Search

• Our current study provided a web-based artificial intelligence that predict poststroke cognitive impairment. • In total, 3209 stroke patients were included. Using the history of patient demographic, comorbidities, and drugs information, we developed and validate a web-based artificial intelligence tool for poststroke cognitive impairment prediction. The CatBoost become the best prediction model among other models. The final model showed that our finding is a well-calibrated and high-performing prediction model. • This study suggested that web-based artificial intelligence model is reliable. Post-stroke cognitive impairment (PSCI) is highly prevalent in modern society. However, there is limited study implying an accurate and explainable machine learning model to predict PSCI. The aim of this study is to develop and validate a web-based artificial intelligence (AI) tool for predicting PSCI. The retrospective cohort study design was conducted to develop and validate a web-based prediction model. Adults who experienced a stroke between January 1, 2004, and September 30, 2017, were enrolled, and patients with PSCI were followed up from the stroke index date until their last follow-up. The model's performance metrics, including accuracy, area under the curve (AUC), recall, precision, and F1 score, were compared. A total of 3209 stroke patients were included in the study. The model demonstrated an accuracy of 0.8793, AUC of 0.9200, recall of 0.6332, precision of 0.9664, and F1 score of 0.7651. In the external validation phase, the accuracy improved to 0.9039, AUC to 0.9094, recall to 0.7457, precision to 0.9168, and F1 score to 0.8224. The final model can be accessed at https://psci-calculator.my.id/. Our results are able to produce a user-friendly interface that is useful for health practitioners to perform early prediction on PSCI. These findings also suggest that the provided AI model is reliable and can serve as a roadmap for future studies using AI models in a clinical setting [ABSTRACT FROM AUTHOR]

The aim of this study was to investigate whether long-term use of Benzodiazepines (BZDs) is associated with breast cancer risk through the combination of population-based observational and gene expression profiling evidence. We conducted a population-based case-control study by using 1998 to 2009year Taiwan National Health Insurance Research Database and investigated the association between BZDs use and breast cancer risk. We selected subjects age of >20years old and six eligible controls matched for age, sex and the index date (i.e., free of any cancer at the case diagnosis date) by using propensity scores. A bioinformatics analysis approach was also performed for the identification of oncogenesis effects of BZDs on breast cancer. We used breast cancer gene expression data from the Cancer Genome Atlas and perturbagen signatures of BZDs from the Library of Integrated Cellular Signatures database in order to identify the oncogenesis effects of BZDs on breast cancer. We found evidence of increased breast cancer risk for diazepam (OR, 1.16; 95%CI, 0.95-1.42; connectivity score [CS], 0.3016), zolpidem (OR, 1.11; 95%CI, 0.95-1.30; CS, 0.2738), but not for lorazepam (OR, 1.04; 95%CI, 0.89-1.23; CS, -0.2952) consistently in both methods. The finding for alparazolam was contradictory from the two methods. Diazepam and zolpidem trends showed association, although not statistically significant, with breast cancer risk in both epidemiological and bioinformatics analyses outcomes. The methodological value of our study is in introducing the way of combining epidemiological and bioinformatics approaches in order to answer a common scientific question. Combining the two approaches would be a substantial step towards uncovering, validation and further application of previously unknown scientific knowledge to the emerging field of precision medicine informatics. [ABSTRACT FROM AUTHOR]

Abstract: Primary hyperhidrosis describes a disorder of excessive sweating. It has a significant negative impact on quality of life. Palmar involvement is the most common affecting most of cases. A common link to these disorders is an extreme non-thermoregulatory sympathetic stimulus of exocrine sweat glands, mostly due to emotional stimuli. Nonsurgical treatment involves topical medication, iontophoresis and systemic anti-cholinergics. More recently the use of intradermal botulinum toxin has gained popularity. Surgical treatment reserved for severe cases, not responding to conservative management involves local excision, curettage and thoracoscopic sympathectomy. In this paper, we explore the trend for treatment of hyperhidrosis in Taiwan by using NHI claim database. [Copyright &y& Elsevier]

Background: Diagnosing acute appendicitis clinically is still difficult. We developed random forests, support vector machines, and artificial neural network models to diagnose acute appendicitis. Methods: Between January 2006 and December 2008, patients who had a consultation session with surgeons for suspected acute appendicitis were enrolled. Seventy-five percent of the data set was used to construct models including random forest, support vector machines, artificial neural networks, and logistic regression. Twenty-five percent of the data set was withheld to evaluate model performance. The area under the receiver operating characteristic curve (AUC) was used to evaluate performance, which was compared with that of the Alvarado score. Results: Data from a total of 180 patients were collected, 135 used for training and 45 for testing. The mean age of patients was 39.4 years (range, 16–85). Final diagnosis revealed 115 patients with and 65 without appendicitis. The AUC of random forest, support vector machines, artificial neural networks, logistic regression, and Alvarado was 0.98, 0.96, 0.91, 0.87, and 0.77, respectively. The sensitivity, specificity, positive, and negative predictive values of random forest were 94%, 100%, 100%, and 87%, respectively. Random forest performed better than artificial neural networks, logistic regression, and Alvarado. Conclusion: We demonstrated that random forest can predict acute appendicitis with good accuracy and, deployed appropriately, can be an effective tool in clinical decision making. [ABSTRACT FROM AUTHOR]

Background: An electronic reporting system is indispensable in facilitating adverse drug event (ADE) management. Much of the literature has shown that not only the ADE report rate can be increased significantly by a well-designed electronic system but also the communication between health care professionals can be improved. Moreover, developing an electronic reporting system is essential for preventing ADEs in a cost-effective manner. Purpose: The purpose of this study was to compare the efficiency and influence of an electronic ADE management system with a traditional working model at a medical center. Methods: An electronic ADE management system was integrated with the four intranet systems in the hospital and made available at every computer terminal. An ADE committee met once every 4 weeks to discuss the strategies to promote the rational use of drugs, such as introducing an automated computer warning system based on sentinel cases. Details of ADEs were collected for 39 months before and after the new system was introduced. Characteristics of ADEs before and after implementation of the new system were analyzed using the χ2 test. Results: The number of ADE reports increased 3.6-fold after the electronic system (394 cases in contrast to 108 cases, p <0.001) was established. ADEs reported by physicians increased from 36 (33%) to 222 (56%), and those reported by nurses increased from 0 (0%) to 72 (18%). Additionally, the percentage of preventable ADEs decreased significantly from 53% to 21% (p <0.001). The distribution of ADE severity patterns and varieties of medication involved were also significantly affected by the system (p <0.001). Conclusion: The electronic ADE management system evidently increased interdisciplinary involvement that led to enhanced medication safety. Moreover, continuous operation and improvement of the management system by incorporating technologies to fit future demands of ADE management is essential for improving patient safety. [Copyright &y& Elsevier]

Background: Outbreaks of several serious infectious diseases have occurred in recent years. In response, to mitigate public health risks, countries worldwide have dedicated efforts to establish an information system for effective disease monitoring, risk assessment, and early warning management for international disease outbreaks. A cloud computing framework can effectively provide the required hardware resources and information access and exchange to conveniently connect information related to infectious diseases and develop a cross-system surveillance and control system for infectious diseases.Objective: The objective of our study was to develop a Hospital Automated Laboratory Reporting (HALR) system based on such a framework and evaluate its effectiveness.Methods: We collected data for 6 months and analyzed the cases reported within this period by the HALR and the Web-based Notifiable Disease Reporting (WebNDR) systems. Furthermore, system evaluation indicators were gathered, including those evaluating sensitivity and specificity.Results: The HALR system reported 15 pathogens and 5174 cases, and the WebNDR system reported 34 cases. In a comparison of the two systems, sensitivity was 100% and specificity varied according to the reported pathogens. In particular, the specificity for Streptococcus pneumoniae, Mycobacterium tuberculosis complex, and hepatitis C virus were 99.8%, 96.6%, and 97.4%, respectively. However, the specificity for influenza virus and hepatitis B virus were only 79.9% and 47.1%, respectively. After the reported data were integrated with patients' diagnostic results in their electronic medical records (EMRs), the specificity for influenza virus and hepatitis B virus increased to 89.2% and 99.1%, respectively.Conclusions: The HALR system can provide early reporting of specified pathogens according to test results, allowing for early detection of outbreaks and providing trends in infectious disease data. The results of this study show that the sensitivity and specificity of early disease detection can be increased by integrating the reported data in the HALR system with the cases' clinical information (eg, diagnostic results) in EMRs, thereby enhancing the control and prevention of infectious diseases. [ABSTRACT FROM AUTHOR]

[This corrects the article DOI: .]. [ABSTRACT FROM AUTHOR]

Background: Empowering personal health records (PHRs) provides basic human right, awareness, and intention for health promotion. As health care delivery changes toward patient-centered services, PHRs become an indispensable platform for consumers and providers. Recently, the government introduced "My health bank," a Web-based electronic medical records (EMRs) repository for consumers. However, it is not yet a PHR. To date, we do not have a platform that can let patients manage their own PHR.Objective: This study creates a vision of a value-added platform for personal health data analysis and manages their health record based on the contents of the "My health bank." This study aimed to examine consumer expectation regarding PHR, using the importance-performance analysis. The purpose of this study was to explore consumer perception regarding this type of a platform: it would try to identify the key success factors and important aspects by using the importance-performance analysis, and give some suggestions for future development based on it.Methods: This is a cross-sectional study conducted in Taiwan. Web-based invitation to participate in this study was distributed through Facebook. Respondents were asked to watch an introductory movie regarding PHR before filling in the questionnaire. The questionnaire was focused on 2 aspects, including (1) system functions, and (2) system design and security and privacy. The questionnaire would employ 12 and 7 questions respectively. The questionnaire was designed following 5-points Likert scale ranging from 1 ("disagree strongly") to 5 ("Agree strongly"). Afterwards, the questionnaire data was sorted using IBM SPSS Statistics 21 for descriptive statistics and the importance-performance analysis.Results: This research received 350 valid questionnaires. Most respondents were female (219 of 350 participants, 62.6%), 21-30 years old (238 of 350 participants, 68.0%), with a university degree (228 of 350 participants, 65.1%). They were still students (195 out of 350 participants, 56.6%), with a monthly income of less than NT $30,000 (230 of 350 participants, 65.7%), and living in the North Taiwan (236 of 350 participants, 67.4%), with a good self-identified health status (171 of 350 participants, 48.9%). After performing the importance-performance analysis, we found the following: (1) instead of complex functions, people just want to have a platform that can let them integrate and manage their medical visit, health examination, and life behavior records; (2) they do not care whether their PHR is shared with others; and (3) most of the participants think the system security design is not important, but they also do not feel satisfied with the current security design.Conclusions: Overall, the issues receiving the most user attention were the system functions, circulation, integrity, ease of use, and continuity of the PHRs, data security, and privacy protection. [ABSTRACT FROM AUTHOR]

Introduction: The amount of information being uploaded onto social video platforms, such as YouTube, Vimeo, and Veoh, continues to spiral, making it increasingly difficult to discern reliable health information from misleading content. There are thousands of YouTube videos promoting misleading information about anorexia (eg, anorexia as a healthy lifestyle). Objective: The aim of this study was to investigate anorexia-related misinformation disseminated through YouTube videos. Methods: We retrieved YouTube videos related to anorexia using the keywords anorexia, anorexia nervosa, proana, and thinspo on October 10, 2011.Three doctors reviewed 140 videos with approximately 11 hours of video content, classifying them as informative, pro-anorexia, or others. By informative we mean content describing the health consequences of anorexia and advice on how to recover from it; by pro-anorexia we mean videos promoting anorexia as a fashion, a source of beauty, and that share tips and methods for becoming and remaining anorexic. The 40 most-viewed videos (20 informative and 20 pro-anorexia videos) were assessed to gauge viewer behavior. Results: The interrater agreement of classification was moderate (Fleiss' kappa=0.5), with 29.3% (n=41) being rated as pro-anorexia, 55.7% (n=78) as informative, and 15.0% (n=21) as others. Pro-anorexia videos were favored 3 times more than informative videos (odds ratio [OR] 3.3, 95% CI 3.3-3.4, P<.001). Conclusions: Pro-anorexia information was identified in 29.3% of anorexia-related videos. Pro-anorexia videos are less common than informative videos; however, in proportional terms, pro-anorexia content is more highly favored and rated by its viewers. Efforts should focus on raising awareness, particularly among teenagers, about the trustworthiness of online information about beauty and healthy lifestyles. Health authorities producing videos to combat anorexia should consider involving celebrities and models to reach a wider audience. More research is needed to study the characteristics of pro-anorexia videos in order to develop algorithms that will automatically detect and filter those videos before they become popular. [ABSTRACT FROM AUTHOR]