Application of Deep Learning in Generating Structured Radiology Reports: A Transformer-Based Technique.

Since radiology reports needed for clinical practice and research are written and stored in free-text narrations, extraction of relative information for further analysis is difficult. In these circumstances, natural language processing (NLP) techniques can facilitate automatic information extraction and transformation of free-text formats to structured data. In recent years, deep learning (DL)-based models have been adapted for NLP experiments with promising results. Despite the significant potential of DL models based on artificial neural networks (ANN) and convolutional neural networks (CNN), the models face some limitations to implement in clinical practice. Transformers, another new DL architecture, have been increasingly applied to improve the process. Therefore, in this study, we propose a transformer-based fine-grained named entity recognition (NER) architecture for clinical information extraction. We collected 88 abdominopelvic sonography reports in free-text formats and annotated them based on our developed information schema. The text-to-text transfer transformer model (T5) and Scifive, a pre-trained domain-specific adaptation of the T5 model, were applied for fine-tuning to extract entities and relations and transform the input into a structured format. Our transformer-based model in this study outperformed previously applied approaches such as ANN and CNN models based on ROUGE-1, ROUGE-2, ROUGE-L, and BLEU scores of 0.816, 0.668, 0.528, and 0.743, respectively, while providing an interpretable structured report.

Organ-specific or personalized treatment for COVID-19: rationale, evidence, and potential candidates.

Although extrapulmonary manifestations of coronavirus disease 2019 (COVID-19) are increasingly reported, no effective therapeutic strategy for these multisystemic complications is available due to a poor understanding of the pathophysiology of COVID-19 multiorgan involvement. In this study, differentially expressed genes (DEGs) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected extrapulmonary organs including human pluripotent stem cells (hPSCs)-derived liver organoids and choroid plexus organoids besides transformed lung alveolar (A549) cells were analyzed. First, pathway enrichment analysis was done to compare the underlying biological pathways enriched upon SARS-CoV-2 infection in different organs. Then, these lists of DEGs were used in a connectivity map (CMap)-based drug repurposing experiment. Also, protein-protein interaction (PPI) network analysis was done to compare the associated hub genes. The results revealed different biological pathways and genes responsible for SARS-CoV-2 multisystemic pathogenesis based on the organ involved that highlighted the need for considering organ-specific treatments or even personalized therapy. Besides, some FDA-approved drugs were proposed as the potential therapeutic candidates for each infected cell line.

A connectivity map-based drug repurposing study and integrative analysis of transcriptomic profiling of SARS-CoV-2 infection.

AIMS: The recent outbreak of COVID-19 has become a global health concern. There are currently no effective treatment strategies and vaccines for the treatment or prevention of this fatal disease. The current study aims to determine promising treatment options for the COVID-19 through a computational drug repurposing approach. MATERIALS AND METHODS: In this study, we focus on differentially expressed genes (DEGs), detected in SARS-CoV-2 infected cell lines including "the primary human lung epithelial cell line NHBE" and "the transformed lung alveolar cell line A549". Next, the identified DEGs are used in the connectivity map (CMap) analysis to identify similarly acting therapeutic candidates. Furthermore, to interpret lists of DEGs, pathway enrichment and protein network analysis are performed. Genes are categorized into easily interpretable pathways based on their biological functions, and overrepresentation of each pathway is tested in comparison to what is expected randomly. KEY FINDINGS: The results suggest the effectiveness of lansoprazole, folic acid, sulfamonomethoxine, tolnaftate, diclofenamide, halcinonide, saquinavir, metronidazole, ebselen, lidocaine and benzocaine, histone deacetylase (HDAC) inhibitors, heat shock protein 90 (HSP90) inhibitors, and many other clinically approved drugs as potent drugs against COVID-19 outbreak. SIGNIFICANCE: Making new drugs remain a lengthy process, so the drug repurposing approach provides an insight into the therapeutics that might be helpful in this pandemic. In this study, pathway enrichment and protein network analysis are also performed, and the effectiveness of some drugs obtained from the CMap analysis has been investigated according to previous researches.

Comparison of risk factors of cardiovascular diseases in male and female nurses.

INTRODUCTION: Cardiovascular disease is one of the most important causes of mortality in the world; identifying and correcting the modifiable risk factors reduce the prevalence of coronary artery disorders. Nurses, with regard to their employment conditions, can be prone to cardiovascular disease. The aim of this study was to compare the risk factors of cardiovascular diseases in male and female nurses. MATERIALS AND METHODS: In this descriptive cross-sectional study, 263 nurses from Jahrom University of Medical Sciences hospitals were enrolled in the study by convenience sampling. The data collection tool was self-report Framingham Risk Score and has two parts: first part: personal data, history of disease, history, cigarette, stress and fat disorder, alcohol consumption, diet, exercise, and average hours and second part: height, weight, body mass index (BMI), waist-to-stature ratio (WSR), waist-to-hip ratio (WHR), blood pressure, triglyceride (TG), cholesterol, and fasting blood sugar. The benchmark for blood pressure was the JNC-7 guide. The Adult Treatment Panel III was the guideline. Independent t-test, Chi-square, and Mann-Whitney tests were used for data analysis. RESULTS: None of the staff reported smoking or alcohol history. Data were analyzed using descriptive and inferential statistics. There was no statistically significant difference between the mean of fasting blood glucose, systolic and diastolic blood pressure, TG and cholesterol, Framingham percentage, religious practices, green tea and black tea, fish, vegetables, and fast food. The data were analyzed with independent t-test, Chi-square, and Mann-Whitney tests. There was no statistically significant difference between the mean of fasting blood glucose, systolic and diastolic blood pressure, TG and cholesterol, Framingham Percentage, religious practices, green tea and black tea, fish, vegetables, and fast food and sports and walking of men and women were not observed. However, there was a statistically significant difference between women and men in indicators such as eating breakfast, family history, fruit consumption, high-density lipoprotein, BMI, WSR, and WHR. CONCLUSION: The results of the study showed that men are at higher risk for cardiovascular diseases and complications than women.

Spiritual intelligence of adolescents with diabetes based on demographic components.

INTRODUCTION: Spiritual intelligence is better defined as a capacity to discover and develop true meaning, deep purpose, and vision in life. The purpose of the present study was to determine the predictive role of demographic variables affecting the overall spiritual intelligence in diabetic adolescents. METHODS: In 2016, a cross-sectional study was conducted involving 200 adolescents with type 1 diabetes referring to the Iranian Diabetes Association consenting to participate. The inclusion criteria were: age ranging from 15 to 21 years, more than a year since last diagnosed with diabetes, patients' full awareness of their disease, not having other physical-psychological illnesses, and not taking any psychiatric or narcotic drugs. Spiritual intelligence was measured using the Spiritual Intelligence Self Report Inventory questionnaire consisting of 24-questions. The alpha Cronbach's method was applied to validate the questionnaire in terms of content, form, and data with the reliability calculated as 0.903. Demographic data were analyzed using SPSS software version 18. RESULTS: On total, 56% of the participants were female, 17.10 ± 1.85, and the mean duration of diabetes was 5.98% ± 3.79%, 62.5% reported diabetes history among immediate relatives. Forty-two percent of the participants were the oldest child in the family first children of the family and 29.5% were studying at the university. The mean score of spiritual intelligence was 60.42 60.42 ing from 15 to 21 years regression test using the enter method (ANOVA: 0.703, F: 0.739) showed that none of the demographic components explored did not significantly alter the scores that assessed spiritual intelligence. CONCLUSION: The outcome of the current study portrayed that demographic features do not necessarily alter the overall spiritual intelligence scores, thereby not necessarily affecting an individual's overall spirituality.

The relationship between spiritual intelligence with self-efficacy in adolescents suffering type 1 diabetes.

INTRODUCTION: An important construct to consider within diabetes management and the changing landscape of diabetes therapies is self-efficacy. Self-efficacy research holds the potential to inform and assist the diabetes team as well as patients with type 1 diabetes. METHODS: In this descriptive-correlation study, 200 adolescents with type 1 diabetes were enrolled. To measure spiritual intelligence, the 24-question Spiritual Intelligence Self-Report Inventory questionnaire and to measure self-efficacy of diabetes, the Self-efficacy Questionnaire (8 questions) were used. Data collection was conducted by simple sampling. Data were analyzed using Pearson analysis, mean, and standard deviation analysis tests. RESULTS: Nearly 66% of the participants were female, the mean age of the samples was 17.10 ± 1.85 years, the mean duration of diabetes was 5.98 ± 3.79 years, and 62.5% had a history of diabetes in first-degree relatives. Almost 42% of the participants were the first children of the family and 29.5% were studying at the university. The mean score of spiritual intelligence was 60.42 ± 12.9. The mean self-efficacy score was 5.41 ± 1.87. The mean scores in the critical thinking, personal meaning production, transcendental awareness, conscious state expansion were 18.31 ± 4.33, 13.17 ± 3.36, 11.26 ± 3.36, 46.14 ± 1.04, 11.33 ± 1.04, and 11.89 ± 3.9, respectively. Cronbach's alpha level on the level of spiritual intelligence and self-efficacy was 0.903 and 0.082, respectively, at 95% confidence level. There was a significant relationship between spiritual intelligence and self-efficacy (P = 0.026). There was no significant relationship between self-efficacy with spiritual intelligence subscales. CONCLUSION: This study showed that spiritual intelligence correlates with self-efficacy and has a decisive role in improving the health of adolescents with diabetes.

The predictive role of spiritual intelligence in self-management in adolescents with type 1 diabetes.

INTRODUCTION: Self-management leads to blood glucose control and reduced morbidity and mortality in adolescents with type 1 diabetes. Different factors affect the self-management whose role and effect are still unknown. Among the influential factors whose effect is vague are spiritual intelligence, and this study aims to investigate the predictive role of spiritual intelligence in diabetes management. MATERIALS AND METHODS: In this descriptive-correlation study, 200 adolescents with type 1 diabetes were enrolled. To measure spiritual intelligence, the 24-question SISRI questionnaire and to measure self-management of diabetes, the SMOD-A questionnaire (48 questions) were used. Data were analyzed using SPSS software version 18 using linear regression analysis tests. Data collection was conducted by simple sampling. RESULTS: Mean score of self-management of diabetes and spirituality was 86.1 ± 15.1 and 60.42 ± 12.9, respectively. Linear regression test (ANOVA: 0.002, F = 9.839) showed effect on diabetes self-management (ß: 0.218). CONCLUSION: This study showed that spiritual intelligence can predict diabetes self-management, though poorly predicted, and by strengthening it, has a decisive role in improving the health of adolescents with diabetes. Considering the findings of this study, a new window of nurses' performance in managing diabetes based on the promotion of spiritual intelligence in the educational, care, counseling, and support roles of nursing science can be opened.