Practical Evaluation of ChatGPT Performance for Radiology Report Generation.

RATIONALE AND OBJECTIVES: The process of generating radiology reports is often time-consuming and labor-intensive, prone to incompleteness, heterogeneity, and errors. By employing natural language processing (NLP)-based techniques, this study explores the potential for enhancing the efficiency of radiology report generation through the remarkable capabilities of ChatGPT (Generative Pre-training Transformer), a prominent large language model (LLM). MATERIALS AND METHODS: Using a sample of 1000 records from the Medical Information Mart for Intensive Care (MIMIC) Chest X-ray Database, this investigation employed Claude.ai to extract initial radiological report keywords. ChatGPT then generated radiology reports using a consistent 3-step prompt template outline. Various lexical and sentence similarity techniques were employed to evaluate the correspondence between the AI assistant-generated reports and reference reports authored by medical professionals. RESULTS: Results showed varying performance among NLP models, with Bart (Bidirectional and Auto-Regressive Transformers) and XLM (Cross-lingual Language Model) displaying high proficiency (mean similarity scores up to 99.3%), closely mirroring physician reports. Conversely, DeBERTa (Decoding-enhanced BERT with disentangled attention) and sequence-matching models scored lower, indicating less alignment with medical language. In the Impression section, the Word-Embedding model excelled with a mean similarity of 84.4%, while others like the Jaccard index showed lower performance. CONCLUSION: Overall, the study highlights significant variations across NLP models in their ability to generate radiology reports consistent with medical professionals' language. Pairwise comparisons and Kruskal-Wallis tests confirmed these differences, emphasizing the need for careful selection and evaluation of NLP models in radiology report generation. This research underscores the potential of ChatGPT to streamline and improve the radiology reporting process, with implications for enhancing efficiency and accuracy in clinical practice.

Nutritional management recommendation systems in polycystic ovary syndrome: a systematic review.

BACKGROUND: People with polycystic ovary syndrome suffer from many symptoms and are at risk of developing diseases such as hypertension and diabetes in the future. Therefore, the importance of self-care doubles. It is mainly to modify the lifestyle, especially following the principles of healthy eating. The purpose of this study is to review artificial intelligence-based systems for providing management recommendations, especially food recommendations. MATERIALS AND METHODS: This study started by searching three databases: PubMed, Scopus, and Web of Science, from inception until 6 June 2023. The result was the retrieval of 15,064 articles. First, we removed duplicate studies. After the title and abstract screening, 119 articles remained. Finally, after reviewing the full text of the articles and considering the inclusion and exclusion criteria, 20 studies were selected for the study. To assess the quality of articles, we used criteria proposed by Malhotra, Wen, and Kitchenham. Out of the total number of included studies, seventeen studies were high quality, while three studies were moderate quality. RESULTS: Most studies were conducted in India in 2021. Out of all the studies, diagnostic recommendation systems were the most frequently researched, accounting for 86% of the total. Precision, sensitivity, specificity, and accuracy were more common than other performance metrics. The most significant challenge or limitation encountered in these studies was the small sample size. CONCLUSION: Recommender systems based on artificial intelligence can help in fields such as prediction, diagnosis, and management of polycystic ovary syndrome. Therefore, since there are no nutritional recommendation systems for these patients in Iran, this study can serve as a starting point for such research.

Artificial Intelligence Approaches on X-ray-oriented Images Process for Early Detection of COVID-19.

Background: COVID-19 is a global public health problem that is crucially important to be diagnosed in the early stages. This study aimed to investigate the use of artificial intelligence (AI) to process X-ray-oriented images to diagnose COVID-19 disease. Methods: A systematic search was conducted in Medline (through PubMed), Scopus, ISI Web of Science, Cochrane Library, and IEEE Xplore Digital Library to identify relevant studies published until 21 September 2020. Results: We identified 208 papers after duplicate removal and filtered them into 60 citations based on inclusion and exclusion criteria. Direct results sufficiently indicated a noticeable increase in the number of published papers in July-2020. The most widely used datasets were, respectively, GitHub repository, hospital-oriented datasets, and Kaggle repository. The Keras library, Tensorflow, and Python had been also widely employed in articles. X-ray images were applied more in the selected articles. The most considerable value of accuracy, sensitivity, specificity, and Area under the ROC Curve was reported for ResNet18 in reviewed techniques; all the mentioned indicators for this mentioned network were equal to one (100%). Conclusion: This review revealed that the application of AI can accelerate the process of diagnosing COVID-19, and these methods are effective for the identification of COVID-19 cases exploiting Chest X-ray images.

Data Requirements for Information Management System Development for Poisoning with Acidic and Alkaline Substances.

INTRODUCTION: Ingestion of acidic or alkaline substances and its long-term effects on digestive system indicates is a common health problem worldwide. To identify the root causes of injuries, standard data collection is required. AIM: The present study was conducted to determine the data requirements for the establishment of information management system for poisoning with acidic and alkaline substances in Iran. METHODS: This is a descriptive and cross-sectional study conducted in 2017. First, we attended at the hospitals affiliated to Iran, Tehran and Shahid Beheshti universities of medical sciences, which had poisoning wards; we studied all forms, reports and medical records of people who had been poisoned by acidic or alkaline substances. In the next step, a comprehensive literature review was carried out to retrieve related resources. Data were collected using data extraction form and Delphi method was used to survey them. Validity of the questionnaire was evaluated through content validity and its reliability checked by the test-retest method and Cronbach's alpha. RESULTS: A minimum data set (MDS) of alkaline and acid poisoning divided into two categories: administrative with three classes including 35 data elements, and clinical with 6 classes including 145 data elements. CONCLUSION: Comprehensive and uniform data elements about alkaline and acid poisoning was not available in Iran. Development of a MDS resulted in standardization and effective management of the data through providing uniform and comprehensive data elements for alkaline and acid poisoning and comparability of information in various levels and made effective decision-making and policy-making possible.

Occupational Disease Registries-Characteristics and Experiences.

INTRODUCTION: Due to growth of occupational diseases and also increase of public awareness about their consequences, attention to various aspects of diseases and improve occupational health and safety has found great importance. Therefore, there is the need for appropriate information management tools such as registries in order to recognitions of diseases patterns and then making decision about prevention, early detection and treatment of them. These registries have different characteristics in various countries according to their occupational health priorities. AIM: Aim of this study is evaluate dimensions of occupational diseases registries including objectives, data sources, responsible institutions, minimum data set, classification systems and process of registration in different countries. MATERIAL AND METHODS: In this study, the papers were searched using the MEDLINE (PubMed) Google scholar, Scopus, ProQuest and Google. The search was done based on keyword in English for all motor engines including "occupational disease", "work related disease", "surveillance", "reporting", "registration system" and "registry" combined with name of the countries including all subheadings. After categorizing search findings in tables, results were compared with each other. RESULTS: Important aspects of the registries studied in ten countries including Finland, France, United Kingdom, Australia, Czech Republic, Malaysia, United States, Singapore, Russia and Turkey. The results show that surveyed countries have statistical, treatment and prevention objectives. Data sources in almost the rest of registries were physicians and employers. The minimum data sets in most of them consist of information about patient, disease, occupation and employer. Some of countries have special occupational related classification systems for themselves and some of them apply international classification systems such as ICD-10. Finally, the process of registration system was different in countries. CONCLUSION: Because occupational diseases are often preventable, but not curable, it is necessary to all countries, to consider prevention and early detection of occupational diseases as the objectives of their registry systems. Also it is recommended that all countries reach an agreement about global characteristics of occupational disease registries. This enables country to compare their data at international levels.

Prevalence of and risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries: systematic review and meta-analysis.

Tuberculosis, in particular drug-resistant tuberculosis, is of global concern due to the high mortality and morbidity associated with it annually. The aim of this study was to determine the prevalence of and the risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries. Four databases (PubMed, BioMed Central, EMBASE, and Web of Science) were searched using key terms. Nineteen eligible articles were identified, of which 12 and seven were used for quantitative and qualitative analysis, respectively. The overall pooled estimate of the prevalence of multidrug-resistant tuberculosis, including both new and previously treated tuberculosis cases, in Iran, Iraq, Turkey and Pakistan was 16% (95% confidence interval [CI] 11-20). The patients with a previous tuberculosis treatment history (odds ratio [OR] = 6.45; 95% CI 5.12-7.79), those aged <45 years (OR = 1.57; 95% CI 1.12-2.03), and those who were males (OR = 1.83; 95% CI 1.19-2.48) had an increased pool risk of developing multidrug-resistant tuberculosis. The forest plot revealed that the pooled odds for the development of multidrug- resistant tuberculosis were 2.01 (95% CI 1.65-2.36). Poor adherence to treatment was one of the predictors of unsuccessful treatment outcomes. Multidrug-resistant tuberculosis is a great concern for public health programs in many countries globally, including those included in this review. The risk factors for the development of multidrug-resistant tuberculosis, specifically a previous tuberculosis treatment history, should be targeted through the implementation of specialized interventions.

Prevalence of and risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries: systematic review and meta-analysis

Abstract Tuberculosis, in particular drug-resistant tuberculosis, is of global concern due to the high mortality and morbidity associated with it annually. The aim of this study was to determine the prevalence of and the risk factors for multidrug-resistant tuberculosis in Iran and its neighboring countries. Four databases (PubMed, BioMed Central, EMBASE, and Web of Science) were searched using key terms. Nineteen eligible articles were identified, of which 12 and seven were used for quantitative and qualitative analysis, respectively. The overall pooled estimate of the prevalence of multidrug-resistant tuberculosis, including both new and previously treated tuberculosis cases, in Iran, Iraq, Turkey and Pakistan was 16% (95% confidence interval [CI] 11-20). The patients with a previous tuberculosis treatment history (odds ratio [OR] = 6.45; 95% CI 5.12-7.79), those aged <45 years (OR = 1.57; 95% CI 1.12-2.03), and those who were males (OR = 1.83; 95% CI 1.19-2.48) had an increased pool risk of developing multidrug-resistant tuberculosis. The forest plot revealed that the pooled odds for the development of multidrug- resistant tuberculosis were 2.01 (95% CI 1.65-2.36). Poor adherence to treatment was one of the predictors of unsuccessful treatment outcomes. Multidrug-resistant tuberculosis is a great concern for public health programs in many countries globally, including those included in this review. The risk factors for the development of multidrug-resistant tuberculosis, specifically a previous tuberculosis treatment history, should be targeted through the implementation of specialized interventions.

Persian mHealth Apps: A Cross Sectional Study Based on Use Case Classification.

Mobile health apps play an important role in healthcare processes and health promotion. In recent years many Persian mhealth apps were developed and are available in various national app markets. Cafebazaar is the largest Persian app store that contains more than 3500 android apps in medical and health & fitness categories. In this study some characteristics of 200 top Persian medical apps of Cafebazaar were investigated and then categorized by their use cases. Results showed that only 6% of apps declare the involvement of at least one health professional in the conception or development of the apps. In 35% of studied apps, no contact information was provided for the users and 10.5% applied reliable sources for their content. 13 distinct use cases were found in all 200 apps of which two were new to an already published use-case model. This study shows that Persian mHealth apps, like other existing apps in the world, have a long way to improve and reach some basic standards. Lack of regulatory agencies and absence of a dynamic evaluation system for mHealth apps might be the main reason of these defects. This study also shows that 20 use cases existing in international health related apps are not yet used in Persian apps and therefore there is a reach potential of creating new apps in mHealth field.

Impact of Training High School Female Students in Ahvaz, Iran in the Social Skills Required to Avoid the Use of Drugs.

INTRODUCTION: Gender composition and the soaring trends of drug and tobacco dependency reveal the priority of social skills training related to drug avoidance self-efficacy among female students. The aim of this study was to verify the impact training high school female students to have the social skills needed to avoid the use of drugs. METHODS: This study was conducted from September 2012 to May 2013 in two high schools in Ahvaz City in southwest Iran. The participants were divided randomly into two groups of 60 students, one experimental group and one control group using the multi-stage simple sampling method. Two questionnaires, i.e. the ASES and TISS questionnaires, were completed before and after the intervention. Descriptive statistics, chi squared, paired-samples t-test, and the independent-samples t-test were used. RESULTS: The participants had a mean age of 14.93 years. Among the 120 participants, 90.8% indicated that they had never smoked a cigarette, and 51.7% of the participants denied having smoked a hookah. There was no significant relationship between the self-sufficiency means of drug avoidance in the two groups of girls before intervention (p ≥ 0.05). However, after intervention, a significant difference was found in test score of self-efficacy of drug avoidance between the two groups, i.e., 94.91 ± 8.3 for the control group versus 99.16 ± 3.8 for the experimental group, p < 0.05). Significant increases were observed for the pre- and post-test scores of self-efficacy of drug avoidance in the experimental group compared to the control group (99.16 ± 3.8 (p = 0.001) vs. 96.58 ± 6.98 (p > 0.05). The mean values of the pre- and post-test scores of social skill before and after intervention increased significantly only for the experimental group (97.60 ± 19.19 vs. 100.58 ± 12.37, p = 0.03). CONCLUSION: Educational intervention can significantly enhance social skills for drug avoidance self-efficacy, so it is recommended that such skills be taught in the high school curriculum.