Search

Purpose: Artificial intelligence (AI) holds great potential for revolutionizing health care by providing clinicians with data-driven insights that support more accurate and efficient clinical decisions. However, applying AI in clinical settings is often challenging due to the complexity and vastness of medical information. This perspective article explores how AI development methodologies can be adapted to support clinicians in their decision-making processes, emphasizing the importance of a hybrid approach that combines AI capabilities with clinicians' expertise. Patients and Methods: We developed a conceptual framework designed to integrate AI-driven hybrid intelligence into clinical practice to enhance decision-making. This framework focuses on adapting key AI concepts, such as backpropagation, quantization, and avoiding overfitting, to help clinicians better interpret complex medical data and improve diagnosis and treatment planning. Results: Several AI methodologies were adapted to enhance clinical decision-making. First, backpropagation allows clinicians to refine initial assessments by revisiting them as new data emerges, improving diagnostic accuracy over time. Second, quantization helps break down complex medical problems into manageable components, enabling clinicians to prioritize critical elements of care. Finally, avoiding overfitting encourages clinicians to balance rare diagnoses with more common explanations, reducing the risk of diagnostic errors and unnecessary complexity. Conclusion: The integration of AI-driven hybrid intelligence has the potential to enhance clinical decision-making. By adapting AI methodologies, clinicians can enhance their ability to analyze data, prioritize treatments, and make more accurate diagnoses while preserving the essential human aspect of health care. This framework highlights the importance of combining AI's strengths with clinicians' expertise for more effective and balanced decision-making in clinical practice. This perspective highlights the value of hybrid intelligence in achieving more balanced, effective, and patient-centered decision-making in health care. [ABSTRACT FROM AUTHOR]

This article discusses the importance of the palatine bone in endoscopic endonasal skull base surgery. The study examines the structure of the palatine bone and its relationship with surrounding bones, as well as its role in identifying and exposing vital neurovascular structures. The palatine bone contains complex structures that are closely related to arteries, nerves, and branches, making it a useful landmark for surgeons. The article concludes that the palatine bone has not received much attention in skull base surgery, but it harbors important landmarks for maximizing the surgical corridor and minimizing unnecessary injury to neurovascular structures. [Extracted from the article]

Background: Generative artificial intelligence (AI), particularly in the form of large language models, has rapidly developed. The LLaMA series are popular and recently updated from LLaMA2 to LLaMA3. However, the impacts of the update on diagnostic performance have not been well documented., Objective: We conducted a comparative evaluation of the diagnostic performance in differential diagnosis lists generated by LLaMA3 and LLaMA2 for case reports., Methods: We analyzed case reports published in the American Journal of Case Reports from 2022 to 2023. After excluding nondiagnostic and pediatric cases, we input the remaining cases into LLaMA3 and LLaMA2 using the same prompt and the same adjustable parameters. Diagnostic performance was defined by whether the differential diagnosis lists included the final diagnosis. Multiple physicians independently evaluated whether the final diagnosis was included in the top 10 differentials generated by LLaMA3 and LLaMA2., Results: In our comparative evaluation of the diagnostic performance between LLaMA3 and LLaMA2, we analyzed differential diagnosis lists for 392 case reports. The final diagnosis was included in the top 10 differentials generated by LLaMA3 in 79.6% (312/392) of the cases, compared to 49.7% (195/392) for LLaMA2, indicating a statistically significant improvement (P<.001). Additionally, LLaMA3 showed higher performance in including the final diagnosis in the top 5 differentials, observed in 63% (247/392) of cases, compared to LLaMA2's 38% (149/392, P<.001). Furthermore, the top diagnosis was accurately identified by LLaMA3 in 33.9% (133/392) of cases, significantly higher than the 22.7% (89/392) achieved by LLaMA2 (P<.001). The analysis across various medical specialties revealed variations in diagnostic performance with LLaMA3 consistently outperforming LLaMA2., Conclusions: The results reveal that the LLaMA3 model significantly outperforms LLaMA2 per diagnostic performance, with a higher percentage of case reports having the final diagnosis listed within the top 10, top 5, and as the top diagnosis. Overall diagnostic performance improved almost 1.5 times from LLaMA2 to LLaMA3. These findings support the rapid development and continuous refinement of generative AI systems to enhance diagnostic processes in medicine. However, these findings should be carefully interpreted for clinical application, as generative AI, including the LLaMA series, has not been approved for medical applications such as AI-enhanced diagnostics., (©Takanobu Hirosawa, Yukinori Harada, Kazuki Tokumasu, Tatsuya Shiraishi, Tomoharu Suzuki, Taro Shimizu. Originally published in JMIR Formative Research (https://formative.jmir.org), 19.11.2024.)

Objective: This study aimed to evaluate the effectiveness of the endoscopic endonasal approach (EEA) in the surgical management of intraorbital tumors and analyze the adjunctive role of the transorbital approach (TOA) and extended modified medial maxillectomy (EMMM) in addressing anatomically complex tumors., Methods: This study retrospectively reviewed 13 cases of primary intraorbital tumors managed with EEA, integrating TOA and EMMM, based on specific tumor location and extent. A detailed analysis was conducted on the surgical techniques used, tumor size and location in relation to critical structures such as the optic nerve, and overall surgical outcomes, with a focus on the extent of resection and postoperative visual function., Results: Of the 13 cases analyzed (4 cavernous hemangiomas, 3 schwannomas, mucosa-associated lymphoid tissue lymphoma, diffuse large B-cell lymphoma, liposarcoma, inflammatory myofibroblastic tumor, osteoma, and myxoid spindle tumor), the EEA served as the primary surgical method, especially for the 8 intraconal tumors situated medially to the optic nerve, with 1 tumor situated inferiorly to the optic nerve. Extraconal tumors, present in 5 cases, necessitated additional approaches: TOA was utilized for tumors with anterior extension, and EMMM was applied to those extending toward the inferior orbital wall. Gross-total resection was accomplished in 80% of the operative cases, with an overall improvement in visual function observed in 69.2% of the patients postsurgery. Complications were infrequent, with enophthalmos requiring subsequent reconstruction and a permanent slight visual field defect in the upper outer quadrant, occurring in 1 case each, underscoring the safety and efficacy of integrated surgical approaches., Conclusions: The combination of EEA with TOA and EMMM provides a comprehensive and adaptable surgical strategy for intraorbital tumors, accommodating various lesion locations and complexities. This combined approach not only facilitates extensive tumor resection but also maximizes the preservation of ocular function and cosmetic outcomes. The favorable results of this study support the use of a multidisciplinary surgical approach and highlight the potential for improved patient outcomes with the continued development of endoscopic techniques. Further research with a larger cohort is essential to validate these findings and establish guidelines for the combined use of these surgical methods.

Lassa fever (LF), caused by Lassa virus (LASV) infection, typically leads to mild symptoms in humans, yet some survivors experience audiovestibular problems. Here we present vestibular histopathological insights in our LF model mice. We observed: 1) hemorrhage within the vestibular ganglion and stroma beneath the sensory epithelium, 2) preserved hair cells and supporting cells, 3) LASV antigen presence in the vestibular ganglion cells and the stroma beneath the sensory epithelium, and 4) CD3-positive T lymphocyte infiltration in the vestibular ganglion and the stroma underlying the sensory epithelium. LASV and/or its immune response likely contributes to the pathogenesis of vestibular dysfunction., (© The Author(s) 2024. Published by Oxford University Press on behalf of Infectious Diseases Society of America. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com.)

Background: Generative artificial intelligence (GAI) systems by Google have recently been updated from Bard to Gemini and Gemini Advanced as of December 2023. Gemini is a basic, free-to-use model after a user's login, while Gemini Advanced operates on a more advanced model requiring a fee-based subscription. These systems have the potential to enhance medical diagnostics. However, the impact of these updates on comprehensive diagnostic accuracy remains unknown., Objective: This study aimed to compare the accuracy of the differential diagnosis lists generated by Gemini Advanced, Gemini, and Bard across comprehensive medical fields using case report series., Methods: We identified a case report series with relevant final diagnoses published in the American Journal Case Reports from January 2022 to March 2023. After excluding nondiagnostic cases and patients aged 10 years and younger, we included the remaining case reports. After refining the case parts as case descriptions, we input the same case descriptions into Gemini Advanced, Gemini, and Bard to generate the top 10 differential diagnosis lists. In total, 2 expert physicians independently evaluated whether the final diagnosis was included in the lists and its ranking. Any discrepancies were resolved by another expert physician. Bonferroni correction was applied to adjust the P values for the number of comparisons among 3 GAI systems, setting the corrected significance level at P value <.02., Results: In total, 392 case reports were included. The inclusion rates of the final diagnosis within the top 10 differential diagnosis lists were 73% (286/392) for Gemini Advanced, 76.5% (300/392) for Gemini, and 68.6% (269/392) for Bard. The top diagnoses matched the final diagnoses in 31.6% (124/392) for Gemini Advanced, 42.6% (167/392) for Gemini, and 31.4% (123/392) for Bard. Gemini demonstrated higher diagnostic accuracy than Bard both within the top 10 differential diagnosis lists (P=.02) and as the top diagnosis (P=.001). In addition, Gemini Advanced achieved significantly lower accuracy than Gemini in identifying the most probable diagnosis (P=.002)., Conclusions: The results of this study suggest that Gemini outperformed Bard in diagnostic accuracy following the model update. However, Gemini Advanced requires further refinement to optimize its performance for future artificial intelligence-enhanced diagnostics. These findings should be interpreted cautiously and considered primarily for research purposes, as these GAI systems have not been adjusted for medical diagnostics nor approved for clinical use., (©Takanobu Hirosawa, Yukinori Harada, Kazuki Tokumasu, Takahiro Ito, Tomoharu Suzuki, Taro Shimizu. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 02.10.2024.)

Background: The endoscopic endonasal approach to paramedian skull base lesions has garnered increasing attention in recent reports. However, it is still a challenging approach. While the primary objective of the approach is the maximal removal of tumors through a minimally invasive procedure, discussions of the approach rarely include information about the maximum preservation of nasal structures. This study aimed to retrospectively review the clinical outcomes of patients who had undergone an endoscopic endonasal approach to paramedian lesions, describe the technical and anatomical nuances related to this approach at the authors' institution, and discuss the maximal preservation of nasal structures., Observations: The authors conducted a descriptive retrospective study of 17 surgical cases of paramedian endoscopic endonasal approaches performed jointly by otolaryngologists and neurosurgeons from August 2018 to August 2022 at a tertiary hospital., Lessons: The approach to the paramedian region of the skull base was examined. Creating an appropriate corridor to maximize the surgical field is essential to allow a safe and accurate procedure. From an otolaryngologist's perspective, the endoscopic modified medial maxillectomy is an essential procedure that maximizes the surgical corridor and maximally preserves nasal morphology. https://thejns.org/doi/10.3171/CASE24218.

Background: Manual chart review using validated assessment tools is a standardised methodology for detecting diagnostic errors. However, this requires considerable human resources and time. ChatGPT, a recently developed artificial intelligence chatbot based on a large language model, can effectively classify text based on suitable prompts. Therefore, ChatGPT can assist manual chart reviews in detecting diagnostic errors., Objective: This study aimed to clarify whether ChatGPT could correctly detect diagnostic errors and possible factors contributing to them based on case presentations., Methods: We analysed 545 published case reports that included diagnostic errors. We imputed the texts of case presentations and the final diagnoses with some original prompts into ChatGPT (GPT-4) to generate responses, including the judgement of diagnostic errors and contributing factors of diagnostic errors. Factors contributing to diagnostic errors were coded according to the following three taxonomies: Diagnosis Error Evaluation and Research (DEER), Reliable Diagnosis Challenges (RDC) and Generic Diagnostic Pitfalls (GDP). The responses on the contributing factors from ChatGPT were compared with those from physicians., Results: ChatGPT correctly detected diagnostic errors in 519/545 cases (95%) and coded statistically larger numbers of factors contributing to diagnostic errors per case than physicians: DEER (median 5 vs 1, p<0.001), RDC (median 4 vs 2, p<0.001) and GDP (median 4 vs 1, p<0.001). The most important contributing factors of diagnostic errors coded by ChatGPT were 'failure/delay in considering the diagnosis' (315, 57.8%) in DEER, 'atypical presentation' (365, 67.0%) in RDC, and 'atypical presentation' (264, 48.4%) in GDP., Conclusion: ChatGPT accurately detects diagnostic errors from case presentations. ChatGPT may be more sensitive than manual reviewing in detecting factors contributing to diagnostic errors, especially for 'atypical presentation'., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)