Computational prediction of Calu-3-based in vitro pulmonary permeability of chemicals.

Pulmonary is a potential route for drug delivery and exposure to toxic chemicals. The human bronchial epithelial cell line Calu-3 is generally considered to be a useful in vitro model of pulmonary permeability by calculating the apparent permeability coefficient (Papp) values. Since in vitro experiments are time-consuming and labor-intensive, computational models for pulmonary permeability are desirable for accelerating drug design and toxic chemical assessment. This study presents the first attempt for developing quantitative structure-activity relationship (QSAR) models for addressing this goal. A total of 57 chemicals with Papp values based on Calu-3 experiments was first curated from literature for model development and testing. Subsequently, eleven descriptors were identified by a sequential forward feature selection algorithm to maximize the cross-validation performance of a voting regression model integrating linear regression and nonlinear random forest algorithms. With applicability domain adjustment, the developed model achieved high performance with correlation coefficient values of 0.935 and 0.824 for cross-validation and independent test, respectively. The preliminary results showed that computational models could be helpful for predicting Calu-3-based in vitro pulmonary permeability of chemicals. Future works include the collection of more data for further validating and improving the model.

Trend and survival benefit of Oncotype DX use among female hormone receptor-positive breast cancer patients in 17 SEER registries, 2004-2015.

PURPOSE: To examine (1) the trend and associated factors of Oncotype DX (ODX) use among hormone receptor-positive (HR+) breast cancer (BC) patients in 2004-2015; (2) the trend of reported chemotherapy by Recurrence Score (RS); and (3) the survival differences associated with ODX use. METHODS: ODX data from Genomic Health Inc. were linked with 17 SEER registries data. HR + BC cases with lymph node negative (N0) or 1-3 positive LNs (N1) from 2004-2015 were analyzed. The Cochrane-Armitage trend test, logistic regression, Kaplan-Meier survival curve, and stratified Cox model were performed. Survival analysis was restricted to HR+/HER2- patients from 2010 to 2014, matched on propensity score. RESULTS: ODX use increased substantially from 2004 to 2015 (N0: 2.0% to 42.7%; N1: 0.3% to 27.9%). Non-Hispanic black and Medicaid insured patients had lower odds of receiving ODX. N0 patients with moderately differentiated or 2.1-5.0 cm tumor and N1 patients with well-differentiated or < 2.0 cm tumor had higher odds of using ODX. The reported chemotherapy use decreased significantly with low and intermediate RS, and increased for high RS among N0 patients. ODX use was associated with better breast cancer-specific survival [hazard ratio (95% CI) N0 1.96 (1.60-2.41), N1 1.90 (1.42-2.54)] and overall survival [N0 2.06 (1.83-2.31), N1 1.72 (1.42-2.09)], especially in the first 36 months. CONCLUSION: ODX use has increased significantly since 2004, nonetheless disparities remain, especially for racial/ethnic minorities and Medicaid insured patients. Administering chemotherapy based on ODX results has been improved among N0 patients. Patients receiving ODX had better survival than those not.

A Partnership in Health-Related Social Media for Young Breast Cancer Survivors.

In the United States, about 11% (26,393) of those diagnosed with breast cancer in 2016 will be young or less than 45 years old. Young breast cancer survivors, compared to older cancer survivors, are a disparate group that experience higher incidence of advanced disease, greater mortality, and poorer quality of life, and are often faced with difficulty locating support that meet the unique needs of young women. The Gulf States Young Breast Cancer Survivor Network, composed of three sister networks, formed a partnership aimed at harnessing the power of social media to reach and impact the lives of young women with breast cancer. The collaborative partnership framework and the power of synergy are shown in merging two existing programs and incorporating a third new program.

Hospitalized burn injury risk associated with benzodiazepines and Z-drugs in elders: A population-based case-control study.

OBJECTIVE: To examine the association between benzodiazepines (BZDs) and Z-drugs treatment and risk of burn injury in elders. METHODS: We designed a nested case-control study. All subjects were aged 65 and older and enrolled in the National Health Insurance program in Taiwan, 2003 to 2012; 813 cases were identified with burn injury for the first time in their inpatient claims, and they were individually matched to 4879 controls based on age, gender, and index year. Benzodiazepines and Z-drugs usage (doses, duration, half-life) and the other covariates including comorbidities, health care utilization, and psychotropic medications used in the 365 days before index events were examined. RESULTS: A significant increased risk of burn injury hospitalization in elders was observed among current Z-drugs users compared with nonusers (adjusted odds ratio [AOR] = 1.59, 95% confidence interval [CI] [1.23, 2.07]). BZDs at high (AOR = 1.81, 95% CI [1.12, 2.94] and medium dosage (AOR = 1.53, 95% CI [1.15, 2.04] and Z-drugs at medium dosage (AOR = 1.60, 95% CI [1.20, 2.12]) were all significantly increased the burn-related injury requiring hospitalization. Polypharmacy of anxiolytic and hypnotic BZDs, long- and short-acting BZDs, and more than one BZD with or without Z-drugs also increased the risk. CONCLUSIONS: BZDs and Z-drugs prescriptions in elders may be associated with increased risk of burn injury hospitalization. When prescribing BZDs and Z-drugs, clinicians should exercise caution with the elderly to minimize risks.

Trends and factors in antipsychotic use of outpatients with anxiety disorders in Taiwan, 2005-2013: A population-based study.

AIM: Antipsychotics off-label use is common in clinical practice but information is limited in regards to the trends of antipsychotic use in specific mental disorders in Taiwan. This study aimed to examine the trends and associated factors of antipsychotic use among outpatients with anxiety disorders in Taiwan during 2005-2013. METHODS: We assessed the annual prescriptions of antipsychotic use in nine consecutive years (2005-2013) using the National Health Insurance Research Database among adults (aged ≥18 years) with anxiety disorders in outpatient visits in Taiwan. We applied logistic regression to examine the trends and associated factors of antipsychotic use. RESULTS: The proportion of antipsychotic medication use for anxiety disorder increased from 8.4% in 2005 to 9.1% in 2013. First-generation antipsychotics (FGA) use was more than that of second-generation antipsychotics (SGA) use in patients with anxiety disorder through the 9-year period. Sulpiride and flupentixol were the two most common FGA in the treatment of anxiety disorder. Patients with specific anxiety disorder (post-traumatic stress disorder, panic disorder/agoraphobia, generalized anxiety disorder, and obsessive-compulsive disorder), female sex, younger age (age < 65 years), comorbidity with major depression or minor depression, antidepressants concurrent use, and visits to psychiatrists, medical centers and primary care were significantly more likely to take prescribed antipsychotics. CONCLUSION: Antipsychotic off-label use significantly increased among patients with anxiety disorder in this national representative cohort. Such increased use of antipsychotics could be driven by augmentation of their prescription for major depression. As their efficacy and safety remain uncertain, further study is warranted.

Association of benzodiazepine and Z-drug use with the risk of hospitalisation for fall-related injuries among older people: a nationwide nested case-control study in Taiwan.

BACKGROUND: Non-benzodiazepine hypnotics (Z-drugs) are advocated to be safer than benzodiazepines (BZDs). This study comprehensively investigated the association of BZD and Z-drug usage with the risk of hospitalisation for fall-related injuries in older people. METHODS: This study used the Taiwan National Health Insurance Database with a nested matched case-control design. We identified 2238 elderly patients who had been hospitalised for fall-related injuries between 2003 and 2012. They were individually matched (1:4) with a comparison group by age, sex, and index year. Conditional logistic regression was used to determine independent effects of drug characteristics (type of exposure, dosage, half-life, and polypharmacy) on older people. RESULTS: Older people hospitalisation for fall-related injuries were significantly associated with current use of BZDs (adjusted odds ratio [AOR] = 1.32, 95% confidential interval [CI] = 1.17-1.50) and Z-drugs (AOR = 1.24, 95%CI = 1.05-1.48). At all dose levels of BZDs, high dose levels of Z-drugs, long-acting BZD, and short-acting BZD use were all significantly increased the risk of fall-related injuries requiring hospitalisation. Polypharmacy, the use of two or more kinds of BZDs, one kind of BZD plus Z-drugs and two or more kinds of BZDs plus Z-drugs, also significantly increased the risk (AOR = 1.61, 95% CI = 1.38-1.89; AOR = 1.65, 95% CI = 1.08-2.50, and AOR = 1.58, 95% CI = 1.21-2.07). CONCLUSIONS: Different dose levels and half-lives of BZDs, a high dose of Z-drugs, and polypharmacy with BZDs and Z-drugs were associated with an increased risk of fall-related injury requiring hospitalisation in older people. Physicians should balance the risks and benefits when prescribing these drug regimens to older people considering the risk of falls.

False positive ketamine urine immunoassay screen result induced by quetiapine: A case report.

Ketamine immunoassay urine drug screen (UDS) is commonly used in Taiwan. However, there was limited report about possible drug which may cause false positive results in ketamine screen test. We report two cases who used quetiapine showed positive in ketamine urine immunoassay screen initially, and found to be false positive in confirmation test. Clinicians should be aware of the false positive result of ketamine UDS caused by currently used medication.

Over-expression of cofilin-1 suppressed growth and invasion of cancer cells is associated with up-regulation of let-7 microRNA.

Cofilin-1, a non-muscle isoform of actin regulatory protein that belongs to the actin-depolymerizing factor (ADF)/cofilin family is known to affect cancer development. Previously, we found that over-expression of cofilin-1 suppressed the growth and invasion of human non-small cell lung cancer (NSCLC) cells in vitro. In this study, we further investigated whether over-expression of cofilin-1 can suppress tumor growth in vivo, and performed a microRNA array analysis to better understand whether specific microRNA would be involved in this event. The results showed that over-expression of cofilin-1 suppressed NSCLC tumor growth using the xenograft tumor model with the non-invasive reporter gene imaging modalities. Additionally, cell motility and invasion were significantly suppressed by over-expressed cofilin-1, and down-regulation of matrix metalloproteinase (MMPs) -1 and -3 was concomitantly detected. According to the microRNA array analysis, the let-7 family, particularly let-7b and let-7e, were apparently up-regulated among 248 microRNAs that were affected after over-expression of cofilin-1 up to 7 days. Knockdown of let-7b or let-7e using chemical locked nucleic acid (LNA) could recover the growth rate and the invasion of cofilin-1 over-expressing cells. Next, the expression of c-myc, LIN28 and Twist-1 proteins known to regulate let-7 were analyzed in cofilin-1 over-expressing cells, and Twist-1 was significantly suppressed under this condition. Up-regulation of let-7 microRNA by over-expressed cofilin-1 could be eliminated by co-transfected Twist-1 cDNA. Taken together, current data suggest that let-7 microRNA would be involved in over-expression of cofilin-1 mediated tumor suppression in vitro and in vivo.

Development of a short version of the Aging Males' Symptoms scale: Mokken scaling analysis and Rasch analysis.

The aim of this study was to develop a psychometrically sound short version of the 17-item Aging Males' Symptoms (AMS) scale using Mokken scale analysis (MSA) and Rasch analysis. We recruited a convenient sample of 1787 men (age: mean (SD) = 43.8 (11.5) years) who visited a men's health polyclinic in Taiwan and completed the AMS scale. The scale was first assessed using MSA. The remaining items were assessed using Rasch analysis. We used a stepwise approach to remove items with χ(2) item statistics and mean square values while monitoring unidimensionality. The item reduction process resulted in a 6-item version of the AMS scale (AMS-6). The AMS-6 scale included a 5-item psychosomatic subscale (original items 1, 4, 5, 8, and 9) and a 1-item sexual subscale (original item 16). Analyses confirmed that the 5-item psychosomatic subscale was a Rasch scale. The AMS-6 correlated well with the AMS scales: the 5-item psychosomatic subscale correlated with the AMS scale (r between 0.50 and 0.92); the 1-item sexual subscale correlated with the sexual subscale of the AMS scale (r = 0.81). A 6-item short form of the AMS scale had satisfactory measurement properties. This version may be useful for estimating psychosomatic and sexual symptoms as well as health-related quality of life with a minimal burden on respondents.

A reliability generalization meta-analysis of coefficient alpha and test-retest coefficient for the aging males' symptoms (AMS) scale.

PURPOSE: The aging males' symptoms (AMS) scale is an instrument used to determine the health-related quality of life in adult and elderly men. The purpose of this study was to synthesize internal consistency (Cronbach's alpha) and test-retest reliability for the AMS scale and its three subscales. METHODS: Of the 123 studies reviewed, 12 provided alpha coefficients which were then used in the meta-analyses of internal consistency. Seven of the 12 included studies provided test-retest coefficients, and these were used in the meta-analyses of test-retest reliability. RESULTS: The AMS scale had excellent internal consistency [α = 0.89 (95% CI 0.88-0.90)]; the mean alpha estimates across the AMS subscales ranged from 0.79 to 0.82. The AMS scale also had good test-retest reliability [r = 0.85 (95% CI 0.82-0.88]; the test-retest reliability coefficients of the AMS subscales ranged from 0.76 to 0.83. There was significant heterogeneity among the included studies. CONCLUSIONS: The AMS scale and the three subscales had fairly good internal consistency and test-retest reliability. Future psychometric studies of the AMS scale should report important characteristics of the participants, details of item scores, and test-retest reliability.

Psychotropic drugs and risk of burn injury in individuals with mental illness: a 10-year population-based case-control study.

PURPOSE: We aimed to investigate the association between psychotropic treatment and risk of burn injury in individuals with mental illness. METHODS: A nested case-control study was conducted by using the National Health Insurance Research Database in Taiwan. A total of 3187 cases with burn injury under International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes 940-949 and 19 122 matched controls were identified from 2003 to 2012. Four kinds of psychotropic agents (antipsychotics (APs), antidepressants (ADs), benzodiazepines, and z-drugs) were examined. Psychotropic exposure status was measured, and a set of potential confounding factors was adjusted in the analyses. Conditional logistic regressions were applied to determine the effect of psychotropic use on burn injury. RESULTS: A significant increased risk of burn injury was observed among psychotropic users compared with non-users (adjusted odds ratio (AOR) = 1.45, 95%CI = 1.31-1.61). When classifying psychotropic users into current, new, continuous, and past users, a significant elevated risk of burn injury was found across all groups (AOR = 1.76, 95%CI = 1.54-2.00 in current users; AOR = 2.02, 95%CI = 1.55-2.65 in new users; AOR = 1.72, 95%CI = 1.50-1.96 in continuous users; and AOR = 1.35, 95%CI = 1.21-1.51 in past users). When assessing each individual kind of examined psychotropic agents, a significant elevated risk of burn injury was found among users of APs, ADs, benzodiazepines, and z-drugs except for current and continuous users of z-drugs. CONCLUSIONS: The results demonstrate an elevated risk of burn injury among individuals with current psychotropic use. The findings underscore the need for greater attention to be given to the cognitive performance and psychomotor abilities of individuals taking psychotropic medications in order to prevent the occurrence of burn injury. Copyright © 2016 John Wiley & Sons, Ltd.

Multitask learning for predicting pulmonary absorption of chemicals.

Pulmonary absorption is an important route for drug delivery and chemical exposure. To streamline the chemical assessment process for the reduction of animal experiments, several animal-free models were developed for pulmonary absorption research. While Calu-3 and Caco-2 cells and their derived computational models were used in estimating pulmonary permeability, the ex vivo isolated perfused lung (IPL) models are considered more clinically relevant measurements. However, the IPL experiments are resource-consuming making it infeasible for the large-scale screening of potential inhaled toxicants and drugs. In silico models are desirable for estimating pulmonary absorption. This study presented a novel machine learning method that employed an extratrees-based multitask learning approach to predict the IPL absorption rate constant (kaIPL) of various chemicals. The shared permeability knowledge was extracted by simultaneously learning three relevant tasks of Caco-2 and Calu-3 cell permeability and IPL absorption rate. Seven informative physicochemical descriptors were identified. A rigorous evaluation of the developed prediction model showed good performance with a high correlation between predictions and observations (r = 0.84) in the independent test dataset. Two case studies of inhalation drugs and respiratory sensitizers revealed the potential application of this model, which may serve as a valuable tool for predicting pulmonary absorption of chemicals.

Oral post-treatment supplementation with a combination of glutamine, citrulline, and antioxidant vitamins additively mitigates jejunal damage, oxidative stress, and inflammation in rats with intestinal ischemia and reperfusion.

INTRODUCTION: Intestinal ischemia and reperfusion (IIR) injury is closely associated with oxidative stress. Evidence shows that oral supplementation with glutamine and citrulline alleviates IIR-induced jejunal damage. We investigated the effects of a combination of glutamine, citrulline, and antioxidant vitamins on IIR-induced jejunal damage, oxidative stress, and inflammation. METHOD: Male Wistar rats that underwent 60 min of superior mesenteric artery occlusion were orally administered glutamine plus citrulline (GC), vitamin C plus E (CE), or a combination of GC and CE 15 min before and 3, 9, and 21 h after reperfusion. Healthy rats without IIR were used as controls. RESULTS: After reperfusion for 24 h, rats with IIR showed lower levels of red blood cells, hemoglobin, serum glucose, and jejunal DNA and increased white blood cell counts compared to controls (1-way ANOVA with the least significant difference, P < 0.05). The IIR-induced decrease in serum albumin and increase in plasma interleukin-6 and jejunal thiobarbituric acid-reactive substances (TBARS) were significantly reversed by GC and/or CE. The results of the 2-way ANOVA indicated that GC was the main factor that increased jejunal villus height and muscularis DNA, and CE was the main factor that increased jejunal muscularis protein and decreased jejunal proinflammatory cytokine levels and myeloperoxidase activity. In addition, GC and CE are the main factors that decrease plasma proinflammatory cytokine levels and the jejunal apoptotic index. CONCLUSION: Oral post-treatment supplementation with glutamine and citrulline, combined with vitamins C and E, may alleviate IIR-induced oxidative stress, inflammation, and jejunal damage.

Rapid intervention team strategy improves intervention quality for patients undergoing hemodialysis with arteriovenous shunt dysfunction or failure.

BACKGROUND: Vascular access dysfunction is a great burden for hemodialysis patients. Early intervention of a dysfunctional arteriovenous shunt is associated with higher technical success and may improve midterm patency. This trial aimed to estimate the feasibility of a new system, the "rapid intervention team" (RIT) strategy. METHODS: We recruited hemodialysis patients who visited our hospital because of arteriovenous shunt dysfunction or failure to undergo an RIT strategy from September 1, 2019 to December 31, 2022. In addition, we included a control group comprising patients who underwent percutaneous intervention for arteriovenous shunt dysfunction or failure before this strategy was implemented from February 1, 2017 to December 31, 2022. Case number, time to intervention, all-cause mortality, cumulative survival rate, and number of patients who required temporary dialysis catheter insertion and recreation were compared between the two groups. The primary endpoints were double-lumen insertion, a composite outcome involving permanent catheter insertion, and the need for recreation. The secondary endpoint was all-cause mortality. RESULTS: We enrolled 1054 patients, including 544 (51.6%) and 510 (48.4%) in the RIT and control groups, respectively. Even with the coronavirus disease of 2019 (COVID-19) pandemic, the number of cases significantly increased after the implementation of the RIT strategy (from 216 in 2019 to 828 in 2022, p for trend <0.001). The RIT group had a shortened time to intervention ( p for trend <0.001). The implementation of the RIT strategy was significantly associated with a reduced risk of insertion of a temporary double-lumen catheter and recreation of vascular access (1% vs 6% and 1% vs 28%, respectively; both p < 0.01). The cumulative survival rate was not significantly different between the RIT and control groups ( p = 0.16). CONCLUSION: The implementation of the RIT strategy improves the quantity and quality of percutaneous transluminal intervention for arteriovenous shunt dysfunction or failure in patients undergoing hemodialysis.

Machine Learning Model for Anesthetic Risk Stratification for Gynecologic and Obstetric Patients: A Novel Approach for Early Detection.

BACKGROUND: Preoperative evaluation is important, our study explored the application of machine learning methods for anesthetic risk classification and for the evaluation of the contributions of various factors. To minimize the effects of confounding variables during model training, we used a homogenous group with similar physiological states and ages undergoing similar pelvic organ-related procedures not involving malignancies. OBJECTIVE: Data on women of reproductive age (age = 20-50 years) who underwent gestational or gynecological surgery between January 1, 2017, and December 31, 2021, were obtained from the National Taiwan University Hospital Integrated Medical Database. METHODS: We first performed an exploratory analysis and selected key features. We then performed data preprocessing to acquire relevant features related to preoperative examination. To further enhance predictive performance, we employed the log likelihood ratio algorithm to generate comorbidity patterns. Lastly, we input the processed features into the light gradient boosting machine (LightGBM) model for training and subsequent prediction. RESULTS: A total of 10,892 patients were included. Within this data set, 9893 patients were classified as having low anesthetic risk (American Society of Anesthesiologists physical status score 1-2), and 999 patients were classified as having high anesthetic risk (American Society of Anesthesiologists physical status score > 2). The area under the receiver operating characteristic curve of the LightGBM model was 90.25. CONCLUSIONS: By combining comorbidity information and clinical laboratory data, our methodology based on the LightGBM model provides more accurate predictions for anesthetic risk classification. CLINICALTRIAL: This study was registered with the Research Ethics Committee of the National Taiwan University Hospital with trial number 202204010RINB.

Spiritual leadership influence on employee creative service performance: a moderated mediation analysis.

This paper expands the understanding of the relationship between spiritual leadership (SPL) and the creative service performance of employees. The research model, based on cognitive evaluation theory, examines the mediating role of employee autonomy and the moderating role of proactive personality in the relationship between SPL and employee creative service performance. Data was collected from 351 employees in China to test the moderated mediation model of this study. The empirical analysis reveals a positive association between SPL and employee autonomy, which in turn leads to increased employee creative service performance. Furthermore, the results show that SPL indirectly affects employee creative service performance via employee autonomy. Additionally, the findings suggest that a proactive personality can enhance the direct effect of SPL on employee autonomy and the indirect effect of SPL on employee creative service performance via employee autonomy. These results contribute significantly to the literature on SPL and creativity. The contributions and implications of this study are discussed in the subsequent section.

Complaint of insomnia as a predictor of aging symptoms in males at a men's health clinic.

INTRODUCTION: Issues of men's health have been greatly researched by scholars in recent decades. At men's health clinics, many patients complain of both insomnia and aging males' symptoms (AMS). These symptoms might be influenced by biological, psychological or even social factors. The aim of this study was to investigate different aspects of the relationship between insomnia and aging symptoms. METHODS: This cross-sectional study included 231 males from a men's health clinic. Participants completed a set of general data and screening assessments, including the AMS rating scale, insomnia severity index (ISI), Beck depression inventory-II (BDI-II) and Beck anxiety inventory Chinese version (BAI), to investigate the severity of aging symptoms, insomnia, depression and anxiety. RESULTS: The ISI correlated significantly with the AMS scale, both with (partial correlation coefficient = 0.470) and without (r = 0.580) controlled variances of depression and anxiety. Using linear regression, aging symptoms were statistically predicted by the severity of the ISI, and a substantial proportion of the variance was explained (adjusted R(2) = 0.410). When all variables were included, this proportion rose to 55.3% (adjusted R(2) = 0.553). CONCLUSION: We suggest that insomnia is a good predictor of aging symptoms across all age groups of men.

Linguistic Pattern-Infused Dual-Channel Bidirectional Long Short-term Memory With Attention for Dengue Case Summary Generation From the Program for Monitoring Emerging Diseases-Mail Database: Algorithm Development Study.

BACKGROUND: Globalization and environmental changes have intensified the emergence or re-emergence of infectious diseases worldwide, such as outbreaks of dengue fever in Southeast Asia. Collaboration on region-wide infectious disease surveillance systems is therefore critical but difficult to achieve because of the different transparency levels of health information systems in different countries. Although the Program for Monitoring Emerging Diseases (ProMED)-mail is the most comprehensive international expert-curated platform providing rich disease outbreak information on humans, animals, and plants, the unstructured text content of the reports makes analysis for further application difficult. OBJECTIVE: To make monitoring the epidemic situation in Southeast Asia more efficient, this study aims to develop an automatic summary of the alert articles from ProMED-mail, a huge textual data source. In this paper, we proposed a text summarization method that uses natural language processing technology to automatically extract important sentences from alert articles in ProMED-mail emails to generate summaries. Using our method, we can quickly capture crucial information to help make important decisions regarding epidemic surveillance. METHODS: Our data, which span a period from 1994 to 2019, come from the ProMED-mail website. We analyzed the collected data to establish a unique Taiwan dengue corpus that was validated with professionals' annotations to achieve almost perfect agreement (Cohen κ=90%). To generate a ProMED-mail summary, we developed a dual-channel bidirectional long short-term memory with attention mechanism with infused latent syntactic features to identify key sentences from the alerting article. RESULTS: Our method is superior to many well-known machine learning and neural network approaches in identifying important sentences, achieving a macroaverage F1 score of 93%. Moreover, it can successfully extract the relevant correct information on dengue fever from a ProMED-mail alerting article, which can help researchers or general users to quickly understand the essence of the alerting article at first glance. In addition to verifying the model, we also recruited 3 professional experts and 2 students from related fields to participate in a satisfaction survey on the generated summaries, and the results show that 84% (63/75) of the summaries received high satisfaction ratings. CONCLUSIONS: The proposed approach successfully fuses latent syntactic features into a deep neural network to analyze the syntactic, semantic, and contextual information in the text. It then exploits the derived information to identify crucial sentences in the ProMED-mail alerting article. The experiment results show that the proposed method is not only effective but also outperforms the compared methods. Our approach also demonstrates the potential for case summary generation from ProMED-mail alerting articles. In terms of practical application, when a new alerting article arrives, our method can quickly identify the relevant case information, which is the most critical part, to use as a reference or for further analysis.

A BERT-based ensemble learning approach for the BioCreative VII challenges: full-text chemical identification and multi-label classification in PubMed articles.

In this research, we explored various state-of-the-art biomedical-specific pre-trained Bidirectional Encoder Representations from Transformers (BERT) models for the National Library of Medicine - Chemistry (NLM CHEM) and LitCovid tracks in the BioCreative VII Challenge, and propose a BERT-based ensemble learning approach to integrate the advantages of various models to improve the system's performance. The experimental results of the NLM-CHEM track demonstrate that our method can achieve remarkable performance, with F1-scores of 85% and 91.8% in strict and approximate evaluations, respectively. Moreover, the proposed Medical Subject Headings identifier (MeSH ID) normalization algorithm is effective in entity normalization, which achieved a F1-score of about 80% in both strict and approximate evaluations. For the LitCovid track, the proposed method is also effective in detecting topics in the Coronavirus disease 2019 (COVID-19) literature, which outperformed the compared methods and achieve state-of-the-art performance in the LitCovid corpus. Database URL: https://www.ncbi.nlm.nih.gov/research/coronavirus/.

Longitudinal Association of Universal Screening and Treatment for Major Depressive Disorder with Survival in Cancer Patients.

Evidence for clinical screening and intervention for depression in cancer and the effect of this intervention on cancer prognosis is suboptimal. This study substantialized a complete model with universal screening and intervention for major depressive disorder (MDD) and explored its effect on survival in patients. This longitudinal study recruited cancer patients routinely screened for MDD with a two-stage model. Data including sex, age, cancer diagnosis, first diagnosis date, date of death, cancer stage, and MDD diagnosis and treatment were collected from medical records and the national registration system for cancer. Kaplan−Meier's survival analysis and the Cox proportional hazards regression model were applied to analyze the effects of associated factors on survival. Further subgroup analysis for 14 types of cancer primary site was also performed. Overall, the hazard for patients adhering to psychiatric treatment for MDD before cancer diagnosis was not statistically different from that for patients without MDD (hazard ratio (HR) = 1.061, 95% CI: 0.889−1.267, p = 0.512). The hazard for patients adhering to psychiatric treatment after cancer diagnosis was significantly lower than that for patients without MDD (HR = 0.702, 95% CI: 0.607−0.812, p < 0.001). Those who were diagnosed with MDD after cancer diagnosis and adhered poorly to psychiatric treatment had the greatest hazard (HR = 1.829, 95% CI: 1.687−1.984, p < 0.001). The effect of intervention for MDD varied across different primary cancer types.