Te-Wei Ho

Disease-Free Survival after Hepatic Resection in Hepatocellular Carcinoma Patients: A Prediction Approach Using Artificial Neural Network

Background A database for hepatocellular carcinoma (HCC) patients who had received hepatic resection was used to develop prediction models for 1-, 3- and 5-year disease-free survival based on a set of clinical parameters for this patient group. Methods The three prediction models included an artificial neural network (ANN) model, a logistic regression (LR) model, and a decision tree (DT) model. Data for 427, 354 and 297 HCC patients with histories of 1-, 3- and 5-year disease-free survival after hepatic resection, respectively, were extracted from the HCC patient database. From each of the three groups, 80% of the cases (342, 283 and 238 cases of 1-, 3- and 5-year disease-free survival, respectively) were selected to provide training data for the prediction models. The remaining 20% of cases in each group (85, 71 and 59 cases in the three respective groups) were assigned to validation groups for performance comparisons of the three models. Area under receiver operating characteristics curve (AUROC) was used as the performance index for evaluating the three models. Conclusions The ANN model outperformed the LR and DT models in terms of prediction accuracy. This study demonstrated the feasibility of using ANNs in medical decision support systems for predicting disease-free survival based on clinical databases in HCC patients who have received hepatic resection.

In-hospital and one-year mortality and their predictors in patients hospitalized for first-ever chronic obstructive pulmonary disease exacerbations: a nationwide population-based study.

Introduction Natural history of chronic obstructive pulmonary disease (COPD) is punctuated by exacerbations; however, little is known about prognosis of the first-ever COPD exacerbation and variables predicting its outcomes. Materials and Methods A population-based cohort study among COPD patients with their first-ever exacerbations requiring hospitalizations was conducted. Main outcomes were in-hospital mortality and one-year mortality after discharge. Demographics, comorbidities, medications and in-hospital events were obtained to explore outcome predictors. Results The cohort comprised 4204 hospitalized COPD patients, of whom 175 (4%) died during the hospitalization. In-hospital mortality was related to higher age (odds ratio [OR]: 1.05 per year; 95% confidence interval [CI]: 1.03–1.06) and Charlson comorbidity index score (OR: 1.08 per point; 95% CI: 1.01–1.15); angiotensin II receptor blockers (OR: 0.61; 95% CI: 0.38–0.98) and β blockers (OR: 0.63; 95% CI: 0.41–0.95) conferred a survival benefit. At one year after discharge, 22% (871/4029) of hospital survivors were dead. On multivariate Cox regression analysis, age and Charlson comorbidity index remained independent predictors of one-year mortality. Longer hospital stay (hazard ratio [HR] 1.01 per day; 95% CI: 1.01–1.01) and ICU admission (HR: 1.33; 95% CI: 1.03–1.73) during the hospitalization were associated with higher mortality risks. Prescription of β blockers (HR: 0.79; 95% CI: 0.67–0.93) and statins (HR: 0.66; 95% CI: 0.47–0.91) on hospital discharge were protective against one-year mortality. Conclusions Even the first-ever severe COPD exacerbation signifies poor prognosis in COPD patients. Comorbidities play a crucial role in determining outcomes and should be carefully assessed. Angiotensin II receptor blockers, β blockers and statins may, in theory, have dual cardiopulmonary protective properties and probably alter prognosis of COPD patients. Nevertheless, the limitations inherent to a claims database study, such as the diagnostic accuracy of COPD and its exacerbation, should be born in mind.

Effectiveness of Telemonitoring in Patients with Chronic Obstructive Pulmonary Disease in Taiwan-A Randomized Controlled Trial

Chronic obstructive pulmonary disease (COPD) is the leading cause of death worldwide, and poses a substantial economic and social burden. Telemonitoring has been proposed as a solution to this growing problem, but its impact on patient outcome is equivocal. This randomized controlled trial aimed to investigate effectiveness of telemonitoring in improving COPD patient outcome. In total, 106 subjects were randomly assigned to the telemonitoring (n = 53) or usual care (n = 53) group. During the two months following discharge, telemonitoring group patients had to report their symptoms daily using an electronic diary. The primary outcome measure was time to first re-admission for COPD exacerbation within six months of discharge. During the follow-up period, time to first re-admission for COPD exacerbation was significantly increased in the telemonitoring group than in the usual care group (p = 0.026). Telemonitoring was also associated with a reduced number of all-cause re-admissions (0.23 vs. 0.68/patient; p = 0.002) and emergency room visits (0.36 vs. 0.91/patient; p = 0.006). In conclusion, telemonitoring intervention was associated with improved outcomes among COPD patients admitted for exacerbation in a country characterized by a small territory and high accessibility to medical services. The findings are encouraging and add further support to implementation of telemonitoring as part of COPD care.

Mortality predicted accuracy for hepatocellular carcinoma patients with hepatic resection using artificial neural network.

The aim of this present study is firstly to compare significant predictors of mortality for hepatocellular carcinoma (HCC) patients undergoing resection between artificial neural network (ANN) and logistic regression (LR) models and secondly to evaluate the predictive accuracy of ANN and LR in different survival year estimation models. We constructed a prognostic model for 434 patients with 21 potential input variables by Cox regression model. Model performance was measured by numbers of significant predictors and predictive accuracy. The results indicated that ANN had double to triple numbers of significant predictors at 1-, 3-, and 5-year survival models as compared with LR models. Scores of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) of 1-, 3-, and 5-year survival estimation models using ANN were superior to those of LR in all the training sets and most of the validation sets. The study demonstrated that ANN not only had a great number of predictors of mortality variables but also provided accurate prediction, as compared with conventional methods. It is suggested that physicians consider using data mining methods as supplemental tools for clinical decision-making and prognostic evaluation.

A Telesurveillance System With Automatic Electrocardiogram Interpretation Based on Support Vector Machine and Rule-Based Processing

Background Telehealth care is a global trend affecting clinical practice around the world. To mitigate the workload of health professionals and provide ubiquitous health care, a comprehensive surveillance system with value-added services based on information technologies must be established. Objective We conducted this study to describe our proposed telesurveillance system designed for monitoring and classifying electrocardiogram (ECG) signals and to evaluate the performance of ECG classification. Methods We established a telesurveillance system with an automatic ECG interpretation mechanism. The system included: (1) automatic ECG signal transmission via telecommunication, (2) ECG signal processing, including noise elimination, peak estimation, and feature extraction, (3) automatic ECG interpretation based on the support vector machine (SVM) classifier and rule-based processing, and (4) display of ECG signals and their analyzed results. We analyzed 213,420 ECG signals that were diagnosed by cardiologists as the gold standard to verify the classification performance. Results In the clinical ECG database from the Telehealth Center of the National Taiwan University Hospital (NTUH), the experimental results showed that the ECG classifier yielded a specificity value of 96.66% for normal rhythm detection, a sensitivity value of 98.50% for disease recognition, and an accuracy value of 81.17% for noise detection. For the detection performance of specific diseases, the recognition model mainly generated sensitivity values of 92.70% for atrial fibrillation, 89.10% for pacemaker rhythm, 88.60% for atrial premature contraction, 72.98% for T-wave inversion, 62.21% for atrial flutter, and 62.57% for first-degree atrioventricular block. Conclusions Through connected telehealth care devices, the telesurveillance system, and the automatic ECG interpretation system, this mechanism was intentionally designed for continuous decision-making support and is reliable enough to reduce the need for face-to-face diagnosis. With this value-added service, the system could widely assist physicians and other health professionals with decision making in clinical practice. The system will be very helpful for the patient who suffers from cardiac disease, but for whom it is inconvenient to go to the hospital very often.

Diabetes mellitus in patients with chronic obstructive pulmonary disease-The impact on mortality

Background Chronic obstructive pulmonary disease (COPD) is the leading cause of morbidity and mortality worldwide. There is evidence to support a connection between COPD and diabetes mellitus (DM), another common medical disorder. However, additional research is required to improve our knowledge of these relationships and their possible implications. In this study, we investigated the impact of DM on patient outcomes through the clinical course of COPD. Methods We conducted a cohort study in patients from the Taiwan Longitudinal Health Insurance Database between 2000 and 2013. Patients with COPD were identified and assessed for pre-existing and incident DM. A Cox proportional hazards model was built to identify factors associated with incident DM and to explore the prognostic effects of DM on COPD patients. A propensity score method was used to match COPD patients with incident DM to controls without incident DM. Results Pre-existing DM was present in 332 (16%) of 2015 COPD patients who had a significantly higher hazard ratio (HR) [1.244, 95% confidence interval (CI) 1.010–1.532] for mortality than that of the COPD patients without pre-existing DM. During the 10-year follow-up period, 304 (19%) of 1568 COPD patients developed incident DM; comorbid hypertension (HR, 1.810; 95% CI, 1.363–2.403), cerebrovascular disease (HR, 1.517; 95% CI, 1.146–2.008) and coronary artery disease (HR, 1.408; 95% CI 1.089–1.820) were significant factors associated with incident DM. Survival was worse for the COPD patients with incident DM than for the matched controls without incident DM (Log-rank, p = 0.027). Conclusions DM, either pre-existing or incident, was associated with worse outcomes in COPD patients. Targeted surveillance and management of DM may be important in clinical care of the COPD population.

Smart computing mechanism for noise detection and elimination in ECG signal

The cardiovascular disease is one of the most common causes of death around the world. The analysis of electrocardiograms (ECGs) is an important tool in early diagnosis of arrhythmias. However, sometime the measurement data would be corrupted by noises which may cause by the wrong equipment operation, poor contact of the electrode, or even the breath of the users. These noises would make cardiologists or automatic detection system hard to make a correct diagnosis. Therefore, the noise detection and elimination of ECG data become an important issue. In this study, we proposed a detection and elimination mechanism for the five types of noise. Besides, if the segment does not have any important information and cannot be repaired, we will eliminate it and combine the remaining usable segments into a pure signal for ECG enhancement. The experimental results showed that the noise recognition classifier yielded 0.956 area under the ROC curve, 84.4% accuracy, 97.8% sensitivity, and 80.5% specificity, respectively. The accuracy of disease detection system also could be improved by using the combination of usable segments. Hence, we believed this smart computing mechanism could address ECG enhancement and interpret a contaminated ECG signal more accurately.

A Service Oriented Tele-health Promotion Information System with Mobile Application☆

Abstract Obesity has become an important health issue in Taiwan due to its increasing prevalence among population and the patients are getting younger. In this research, we build a health care information system, named the Pauian Health, for people who were on diet and to control their weight, or others to keep in shape. The Pauian Health is designed based on model–view–controller (MVC) pattern with a proposed architecture framework and has been successfully implemented in Pauian Archiland Company. The architecture centralizes the functions of accessing databases, user identification, and the validation of inherited clinical knowledge in a single component. Under this architecture, the system ensures its scalability, extensibility, data consistency, and the ability of cross-platform. This architecture has also been implemented in different devices and platforms, including iPhone, iPad and website. The architecture also supports unstable network environment, which uses Token as session identifier and user validation. The proposed framework has the potential in duplicating the service for different targeted users or deployed as a cloud service, which is fully capable in extending the service in the future.

Validity of ICD9-CM codes to diagnose chronic obstructive pulmonary disease from National Health Insurance claim data in Taiwan

Purpose Claim data from Taiwan’s National Health Insurance (NHI) database have previously been utilized in the study of COPD. However, there are limited data on the positive predictive value of claim data for COPD diagnosis. Therefore, this study aimed to characterize and validate the COPD cohort identified from the NHI research database. Methods This cross-sectional study compared records from claim data with those from a medical center. From 2007 to 2014, a COPD cohort was constructed from claim data using ICD9-CM codes for COPD. The diagnostic positive predictive value of these data was assessed with reference to physician-verified COPD. In addition, a multivariate logistic regression model was built to identify independent factors associated with the positive predictive value of COPD diagnosis by claim data. Results During the 8-year study period, a total of 12,127 subjects met the criterion of having two or more outpatient codes in 1 year or one or more inpatient COPD codes in their claim data. Of this total, the diagnosis of COPD was verified by physicians in 7,701 (63.5%) subjects. Applying a more stringent criterion – three or more outpatient codes or two or more inpatient codes – improved the diagnostic positive predictive value to 72.2%. Age ≥65 years and a claim for spirometry were the two most important factors associated with the positive predictive value of claim-data-defined COPD. Adding spirometry testing to diagnostic ICD9-CM codes for COPD increased the positive predictive value to 84.6%. Conclusion This study emphasizes the importance of validation of disease-specific diagnosis prior to applying an administrative database in clinical studies. It also indicates the limitation of ICD9-CM codes alone in recognizing COPD patients within the NHI research database.

Compliance with clinical guidelines for chronic obstructive pulmonary disease: a nationwide database study

Every disease has its own characteristics, so different clinical guidelines are used to recommend the appropriate treatment or take care of patients. Clinical guidelines can not only help medical staff in their work, but also improve a patients prognosis and quality of healthcare, and reduce the medical cost. In order to provide an accurate assessment and evidence-based procedure, the Global initiative for chronic Obstructive Lung Disease (GOLD) published clinical guidelines for Chronic Obstructive Pulmonary Disease (COPD) in 2001. Taiwans National Health Insurance Research Database (NHIRD) is one of the largest e-Health databases around the world. The aim of this study was to evaluate the secular trend for guideline compliance in Taiwan and assess the influence of hospital levels and clinician speciality on it by using a Taiwanese eHealth database. Generally, the database is a good content source for compliance checking. The compliance of GOLD diagnoses and assessment guidelines in Taiwan has been increasing year by year. A wide variation in the procedure usage rate is statistically significant among different levels of hospitals and clinician specialties. Hence, we are very pleased to see the improvement of clinical guideline compliance in Taiwan in recent years. However, we still should make more effort to improve guideline compliance in the future in order to provide better medical quality for patients.