Prognostic factors for survival in unresectable stage III EGFR mutation-positive lung adenocarcinoma: impact of pre-CCRT PET-CT.

PURPOSE: To assess the survival impact of pre-concurrent chemoradiotherapy (CCRT) staging with positron emission tomography-CT (PET-CT) in patients with unresectable epidermal growth factor receptor (EGFR) mutation-positive adenocarcinoma. METHODS: Patients with unresectable stage IIIA-IIIC EGFR mutation-positive adenocarcinoma undergoing definitive CCRT were divided into two groups: those who received PET-CT staging prior to CCRT and those with other staging methods. Survival outcomes were compared after propensity score matching. RESULTS: Analysis of 11 856 patients (5928 in each group) showed that PET-CT staging was associated with improved survival (adjusted HR of all-cause mortality: 0.74, 95% CI 0.71 to 0.79). Other prognostic factors included male sex, age group, clinical stage, adjuvant treatment, smoking status, Charlson Comorbidity Index score and treatment setting. CONCLUSION: Pre-CCRT staging with PET-CT in patients with unresectable EGFR mutation-positive adenocarcinoma of clinical stage IIIA-IIIC was associated with enhanced survival. Independent prognostic factors were also identified.

Development of a Machine Learning Algorithm to Correlate Lumbar Disc Height on X-rays with Disc Bulging or Herniation.

Lumbar disc bulging or herniation (LDBH) is one of the major causes of spinal stenosis and related nerve compression, and its severity is the major determinant for spine surgery. MRI of the spine is the most important diagnostic tool for evaluating the need for surgical intervention in patients with LDBH. However, MRI utilization is limited by its low accessibility. Spinal X-rays can rapidly provide information on the bony structure of the patient. Our study aimed to identify the factors associated with LDBH, including disc height, and establish a clinical diagnostic tool to support its diagnosis based on lumbar X-ray findings. In this study, a total of 458 patients were used for analysis and 13 clinical and imaging variables were collected. Five machine-learning (ML) methods, including LASSO regression, MARS, decision tree, random forest, and extreme gradient boosting, were applied and integrated to identify important variables for predicting LDBH from lumbar spine X-rays. The results showed L4-5 posterior disc height, age, and L1-2 anterior disc height to be the top predictors, and a decision tree algorithm was constructed to support clinical decision-making. Our study highlights the potential of ML-based decision tools for surgeons and emphasizes the importance of L1-2 disc height in relation to LDBH. Future research will expand on these findings to develop a more comprehensive decision-supporting model.

Effects of SGLT2 inhibitors on clinical cancer survival in patients with type 2 diabetes.

PURPOSE: According to the preclinical data, sodium-glucose cotransporter 2 (SGLT2) inhibitors (SGLT2is) may exert anticancer effects. Here, we clarified the cancer-specific mortality (primary outcome) and all-cause mortality (secondary outcome) of SGLT2is and their dose-dependency in patients with cancer undergoing standard curative treatments. METHODS: We analyzed data from patients with type 2 diabetes mellitus (T2DM) diagnosed with cancer between January 1, 2016, and December 31, 2018, enrolled from the Taiwan Cancer Registry database. Kaplan-Meier method was used to estimate all-cause mortality and cancer-specific mortality, comparing survival curves between SGLT2i users and nonusers using the stratified log-rank test. Cox proportional hazards regression was conducted to identify independent predictors for all-cause and cancer-specific mortality among the covariates. RESULTS: We performed 1:2 propensity score matching of our data, which yielded a final cohort of 50,133 patients with cancer; of them, 16,711 and 33,422 were in the SGLT2i user and nonuser groups, respectively. The adjusted hazard ratio (aHR) for cancer-specific and all-cause mortality in SGLT2i users compared with nonusers was 0.21 (95 % confidence interval [CI]: 0.20-0.22) and 0.22 (95 % CI: 0.21-0.23). We divided the patients into four subgroups stratified by quartiles (Q) of cumulative defined daily doses per year (cDDDs), and all-cause and cancer-specific mortality was noted to significantly decrease with increases in dosage (from Q1 to Q4 cDDDs) in SGLT2i users compared with in nonusers (P < 0.001). CONCLUSION: SGLT2is increase overall survival and cancer-specific survival in patients with cancer in a dose-dependent manner.

Comparative Effectiveness of Intensity-Modulated Proton Therapy Versus Intensity-Modulated Radiotherapy for Patients With Inoperable Esophageal Squamous Cell Carcinoma Undergoing Curative-Intent Concurrent Chemoradiotherapy.

INTRODUCTION: This study compared outcomes in patients with inoperable esophageal squamous cell carcinoma (ESCC) undergoing curative-intent concurrent chemoradiotherapy (CCRT) with intensity-modulated radiotherapy (IMRT) versus intensity-modulated proton therapy (IMPT). METHODS: The study encompassed a retrospective cohort analysis of patients with inoperable ESCC who underwent curative-intent CCRT from January 1, 2015, to December 31, 2020, with data sourced from the Taiwan Cancer Registry Database. In this study, both IMRT and IMPT delivered a total equivalent effective dose of approximately 5040 cGy in 28 fractions, accompanied by platinum-based chemotherapy administered as per established protocols. Multivariate Cox regression analyses were performed to assess oncologic outcomes, and statistical analyses were conducted, including inverse probability of treatment-weighted and Fine and Gray method for competing risks. RESULTS: The observed risks of ESCC-specific and all-cause mortality were lower in patients treated with IMPT compared with those treated with IMRT, with adjusted hazard ratios (aHRs) of 0.62 (95% confidence interval [CI]: 0.58-0.70) and 0.72 (95% CI: 0.66-0.80), respectively. IMPT also reduced grade 2 radiation-induced side effects, such as pneumonitis, fatigue, and major adverse cardiovascular events, with aHRs (95% CI) of 0.76 (0.66-0.82), 0.10 (0.07-0.14), and 0.70 (0.67-0.73), respectively. However, IMPT was associated with an increased risk of grade 2 radiation dermatitis, with aHR (95% CI) of 1.48 (1.36-1.60). No substantial differences were found in the incidence of radiation esophagitis between IMPT and IMRT when adjusting for covariates. CONCLUSION: IMPT seems to be associated with superiority over IMRT in managing patients with inoperable ESCC undergoing curative-intent CCRT, suggesting improved survival outcomes and reduced toxicity. These findings have significant implications for the treatment of ESCC, particularly when surgery is not an option.

Statin use reduces radiation-induced stroke risk in advanced nasopharyngeal carcinoma patients.

OBJECTIVE: This cohort study aimed to evaluate the impact of statin use on ischemic stroke risk in patients with advanced nasopharyngeal carcinoma (NPC) undergoing standard concurrent chemoradiotherapy (CCRT). METHODS: Using data from the Taiwan Cancer Registry Database, we conducted an inverse probability of treatment-weighted Cox regression analysis to examine the association between statin use during CCRT and ischemic stroke risk. RESULTS: The adjusted hazard ratio (aHR) for ischemic stroke in the statin group compared to the non-statin group was 0.70 (95 % CI: 0.54-0.92; P < 0.0107). This protective effect was observed across different statin classes, with hydrophilic statins such as pravastatin showing an aHR of 0.37 (95 % CI: 0.17-0.85) and lipophilic statins including atorvastatin displaying an aHR of 0.32 (95 % CI: 0.21-0.50) compared to non-statin use. Analysis of cumulative defined daily doses (cDDD) revealed a dose-response relationship, with lower stroke risk observed in higher quartiles of cDDD. Additionally, patients with a daily defined dose (DDD) > 1 had a reduced risk of stroke with an aHR of 0.49 (95 % CI: 0.31-0.63), while those with DDD ≤ 1 showed an aHR of 0.59 (95 % CI: 0.40-0.84). CONCLUSIONS: Our study provides evidence supporting the beneficial effects of statin use during the CCRT period in reducing radiation-induced stroke risk among patients with advanced NPC undergoing definitive CCRT. Notably, pravastatin and atorvastatin demonstrated significant reductions in stroke occurrence. Furthermore, the findings suggest a dose-response relationship, where higher cumulative doses and greater daily dose intensity of statin use were associated with a lower risk of stroke.

Antihistamines H1 use on survival outcomes in esophageal squamous cell carcinoma patients undergoing concurrent chemoradiotherapy.

Esophageal squamous cell carcinoma (ESCC) is a leading cause of cancer-related mortality in Taiwan, with poor survival rates despite standard treatment with concurrent chemoradiotherapy (CCRT). Antihistamines H1 (AH1) may have anticancer effects by reducing allergic reactions, activating mitogen-activated protein kinases, and regulating the immune system. However, the impact of AH1 use during CCRT on survival outcomes in patients with ESCC remains uncertain. A propensity score-matched cohort study was conducted using data from the Taiwan Cancer Registry Database and National Health Insurance Research Database. The primary outcome measures were overall survival and ESCC-specific survival. We analyzed the effects of AH1 use during CCRT on these outcomes using multivariable Cox proportional hazards regression models. The current study involved 981 individuals diagnosed with ESCC who underwent standard CCRT. Out of these, 309 were placed in the non-AH1 group and 672 in the AH1 group. AH1 use during CCRT was found to be associated with improved overall survival (adjusted hazard ratio [HR], 0.52; 95% CI, 0.44-0.60; P<0.0001) and ESCC-specific survival (adjusted HR, 0.47; 95% CI, 0.39-0.56; P<0.0001) compared with nonuse. A dose-response relationship was also observed, with higher cumulative defined daily doses of AH1 associated with lower mortality. The optimal daily intensity dose for AH1 use was found to be 0.84 defined daily doses with the lowest mortality. Our study demonstrates that AH1 use during CCRT for ESCC is associated with improved overall survival and ESCC-specific survival.

Data-driven, two-stage machine learning algorithm-based prediction scheme for assessing 1-year and 3-year mortality risk in chronic hemodialysis patients.

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.

Optimizing statin therapy for primary prevention of cardiovascular disease in type 2 diabetes mellitus patients: Exploring dose, class, and intensity.

PURPOSE: To investigate the impact of statin use on primary prevention of cardiovascular disease (CVD) in patients with type 2 diabetes mellitus (T2DM) in a dose-, class-, and use intensity-dependent manner. METHODS: We used an inverse probability treatment-weighted Cox hazards model, with statin use status as a time-dependent variable. RESULTS: Our results showed that statin use was associated with a significant reduction in CVD risk with an adjusted hazard ratio of 0.39. Pitavastatin was found to have the lowest CVD risk among the different classes of statins, followed by rosuvastatin, pravastatin, atorvastatin, simvastatin, fluvastatin, and lovastatin. Our analysis also revealed that a higher cumulative defined daily dose per year of statin was associated with a lower CVD risk. Additionally, a higher intensity of daily statin dose was associated with a lower CVD risk in patients with T2DM. CONCLUSION: This study highlights the importance of statin use in reducing the risk of CVD in patients with T2DM, and the significance of dose, class, and intensity of statin use, in particular, pitavastatin class of statins was found to be the most effective in primary prevention of CVD in T2DM.

Treatment pattern and health care resource utilization for Taiwanese patients with migraine: a population-based study.

Objectives: Given the substantial disease burden, appropriate and effective management of migraine is a public health priority. To gain insights into real-world migraine management practices in Taiwan, current treatment patterns, costs, and health care resource use were assessed. Methods: This was a retrospective, longitudinal study using the Taiwan National Health Insurance Research Database. Included patients had an initial diagnosis of migraine (defined using International Classification of Diseases codes) between 1 January 2013 and 31 December 2017. Data analyzed included demographics; the use, number, and type of acute and preventive medications; and drug and medical services costs. Data were stratified according to migraine type (chronic [CM] or episodic [EM] migraine). Results: A total of 312,718 patients were included in the analyses: 53,992 (17.3%) had CM and 258,726 (82.7%) had EM. Most patients (81.7%) had used acute and/or preventive medications; acute medications used more frequently than preventive medications (78.0% vs. 20.2%). Acute medications were used by 81.6 and 77.3% of patients with CM and EM, respectively. Commonly used acute medications were acetaminophen (68.8%), ergots (49.4%), and non-steroidal anti-inflammatory drugs (38.4%); the use of triptans (6.0%), tramadol (3.1%), and other opioids (0.2%) was less common. A total of 28.6 and 18.5% of patients with CM and EM, respectively, used preventive medications. Flunarizine (68.9%), propranolol (40.7%), and topiramate (16.0%) were the most commonly used preventive medications. Most patients had used 1-2 acute or preventive medications, with the use of ≥3 acute or preventive medications more common in patients with CM than EM. Average total medical cost per annum was 4,169 New Taiwan Dollars (NTDs) per CM patient and 2,928 NTDs per EM patient, with CM patients having higher costs associated with medical service utilization and acute medication use. Conclusion: These real-world data suggest unmet needs for Taiwanese patients with migraine, including under-utilization of preventive medications and greater costs and health care resource use for patients with CM versus EM. These findings provide important information on treatment patterns, cost, and health care resource use for patients with migraine in Taiwan.

Dental scaling and lower risk of spontaneous intracranial hemorrhage.

Background: -Spontaneous intracranial hemorrhage (ICH) has high fatality while has few proven treatments. We aim at investigating the association between dental scaling (DS) and the risk of ICH. Methods: -In this cohort study, two cohorts were matched by propensity score based on potential confounders. Data from ICH between January 2008 and December 2014 in Taiwan were analyzed. The subjects underwent DS at least 6 times between January 1, 2002, and December 31, 2007, while the matched controls did not undergo any DS during the same period. Cumulative incidences and hazard ratios (HRs) were calculated after adjusting for competing confounders. Results: -Each cohort consisted of 681,126 subjects. Compared with the non-DS cohort, the regular-DS cohort had a significantly lower incidence of ICH (0.8% vs 1.2%; P < 0.0001), and the adjusted hazards ratio (aHR) of 7-year ICH was 0.61 (95% confidence interval, CI, 0.59-0.63; P < 0.0001). The 30-39-year age group of the regular-DS cohort had the lowest HR (0.57; 95% CI, 0.52-0.61; P < 0.0001) of 7-year ICH when compared with similar controls. Compared with the controls, the regular-DS cohort also had significantly lower HR (0.82; 95% CI, 0.81-0.82; P < 0.0001) of 7-year hypertension. Compared with those without DS, the lowest risk of intracerebral hemorrhage was observed in the male participants with regular DS (0.43; 95% CI, 0.40-0.47; P < 0.0001). Conclusions: -Regular DS was consistently associated with lower ICH risk in subjects aged 30-59 years, which may benefit from the decreased HBP risk. DS had a potential role in the prophylaxis for ICH, a condition with a high disability or mortality.

The Protective Effect of Vitamin D on Dementia Risk in Hemodialysis Patients.

BACKGROUND: Patients with end-stage renal disease (ESRD) undergoing hemodialysis are at an elevated risk of developing dementia, potentially linked to the high prevalence of vitamin D deficiency in this population, which may contribute to cognitive impairment. Nevertheless, the impact of vitamin D supplementation on the risk of dementia in hemodialysis patients remains uncertain, necessitating further investigation to elucidate the potential benefits of vitamin D intervention in this vulnerable group. METHODS: In this propensity-score-matched comparative cohort study, we sought to assess the impact of vitamin D supplementation on the occurrence of dementia in patients with end-stage renal disease (ESRD) undergoing hemodialysis. A total of 1424 patients were included and matched 1:1 using propensity scores. The study population was divided into two groups: those receiving vitamin D supplementation at a dose of ≥70 µg/week and those without any supplementation. The primary outcome of interest was the incidence of dementia. We calculated adjusted hazard ratios (aHRs) to examine the association between vitamin D supplementation and the risk of dementia while controlling for relevant covariates. RESULTS: The adjusted hazard ratio (aHR) comparing vitamin D supplementation to no supplementation was 0.44 (95% CI 0.29-0.69; p < 0.0001), demonstrating a significant decrease in the risk of dementia associated with vitamin D supplementation. The aHRs for vitamin D supplementation at different dose ranges (70-105, 106-350, 351-1000, and >1000 µg/week) were 0.51, 0.49, 0.43, and 0.41, respectively (p for trend < 0.0001). These findings suggest a potential dose-dependent relationship between vitamin D supplementation and the reduction of dementia risk. CONCLUSIONS: In our study, we found that vitamin D supplementation at doses of ≥70 µg/week significantly reduced the risk of dementia in patients with end-stage renal disease (ESRD) undergoing hemodialysis. Furthermore, our results indicated a dose-dependent effect, with higher doses of supplementation correlating with a greater reduction in dementia risk. These findings underscore the potential of vitamin D supplementation as a preventive approach for cognitive impairment in this high-risk population.

Statin use and its association with decreased risk of esophageal squamous cell carcinoma in betel nut chewers.

BACKGROUND: Betel nut chewing involves the chewing of areca nuts or betel quid (areca nuts wrapped in betel leaves), which is associated with an increased risk of esophageal squamous cell carcinoma (ESCC). Statins have anticancer properties. We investigated the association between statin use and ESCC risk in betel nut chewers. METHODS: The study included 105 387 betel nut chewers matched statin users and nonusers. Statin use was defined as the use of ≥28 cumulative defined daily doses (cDDDs) of statin. The primary outcome was incidence of ESCC. RESULTS: The incidence rate of ESCC was significantly lower in statin users than in nonusers (2.03 vs. 3.02 per 100 000 person-years). Statin users had a lower incidence rate ratio of 0.66 for ESCC (95% confidence interval [CI]: 0.43-0.85) relative to nonusers. After potential confounders were adjusted for, statin use was determined to be associated with a reduced risk of ESCC (adjusted hazard ratio [aHR], 0.68; 95% CI: 0.51-0.91). A dose-response relationship was observed between statin use and ESCC risk; the aHRs for statin use at 28-182 cDDDs, 183-488 cDDDs, 489-1043 cDDDs, and > 1043 cDDDs were 0.92, 0.89, 0.66, and 0.64, respectively. CONCLUSION: Statin use was revealed to be associated with a reduced risk of ESCC in betel nut chewers.

Protective Effects of Different Classes, Intensity, Cumulative Dose-Dependent of Statins Against Primary Ischemic Stroke in Patients with Type 2 Diabetes Mellitus.

PURPOSE OF REVIEW: The aim of this study is to investigate the protective effects of different statin classes, intensity, and cumulative dose-dependent against primary ischemic stroke in patients with T2DM. RECENT FINDINGS: The Cox hazards model was used to evaluate statin use on primary ischemic stroke. Case group: T2DM patients who received statins; control group: T2DM patients who received no statins during the follow-up. Adjusted hazard ratio (aHR) for primary ischemic stroke was 0.45 (95% CI: 0.44 to 0.46). Cox regression analysis showed significant reductions in primary ischemic stroke incidence in users of different statin classes. Corresponding aHRs (95% CI) were 0.09 to 0.79 for pitavastatin, rosuvastatin, atorvastatin, pravastatin, simvastatin, fluvastatin, and lovastatin. Multivariate analyses indicated significant reductions in primary ischemic stroke incidence for patients who received different cumulative defined daily doses (cDDDs) per year (cDDD-year). Corresponding aHRs (95% CI) were 0.17 to 0.77 for quartiles 4 to 1 of cDDD-years, respectively (P for trend < .0001). Optimal intensity daily dose of statin use was 0.89 DDD with the lowest aHR of primary ischemic stroke compared with other DDDs. Persistent statin use reduces the risk of primary ischemic stroke in T2DM patients. Higher cDDD-year values are associated with higher reductions in primary ischemic stroke risk in T2DM patients.

Chinese Herbal Medicine Improved Survival in Stage IV Breast Cancer Patients: Data Mining of the Incorporated Taiwan Cancer Registry Database and Hospital Database.

BACKGROUND: According to recent research, breast cancer has become the most commonly diagnosed non-skin cancer type among the entire population. Meanwhile, Chinese herbal medicine (CHM) has become an important therapy to improve the survival rate and quality of life in metastatic cancer patients, as part of a wider trend toward more personalized medicine. However, there is a lack of research in terms of the association between stage IV breast cancer and CHM. Therefore, this study aimed to investigate the association between CHM and the survival rate in breast cancer patients at different cancer stages, with a particular focus on patients diagnosed with stage IV. METHODS: Patients with an initial diagnosis of breast cancer identified from the Taiwan Cancer Registry Database (TCRD) and China Medical University Hospital (CMUH) database were included in this study. Demographic characteristics including gender, age, and comorbidities were evaluated. Between-group differences for continuous and categorical variables were evaluated by the Student's t-test and Chi-square test, respectively. Patients diagnosed with breast cancer were recruited and divided into cohorts of CHM users and non-users with a 1:1 propensity score matching. The survival of breast cancer patients was assessed by the Cox proportional hazard model. The cumulative incidence of survival was assessed by Kaplan-Meier analysis. RESULTS: The adjuvant CHM treatment was associated with a higher survival rate in stage IV breast cancer patients (HR: 0.45, 95% CI: 0.2853-0.7044]. Additionally, the use of CHM had a positive impact on survival in stage IV breast cancer patients who had received surgery (P: .0273, HR: 0.3406, 95% CI: 0.1309-0.8865), chemotherapy (P: .0004, HR: 0.3893, 95% CI: 0.231-0.656), and hormone therapy (P: .0013, HR: 0.3491, 95% CI: 0.1836-0.6636). In terms of the specific CHM associated with survival, Zhi-Gan-Cao-Tang (ZGCT), Phellodendron chinense Schneid. (huang-bai), and Paeonia lactiflora Pall. (chi-shao) were the 3 most commonly prescribed herbal medicines correlated with a higher survival rate among stage IV breast cancer patients. CONCLUSIONS: CHM associated with conventional management achieved significant survival benefits in patients with stage IV breast cancer. Additional randomized controlled trials for prospective study are recommended for further validation.

Using the H2O Automatic Machine Learning Algorithms to Identify Predictors of Web-Based Medical Record Nonuse Among Patients in a Data-Rich Environment: Mixed Methods Study.

BACKGROUND: With 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. OBJECTIVE: On the basis of demographic and individual behavioral characteristics, this study explores the predictors of web-based medical record nonuse among patients. METHODS: Data 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. RESULTS: Among 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%). CONCLUSIONS: When 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.

H1-antihistamine use and head and neck cancer risk in type 2 diabetes mellitus.

This study aimed to examine the association between the use of H1-antihistamines (AHs) and head and neck cancer (HNC) risk in patients with type 2 diabetes mellitus (T2DM). Data from the National Health Insurance Research Database of Taiwan were analyzed for the period from 2008 to 2018. A propensity-score-matched cohort of 54,384 patients each in the AH user and nonuser groups was created and analyzed using Kaplan-Meier method and Cox proportional hazards regression. The results showed that the risk of HNC was significantly lower in AH users (adjusted hazard ratio: 0.55, 95% CI: 0.48 to 0.64) and the incidence rate was also lower (5.16 vs. 8.10 per 100,000 person-years). The lower HNC incidence rate in AH users (95% CI: 0.63; 0.55 to 0.73) suggests that AH use may reduce the risk of HNC in T2DM patients.