Explore the vast range of titles available.

Methadone maintenance treatment (MMT) can alleviate opioid dependence. However, MMT possibly increases the risk of motor vehicle collisions. The current study investigated preliminary estimation of motor vehicle collision incidence rates. Furthermore, in this population-based retrospective cohort study with frequency-matched controls, opiate adults receiving MMT (cases) and those not receiving MMT (controls) were identified at a 1:2 ratio by linking data from several nationwide administrative registry databases. From 2009 to 2016, the crude incidence rate of motor vehicle collisions was the lowest in the general adult population, followed by that in opiate adults, and it was the highest in adults receiving MMT. The incidence rates of motor vehicle collisions were significantly higher in opiate users receiving MMT than in those not receiving MMT. Kaplan–Meier curves of the incidence of motor vehicle collisions differed significantly between groups, with a significant increased risk during the first 90 days of follow-up. In conclusion, drivers receiving MMT have higher motor vehicle collision risk than those not receiving MMT in opiate users, and it is worthy of noticing road safety in such drivers, particularly during the first 90 days of MMT. In 2019, 58 million people were estimated to use opioids – a group of substances that include drugs like heroin and morphine. Dependence on opioids can be managed using a prescribed dose of an opioid called methadone, which is administered through a controlled treatment plan. This so-called methadone maintenance treatment manages withdrawal symptoms in opioid-dependent individuals and can reduce the occurrences of overdose, criminal activity and transmission of diseases such as HIV. However, methadone acts on the same brain receptors as other opioids, and individuals receiving methadone may experience impaired motoric and cognitive functioning, including reduced driving ability. It is therefore important to know whether methadone maintenance treatment may increase an individual’s risk to cause road accidents. To assess motor vehicle collision risk associated with individuals receiving methadone maintenance treatment, Yang et al. analysed data from the Taiwan National Health Insurance Research Database and six Taiwanese administrative registries, including the ministries of health and welfare, interior and justice, and registries in substitution maintenance therapy, road accidents and the National Police Agency. Initial analyses found that individuals receiving treatment had a higher risk to be involved in car accidents than the general adult population or those without methadone maintenance treatment. Further tests showed that individuals receiving treatment were at three times higher risk of collisions than individuals not receiving treatment, particularly in the first 90 days. These findings may help individuals undergoing methadone maintenance treatment manage their risk of motor vehicle collisions. Further investigation is needed to reveal the underlying mechanisms of methadone-related impairment of driving ability.

Chronic obstructive pulmonary disease (COPD) is a major health burden worldwide and in Taiwan, ranking as the third leading cause of death globally, and its prevalence in Taiwan continues to rise. Readmission within 14 days is a key indicator of disease instability and care efficiency, driven jointly by patient-level physiological vulnerability (such as reduced lung function and multiple comorbidities) and healthcare system-level deficiencies in transitional care. To mitigate the growing burden and improve quality of care, it is urgently necessary to develop an AI-based prediction model for 14-day readmission. Such a model could enable early identification of high-risk patients and trigger multidisciplinary interventions, such as pulmonary rehabilitation and remote monitoring, to effectively reduce avoidable early readmissions. However, medical data are commonly characterized by severe class imbalance, which limits the ability of conventional machine learning methods to identify minority-class cases. In this study, we used real-world clinical data from multiple hospitals in Kaohsiung City to construct a prediction framework that integrates data generation and ensemble learning to forecast readmission risk among patients with chronic obstructive pulmonary disease (COPD). CTGAN and kernel density estimation (KDE) were employed to augment the minority class, and the impact of these two generation approaches on model performance was compared across different augmentation ratios. We adopted a stacking architecture composed of six base models as the core framework and conducted systematic comparisons against the baseline models XGBoost, AdaBoost, Random Forest, and LightGBM across multiple recall thresholds, different feature configurations, and alternative data generation strategies. Overall, the results show that, under high-recall targets, KDE combined with stacking achieves the most stable and superior overall performance relative to the baseline models. We further performed ablation experiments by sequentially removing each base model to evaluate and analyze its contribution. The results indicate that removing KNN yields the greatest negative impact on the stacking classifier, particularly under high-recall settings where the declines in precision and F1-score are most pronounced, suggesting that KNN is most sensitive to the distributional changes introduced by KDE-generated data. This configuration simultaneously improves precision, F1-score, and specificity, and is therefore adopted as the final recommended model setting in this study.

Using the 2000-2010 Taiwan National Health Insurance Research Database, we selected 1767 patients aged [greater than over equal to] 40 years with new-onset PD during 2000-2009. Among them, 324 patients with a new incidence of depression were enrolled as cases and 972 patients without depression were randomly selected as controls. The groups were frequency-matched at a ratio of 1:3 by age, sex, and index year. Thus, this nested case-control study compared differences between the cases and the controls. Logistic regression models were used to identify risk factors for depression in PD. Compared with the controls, the odds ratio (OR) of anxiety disorders in the cases was 1.53 (95% confidence interval [95% CI], 1.16-2.02; P = 0.003), after adjusting for the confounding factors of age, sex, index year, geographic region, urban level, monthly income, and other coexisting medical conditions. The OR for sleep disturbances in the cases was 1.49 (95% CI, 1.14-1.96; P = 0.004) compared to the controls, after adjusting these confounding factors. Hence, the risk factors for depression in PD were nonsignificantly associated with physical comorbidities. In the present study, depression in PD was significantly associated with anxiety disorders and sleep disturbances. Integrated care for early identification and treatment of neuropsychiatric comorbidities is crucial in patients with new-onset PD so as to prevent further PD degeneration.

In recent years, data augmentation techniques have become the predominant approach for addressing highly imbalanced classification problems in machine learning. Algorithms such as the Synthetic Minority Over-sampling Technique (SMOTE) and Conditional Tabular Generative Adversarial Network (CTGAN) have proven effective in synthesizing minority class samples. However, these methods often introduce distributional bias and noise, potentially leading to model overfitting, reduced predictive performance, increased computational costs, and elevated cybersecurity risks. To overcome these limitations, we propose a novel architecture, FADEL, which integrates feature-type awareness with a supervised discretization strategy. FADEL introduces a unique feature augmentation ensemble framework that preserves the original data distribution by concurrently processing continuous and discretized features. It dynamically routes these feature sets to their most compatible base models, thereby improving minority class recognition without the need for data-level balancing or augmentation techniques. Experimental results demonstrate that FADEL, solely leveraging feature augmentation without any data augmentation, achieves a recall of 90.8% and a G-mean of 94.5% on the internal test set from Kaohsiung Chang Gung Memorial Hospital in Taiwan. On the external validation set from Kaohsiung Medical University Chung-Ho Memorial Hospital, it maintains a recall of 91.9% and a G-mean of 86.7%. These results outperform conventional ensemble methods trained on CTGAN-balanced datasets, confirming the superior stability, computational efficiency, and cross-institutional generalizability of the FADEL architecture. Altogether, FADEL uses feature augmentation to offer a robust and practical solution to extreme class imbalance, outperforming mainstream data augmentation-based approaches.

Behçet's disease (BD) is a recurrent, multisystemic, inflammatory disorder that mainly affects blood vessels. Because recurrent inflammation of blood vessels in the brain plays a crucial role in the development of ischemic stroke, we hypothesized that patients with BD might have an elevated risk of ischemic stroke. This potential association has been suggested in a few case reports, but not epidemiological studies. Hence, the present study aimed to examine the relation between BD and subsequent ischemic stroke in Taiwan using a nationwide, population-based database. To establish a study cohort, the longitudinal data of 306 patients newly diagnosed with BD during 2000-2010 were extracted from the National Health Insurance Research Database, Taiwan. For comparison of ischemic stroke incidence, a control cohort of 1224 subjects without BD was established using a frequency-matched ratio of 1:4 for age, sex, and pre-existing comorbidities. During the 10-year follow-up, 13 (4.2%) patients with BD and 20 (1.6%) control subjects experienced ischemic stroke. Kaplan-Meier analysis revealed the higher prevalence of ischemic stroke in the BD group (log-rank test, p = 0.001). After adjusting for comorbidities and demographic characteristics, Cox regression analysis revealed that patients with BD had a 2.77-fold risk of ischemic stroke (95% confidence interval, 1.38-5.57) compared to control subjects. Patients with BD have an elevated risk of ischemic stroke. Hence, BD may affect the vascular system in the brain, resulting in a stroke event.

Background: Multimorbidity and polypharmacy increase the risk of hospitalization in older adults receiving potentially inappropriate medication (PIM). The current study compared the ability of PIM-Taiwan, PRISCUS, and Beers criteria to predict 90-day rehospitalization in older patients with and without PIM. Methods: The retrospective cohort study used Taiwan’s Longitudinal Health Insurance Database to retrieve quarterly information about prescribed medication for adults aged ≥65 years hospitalized between 2001 and 2018. We analyzed the association of PIM with 90-day rehospitalization using logistic regression. Results: The study cohort included 206,058 older adults (mean age: 72.5 years). In the analysis, 133,201 (64.6%), 97,790 (47.5%), and 147,450 (71.6%), were identified as having PIM exposure in PIM-Taiwan, PRICUS, and Beers criteria, respectively. PIM-Taiwan criteria found exposure to PIM affecting the cardiovascular (adjusted OR [aOR] 1.37, 95% confidence interval [CI] = 1.32–1.41), gastrointestinal (aOR 1.26, 95% CI = 1.23–1.30), central nervous (aOR 1.11, 95% CI = 1.08–1.14), and respiratory (aOR 1.16, 95% CI = 1.12–1.20) systems significantly increased the risk of 90-day rehospitalization, after adjustment for covariates. In PRISCUS criteria, exposure to PIM affecting the respiratory (aOR 1.48, 95% CI = 1.41–1.56), central nervous (aOR 1.12, 95% CI = 1.09–1.15), and cardiovascular (aOR 1.20, 95% CI = 1.16–1.24) systems significantly increased the risk. In Beers criteria, exposure to PIM affecting the cardiovascular (aOR 1.37, 95% CI = 1.32–1.41), gastrointestinal (aOR 1.38, 95% CI = 1.35–1.42), central nervous (aOR 1.18, 95% CI = 1.15–1.21), endocrine (aOR 1.10, 95% CI = 1.06–1.15), and respiratory (aOR 1.09, 95% CI = 1.04–1.13) systems significantly increased the risk. Patients with 90-day rehospitalization had higher rates of the potentially harmful drug-drug interaction (DDI) pairs of serotonin syndrome (n = 19; 48.8%), QT prolongation (n = 4; 30.8%), extrapyramidal symptoms (EPS) (n = 102; 24.5%), and hypokalemia (n = 275; 20.1%). Conclusion: Beers criteria was more efficient in predicting 90-day rehospitalization among older adults experiencing PIM in Taiwan than either PIM-Taiwan or PRISCUS. The risk of 90-day rehospitalization was associated with the potentially harmful DDI classes of serotonin syndrome, QT prolongation, EPS, and hypokalemia.

Poor adherence to antipsychotics in patients with schizophrenia is a leading cause of relapse and functional deterioration. Long-acting injectable paliperidone may reduce relapse risks, health-care utilisation, and health-care costs in these patients. In this 24-month mirror-image study, we compared health-care utilization and costs before and after the initiation of paliperidone palmitate 3-monthly (PP3M) treatment in patients with schizophrenia spectrum disorders. Before the initiation of PP3M, the patients received paliperidone 1-monthly (PP1M) treatment. The primary study outcomes were changes in health-care utilisation and costs over the study period. This study included 34 patients with schizophrenia spectrum disorders. During the 12-months period after the initiation of PP3M treatment, the mean duration of hospitalisation decreased from 57.7 to 28.5 days (p = 0.03). Moreover, significant reductions were noted in emergency room visits (PP1M vs PP3M: 0.3 vs 0.0, respectively; p = 0.05) and health-care costs (PP1M vs PP3M: 107,328.8 vs 57,848.6, respectively; p = 0.03). PP3M may significantly reduce hospitalisation duration, emergency room visits, and health-care costs in patients with schizophrenia.

Pneumonia is the leading cause of death in patients with Parkinson's disease (PD). However, few studies have been performed to explore the risk factors for pneumonia development in patients with PD. We conducted a nationwide population-based cohort study of patients with PD to identify the risk factors for these patients developing pneumonia. Participants with newly diagnosed PD between 2000 and 2009 were enrolled from the 2000-2010 National Health Insurance Research Database in Taiwan. We compared patients with PD with an incidence of hospitalization with pneumonia vs those without, and Cox proportional hazard models were used to estimate the risk of pneumonia. Of the 2,001 enrolled patients (mean follow-up duration 5.8 years, range: 2.7-14.7 years), 381 (19.0%) had an incidence of hospitalization with pneumonia during the study period. Multivariate Cox proportional hazards analysis identified older age group (≥80 years of age, hazard ratio [HR] =3.15 [95% confidence interval 2.32-4.28]), male sex (HR =1.59 [1.29-1.96]), certain geographic regions (northern, HR =1.36 [1.04-1.78], southern and eastern, HR =1.40 [1.05-1.88]), rural areas (HR =1.34 [1.05-1.72]), chronic heart failure (HR =1.53 [1.02-2.29]), and chronic kidney disease (HR =1.39 [1.03-1.90]) as risk factors for hospitalization with pneumonia in patients with PD. However, treatment for dental caries was a protective factor (HR =0.80 [0.64-0.99]). The results of this study highlight risk factors that are associated with hospitalization with pneumonia, and, for the first time, suggest a link between treated dental caries and a diminished risk of hospitalization with pneumonia in patients with PD.

The number of people living with dementia globally is increasing rapidly, and there is no effective therapy. Dietary pattern is one important risk factor for the development and progression of dementia. We undertake this study to determine whether Taiwanese vegetarian diet in midlife affects dementia incidence in later years in a prospective cohort. We followed 5710 participants (average age less than 60) in the Tzu Chi Vegetarian Study (TCVS). We started recruiting in 2005 and followed until the end of 2014 when the database changed from ICD-9-CM to ICD-10-CM codes. The incidence of dementia was obtained through linkage to the National Health Insurance Research Database. We used Cox proportional hazards regression to estimate the hazard ratio of dementia between vegetarians and nonvegetarians. There were 121 cases of dementia (37 vegetarians and 84 nonvegetarians) diagnosed. Vegetarians were associated with reduced risk of clinically overt dementia compared with nonvegetarians (hazard ratio = 0.671, confidence interval: 0.452–0.996, p < 0.05) after adjusting for gender, age, smoking, drinking, education level, marriage, regular exercise, and comorbidities with stepwise regression.