Artificial neural network-based analysis of the safety and efficacy of thrombolysis for ischemic stroke in older adults in Taiwan

@#Background: The risk and benefit of tissue plasminogen activator (tPA) for aged>80 years with acute ischemic stroke (AIS) are controversial. In this study, we investigated the safety and efficacy of tPA in this population and utilized the artificial neural network (ANN) to established outcome predictive models. Methods: We retrospectively reviewed the stroke registry data of patients with AIS, aged >80 years who arrived at the hospital within 3 hours from the onset of symptoms. The characteristics and the outcomes, presented as modified Rankin Scale (mRS), and mortality rate at 3 months between the tPA-treated and non-tPA groups were analyzed. An ANN algorithm was applied to establish predictive models. Results: A total of 80 patients aged>80 years with AIS were identified, and 49 of them received tPA. After adequate training, our ANN models accurately predicted the outcomes with the area under the receiver operating characteristic curves of 0.974, and a low error to predict the mRS score at 3 months. After applying our prediction model to those in the non-tPA group, we demonstrated the potential benefits in those patients if they had undergone tPA therapy. Conclusions: Our results show that ANN can be a potentially useful tool for predicting the treatment outcomes of tPA. Such novel machine learning-based models may help with therapeutic decision making in clinical settings.

Comparison of Models for the Prediction of Medical Costs of Spinal Fusion in Taiwan Diagnosis-Related Groups by Machine Learning Algorithms / 대한의료정보학회지

OBJECTIVES: The aims of this study were to compare the performance of machine learning methods for the prediction of the medical costs associated with spinal fusion in terms of profit or loss in Taiwan Diagnosis-Related Groups (Tw-DRGs) and to apply these methods to explore the important factors associated with the medical costs of spinal fusion. METHODS: A data set was obtained from a regional hospital in Taoyuan city in Taiwan, which contained data from 2010 to 2013 on patients of Tw-DRG49702 (posterior and other spinal fusion without complications or comorbidities). Naïve-Bayesian, support vector machines, logistic regression, C4.5 decision tree, and random forest methods were employed for prediction using WEKA 3.8.1. RESULTS: Five hundred thirty-two cases were categorized as belonging to the Tw-DRG49702 group. The mean medical cost was US $4,549.7, and the mean age of the patients was 62.4 years. The mean length of stay was 9.3 days. The length of stay was an important variable in terms of determining medical costs for patients undergoing spinal fusion. The random forest method had the best predictive performance in comparison to the other methods, achieving an accuracy of 84.30%, a sensitivity of 71.4%, a specificity of 92.2%, and an AUC of 0.904. CONCLUSIONS: Our study demonstrated that the random forest model can be employed to predict the medical costs of Tw-DRG49702, and could inform hospital strategy in terms of increasing the financial management efficiency of this operation.

Tamoxifen and the Risk of Parkinson's Disease in Female Patients with Breast Cancer in Asian People: A Nationwide Population-Based Study / 한국유방암학회지

PURPOSE: Whether tamoxifen affects the risk of neurodegenerative disease is controversial. This nationwide population-based study investigated the risk of Parkinson's disease (PD) associated with tamoxifen treatment in female patients with breast cancer using Taiwan's National Health Insurance Research Database. METHODS: A total of 5,185 and 5,592 female patients with breast cancer who did and did not, respectively, receive tamoxifen treatment between 2000 and 2009 were included in the study. Patients who subsequently developed PD were identified. A Cox proportional hazards model was used to compare the risk of PD between the aforementioned groups. RESULTS: Tamoxifen did not significantly increase the crude rate of developing PD in female patients with breast cancer (tamoxifen group, 16/5,169; non-tamoxifen group, 11/5,581; p=0.246). Tamoxifen did not significantly increase the adjusted hazard ratio (aHR) for subsequently developing PD (aHR, 1.310; 95% confidence interval [CI], 0.605–2.837; p=0.494). However, tamoxifen significantly increased the risk of PD among patients followed up for more than 6 years (aHR, 2.435; 95% CI, 1.008–5.882; p=0.048). CONCLUSION: Tamoxifen treatment may increase the risk of PD in Taiwanese female patients with breast cancer more than 6 years after the initiation of treatment.

A clinical trial of acupuncture for treating chronic fatigue syndrome in Hong Kong / 中西医结合学报

OBJECTIVE: To evaluate the efficacy of acupuncture in treating chronic fatigue syndrome (CFS) in Hong Kong. METHODS: A single-blinded, randomized controlled trial design was adopted. Participants meeting inclusion criteria were randomly assigned to a treatment and a control group according to 1:1 ratio, resulting in an effective sample size of 99, with 50 and 49 patients in treatment and control group respectively. The same set of acupuncture points, which were selected according to traditional Chinese medicine theories, was applied in both groups, while conventional needle acupuncture was applied in treatment group and sham acupuncture (without skin penetration) was applied in control group. Schedule of treatment was the same in both groups, i.e. twice a week for 4 weeks. Key outcome measures were Chalder's Fatigue Scale, diagnostic criteria for CFS of the US's Centre for Disease Control and SF-12 health-related quality of life (HQOL) questionnaire. Adverse events, if any, were recorded. RESULTS: Improvements in physical and mental fatigue and HQOL in both groups were observed, but the improvements in treatment group were significantly bigger than in control group (P<0.01 or P<0.05). No adverse events occurred. CONCLUSION: Acupuncture is a safe, effective treatment for CFS.