levels by 0.8 (95% CI: - 1.40, - 0.20) and 0.9 nmol/L (95% CI: - 1.43, - 0.33). Furthermore, serum triglycerides (TG) levels were inversely associated with testosterone levels (ß = - 0.51, 95% CI: - 0.77, - 0.24). Men in the higher tertile of fried-processed dietary pattern scores were associated with decreased testosterone levels by 0.8 nmol/L (95% CI: - 1.40, - 0.16), reduced testosterone-to-TG (T/TG) ratio by 1.8 units (95% CI: - 2.99, - 0.53), and increased risk of moderate/severe impaired kidney function (eGFR < 60 mL/min/1.73 m2) and proteinuria severity by 1.35 (95% CI: 1.15, 1.58) and 1.18 (95% CI: 1.02, 1.37) times respectively. In contrast, the vege-seafood dietary pattern was negatively associated with severity of impaired kidney function and proteinuria after multivariable adjustment, but had no association with testosterone levels and T/TG ratio. CONCLUSIONS: The fried-processed dietary pattern is negatively associated with testosterone levels but positively associated with the severity of impaired kidney function. However, the vege-seafood and dairy-grain dietary patterns appear to have beneficial effects.

Association of kidney function-related dietary pattern, weight status, and cardiovascular risk factors with severity of impaired kidney function in middle-aged and older adults with chronic kidney disease: a cross-sectional population study.

BACKGROUND: Chronic Kidney Disease (CKD), characterized by impaired kidney function, affects over 1.5 million individuals in Taiwan. Cardiovascular disease (CVD) is commonly found in patients with CKD, and the increased prevalence of obesity can have some implications for the risk of both CKD and CVD. Since diet plays an important role in the development of obesity, CVD and CKD, our study was designed to investigate the association of kidney function-related dietary pattern with weight status, cardiovascular risk factors, and the severity of impaired kidney function in middle-aged and older adults in Taiwan. METHODS: A total of 41,128 participants aged 40 to 95 years old with an estimated glomerular filtration rate (eGFR) less than 90 mL/min/1.73 m2 and proteinuria were recruited from Mei Jau Health Institute between 2008 and 2010. The kidney function-related dietary pattern was identified using reduced rank regression (RRR) and was known as high consumption of preserved or processed food, meat, organ meats, rice/flour products, and, low consumption of fruit, dark-colored vegetables, bread, and beans. A multivariable logistic regression analysis was used to identify the association of weight status and cardiovascular risk factors with moderately/severely impaired kidney function (eGFR < 60 mL/min/1.73 m2) and the association of dietary pattern with the outcomes aforementioned. RESULTS: Moderately/severely impaired kidney function participants were heavier and had higher abnormality of cardiovascular risk factors compared with those with mildly impaired kidney function. Weight status (OR = 1.28, 95% CI 1.12-1.45, P <  0.001 for obesity) and cardiovascular risk factors (OR = 1.52, 95% CI 1.31-1.77, P <  0.001 for high total cholesterol/HDL-C ratio and OR = 1.56, 95% CI 1.41-1.72, P <  0.001 for hypercalcemia) were positively associated with increased risk of moderately/severely impaired kidney function. The kidney function-related dietary pattern was correlated with overweight or obese (OR = 2.07, 95% CI 1.89-2.27, P <  0.01) weight status, increased cardiovascular risk by 10-31%, and the risk of moderately/severely impaired kidney function (OR = 1.15, 95% CI 1.02-1.29, P <  0.05). CONCLUSIONS: The RRR-derived kidney function-related dietary pattern, characterized by high intake of processed and animal foods and low intake of plant foods, predicts the risks for developing cardiovascular disease and moderately/severely impaired kidney function among middle-aged and older adults.

Association of dietary patterns, anthropometric measurements, and metabolic parameters with C-reactive protein and neutrophil-to-lymphocyte ratio in middle-aged and older adults with metabolic syndrome in Taiwan: a cross-sectional study.

BACKGROUND: Metabolic syndrome is commonly associated with inflammation. The underlying factors of inflammation in metabolic syndrome are not fully understood. The objective of the study was to determine the association of dietary patterns, anthropometric measurements, and metabolic parameters with inflammatory markers in middle-aged and older adults with metabolic syndrome in Taiwan. METHODS: A total of 26,016 subjects aged ≥35 y with metabolic syndrome were recruited from Mei Jau institution between 2004 and 2013 for a cross sectional study. Metabolic syndrome was defined by the International Diabetes Federation. Multivariate logistic regression was performed to evaluate the association of dietary patterns, anthropometric measurements, and metabolic parameters with C-reactive protein (CRP) and neutrophil-to-lymphocyte ratio (NLR) in men and women with metabolic syndrome. Crude and adjusted models were analyzed by gender. RESULTS: The western dietary pattern, obesity, high body fat, high waist or hip circumference, and high waist-to-hip ratio were significantly associated with increased odds ratios of high CRP and NLR in both genders. High systolic or diastolic blood pressure (BP), low high-density lipoprotein-cholesterol (HDL-C), high low-density lipoprotein-cholesterol (LDL-C), high total cholesterol (TC), high serum triglycerides (TG), and high fasting blood glucose (FBG) were significantly correlated with increased odds ratios of high CRP in both genders. Low HDL-C, high LDL-C, high serum TG, and high FBG were significantly associated with increased odds ratios of high NLR in both genders. However, high systolic (OR = 1.124, 95% CI 1.047-1.206, P < 0.01) or diastolic BP (OR = 1.176, 95% CI 1.087-1.273, P < 0.001) and high TC (OR = 1.138, 95% CI 1.062-1.220, P < 0.001) were significantly correlated with increased odds ratios of high NLR only in men. CONCLUSIONS: The western dietary pattern, obese-related anthropometric parameters, and most components of metabolic syndrome are positively associated with CRP levels and NLR in men and women with metabolic syndrome.

Dietary patterns, gender, and weight status among middle-aged and older adults in Taiwan: a cross-sectional study.

BACKGROUND: Diet has been associated with differences in weight and nutritional status of an individual. The prevalence of overweight and obesity increased among adults in Taiwan. Hence, we examined the relationship between dietary patterns and weight status by gender among middle-aged and older adults in Taiwan. METHODS: The cross-sectional data of 62,965 participants aged ≥40 years were retrieved from the Mei Jau health screening institutions' database collected from 2001 and 2010. Diet information was evaluated using a food frequency questionnaire, while the dietary patterns were derived using principal component analysis before summing up and dividing into quintiles of consumption. The association between dietary patterns and weight status among adult men and women was explored using multinomial logistic regression models. Three models were analyzed before stratifying data by gender. RESULTS: Two dietary patterns were derived with one reflecting a high consumption of vegetables and fruits (vegetable-fruit dietary pattern) and the other a high consumption of meat and processed foods (meat-processed dietary pattern). After adjustment, highest consumption of vegetables and fruits (Q5) reduced the likelihood of being overweight (OR = 0.91; 95% CI, 0.85-0.97) or obese (OR = 0.85; 95% CI, 0.78-0.92), while highest consumption of meat and processed foods increased the likelihood of being overweight (OR = 1.50; 95% CI, 1.40-1.59) or obese (OR = 1.94; 95% CI, 1.79-2.10). Women were less likely to be overweight or obese with the highest intake of fruits and vegetables (Q5) while both genders were more likely to be overweight or obese with high consumption of meat and processed foods. CONCLUSIONS: High intake of vegetables and fruits is associated with lower odds of being overweight or obese, especially among women. But, high intake of meat and processed foods is associated with higher odds of overweight and obesity in both genders.

Importance-Performance Analysis of Personal Health Records in Taiwan: A Web-Based Survey.

BACKGROUND: Empowering personal health records (PHRs) provides basic human right, awareness, and intention for health promotion. As health care delivery changes toward patient-centered services, PHRs become an indispensable platform for consumers and providers. Recently, the government introduced "My health bank," a Web-based electronic medical records (EMRs) repository for consumers. However, it is not yet a PHR. To date, we do not have a platform that can let patients manage their own PHR. OBJECTIVE: This study creates a vision of a value-added platform for personal health data analysis and manages their health record based on the contents of the "My health bank." This study aimed to examine consumer expectation regarding PHR, using the importance-performance analysis. The purpose of this study was to explore consumer perception regarding this type of a platform: it would try to identify the key success factors and important aspects by using the importance-performance analysis, and give some suggestions for future development based on it. METHODS: This is a cross-sectional study conducted in Taiwan. Web-based invitation to participate in this study was distributed through Facebook. Respondents were asked to watch an introductory movie regarding PHR before filling in the questionnaire. The questionnaire was focused on 2 aspects, including (1) system functions, and (2) system design and security and privacy. The questionnaire would employ 12 and 7 questions respectively. The questionnaire was designed following 5-points Likert scale ranging from 1 ("disagree strongly") to 5 ("Agree strongly"). Afterwards, the questionnaire data was sorted using IBM SPSS Statistics 21 for descriptive statistics and the importance-performance analysis. RESULTS: This research received 350 valid questionnaires. Most respondents were female (219 of 350 participants, 62.6%), 21-30 years old (238 of 350 participants, 68.0%), with a university degree (228 of 350 participants, 65.1%). They were still students (195 out of 350 participants, 56.6%), with a monthly income of less than NT $30,000 (230 of 350 participants, 65.7%), and living in the North Taiwan (236 of 350 participants, 67.4%), with a good self-identified health status (171 of 350 participants, 48.9%). After performing the importance-performance analysis, we found the following: (1) instead of complex functions, people just want to have a platform that can let them integrate and manage their medical visit, health examination, and life behavior records; (2) they do not care whether their PHR is shared with others; and (3) most of the participants think the system security design is not important, but they also do not feel satisfied with the current security design. CONCLUSIONS: Overall, the issues receiving the most user attention were the system functions, circulation, integrity, ease of use, and continuity of the PHRs, data security, and privacy protection.

Metadata Correction: Importance-Performance Analysis of Personal Health Records in Taiwan: A Web-Based Survey.

[This corrects the article DOI: .].

Association between Dietary Patterns and Kidney Function Parameters in Adults with Metabolic Syndrome: A Cross-Sectional Study.

This study explored the association between dietary patterns and kidney function parameters in adults with metabolic syndrome in Taiwan. This cross-sectional study was undertaken in 56,476 adults from the health screening centers in Taiwan from 2001 to 2010. Dietary intake and dietary patterns were assessed using a food frequency questionnaire and principal component analysis, respectively. Blood urea nitrogen (BUN), creatinine, estimated glomerular filtration rate (eGFR), and uric acid were measured as clinical parameters of kidney function. Multivariate linear regression was conducted to explore the relationship between dietary patterns and kidney function parameters. After adjusting for confounders, the highest tertiles of the processed food-sweets dietary pattern and the meat-seafood-eggs dietary pattern were associated with increased BUN, creatinine, and uric acid but decreased eGFR (all adjusted p < 0.05). Meanwhile, the highest tertiles of the veggie-fruit-grains dietary pattern and the milk-dairy dietary pattern were associated with decreased BUN, creatinine, and uric acid but increased eGFR (all adjusted p < 0.05). A processed food-sweets dietary pattern or a meat-seafood-eggs dietary pattern is associated with worse kidney function parameters in adults with metabolic syndrome. In contrast, a veggie-fruit-grains dietary pattern or a milk-dairy dietary pattern is associated with better kidney function parameters.

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.

Association of Sleep Duration and Insomnia Symptoms with Components of Metabolic Syndrome and Inflammation in Middle-Aged and Older Adults with Metabolic Syndrome in Taiwan.

The study determined the association of sleep duration and insomnia symptoms with the components of metabolic syndrome and inflammation in middle-aged and older adults with metabolic syndrome in Taiwan. This cross-sectional study used the database compiled in Taiwan between 2004-2013. A total of 26,016 volunteers aged 35 years and above were selected. Metabolic syndrome was defined according to the International Diabetes Federation. Compared with regular sleep duration (6-8 h/day), short (<6 h/day) or long sleep duration (>8 h/day) and insomnia symptoms significantly increased the odds ratios of high waist circumference, high blood pressure, low high-density lipoprotein-cholesterol, high triglycerides, high fasting blood glucose, and high C-reactive protein. Insomnia symptoms did not modify the effects of sleep duration on the components of metabolic syndrome and inflammation. Our study suggests that short or long sleep duration and insomnia symptoms may have an adverse effect on metabolic syndrome and inflammation.

Inflammatory Dietary Pattern Predicts Dyslipidemia and Anemia in Middle-Aged and Older Taiwanese Adults with Declined Kidney Function: A Cross-Sectional Population Study from 2008 to 2010.

Dyslipidemia, anemia, and inflammation are associated with declined kidney function. This study investigated the association of inflammatory dietary pattern with dyslipidemia, anemia, and kidney function biomarkers among middle-aged and older Taiwanese adults with declined kidney function. Biochemical data and food frequency questionnaire were obtained from 41,128 participants with estimated glomerular filtration rate (eGFR) <90 mL/min/1.73 m2 and positive urinary protein. Inflammatory dietary pattern was identified by reduced rank regression with C-reactive protein (CRP) and neutrophil-to-lymphocyte ratio (N/L) as response variables. Males had higher prevalence of dyslipidemia and higher inflammatory markers, but lower prevalence of anemia and lower eGFR levels compared to females. Inflammatory dietary pattern characterized with low intakes of seafood, grains, vegetables, and fruits but high intakes of meat, eggs, preserved/processed foods, and sugary drinks was associated with an increased risk of dyslipidemia by 21% in males and an increased risk of anemia by 28-47% in both genders. Furthermore, high consumption of inflammatory dietary pattern was associated with reduced eGFR (males ß = -0.85, 95% CI -1.26 to -0.43, females ß = -0.53, 95% CI -0.98 to -0.08) and increased N/L and/or CRP in both genders. In conclusion, inflammatory dietary pattern is positively associated with dyslipidemia, anemia, and decreased kidney function in middle-aged and older adults with declined kidney function.

Association of Dietary Patterns with Components of Metabolic Syndrome and Inflammation among Middle-Aged and Older Adults with Metabolic Syndrome in Taiwan.

This study examined the correlation of dietary patterns with components of metabolic syndrome (MetS) and inflammation among middle-aged and older adults with MetS in Taiwan. This cross-sectional study used data from the Mei Jau International Health Management Institution in Taiwan between 2004 and 2013. A total of 26,016 subjects aged 35 years and above were selected for analysis. MetS was defined according to the International Diabetes Federation. Three dietary patterns were identified by principal component analysis. High intake of a meat-instant food dietary pattern (rich in animal protein, saturated fat, sweets, sodium, and food additives) was positively associated with components of MetS and C-reactive protein (CRP), while high intake of a vege-seafood dietary pattern (rich in dietary fiber, vitamins, minerals, and unsaturated fat) or a cereal-dairy dietary pattern (rich in dietary fiber, antioxidants, phytochemicals, complex carbohydrate, prebiotics, and probiotics) was inversely associated with components of MetS and CRP. Our findings suggested that intake of a vege-seafood dietary pattern or a cereal-dairy dietary pattern decreased the risk of developing MetS and inflammation among middle-aged and older adults with MetS.

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.

Association between Dietary Patterns and Cardiovascular Risk Factors among Middle-Aged and Elderly Adults in Taiwan: A Population-Based Study from 2003 to 2012.

BACKGROUND: Cardiovascular disease (CVD) is one of the leading causes of mortality and loss of disability-adjusted life years in developed countries. This study derived a dietary pattern using an a priori method and additionally derived dietary patterns using a posteriori methods, and assessed the relationship with CVD risk factors in Taiwanese middle-aged and elderly adults. METHODS: Cross-sectional analyses of 62,965 subjects aged 40 years and above from the Mei Jau (MJ) database collected between 2003 and 2012 in Taiwan. Diet was assessed using a 22 item semi-quantitative food frequency questionnaire. Using this information, three dietary patterns were generated. The a priori diet was labeled the Taiwanese dietary pattern and was derived using hypothesized effect of 22 food groups, while two a posteriori dietary patterns, "vegi-fruits" and "meat-processed", were derived using principal component analysis. The association between dietary patterns and a range of CVD risk factors (i.e. blood lipids, blood glucose and C-reactive protein) was evaluated using linear regression. RESULTS: The results showed that high intake (Q5, quintile 5) of Taiwanese diet was negatively associated with CVD risk factors at (p < 0.001, model 3), but not with triacylglycerol. In addition, high intake of vegi-fruit dietary pattern (Q5) was negatively associated with CVD risk factors (p < 0.001), but not with high-density lipoprotein, while high consumption of meat-processed dietary pattern (Q5) was positively associated with CVD risk factors (p < 0.001), but negatively related with triacylglycerol in Q3 level and no association with C-reactive protein. CONCLUSION: A negative association was observed between Taiwanese or vegi-fruit dietary patterns and CVD risk factors, while a positive association was found between meat-processed dietary pattern and CVD risk factors. The findings suggested that a diet rich in vegetables and fruits has a beneficial effect in the management of CVD risk factors.

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.

Effect of weather and time on trauma events determined using emergency medical service registry data.

INTRODUCTION: Trauma admissions are associated with weather and temporal factors; however, previous study results regarding these factors are contradictory. We hypothesised that weather and temporal factors have different effects on specific trauma events in an emergency medical service (EMS) system. METHODS: EMS data from January 1, 2009, to December 31, 2010, were obtained from the fire department of Taipei City and associated with the local weather data. EMS trauma events were categorised into total trauma, traffic accidents (TAs), motorbike accidents (MBAs), and falls. Hourly data on trauma patients were analysed using the zero-inflated Poisson model. RESULTS: The hourly incidence of total trauma increased with the magnitude of precipitation (incidence rate ratio [IRR]=1.06, 1.09, and 1.11 in light, moderate, and heavy rain, respectively), and this effect was more prominent in fall patients than in patients with other injuries (IRR=1.07, 1.21, and 1.32). However, the hourly incidence of TAs and MBAs was associated only with light rain (IRR=1.11 and 1.06, respectively). An hour of sunshine exposure was associated with an increase in the hourly incidence of all groups, and higher temperatures were associated with an increased hourly incidence of total trauma, TAs, and MBAs, but not falls. The hourly incidence of falls increased only in late fall and winter. Compared with the hourly incidence between 3 am and 7 am, the hourly incidence of all groups plateaued between 7 am and 11 pm and declined from 11 pm to 3 am. During the plateau period, 2 peaks in the incidence of TAs (IRR=5.03 and 5.07, respectively) and MBAs (IRR=5.81 and 5.51, respectively) were observed during 7-11 am and 3-7 pm. The hourly incidence of total trauma, TAs, and MBAs plateaued during workdays, peaked on Fridays, declined on Saturdays, and troughed on Sundays. The incidence of falls increased only on Mondays (IRR=1.09). CONCLUSIONS: Weather and temporal factors had different impacts on the incidence of traffic-related accidents and falls. Therefore, EMS data may have implications in preventing injuries and planning resource use for prehospital trauma rescue.