OBJECTIVE: Researchers commonly use automated solutions such as Natural Language Processing (NLP) systems to extract clinical information from large volumes of unstructured data. However, clinical text\'s poor semantic structure and domain-specific vocabulary can make it challenging to develop a one-size-fits-all solution. Large Language Models (LLMs), such as OpenAI\'s Generative Pre-Trained Transformer 3 (GPT-3), offer a promising solution for capturing and standardizing unstructured clinical information. This study evaluated the performance of InstructGPT, a family of models derived from LLM GPT-3, to extract relevant patient information from medical case reports and discussed the advantages and disadvantages of LLMs versus dedicated NLP methods.
METHODS: In this paper, 208 articles related to case reports of foreign body injuries in children were identified by searching PubMed, Scopus, and Web of Science. A reviewer manually extracted information on sex, age, the object that caused the injury, and the injured body part for each patient to build a gold standard to compare the performance of InstructGPT.
RESULTS: InstructGPT achieved high accuracy in classifying the sex, age, object and body part involved in the injury, with 94%, 82%, 94% and 89%, respectively. When excluding articles for which InstructGPT could not retrieve any information, the accuracy for determining the child\'s sex and age improved to 97%, and the accuracy for identifying the injured body part improved to 93%. InstructGPT was also able to extract information from non-English language articles.
CONCLUSIONS: The study highlights that LLMs have the potential to eliminate the necessity for task-specific training (zero-shot extraction), allowing the retrieval of clinical information from unstructured natural language text, particularly from published scientific literature like case reports, by directly utilizing the PDF file of the article without any pre-processing and without requiring any technical expertise in NLP or Machine Learning. The diverse nature of the corpus, which includes articles written in languages other than English, some of which contain a wide range of clinical details while others lack information, adds to the strength of the study.

OBJECTIVE: This study aimed to investigate the efficacy of fine-tuned large language models (LLM) in classifying brain MRI reports into pretreatment, posttreatment, and nontumor cases.
METHODS: This retrospective study included 759, 284, and 164 brain MRI reports for training, validation, and test dataset. Radiologists stratified the reports into three groups: nontumor (group 1), posttreatment tumor (group 2), and pretreatment tumor (group 3) cases. A pretrained Bidirectional Encoder Representations from Transformers Japanese model was fine-tuned using the training dataset and evaluated on the validation dataset. The model which demonstrated the highest accuracy on the validation dataset was selected as the final model. Two additional radiologists were involved in classifying reports in the test datasets for the three groups. The model\'s performance on test dataset was compared to that of two radiologists.
RESULTS: The fine-tuned LLM attained an overall accuracy of 0.970 (95% CI: 0.930-0.990). The model\'s sensitivity for group 1/2/3 was 1.000/0.864/0.978. The model\'s specificity for group1/2/3 was 0.991/0.993/0.958. No statistically significant differences were found in terms of accuracy, sensitivity, and specificity between the LLM and human readers (p ≥ 0.371). The LLM completed the classification task approximately 20-26-fold faster than the radiologists. The area under the receiver operating characteristic curve for discriminating groups 2 and 3 from group 1 was 0.994 (95% CI: 0.982-1.000) and for discriminating group 3 from groups 1 and 2 was 0.992 (95% CI: 0.982-1.000).
CONCLUSIONS: Fine-tuned LLM demonstrated a comparable performance with radiologists in classifying brain MRI reports, while requiring substantially less time.

BACKGROUND: Patients find technology tools to be more approachable for seeking sensitive health-related information, such as reproductive health information. The inventive conversational ability of artificial intelligence (AI) chatbots, such as ChatGPT (OpenAI Inc), offers a potential means for patients to effectively locate answers to their health-related questions digitally.
OBJECTIVE: A pilot study was conducted to compare the novel ChatGPT with the existing Google Search technology for their ability to offer accurate, effective, and current information regarding proceeding action after missing a dose of oral contraceptive pill.
METHODS: A sequence of 11 questions, mimicking a patient inquiring about the action to take after missing a dose of an oral contraceptive pill, were input into ChatGPT as a cascade, given the conversational ability of ChatGPT. The questions were input into 4 different ChatGPT accounts, with the account holders being of various demographics, to evaluate potential differences and biases in the responses given to different account holders. The leading question, \"what should I do if I missed a day of my oral contraception birth control?\" alone was then input into Google Search, given its nonconversational nature. The results from the ChatGPT questions and the Google Search results for the leading question were evaluated on their readability, accuracy, and effective delivery of information.
RESULTS: The ChatGPT results were determined to be at an overall higher-grade reading level, with a longer reading duration, less accurate, less current, and with a less effective delivery of information. In contrast, the Google Search resulting answer box and snippets were at a lower-grade reading level, shorter reading duration, more current, able to reference the origin of the information (transparent), and provided the information in various formats in addition to text.
CONCLUSIONS: ChatGPT has room for improvement in accuracy, transparency, recency, and reliability before it can equitably be implemented into health care information delivery and provide the potential benefits it poses. However, AI may be used as a tool for providers to educate their patients in preferred, creative, and efficient ways, such as using AI to generate accessible short educational videos from health care provider-vetted information. Larger studies representing a diverse group of users are needed.

The purposes were to assess the efficacy of AI-generated radiology reports in terms of report summary, patient-friendliness, and recommendations and to evaluate the consistent performance of report quality and accuracy, contributing to the advancement of radiology workflow. Total 685 spine MRI reports were retrieved from our hospital database. AI-generated radiology reports were generated in three formats: (1) summary reports, (2) patient-friendly reports, and (3) recommendations. The occurrence of artificial hallucinations was evaluated in the AI-generated reports. Two radiologists conducted qualitative and quantitative assessments considering the original report as a standard reference. Two non-physician raters assessed their understanding of the content of original and patient-friendly reports using a 5-point Likert scale. The scoring of the AI-generated radiology reports were overall high average scores across all three formats. The average comprehension score for the original report was 2.71 ± 0.73, while the score for the patient-friendly reports significantly increased to 4.69 ± 0.48 (p < 0.001). There were 1.12% artificial hallucinations and 7.40% potentially harmful translations. In conclusion, the potential benefits of using generative AI assistants to generate these reports include improved report quality, greater efficiency in radiology workflow for producing summaries, patient-centered reports, and recommendations, and a move toward patient-centered radiology.

Channel modeling is a first step towards the successful projecting of any wireless communication system. Hence, in this paper, we analyze the performance at the output of a multi-branch selection combining (SC) diversity receiver in a wireless environment that has been distracted by fading and co-channel interference (CCI), whereby the fading is modelled by newer Beaulieu-Xie (BX) distribution, and the CCI is modelled by the κ-µ distribution. The BX distribution provides the ability to include in consideration any number of line-of-sight (LOS) useful signal components and non-LOS (NLOS) useful signal components. This distribution contains characteristics of some other fading models thanks to its flexible fading parameters, which also applies to the κ-µ distribution. We derived here the expressions for the probability density function (PDF) and cumulative distribution function (CDF) for the output signal-to-co-channel interference ratio (SIR). After that, other performances are obtained, namely: outage probability (Pout), channel capacity (CC), moment-generating function (MGF), average bit error probability (ABEP), level crossing rate (LCR), and average fade duration (AFD). Numerical results are presented in several graphs versus the SIR for different values of fading and CCI parameters, as well as the number of input branches in the SC receiver. Then, the impact of parameters on all performance is checked. From our numerical results, it is possible to directly obtain the performance for all derived and displayed quantities for cases of previously known distributions of fading and CCI by inserting the appropriate parameter values. In the second part of the paper, a workflow for automated network experimentation relying on the synergy of Large Language Models (LLMs) and model-driven engineering (MDE) is presented, while the previously derived expressions are used for evaluation. Due to the aforementioned, the biggest value of the obtained results is the applicability to the cases of a large number of other distributions for fading and CCI by replacing the corresponding parameters in the formulas for the respective performances.

This study explores the potential of using large language models to assist content analysis by conducting a case study to identify adverse events (AEs) in social media posts. The case study compares ChatGPT\'s performance with human annotators\' in detecting AEs associated with delta-8-tetrahydrocannabinol, a cannabis-derived product. Using the identical instructions given to human annotators, ChatGPT closely approximated human results, with a high degree of agreement noted: 94.4% (9436/10,000) for any AE detection (Fleiss κ=0.95) and 99.3% (9931/10,000) for serious AEs (κ=0.96). These findings suggest that ChatGPT has the potential to replicate human annotation accurately and efficiently. The study recognizes possible limitations, including concerns about the generalizability due to ChatGPT\'s training data, and prompts further research with different models, data sources, and content analysis tasks. The study highlights the promise of large language models for enhancing the efficiency of biomedical research.

BACKGROUND: Healthcare systems are increasingly resource constrained, leaving less time for important patient-provider interactions. Conversational agents (CAs) could be used to support the provision of information and to answer patients\' questions. However, information must be accessible to a variety of patient populations, which requires understanding questions expressed at different language levels.
METHODS: This study describes the use of Large Language Models (LLMs) to evaluate predefined medical content in CAs across patient populations. These simulated populations are characterized by a range of health literacy. The evaluation framework includes both fully automated and semi-automated procedures to assess the performance of a CA.
RESULTS: A case study in the domain of mammography shows that LLMs can simulate questions from different patient populations. However, the accuracy of the answers provided varies depending on the level of health literacy.
CONCLUSIONS: Our scalable evaluation framework enables the simulation of patient populations with different health literacy levels and helps to evaluate domain specific CAs, thus promoting their integration into clinical practice. Future research aims to extend the framework to CAs without predefined content and to apply LLMs to adapt medical information to the specific (health) literacy level of the user.

OBJECTIVE: The Liver Imaging Reporting and Data System (LI-RADS) offers a standardized approach for imaging hepatocellular carcinoma. However, the diverse styles and structures of radiology reports complicate automatic data extraction. Large language models hold the potential for structured data extraction from free-text reports. Our objective was to evaluate the performance of Generative Pre-trained Transformer (GPT)-4 in extracting LI-RADS features and categories from free-text liver magnetic resonance imaging (MRI) reports.
METHODS: Three radiologists generated 160 fictitious free-text liver MRI reports written in Korean and English, simulating real-world practice. Of these, 20 were used for prompt engineering, and 140 formed the internal test cohort. Seventy-two genuine reports, authored by 17 radiologists were collected and de-identified for the external test cohort. LI-RADS features were extracted using GPT-4, with a Python script calculating categories. Accuracies in each test cohort were compared.
RESULTS: On the external test, the accuracy for the extraction of major LI-RADS features, which encompass size, nonrim arterial phase hyperenhancement, nonperipheral \'washout\', enhancing \'capsule\' and threshold growth, ranged from .92 to .99. For the rest of the LI-RADS features, the accuracy ranged from .86 to .97. For the LI-RADS category, the model showed an accuracy of .85 (95% CI: .76, .93).
CONCLUSIONS: GPT-4 shows promise in extracting LI-RADS features, yet further refinement of its prompting strategy and advancements in its neural network architecture are crucial for reliable use in processing complex real-world MRI reports.

OBJECTIVE: This study addresses the critical need for accurate summarization in radiology by comparing various Large Language Model (LLM)-based approaches for automatic summary generation. With the increasing volume of patient information, accurately and concisely conveying radiological findings becomes crucial for effective clinical decision-making. Minor inaccuracies in summaries can lead to significant consequences, highlighting the need for reliable automated summarization tools.
METHODS: We employed two language models - Text-to-Text Transfer Transformer (T5) and Bidirectional and Auto-Regressive Transformers (BART) - in both fine-tuned and zero-shot learning scenarios and compared them with a Recurrent Neural Network (RNN). Additionally, we conducted a comparative analysis of 100 MRI report summaries, using expert human judgment and criteria such as coherence, relevance, fluency, and consistency, to evaluate the models against the original radiologist summaries. To facilitate this, we compiled a dataset of 15,508 retrospective knee Magnetic Resonance Imaging (MRI) reports from our Radiology Information System (RIS), focusing on the findings section to predict the radiologist\'s summary.
RESULTS: The fine-tuned models outperform the neural network and show superior performance in the zero-shot variant. Specifically, the T5 model achieved a Rouge-L score of 0.638. Based on the radiologist readers\' study, the summaries produced by this model were found to be very similar to those produced by a radiologist, with about 70% similarity in fluency and consistency between the T5-generated summaries and the original ones.
CONCLUSIONS: Technological advances, especially in NLP and LLM, hold great promise for improving and streamlining the summarization of radiological findings, thus providing valuable assistance to radiologists in their work.

Background: The scarcity of medical resources and personnel has worsened due to COVID-19. Telemedicine faces challenges in assessing wounds without physical examination. Evaluating pressure injuries is time consuming, energy intensive, and inconsistent. Most of today\'s telemedicine platforms utilize graphical user interfaces with complex operational procedures and limited channels for information dissemination. The study aims to establish a smart telemedicine diagnosis system based on YOLOv7 and large language model. Methods: The YOLOv7 model is trained using a clinical data set, with data augmentation techniques employed to enhance the data set to identify six types of pressure injury images. The established system features a front-end interface that includes responsive web design and a chatbot with ChatGPT, and it is integrated with a database for personal information management. Results: This research provides a practical pressure injury staging classification model with an average F1 score of 0.9238. The system remotely provides real-time accurate diagnoses and prescriptions, guiding patients to seek various medical help levels based on symptom severity. Conclusions: This study establishes a smart telemedicine auxiliary diagnosis system based on the YOLOv7 model, which possesses capabilities for classification and real-time detection. During teleconsultations, it provides immediate and accurate diagnostic information and prescription recommendations and seeks various medical assistance based on the severity of symptoms. Through the setup of a chatbot with ChatGPT, different users can quickly achieve their respective objectives.