Search

Abstract Life expectancy is likely to be substantially reduced in patients undergoing chronic hemodialysis (CHD). However, machine learning (ML) may predict the risk factors of mortality in patients with CHD by analyzing the serum laboratory data from regular dialysis routine. This study aimed to establish the mortality prediction model of CHD patients by adopting two-stage ML algorithm-based prediction scheme, combined with importance of risk factors identified by different ML methods. This is a retrospective, observational cohort study. We included 800 patients undergoing CHD between December 2006 and December 2012 in Shin-Kong Wu Ho-Su Memorial Hospital. This study analyzed laboratory data including 44 indicators. We used five ML methods, namely, logistic regression (LGR), decision tree (DT), random forest (RF), gradient boosting (GB), and eXtreme gradient boosting (XGB), to develop a two-stage ML algorithm-based prediction scheme and evaluate the important factors that predict CHD mortality. LGR served as a bench method. Regarding the validation and testing datasets from 1- and 3-year mortality prediction model, the RF had better accuracy and area-under-curve results among the five different ML methods. The stepwise RF model, which incorporates the most important factors of CHD mortality risk based on the average rank from DT, RF, GB, and XGB, exhibited superior predictive performance compared to LGR in predicting mortality among CHD patients over both 1-year and 3-year periods. We had developed a two-stage ML algorithm-based prediction scheme by implementing the stepwise RF that demonstrated satisfactory performance in predicting mortality in patients with CHD over 1- and 3-year periods. The findings of this study can offer valuable information to nephrologists, enhancing patient-centered decision-making and increasing awareness about risky laboratory data, particularly for patients with a high short-term mortality risk.

Abstract Purpose No large-scale prospective randomized study with a long-term follow-up period has evaluated the survival outcomes of preconcurrent chemoradiotherapy (CCRT) 18-fluorodeoxyglucose positron emission tomography–computed tomography (18FDG PET–CT) in patients with non–human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma (OPSCC). Patients and Methods We included patients with stage I–IVA p16-negative OPSCC receiving definitive CCRT and categorized them into two groups according to pre-CCRT 18FDG PET–CT and compared their outcomes: the case group consisted of patients who underwent pre-CCRT 18FDG PET–CT, whereas the comparison group consisted of patients who did not receive pre-CCRT 18FDG PET–CT. Results The final cohort consisted of 3942 patients (1663 and 2279 in the case and comparison groups, respectively). According to multivariable Cox regression analysis, pre-CCRT 18FDG PET–CT was not a significant prognostic factor for overall survival in patients with stages I–II of p16-negative OPSCC receiving standard CCRT. The adjusted hazard ratio (95% confidence interval) of all-cause death for the patients with advanced stages (III–IVA) of p16-negative OPSCC receiving pre-CCRT 18FDG PET–CT was 0.75 (0.87–0.94, P = 0.0236). Conclusions Routine use of pre-CCRT 18FDG PET–CT is not necessary for each patient with p16-negative OPSCC. Pre-CCRT 18FDG PET–CT is associated with improved survival in patients with stage III–IVA p16-negative OSCC, but might be not in those with stage I–II p16-negative OPSCC. Condensed abstract No large-scale prospective randomized study with a long-term follow-up period has evaluated the survival outcomes of preconcurrent chemoradiotherapy (CCRT) 18-fluorodeoxyglucose positron emission tomography–computed tomography (18FDG PET–CT) in patients with p16-negative oropharyngeal squamous cell carcinoma (OPSCC). Our study is the first, largest, homogenous modality study on PET–CT including a long-term follow-up cohort to examine the survival outcomes of pre-CCRT 18FDG PET–CT or non-pre-CCRT PET–CT for patients with p16-negative OPSCC receiving standard CCRT stratified by different clinical stages. Routine use of pre-CCRT 18FDG PET–CT is not necessary for each patient with p16-negative OPSCC. Pre-CCRT 18FDG PET–CT is associated with improved survival in patients with stage III–IVA p16-negative OPSCC, but might be not in those with stage I–II p16-negative OPSCC.

Background/Purpose: Accurate staging is the first step for optimal treatment selection in patients with nasopharyngeal carcinoma (NPC). In this propensity-score-matched, population-based cohort study, we investigated the survival effects of pretreatment 8-fluorodeoxyglucose positron emission tomography–computed tomography (18FDG-PET–CT) on patients with NPC. Methods: We included patients with stage I–IVA NPC receiving radiotherapy or concurrent chemoradiotherapy and categorized them into two 1:1 propensity score–matched groups according to whether or not they underwent pretreatment 18FDG-PET–CT and compared their outcomes. Results: Of the 10,756 patients, propensity score matching yielded 4366 patients in each group. According to multivariable Cox regression analyses, the most prominent correlation between pretreatment 18FDG-PET–CT and all-cause death was observed in patients with stage II NPC (adjusted hazard ratio [aHR], 0.77; 95% confidence interval [CI], 0.60–0.90; P = .0433), followed by patients with stage III NPC (aHR, 0.81; 95% CI, 0.69–0.94; P = .0071) and patients with stage IVA NPC (aHR, 0.88; 95% CI, 0.79–0.97; P = .0091). This association was not significant in patients with stage I NPC (aHR, 1.20; 95% CI, 0.75–1.93; P = .4426). Conclusion: Pretreatment 18FDG-PET–CT is associated with longer survival in patients with clinical stage II–IVA NPC but not in stage I NPC.

BackgroundWith the advent of electronic storage of medical records and the internet, patients can access web-based medical records. This has facilitated doctor-patient communication and built trust between them. However, many patients avoid using web-based medical records despite their greater availability and readability. ObjectiveOn the basis of demographic and individual behavioral characteristics, this study explores the predictors of web-based medical record nonuse among patients. MethodsData were collected from the National Cancer Institute 2019 to 2020 Health Information National Trends Survey. First, based on the data-rich environment, the chi-square test (categorical variables) and 2-tailed t tests (continuous variables) were performed on the response variables and the variables in the questionnaire. According to the test results, the variables were initially screened, and those that passed the test were selected for subsequent analysis. Second, participants were excluded from the study if any of the initially screened variables were missing. Third, the data obtained were modeled using 5 machine learning algorithms, namely, logistic regression, automatic generalized linear model, automatic random forest, automatic deep neural network, and automatic gradient boosting machine, to identify and investigate factors affecting web-based medical record nonuse. The aforementioned automatic machine learning algorithms were based on the R interface (R Foundation for Statistical Computing) of the H2O (H2O.ai) scalable machine learning platform. Finally, 5-fold cross-validation was adopted for 80% of the data set, which was used as the training data to determine hyperparameters of 5 algorithms, and 20% of the data set was used as the test data for model comparison. ResultsAmong the 9072 respondents, 5409 (59.62%) had no experience using web-based medical records. Using the 5 algorithms, 29 variables were identified as crucial predictors of nonuse of web-based medical records. These 29 variables comprised 6 (21%) sociodemographic variables (age, BMI, race, marital status, education, and income) and 23 (79%) variables related to individual lifestyles and behavioral habits (such as electronic and internet use, individuals’ health status and their level of health concern, etc). H2O’s automatic machine learning methods have a high model accuracy. On the basis of the performance of the validation data set, the optimal model was the automatic random forest with the highest area under the curve in the validation set (88.52%) and the test set (82.87%). ConclusionsWhen monitoring web-based medical record use trends, research should focus on social factors such as age, education, BMI, and marital status, as well as personal lifestyle and behavioral habits, including smoking, use of electronic devices and the internet, patients’ personal health status, and their level of health concern. The use of electronic medical records can be targeted to specific patient groups, allowing more people to benefit from their usefulness.

The synthesis of primary amines via the reductive amination of alcohols involves a hydrogen-borrowing or hydrogen-transfer mechanism, which consists of three main steps: alcohol hydroxyl dehydrogenation, carbonyl imidization, and imine hydrogenation. Heterogeneous catalysts are widely used for this reaction because of their high performance and amenability to separation and reuse. However, the efficiency of reductive amination is limited by the dehydrogenation step, which is severely affected by the competitive adsorption of NH3. We hope to improve the efficiency of reductive amination by increasing dehydrogenation efficiency. Therefore, in this overview, we introduce the research progress of alcohol reductive amination reaction catalyzed by heterogeneous metal catalysts, focusing on methods of enhancing dehydrogenation efficiency by screening the metal component and the acidity/alkalinity of the support. Finally, we propose some new strategies for the preparation of catalysts from the perspective of overcoming the competitive adsorption of NH3 and speculate on the design and synthesis of novel catalysts with high performance in the future.

Abstract Nonvalvular atrial fibrillation (NVAF) and carotid stenosis are important risk factors for stroke. Carotid angioplasty and stent placement (CAS) is recommended for patients with symptomatic high-grade carotid stenosis. The optimal medical management for patients with NVAF after CAS remains unclear. We aimed to clarify this issue using real-world data from the Taiwanese National Health Insurance Research Database (NHIRD). In total, 2116 consecutive NVAF patients who received CAS between January 1, 2010, and December 31, 2016, from NHIRD were divided into groups based on post-procedure medication as follows: only antiplatelet agent (OAP, n = 587); only anticoagulation agent (OAC, n = 477); dual antiplatelet agents (DAP, n = 49); and a combination of antiplatelet and anticoagulation agents (CAPAC, n = 304). Mortality, vascular events, and major bleeding episodes were compared after matching with the Charlson comorbidity index and CHA2DS2-VASc score. The CAPAC and the OAC groups had lower mortality rates than the OAP group (P = 0.0219), with no statistical differences in major bleeding, ischemic stroke, or vascular events. Conclusively, OAC therapy after CAS appears suitable for NVAF patients. CAPAC therapy might be considered as initial therapy or when there is concern about vascular events.

Condensed abstractNo large-scale, well-designed randomized study with a long-term follow-up has evaluated the survival effect of pretreatment 18-fluorodeoxyglucose positron emission tomography–computed tomography (18FDG-PET–CT) on patients with stage IB–IVA cervical cancer receiving image-guided intensity-modulated radiation therapy (IG-IMRT). This is the first head-to-head propensity score–matched, nationwide population-based cohort study evaluating this survival effect. The results revealed that pretreatment 18FDG-PET–CT might be associated with longer survival in patients with stage IB–IVA cervical cancer receiving radiotherapy or concurrent chemoradiotherapy, especially in the IG-IMRT era.PurposeNo large-scale, well-designed randomized study with a long-term follow-up has evaluated the survival effect of pretreatment 18-fluorodeoxyglucose positron emission tomography–computed tomography (18FDG-PET–CT) on patients with stage IB–IVA cervical cancer receiving image-guided intensity-modulated radiation therapy (IG-IMRT). Therefore, in this propensity score–matched, population-based cohort study, we investigated these survival effects.Patients and methodsWe included 4167 patients with stage IB–IVA cervical cancer receiving radiotherapy (RT) or concurrent chemoradiotherapy (CCRT) through the IG-IMRT technique. The patients were categorized into two 1:2 propensity score–matched groups depending on whether they underwent pretreatment 18FDG-PET–CT, and their outcomes were compared.ResultsWe included 2778 and 1389 patients with cervical cancer in the nonpretreatment and pretreatment PET–CT groups, respectively. Univariable and multivariable analyses revealed an association between pretreatment PET–CT and improved survival in the patients (in the adjusted model, the adjusted hazard ratio [aHR] was 0.88; 95% confidence interval [CI], 0.80–0.97: P = 0.010). Regardless of the cancer stage (early or advanced), pretreatment PET–CT was significantly superior to nonpretreatment PET–CT in terms of all-cause death (aHR, 0.78; 95% CI, 0.60–0.92; P = 0.013 and aHR, 0.90; 95% CI, 0.81–0.99; P = 0.039 for the early [IB–IIA] and advanced stages [IIB–IVA], respectively).ConclusionsPretreatment 18FDG-PET–CT might be associated with longer survival in patients with stage IB–IVA cervical cancer receiving RT or CCRT, especially in the era of IG-IMRT.

Abstract Background The relationship between sleep duration and physical fitness is one aspect of sleep health. Potential factors associated with sleep duration interfere with physical fitness performance, but the impact trends on physical fitness indicators remain unclear. Methods This study examined associations between sleep duration and physical fitness among young to middle-aged adults in Taiwan. A total of 42,781 Taiwanese adults aged 23–45 participated in the National Physical Fitness Examination Survey 2013 (NPFES-2013) in Taiwan between October 2013 and March 2014. A standardized structural questionnaire was used to record participants’ sleep duration, which was stratified as short (

Purpose: to examine the impact of statins on reducing all-cause mortality among individuals diagnosed with type 2 diabetes. This investigation explored the potential correlations between dosage, drug classification, and usage intensity with the observed outcomes. Methods: The research sample consisted of individuals aged 40 years or older diagnosed with type 2 diabetes. Statin usage was determined as a frequent usage over a minimum of one month subsequent to type 2 diabetes diagnosis, where the average statin dose was ≥28 cumulative defined daily doses per year (cDDD-year). The analysis employed an inverse probability of treatment-weighted Cox hazard model, utilizing statin usage status as a time-varying variable, to evaluate the impact of statin use on all-cause mortality. Results: The incidence of mortality was comparatively lower among the cohort of statin users (n = 50,804 (12.03%)), in contrast to nonusers (n = 118,765 (27.79%)). After adjustments, the hazard ratio (aHR; 95% confidence interval (CI)) for all-cause mortality was estimated to be 0.32 (0.31–0.33). Compared with nonusers, pitavastatin, rosuvastatin, pravastatin, simvastatin, atorvastatin, fluvastatin, and lovastatin users demonstrated significant reductions in all-cause mortality (aHRs (95% CIs) = 0.06 (0.04–0.09), 0.28 (0.27–0.29), 0.29 (0.28–0.31), 0.31 (0.30–0.32), 0.31 (0.30–0.32), 0.36 (0.35–0.38), and 0.48 (0.47–0.50), respectively). In Q1, Q2, Q3, and Q4 of cDDD-year, our multivariate analysis demonstrated significant reductions in all-cause mortality (aHRs (95% CIs) = 0.51 (0.5–0.52), 0.36 (0.35–0.37), 0.24 (0.23–0.25), and 0.13 (0.13–0.14), respectively; p for trend

Abstract Hypertension in childhood and adolescence is associated with adult cardiovascular morbidity and mortality. However, the reported prevalence of pediatric hypertension varies considerably. We conducted a pioneer nationwide population-based study to investigate the prevalence of hypertension among children and adolescents. Pediatric patients who had been diagnosed with hypertension between 2000 and 2013 were selected from the National Health Insurance Research Database in Taiwan. Other metabolic syndrome-related diseases that would increase cardiovascular risk, including diabetes mellitus (DM), hyperlipidemia, and obesity, were also retrieved for further evaluation. In total, 10,364 children and adolescents diagnosed with hypertension were identified. The prevalence of pediatric hypertension in Taiwan ranged from 0.19 to 0.38 per 1000 children and adolescents between 2000 and 2013. Essential hypertension was most commonly coded (90.6%), which was much more than secondary hypertension (14.3%). Children and adolescents with hypertension were often associated with DM, hyperlipidemia, and obesity, with the odds ratios as 14.05 (95% confidence interval (CI) 11.74–16.81, p

PurposeTo characterize the association between the frequency of screening for diabetic retinopathy (DR) and the detection of DR in patients with newly diagnosed type 2 diabetes mellitus (T2DM).MethodsThis nationwide population-based cohort study used data from the National Health Insurance Research Database to identify adult patients who were newly diagnosed with T2DM between 2000 and 2004. Data from their follow-up Diabetic retinopathy (DR) treatments over the next 10 years following diagnosis were also analyzed.ResultsThe 41,522 subjects were respectively assigned to a periodic screening group (n = 3850) and nonperiodic screening group (n = 37,672). Significant differences were observed between the two groups in terms of age, Charlson Comorbidity Index (CCI), sex, DR treatment, and the prevalence of DR. The association between periodic screening and DR treatment, only the elderly, female, and patient with severe CCI status showed the significance in the further stratified analysis.ConclusionPeriodic screening (annual or biannual screening in the first 5 years) was more effective than nonperiodic screening in detecting instances of DR in the middle-to-advanced aged group but not among younger patients. Screening pattern did not have a significant effect on the likelihood of DR-related treatment during the 5-year follow-up. It appears that a tight screening schedule for the first 5 years after diagnosis with diabetes is not necessary.

Lipid-lowering agents display limited benefits on cardiovascular diseases and mortality in patients undergoing dialysis. Therefore, they are not routinely recommended for dialysis patients. The aim of this study was to assess the effects of lipid-lowering agents on clinical outcomes in dialysis patients on the basis of real-world evidence. This research used Taiwan’s National Health Insurance Research Database to identify dialysis patients from January 2009 to December 2015; patients were then categorized into a case group treated with lipid-lowering agents (n = 3,933) and a control group without lipid-lowering agents (n = 24,267). Patients were matched by age, sex, and comorbidities in a 1:1 ratio. This study used the Cox regression model to estimate the hazard ratios (HRs) for mortality and major adverse cardiovascular events (MACEs) for events recorded until December 2017. During a mean follow-up period of approximately 3.1 years, 1726 [43.9%, incidence 0.123/person-year (PY)] deaths and 598 (15.2%, incidence 0.047/PY) MACEs occurred in the case group and 2031 (51.6%, incidence 0.153/PY) deaths and 649 (16.5% incidence 0.055/PY) MACEs occurred in the control group. In the multivariable analysis of the Cox regression model, lipid-lowering agent users showed a significantly lower risk of death [HR: 0.75; 95% confidence interval (CI): 0.70–0.80] and MACEs (HR: 0.88; 95% CI: 0.78–0.98) than lipid-lowering agent non-users. Moreover, the survival benefit of lipid-lowering agents was significant across most subgroups. Dialysis patients treated with lipid-lowering agents display a 25 and 12% reduction in their risk of mortality and MACEs, respectively. Therefore, lipid-lowering agents might be considered when treating dialysis patients with hyperlipidemia.

Esophageal cancer is a common and aggressive cancer, with a five-year survival rate of approximately 20%. Therefore, identifying safe and effective medications that can reduce the risk of esophageal cancer is of great importance. Objective: To examine the association between H1-antihistamines (AHs) use and the incidence of esophageal squamous cell carcinoma (ESCC) in a head-to-head propensity score matching (PSM) comparative study. Design: Retrospective cohort study. Setting: Nationwide population-based study in Taiwan. Participants: 1289,526 adults from the National Health Insurance Research Database from 2008 to 2018. Exposures: AH use. Main Outcomes and Measures: Incidence rates (IRs), incidence rate ratios (IRRs), and adjusted hazard ratios (aHRs) of ESCC in AH users compared with nonusers. Results: AH users had a significantly higher IR of ESCC than nonusers (1.47 vs. 1.36 per 100,000 person-years). The IRR (95% CI) for ESCC was 1.18 (1.08–1.28) in AH users compared with nonusers. After adjustment for age, sex, income levels, urbanization, cigarettes smoking, alcoholic related diseases, comorbidities, medication use, and Charlson Comorbidity Index scores, the aHR (95% CI) for ESCC was 1.22 (1.12–1.33) in AH users compared with nonusers. A dose–response relationship was also observed, with aHRs for AH use at 28–182, 183–488, 489–1043, and >1043 cumulative defined daily doses (cDDDs) of 1.12, 1.20, 1.25, and 1.37, respectively, compared with

We propose a miniaturized quad-band filter (QBF), designed using substrate-integrated coaxial cavities (SICCs). The employed SICC structure consists of two vertically stacked substrates with a large circular patch embedded in between. The embedded patch is segmented unevenly into four pieces, which are shorted to the cavity’s bottom wall through one or two blind vias. This SICC structure exhibits four independently controlled resonances with frequencies much lower than the frequency of its conventional SIW cavity counterpart, thus achieving size reduction. A sample quad-band filter is designed and fabricated for experimental measurement. Reasonably good agreement between measured and simulated data is observed.

Coronary artery disease (CAD) is a common major disease. Revascularization with percutaneous coronary intervention (PCI) or coronary artery bypass graft (CABG) could relieve symptoms and myocardial ischemia. As the treatment improves and evolves, the number of aged patients with complex diseases and multiple comorbidities gradually increases. Furthermore, in patients with multivessel disease, 3-vessel PCI may lead to a higher risk of complications during the procedure, leading to further ischemia and higher long-term mortality than PCI for one vessel or two vessels. Nevertheless, the risk factors for accurately predicting patient mortality after 3-vessel PCI are unclear. Thus, a new risk prediction model for primary PCI (PPCI) patients’ needs to be established to help physicians and patients make decisions more quickly and accurately. This research aimed to construct a prediction model and find which risk factors will affect mortality in 3-vessel PPCI patients. This nationwide population-based cohort study crossed multiple hospitals and selected 3-vessel PPCI patients from January 2007 to December 2009. Then five different single machine learning methods were applied to select significant predictors and implement ensemble models to predict the mortality rate. Of the 2337 patients who underwent 3-vessel PPCI, a total of 1188 (50.83%) survived and 1149 (49.17%) died. Age, congestive heart failure (CHF), and chronic renal failure (CRF) are mortality’s most important variables. When CRF patients accept 3-vessel PPCI at ages between 68–75, they will possibly have a 94% death rate; Furthermore, this study used the top 15 variables averaged by each machine learning method to make a prediction model, and the ensemble learning model can accurately predict the long-term survival of 3-vessel PPCI patients, the accurate predictions rate achieved in 88.7%. Prediction models can provide helpful information for the clinical physician and enhance clinical decision-making. Furthermore, it can help physicians quickly identify the risk features, design clinical trials, and allocate hospital resources effectively.

Portable magnetic-assisted capsule endoscopy (MACE) provides satisfactory patient experience and safety with comparable performance in diagnosis of organic lesions when compared to conventional upper gastrointestinal endoscopy. In this study, a total of 58 homecare patients were included for MACE either in the hospital (n = 42) or at home (n = 16), with mean age of 71.1 ± 12.4 years. A total of 55 patients (94.83%) had completed the MACE with diagnosis of reflux esophagitis (43.6%), gastritis (54.5%), erosions (21.8%), fundic polyps (14.5%), peptic ulcers (25.9%), etc. Most patients (n = 47, 85.5%) were satisfied with the experience, and all patients who received MACE at home (n = 15, 100%) appreciated the convenience of endoscopy at home. Less than half of the patients (n = 24, 43.6%) could afford MACE if the expense was not covered by health insurance (USD 714). Time consumption from both traffic and capsule manipulation was also challenging for the physicians, as it took an average of 24.7 min to complete MACE, but it added up to a total of 92.7 min at home, which is about 15 times that of conventional endoscopy in hospital. More efforts are needed to ease the financial burden of patients, and optimization of workflow in community practice may help lift the obstacles revealed in this study.

Secondary hormone therapy, abiraterone and enzalutamide, has improved outcomes for metastatic castration-resistant prostate cancer (mCRPC) and prolonged patients’ lives significantly. Various studies have compared the cancer-related outcomes, adverse effects, and drug-induced comorbidities in patients with mCRPC who are treated with abiraterone or enzalutamide. However, few studies have explored associations between survival and comorbidities or comprehensive analyzed newly developed comorbidities during and after secondary hormone therapy. We attempted to clarify whether the Charlson comorbidity index (CCI) overall or itemized is predictive for overall survival, and we compared newly developed comorbidities between abiraterone and enzalutamide groups. We extracted data about expenses and comorbidities for patients who have mCRPC, received abiraterone and enzalutamide and met pre-examination operation criteria between September 2016 and December 2017 from the Taiwan National Health Insurance database. A total of 1153 patients with mCRPC who received abiraterone (n = 782) or enzalutamide (n = 371) with or without previous chemotherapy were included. We used the propensity score to match confounding factors, including age, pre-existing comorbidities, and precipitating factors for comorbidity (e.g., hypertension, hyperlipidemia), to eliminate selection bias in the comparison of newly developed comorbidities. Cox regression analysis was used for overall survival. We found that enzalutamide is superior to abiraterone with regard to overall survival. Our study revealed that there is no statistically significant difference in development of new comorbidities between abiraterone and enzalutamide group. Moreover, the CCI score, rather than any single item of the CCI, was a statistically significant predictor for overall survival.

The health effects associated with fine particulate matter (PM2.5) have attracted considerable public attention in recent decades. It has been verified that PM2.5 can damage the respiratory and cardiovascular systems and cause various diseases. While the association between diseases and PM2.5 has been widely studied, this work aims to analyze the association between PM2.5 and hospital visit rates for respiratory diseases in Taiwan. To this end, a disease mapping model that considers spatial effects is applied to estimate the association. The results show that there is a positive association between hospital visit rates and the PM2.5 concentrations in the Taiwanese population in 2012 after controlling for other variables, such as smoking rates and the number of hospitals in each region. This finding indicates that control of PM2.5 could decrease hospital visit rates for respiratory diseases in Taiwan.

Background and PurposePattern differentiation is a critical element of the prescription process for Traditional Chinese Medicine (TCM) practitioners. Application of advanced machine learning techniques will enhance the effectiveness of TCM in clinical practice. The aim of this study is to explore the relationships between clinical features and TCM patterns in breast cancer patients.MethodsThe dataset of breast cancer patients receiving TCM treatment was recruited from a single medical center. We utilized a neural network model to standardize terminologies and address TCM pattern differentiation in breast cancer cases. Cluster analysis was applied to classify the clinical features in the breast cancer patient dataset. To evaluate the performance of the proposed method, we further compared the TCM patterns to therapeutic principles of Chinese herbal medication in Taiwan.ResultsA total of 2,738 breast cancer cases were recruited and standardized. They were divided into 5 groups according to clinical features via cluster analysis. The pattern differentiation model revealed that liver-gallbladder dampness-heat was the primary TCM pattern identified in patients. The main therapeutic goals of the top 10 Chinese herbal medicines prescribed for breast cancer patients were to clear heat, drain dampness, and detoxify. These results demonstrated that the neural network successfully identified patterns from a dataset similar to the prescriptions of TCM clinical practitioners.ConclusionThis is the first study using machine-learning methodology to standardize and analyze TCM electronic medical records. The patterns revealed by the analyses were highly correlated with the therapeutic principles of TCM practitioners. Machine learning technology could assist TCM practitioners to comprehensively differentiate patterns and identify effective Chinese herbal medicine treatments in clinical practice.

This paper tries to trace our research history briefly from Barlow and Proschan to attain general replacement models. We begin with a random age replacement policy that is planned at a random time Y and call it as random replacement. When the distribution of Y becomes a degenerate distribution placing unit mass at T, age replacement is formulated. We obtain the general formulas for optimum replacement times. We next suppose the unit works for a job with random works, and replacement policies with N cycles are discussed. As follows, we combine age and random replacement models and discuss replacement first, replacement last, replacement overtime, replacement overtime first and replacement overtime last. By formulating the distributions of replacement times with n variables, general replacement models with n replacement times are obtained.

Background: Low-dose aspirin (100 mg) is widely used in preventing cardiovascular disease in chronic kidney disease (CKD) because its benefits outweighs the harm, however, its effect on clinical outcomes in patients with predialysis advanced CKD is still unclear. This study aimed to assess the effect of aspirin use on clinical outcomes in such group. Methods: Patients were selected from a nationwide diabetes database from January 2009 to June 2017, and divided into two groups, a case group with aspirin use (n = 3021) and a control group without aspirin use (n = 9063), by propensity score matching with a 1:3 ratio. The Cox regression model was used to estimate the hazard ratio (HR). Moreover, machine learning method feature selection was used to assess the importance of parameters in the clinical outcomes. Results: In a mean follow-up of 1.54 years, aspirin use was associated with higher risk for entering dialysis (HR, 1.15 [95%CI, 1.10–1.21]) and death before entering dialysis (1.46 [1.25–1.71]), which were also supported by feature selection. The renal effect of aspirin use was consistent across patient subgroups. Nonusers and aspirin users did not show a significant difference, except for gastrointestinal bleeding (1.05 [0.96–1.15]), intracranial hemorrhage events (1.23 [0.98–1.55]), or ischemic stroke (1.15 [0.98–1.55]). Conclusions: Patients with predialysis advanced CKD and anemia who received aspirin exhibited higher risk of entering dialysis and death before entering dialysis by 15% and 46%, respectively.

Most patients face expensive healthcare management after coronary artery bypass grafting (CABG) surgery, which brings a substantial financial burden to the government. The National Health Insurance Research Database (NHIRD) is a complete database containing over 99% of individuals’ medical information in Taiwan. Our research used the latest data that selected patients who accepted their first CABG surgery between January 2014 and December 2017 (n = 12,945) to predict which factors will affect medical expenses, and built the prediction model using different machine learning algorithms. After analysis, our result showed that the surgical expenditure (X4) and 1-year medical expenditure before the CABG operation (X14), and the number of hemodialysis (X15), were the key factors affecting the 1-year medical expenses of CABG patients after discharge. Furthermore, the XGBoost and SVR methods are both the best predictive models. Thus, our research suggests enhancing the healthcare management for patients with kidney-related diseases to avoid costly complications. We provide helpful information for medical management, which may decrease health insurance burdens in the future.

Coronary artery bypass surgery grafting (CABG) is a commonly efficient treatment for coronary artery disease patients. Even if we know the underlying disease, and advancing age is related to survival, there is no research using the one year before surgery and operation-associated factors as predicting elements. This research used different machine-learning methods to select the features and predict older adults’ survival (more than 65 years old). This nationwide population-based cohort study used the National Health Insurance Research Database (NHIRD), the largest and most complete dataset in Taiwan. We extracted the data of older patients who had received their first CABG surgery criteria between January 2008 and December 2009 (n = 3728), and we used five different machine-learning methods to select the features and predict survival rates. The results show that, without variable selection, XGBoost had the best predictive ability. Upon selecting XGBoost and adding the CHA2DS score, acute pancreatitis, and acute kidney failure for further predictive analysis, MARS had the best prediction performance, and it only needed 10 variables. This study’s advantages are that it is innovative and useful for clinical decision making, and machine learning could achieve better prediction with fewer variables. If we could predict patients’ survival risk before a CABG operation, early prevention and disease management would be possible.

The purpose of this study was to evaluate the recurrence rate and medical expenses of acute myocardial infarction (AMI) following inpatient cardiac rehabilitation. A total of 834 patients with AMI were divided into Group 1 (with inpatient cardiac rehabilitation) and Group 2 (without inpatient cardiac rehabilitation). The results showed that Group 1 had a lower AMI recurrence rate (a 0.640-fold lower hazards ratio) than Group 2 [95% confidence interval (CI) = 0.197–1.863; p = 0.004]. Compared with the medical costs of Group 2, Group 1 also had lower medical costs (a 0.947-fold lower hazards ratio) than Group 2 (95% CI = 0.934–0.981; p = 0.042). These findings have implications for the decision making of clinicians and health policymakers attempting to provide adequate services for patients with AMI.