ChatGPT in radiology structured reporting: analysis of ChatGPT-3.5 Turbo and GPT-4 in reducing word count and recalling findings.
Ontology highlight
ABSTRACT:
SUBMITTER: Mallio CA
PROVIDER: S-EPMC10895108 | biostudies-literature | 2024 Feb
REPOSITORIES: biostudies-literature
Publications
ChatGPT in radiology structured reporting: analysis of ChatGPT-3.5 Turbo and GPT-4 in reducing word count and recalling findings.
Mallio Carlo A CA Bernetti Caterina C Sertorio Andrea C AC Zobel Bruno Beomonte BB
Quantitative imaging in medicine and surgery 20240105 2
Similar Datasets
Project description:To compare the content, clarity, and clinical usefulness of conventional (ie, free-form) and structured radiology reports of body computed tomographic (CT) scans, as evaluated by referring physicians, attending radiologists, and radiology fellows at a tertiary care cancer center.The institutional review board approved the study as a quality improvement initiative; no written consent was required. Three radiologists, three radiology fellows, three surgeons, and two medical oncologists evaluated 330 randomly selected conventional and structured radiology reports of body CT scans. For nonradiologists, reports were randomly selected from patients with diagnoses relevant to the physician's area of specialization. Each physician read 15 reports in each format and rated both the content and clarity of each report from 1 (very dissatisfied or very confusing) to 10 (very satisfied or very clear). By using a previously published radiology report grading scale, physicians graded each report's effectiveness in advancing the patient's position on the clinical spectrum. Mixed-effects models were used to test differences between report types.Mean content satisfaction ratings were 7.61 (95% confidence interval [CI]: 7.12, 8.16) for conventional reports and 8.33 (95% CI: 7.82, 8.86) for structured reports, and the difference was significant (P < .0001). Mean clarity satisfaction ratings were 7.45 (95% CI: 6.89, 8.02) for conventional reports and 8.25 (95% CI: 7.68, 8.82) for structured reports, and the difference was significant (P < .0001). Grade ratings did not differ significantly between conventional and structured reports.Referring clinicians and radiologists found that structured reports had better content and greater clarity than conventional reports.
| S-EPMC3121011 | biostudies-other
Project description:ObjectiveAccurately identifying clinical phenotypes from Electronic Health Records (EHRs) provides additional insights into patients' health, especially when such information is unavailable in structured data. This study evaluates the application of OpenAI's Generative Pre-trained Transformer (GPT)-4 model to identify clinical phenotypes from EHR text in non-small cell lung cancer (NSCLC) patients. The goal was to identify disease stages, treatments and progression utilizing GPT-4, and compare its performance against GPT-3.5-turbo, Flan-T5-xl, Flan-T5-xxl, Llama-3-8B, and 2 rule-based and machine learning-based methods, namely, scispaCy and medspaCy.Materials and methodsPhenotypes such as initial cancer stage, initial treatment, evidence of cancer recurrence, and affected organs during recurrence were identified from 13 646 clinical notes for 63 NSCLC patients from Washington University in St. Louis, Missouri. The performance of the GPT-4 model is evaluated against GPT-3.5-turbo, Flan-T5-xxl, Flan-T5-xl, Llama-3-8B, medspaCy, and scispaCy by comparing precision, recall, and micro-F1 scores.ResultsGPT-4 achieved higher F1 score, precision, and recall compared to Flan-T5-xl, Flan-T5-xxl, Llama-3-8B, medspaCy, and scispaCy's models. GPT-3.5-turbo performed similarly to that of GPT-4. GPT, Flan-T5, and Llama models were not constrained by explicit rule requirements for contextual pattern recognition. spaCy models relied on predefined patterns, leading to their suboptimal performance.Discussion and conclusionGPT-4 improves clinical phenotype identification due to its robust pre-training and remarkable pattern recognition capability on the embedded tokens. It demonstrates data-driven effectiveness even with limited context in the input. While rule-based models remain useful for some tasks, GPT models offer improved contextual understanding of the text, and robust clinical phenotype extraction.
| S-EPMC11221943 | biostudies-literature
Project description:BackgroundChatGPT (OpenAI) has shown great potential in clinical diagnosis and could become an excellent auxiliary tool in clinical practice. This study investigates and evaluates ChatGPT in diagnostic capabilities by comparing the performance of GPT-3.5 and GPT-4.0 across model iterations.ObjectiveThis study aims to evaluate the precise diagnostic ability of GPT-3.5 and GPT-4.0 for colon cancer and its potential as an auxiliary diagnostic tool for surgeons and compare the diagnostic accuracy rates between GTP-3.5 and GPT-4.0. We precisely assess the accuracy of primary and secondary diagnoses and analyze the causes of misdiagnoses in GPT-3.5 and GPT-4.0 according to 7 categories: patient histories, symptoms, physical signs, laboratory examinations, imaging examinations, pathological examinations, and intraoperative findings.MethodsWe retrieved 316 case reports for intestinal cancer from the Chinese Medical Association Publishing House database, of which 286 cases were deemed valid after data cleansing. The cases were translated from Mandarin to English and then input into GPT-3.5 and GPT-4.0 using a simple, direct prompt to elicit primary and secondary diagnoses. We conducted a comparative study to evaluate the diagnostic accuracy of GPT-4.0 and GPT-3.5. Three senior surgeons from the General Surgery Department, specializing in Colorectal Surgery, assessed the diagnostic information at the Chinese PLA (People's Liberation Army) General Hospital. The accuracy of primary and secondary diagnoses was scored based on predefined criteria. Additionally, we analyzed and compared the causes of misdiagnoses in both models according to 7 categories: patient histories, symptoms, physical signs, laboratory examinations, imaging examinations, pathological examinations, and intraoperative findings.ResultsOut of 286 cases, GPT-4.0 and GPT-3.5 both demonstrated high diagnostic accuracy for primary diagnoses, but the accuracy rates of GPT-4.0 were significantly higher than GPT-3.5 (mean 0.972, SD 0.137 vs mean 0.855, SD 0.335; t285=5.753; P<.001). For secondary diagnoses, the accuracy rates of GPT-4.0 were also significantly higher than GPT-3.5 (mean 0.908, SD 0.159 vs mean 0.617, SD 0.349; t285=-7.727; P<.001). GPT-3.5 showed limitations in processing patient history, symptom presentation, laboratory tests, and imaging data. While GPT-4.0 improved upon GPT-3.5, it still has limitations in identifying symptoms and laboratory test data. For both primary and secondary diagnoses, there was no significant difference in accuracy related to age, gender, or system group between GPT-4.0 and GPT-3.5.ConclusionsThis study demonstrates that ChatGPT, particularly GPT-4.0, possesses significant diagnostic potential, with GPT-4.0 exhibiting higher accuracy than GPT-3.5. However, GPT-4.0 still has limitations, particularly in recognizing patient symptoms and laboratory data, indicating a need for more research in real-world clinical settings to enhance its diagnostic capabilities.
| S-EPMC11422746 | biostudies-literature
Project description:BackgroundArtificial intelligence, particularly chatbot systems, is becoming an instrumental tool in health care, aiding clinical decision-making and patient engagement.ObjectiveThis study aims to analyze the performance of ChatGPT-3.5 and ChatGPT-4 in addressing complex clinical and ethical dilemmas, and to illustrate their potential role in health care decision-making while comparing seniors' and residents' ratings, and specific question types.MethodsA total of 4 specialized physicians formulated 176 real-world clinical questions. A total of 8 senior physicians and residents assessed responses from GPT-3.5 and GPT-4 on a 1-5 scale across 5 categories: accuracy, relevance, clarity, utility, and comprehensiveness. Evaluations were conducted within internal medicine, emergency medicine, and ethics. Comparisons were made globally, between seniors and residents, and across classifications.ResultsBoth GPT models received high mean scores (4.4, SD 0.8 for GPT-4 and 4.1, SD 1.0 for GPT-3.5). GPT-4 outperformed GPT-3.5 across all rating dimensions, with seniors consistently rating responses higher than residents for both models. Specifically, seniors rated GPT-4 as more beneficial and complete (mean 4.6 vs 4.0 and 4.6 vs 4.1, respectively; P<.001), and GPT-3.5 similarly (mean 4.1 vs 3.7 and 3.9 vs 3.5, respectively; P<.001). Ethical queries received the highest ratings for both models, with mean scores reflecting consistency across accuracy and completeness criteria. Distinctions among question types were significant, particularly for the GPT-4 mean scores in completeness across emergency, internal, and ethical questions (4.2, SD 1.0; 4.3, SD 0.8; and 4.5, SD 0.7, respectively; P<.001), and for GPT-3.5's accuracy, beneficial, and completeness dimensions.ConclusionsChatGPT's potential to assist physicians with medical issues is promising, with prospects to enhance diagnostics, treatments, and ethics. While integration into clinical workflows may be valuable, it must complement, not replace, human expertise. Continued research is essential to ensure safe and effective implementation in clinical environments.
| S-EPMC11240076 | biostudies-literature
Project description:ObjectivesThe aim of this study was to investigate GPT-3.5 in generating and coding medical documents with International Classification of Diseases (ICD)-10 codes for data augmentation on low-resource labels.Materials and methodsEmploying GPT-3.5 we generated and coded 9606 discharge summaries based on lists of ICD-10 code descriptions of patients with infrequent (or generation) codes within the MIMIC-IV dataset. Combined with the baseline training set, this formed an augmented training set. Neural coding models were trained on baseline and augmented data and evaluated on an MIMIC-IV test set. We report micro- and macro-F1 scores on the full codeset, generation codes, and their families. Weak Hierarchical Confusion Matrices determined within-family and outside-of-family coding errors in the latter codesets. The coding performance of GPT-3.5 was evaluated on prompt-guided self-generated data and real MIMIC-IV data. Clinicians evaluated the clinical acceptability of the generated documents.ResultsData augmentation results in slightly lower overall model performance but improves performance for the generation candidate codes and their families, including 1 absent from the baseline training data. Augmented models display lower out-of-family error rates. GPT-3.5 identifies ICD-10 codes by their prompted descriptions but underperforms on real data. Evaluators highlight the correctness of generated concepts while suffering in variety, supporting information, and narrative.Discussion and conclusionWhile GPT-3.5 alone given our prompt setting is unsuitable for ICD-10 coding, it supports data augmentation for training neural models. Augmentation positively affects generation code families but mainly benefits codes with existing examples. Augmentation reduces out-of-family errors. Documents generated by GPT-3.5 state prompted concepts correctly but lack variety, and authenticity in narratives.
| S-EPMC11413433 | biostudies-literature
Project description:BackgroundChatGPT, a recently developed artificial intelligence (AI) chatbot, has demonstrated improved performance in examinations in the medical field. However, thus far, an overall evaluation of the potential of ChatGPT models (ChatGPT-3.5 and GPT-4) in a variety of national health licensing examinations is lacking. This study aimed to provide a comprehensive assessment of the ChatGPT models' performance in national licensing examinations for medical, pharmacy, dentistry, and nursing research through a meta-analysis.MethodsFollowing the PRISMA protocol, full-text articles from MEDLINE/PubMed, EMBASE, ERIC, Cochrane Library, Web of Science, and key journals were reviewed from the time of ChatGPT's introduction to February 27, 2024. Studies were eligible if they evaluated the performance of a ChatGPT model (ChatGPT-3.5 or GPT-4); related to national licensing examinations in the fields of medicine, pharmacy, dentistry, or nursing; involved multiple-choice questions; and provided data that enabled the calculation of effect size. Two reviewers independently completed data extraction, coding, and quality assessment. The JBI Critical Appraisal Tools were used to assess the quality of the selected articles. Overall effect size and 95% confidence intervals [CIs] were calculated using a random-effects model.ResultsA total of 23 studies were considered for this review, which evaluated the accuracy of four types of national licensing examinations. The selected articles were in the fields of medicine (n = 17), pharmacy (n = 3), nursing (n = 2), and dentistry (n = 1). They reported varying accuracy levels, ranging from 36 to 77% for ChatGPT-3.5 and 64.4-100% for GPT-4. The overall effect size for the percentage of accuracy was 70.1% (95% CI, 65-74.8%), which was statistically significant (p < 0.001). Subgroup analyses revealed that GPT-4 demonstrated significantly higher accuracy in providing correct responses than its earlier version, ChatGPT-3.5. Additionally, in the context of health licensing examinations, the ChatGPT models exhibited greater proficiency in the following order: pharmacy, medicine, dentistry, and nursing. However, the lack of a broader set of questions, including open-ended and scenario-based questions, and significant heterogeneity were limitations of this meta-analysis.ConclusionsThis study sheds light on the accuracy of ChatGPT models in four national health licensing examinations across various countries and provides a practical basis and theoretical support for future research. Further studies are needed to explore their utilization in medical and health education by including a broader and more diverse range of questions, along with more advanced versions of AI chatbots.
| S-EPMC11406751 | biostudies-literature
Project description:ObjectiveDespite rising popularity and performance, studies evaluating the use of large language models for clinical decision support are lacking. Here, we evaluate ChatGPT (Generative Pre-trained Transformer)-3.5 and GPT-4's (OpenAI, San Francisco, California) capacity for clinical decision support in radiology via the identification of appropriate imaging services for two important clinical presentations: breast cancer screening and breast pain.MethodsWe compared ChatGPT's responses to the ACR Appropriateness Criteria for breast pain and breast cancer screening. Our prompt formats included an open-ended (OE) and a select all that apply (SATA) format. Scoring criteria evaluated whether proposed imaging modalities were in accordance with ACR guidelines. Three replicate entries were conducted for each prompt, and the average of these was used to determine final scores.ResultsBoth ChatGPT-3.5 and ChatGPT-4 achieved an average OE score of 1.830 (out of 2) for breast cancer screening prompts. ChatGPT-3.5 achieved a SATA average percentage correct of 88.9%, compared with ChatGPT-4's average percentage correct of 98.4% for breast cancer screening prompts. For breast pain, ChatGPT-3.5 achieved an average OE score of 1.125 (out of 2) and a SATA average percentage correct of 58.3%, as compared with an average OE score of 1.666 (out of 2) and a SATA average percentage correct of 77.7%.DiscussionOur results demonstrate the eventual feasibility of using large language models like ChatGPT for radiologic decision making, with the potential to improve clinical workflow and responsible use of radiology services. More use cases and greater accuracy are necessary to evaluate and implement such tools.
| S-EPMC10733745 | biostudies-literature
Project description:BackgroundThe competence of ChatGPT (Chat Generative Pre-Trained Transformer) in non-English languages is not well studied.ObjectiveThis study compared the performances of GPT-3.5 (Generative Pre-trained Transformer) and GPT-4 on the Japanese Medical Licensing Examination (JMLE) to evaluate the reliability of these models for clinical reasoning and medical knowledge in non-English languages.MethodsThis study used the default mode of ChatGPT, which is based on GPT-3.5; the GPT-4 model of ChatGPT Plus; and the 117th JMLE in 2023. A total of 254 questions were included in the final analysis, which were categorized into 3 types, namely general, clinical, and clinical sentence questions.ResultsThe results indicated that GPT-4 outperformed GPT-3.5 in terms of accuracy, particularly for general, clinical, and clinical sentence questions. GPT-4 also performed better on difficult questions and specific disease questions. Furthermore, GPT-4 achieved the passing criteria for the JMLE, indicating its reliability for clinical reasoning and medical knowledge in non-English languages.ConclusionsGPT-4 could become a valuable tool for medical education and clinical support in non-English-speaking regions, such as Japan.
| S-EPMC10365615 | biostudies-literature
Project description:BackgroundIn Japan, consumers can purchase most over-the-counter (OTC) drugs without pharmacist guidance. Recently, generative artificial intelligence (AI) has become increasingly popular. Therefore, medical professionals need to consider the use of generative AI by consumers for medication counseling. We have previously reported responses in Japanese from ChatGPT-3.5 to 264 questions regarding whether each of 22 OTC drugs can be taken under 12 typical patient conditions. The proportion of responses that satisfied the criteria of 1) accuracy, 2) relevance, and 3) reliability with respect to package insert instructions was 20.8%. In November 2023, GPTs were launched, enabling us to construct a customized ChatGPT, using natural language. In the present study, we compared performance in providing medication guidance among a newly customized GPT, the latest non-customized version ChatGPT-4o, and the previous version, ChatGPT-3.5. The aim was to determine whether the customization and version update of ChatGPT improved performance and to evaluate its potential usefulness.MethodsWe configured customized ChatGPT-4 by executing five instructions in Japanese and uploaded the text of package inserts for 22 OTC drugs as knowledge. We asked the same 264 questions as in our previous study.ResultsWith the customized ChatGPT-4, the percentages of responses that satisfied the criteria of accuracy, relevance, and reliability were 93.2%, 100%, and 60.2%, respectively. Additionally, 56.1% of responses satisfied all three criteria, 2.7-fold higher compared with ChatGPT-3.5 and 1.3-fold higher compared with ChatGPT-4o.ConclusionThe performance of our customized GPT far exceeded that of ChatGPT-3.5. In particular, the proportion of appropriate responses to the questions using brand names was significantly improved. ChatGPT can be customized by providing drug package insert information and using appropriate prompt engineering, potentially offering helpful tools in clinical pharmacy.
| S-EPMC11863229 | biostudies-literature
Project description:The study aimed to evaluate the performance of two Large Language Models (LLMs): ChatGPT (based on GPT-3.5) and GPT-4 with two temperature parameter values, on the Polish Medical Final Examination (MFE). The models were tested on three editions of the MFE from: Spring 2022, Autumn 2022, and Spring 2023 in two language versions-English and Polish. The accuracies of both models were compared and the relationships between the correctness of answers with the answer's metrics were investigated. The study demonstrated that GPT-4 outperformed GPT-3.5 in all three examinations regardless of the language used. GPT-4 achieved mean accuracies of 79.7% for both Polish and English versions, passing all MFE versions. GPT-3.5 had mean accuracies of 54.8% for Polish and 60.3% for English, passing none and 2 of 3 Polish versions for temperature parameter equal to 0 and 1 respectively while passing all English versions regardless of the temperature parameter value. GPT-4 score was mostly lower than the average score of a medical student. There was a statistically significant correlation between the correctness of the answers and the index of difficulty for both models. The overall accuracy of both models was still suboptimal and worse than the average for medical students. This emphasizes the need for further improvements in LLMs before they can be reliably deployed in medical settings. These findings suggest an increasing potential for the usage of LLMs in terms of medical education.
| S-EPMC10665355 | biostudies-literature