RESUMEN

Significance: Advancements in label-free microscopy could provide real-time, non-invasive imaging with unique sources of contrast and automated standardized analysis to characterize heterogeneous and dynamic biological processes. These tools would overcome challenges with widely used methods that are destructive (e.g., histology, flow cytometry) or lack cellular resolution (e.g., plate-based assays, whole animal bioluminescence imaging). Aim: This perspective aims to (1) justify the need for label-free microscopy to track heterogeneous cellular functions over time and space within unperturbed systems and (2) recommend improvements regarding instrumentation, image analysis, and image interpretation to address these needs. Approach: Three key research areas (cancer research, autoimmune disease, and tissue and cell engineering) are considered to support the need for label-free microscopy to characterize heterogeneity and dynamics within biological systems. Based on the strengths (e.g., multiple sources of molecular contrast, non-invasive monitoring) and weaknesses (e.g., imaging depth, image interpretation) of several label-free microscopy modalities, improvements for future imaging systems are recommended. Conclusion: Improvements in instrumentation including strategies that increase resolution and imaging speed, standardization and centralization of image analysis tools, and robust data validation and interpretation will expand the applications of label-free microscopy to study heterogeneous and dynamic biological systems.

Asunto(s)

RESUMEN

Sections stained in periodic acid-Schiff (PAS), periodic acid-methenamine silver (PAM), hematoxylin and eosin (H&E), and Masson's trichrome (MT) stain with minimal morphological discordance are helpful for pathological diagnosis in renal biopsy. Here, we propose an artificial intelligence-based re-stainer called PPHM-GAN (PAS, PAM, H&E, and MT-generative adversarial networks) with multi-stain to multi-stain transformation capability. We trained three GAN models on 512 × 512-pixel patches from 26 training cases. The model with the best transformation quality was selected for each pair of stain transformations by human evaluation. Frechet inception distances, peak signal-to-noise ratio, structural similarity index measure, contrast structural similarity, and newly introduced domain shift inception score were calculated as auxiliary quality metrics. We validated the diagnostic utility using 5120 × 5120 patches of ten validation cases for major glomerular and interstitial abnormalities. Transformed stains were sometimes superior to original stains for the recognition of crescent formation, mesangial hypercellularity, glomerular sclerosis, interstitial lesions, or arteriosclerosis. 23 of 24 glomeruli (95.83 %) from 9 additional validation cases transformed to PAM, PAS, or MT facilitated recognition of crescent formation. Stain transformations to PAM (p = 4.0E-11) and transformations from H&E (p = 4.8E-9) most improved crescent formation recognition. PPHM-GAN maximizes information from a given section by providing several stains in a virtual single-section view, and may change the staining and diagnostic strategy.

RESUMEN

BACKGROUND: Rapid developments in artificial intelligence have begun to necessitate changes and transformations in nursing education. OBJECTIVE: This study aimed to evaluate the impact of an artificial intelligence-supported case created in the in-class case analysis lecture for nursing students on students' case management performance and satisfaction. DESIGN: This study was a randomized controlled trial. METHOD: The study involved 188 third-year nursing students randomly assigned to the AI group (n=94) or the control group (n=94). An information form, case evaluation form, knowledge test and Mentimeter application were used to assess the students' case management performance and nursing diagnoses. The level of satisfaction with the case analysis lecture was evaluated using the VAS scale. RESULTS: The case management performance scores of the students in the artificial intelligence group were significantly higher than those of the control group (p<0.05). There was no statistically significant difference in satisfaction levels between the artificial intelligence (AI) group and the control group (p>0.05). CONCLUSIONS: The study's results indicated that AI-supported cases improved students' case management performance and were as effective as instructor-led cases regarding satisfaction with the case analysis lecture, focus and interest in the case. The integration of artificial intelligence into traditional nursing education curricula is recommended. CLINICAL TRIALS REGISTRATION NUMBER: https://register. CLINICALTRIALS: gov; (NCT06443983).

RESUMEN

Visual methods in mental health research have been extensively explored and utilized following the expanse of art-therapy. The existing literature shows visual arts as a valuable research method with multi-fold benefits for both researchers and research participants. However, the way contemporary art is understood, conceptualized, and experienced has been challenged by the current digital advancements in our society. Despite heated debates whether AI may diminish the value of human creativity, AI-generated art is a complex reality that started to influence the way visual research is conducted. Within this context, researchers employing visual methods need to develop a deeper understanding of this topic. For this purpose, this article explores the concept of AI-generated images with a focus on benefits and limitations when applied to mental health research and potentially other areas of health and social care. As this is an emerging topic, more research on the effectiveness and therapeutic value of AI-generated images is required beyond the current anecdotical evidence, from the perspective of the researchers and research participants.

RESUMEN

PURPOSE: The purpose of this study was to investigate the added value of artificial intelligence (AI) solutions for the detection of arterial stenosis (AS) on head and neck CT angiography (CTA). MATERIALS AND METHODS: Patients who underwent head and neck CTA examinations at two hospitals were retrospectively included. CTA examinations were randomized into group 1 (without AI-washout-with AI) and group 2 (with AI-washout-without AI), and six readers (two radiology residents, two non-neuroradiologists, and two neuroradiologists) independently interpreted each CTA examination without and with AI solutions. Additionally, reading time was recorded for each patient. Digital subtraction angiography was used as the standard of reference. The diagnostic performance for AS at lesion and patient levels with four AS thresholds (30 %, 50 %, 70 %, and 100 %) was assessed by calculating sensitivity, false-positive lesions index (FPLI), specificity, and accuracy. RESULTS: A total of 268 patients (169 men, 63.1 %) with a median age of 65 years (first quartile, 57; third quartile, 72; age range: 28-88 years) were included. At the lesion level, AI improved the sensitivity of all readers by 5.2 % for detecting AS ≥ 30 % (P < 0.001). Concurrently, AI reduced the FPLI of all readers and specifically neuroradiologists for detecting non-occlusive AS (all P < 0.05). At the patient level, AI improved the accuracy of all readers by 4.1 % (73.9 % [1189/1608] without AI vs. 78.0 % [1254/1608] with AI) (P < 0.001). Sensitivity for AS ≥ 30 % and the specificity for AS ≥ 70 % increased for all readers with AI assistance (P = 0.01). The median reading time for all readers was reduced from 268 s without AI to 241 s with AI (P< 0.001). CONCLUSION: AI-assisted diagnosis improves the performance of radiologists in detecting head and neck AS, and shortens reading time.

RESUMEN

PURPOSE: The purpose of this study was to compare the diagnostic performance of an artificial intelligence (AI) solution for the detection of fractures of pelvic, proximal femur or extremity fractures in adults with radiologist interpretation of radiographs, using standard dose CT examination as the standard of reference. MATERIALS AND METHODS: This retrospective study included 94 adult patients with suspected bone fractures who underwent a standard dose CT examination and radiographs of the pelvis and/or hip and extremities at our institution between January 2022 and August 2023. For all patients, an AI solution was used retrospectively on the radiographs to detect and localize bone fractures of the pelvis and/or hip and extremities. Results of the AI solution were compared to the reading of each radiograph by a radiologist using McNemar test. The results of standard dose CT examination as interpreted by a senior radiologist were used as the standard of reference. RESULT: A total of 94 patients (63 women; mean age, 56.4 ± 22.5 [standard deviation] years) were included. Forty-seven patients had at least one fracture, and a total of 71 fractures were deemed present using the standard of reference (25 hand/wrist, 16 pelvis, 30 foot/ankle). Using the standard of reference, the analysis of radiographs by the AI solution resulted in 58 true positive, 13 false negative, 33 true negative and 15 false positive findings, yielding 82 % sensitivity (58/71; 95 % confidence interval [CI]: 71-89 %), 69 % specificity (33/48; 95 % CI: 55-80 %), and 76 % accuracy (91/119; 95 % CI: 69-84 %). Using the standard of reference, the reading of the radiologist resulted in 65 true positive, 6 false negative, 42 true negative and 6 false positive findings, yielding 92 % sensitivity (65/71; 95 % CI: 82-96 %), 88 % specificity (42/48; 95 % CI: 75-94 %), and 90 % accuracy (107/119; 95 % CI: 85-95 %). The radiologist outperformed the AI solution in terms of sensitivity (P = 0.045), specificity (P = 0.016), and accuracy (P < 0.001). CONCLUSION: In this study, the radiologist outperformed the AI solution for the diagnosis of pelvic, hip and extremity fractures of the using radiographs. This raises the question of whether a strong standard of reference for evaluating AI solutions should be used in future studies comparing AI and human reading in fracture detection using radiographs.

RESUMEN

Canonical cases of learning involve novel observations external to the mind, but learning can also occur through mental processes such as explaining to oneself, mental simulation, analogical comparison, and reasoning. Recent advances in artificial intelligence (AI) reveal that such learning is not restricted to human minds: artificial minds can also self-correct and arrive at new conclusions by engaging in processes of 'learning by thinking' (LbT). How can elements already in the mind generate new knowledge? This article aims to resolve this paradox, and in so doing highlights an important feature of natural and artificial minds - to navigate uncertain environments with variable goals, minds with limited resources must construct knowledge representations 'on demand'. LbT supports this construction.

RESUMEN

BACKGROUND: Transcranial color Doppler (TCD) is currently the only noninvasive bedside tool capable of providing real-time information on cerebral hemodynamics. However, being operator dependent, TCD monitoring is not feasible in many institutions. Robotic assisted TCD (ra-TCD) was recently developed to overcome these constraints. The aim of this study was to evaluate the safety and feasibility of cerebral monitoring with a novel ra-TCD in acute neurovascular care. METHODS: This is a two-center prospective study conducted between August 2021 and February 2022 at Padua University Hospital (Padua, Italy) and Kepler University Hospital (Linz, Austria). Adult patients with conditions impacting cerebral hemodynamics or patients undergoing invasive procedures affecting cerebral hemodynamics were recruited for prolonged monitoring (> 30 min) of the middle cerebral artery with a novel ra-TCD (NovaGuide Intelligent Ultrasound, NeuraSignal, Los Angeles, CA). Manual TCD was also performed for comparison by an experienced operator. Feasibility and safety rates were recorded. RESULTS: A total of 92 patients (age: mean 68.5 years, range 36-91; sex: male 57 [62%]) were enrolled in the two centers: 54 in Padua, 38 in Linz. The examination was feasible in the majority of patients (85.9%); the head cradle design and its radiopacity hindered its use during carotid endarterectomy and mechanical thrombectomy. Regarding safety, only one patient (1.1%) reported a minor local edema due to prolonged probe pressure. Velocity values were similar between ra-TCD and manual TCD. CONCLUSIONS: This novel ra-TCD showed an excellent safety and feasibility and proved to be as reliable as manual TCD in detecting blood flow velocities. These findings support its wider use for cerebral hemodynamics monitoring in acute neurovascular care. However, further technical improvements are needed to expand the range of applicable settings.

RESUMEN

PURPOSE: This study aims to identify and assess the factors challenging the integration of artificial intelligence (AI) technologies in healthcare workplaces. DESIGN/METHODOLOGY/APPROACH: The study utilized a mixed approach, that starts with a literature review, then developing and testing a questionnaire survey of the factors challenging the integration of AI technologies in healthcare workplaces. In total, 46 factors were identified and classified under 6 groups. These factors were assessed by four different stakeholder categories: facilities managers, medical staff, operational staff and patients/visitors. The evaluations gathered were examined to determine the relative importance index (RII), importance rating (IR) and ranking of each factor. FINDINGS: All 46 factors were assessed as "Very Important" through the overall assessment by the four stakeholder categories. The results indicated that the most important factors, across all groups, are "AI ability to learn from patient data", "insufficient data privacy measures for patients", "availability of technical support and maintenance services", "physicians' acceptance of AI in healthcare", "reliability and uptime of AI systems" and "ability to reduce medical errors". PRACTICAL IMPLICATIONS: Determining the importance ratings of the factors can lead to better resource allocation and the development of strategies to facilitate the adoption and implementation of these technologies, thus promoting the development of innovative solutions to improve healthcare practices. ORIGINALITY/VALUE: This study contributes to the body of knowledge in the domain of technology adoption and implementation in the medical workplace, through improving stakeholders' comprehension of the factors challenging the integration of AI technologies.

Asunto(s)

RESUMEN

PURPOSE: The study explores the evolving landscape of cataract diagnosis, focusing on both traditional methods and innovative technological integrations. It aims to address challenges with subjectivity in traditional cataract grading and to evaluate how new technologies can enhance diagnostic accuracy and accessibility. METHODS: The research introduces and examines the use of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in automating and improving cataract screening processes. It also explores the role of the Metaverse, Digital Twins, and Teleophthalmology for immersive patient education, real-time virtual replicas of eyes, and remote access to specialized care. RESULTS: Various ML and DL techniques demonstrated significant accuracy in cataract detection. The integration of these technologies, along with the Metaverse, Digital Twins, and Teleophthalmology, provides a comprehensive framework for accurate and accessible cataract diagnosis. CONCLUSION: There is a notable paradigm shift toward individualized, predictive, and transformative eye care. The advancements in technology address existing diagnostic challenges and mitigate the shortage of ophthalmologists by extending high-quality care to underserved regions. These developments pave the way for improved cataract management and broader accessibility.

RESUMEN

BACKGROUND: Lung cancer has the highest mortality rate among malignancies globally. In addition, due to the growing number of smokers there is considerable concern over its growth. Early detection is an essential step towards reducing complications in this regard and helps to ensure the most effective treatment, reduce health care costs, and increase survival rates. AIMS: To define the most efficient and cost-effective method of early detection in clinical practice. MATERIALS AND METHODS: We collected the Information used to write this review by searching papers through PUBMED that were published from 2021 to 2024, mainly systematic reviews, meta-analyses and clinical-trials. We also included other older but notable papers that we found essential and valuable for understanding. RESULTS: EB-OCT has a varied sensitivity and specificity-an average of 94.3% and 89.9 for each. On the other hand, detecting biomarkers via liquid biopsy carries an average sensitivity of 91.4% for RNA molecules detection, and 97% for combined methylated DNA panels. Moreover, CTCs detection did not prove to have a significant role as a screening method due to the rarity of CTCs in the bloodstream thus the need for more blood samples and for enrichment techniques. DISCUSSION: Although low-dose CT scan (LDCT) is the current golden standard screening procedure, it is accompanied by a highly false positive rate. In comparison to other radiological screening methods, Endobronchial optical coherence tomography (EB-OCT) has shown a noticeable advantage with a significant degree of accuracy in distinguishing between subtypes of non-small cell lung cancer. Moreover, numerous biomarkers, including RNA molecules, circulating tumor cells, CTCs, and methylated DNA, have been studied in the literature. Many of these biomarkers have a specific high sensitivity and specificity, making them potential candidates for future early detection approaches. CONCLUSION: LDCT is still the golden standard and the only recommended screening procedure for its high sensitivity and specificity and proven cost-effectiveness. Nevertheless, the notable false positive results acquired during the LDCT examination caused a presumed concern, which drives researchers to investigate better screening procedures and approaches, particularly with the rise of the AI era or by combining two methods in a well-studied screening program like LDCT and liquid biopsy. we suggest conducting more clinical studies on larger populations with a clear demographical target and adopting approaches for combining one of these new methods with LDCT to decrease false-positive cases in early detection.

Asunto(s)

RESUMEN

Introduction: Medical services are getting automated and intelligent. An emerging medical service is the AI pharmacy intravenous admixture service (PIVAS) that prepares infusions through robots. However, patients may distrust these robots. Therefore, this study aims to investigate the psychological mechanism of patients' trust in AI PIVAS. Methods: We conducted one field study and four experimental studies to test our hypotheses. Study 1 and 2 investigated patients' trust of AI PIVAS. Study 3 and 4 examined the effect of subjective understanding on trust in AI PIVAS. Study 5 examined the moderating effect of informed consent. Results: The results indicated that patients' reluctance to trust AI PIVAS (Studies 1-2) stems from their lack of subjective understanding (Study 3). Particularly, patients have an illusion of understanding humans and difficulty in understanding AI (Study 4). In addition, informed consent emerges as a moderating factor, which improves patients' subjective understanding of AI PIVAS, thereby increasing their trust (Study 5). Discussion: The study contributes to the literature on algorithm aversion and cognitive psychology by providing insights into the mechanisms and boundary conditions of trust in the context of AI PIVAS. Findings suggest that medical service providers should explain the criteria or process to improve patients' subjective understanding of medical AI, thus increasing the trust in algorithm-based services.

RESUMEN

Recent advancements in artificial intelligence (AI) and machine learning offer numerous opportunities in musculoskeletal radiology to potentially bolster diagnostic accuracy, workflow efficiency, and predictive modeling. AI tools have the capability to assist radiologists in many tasks ranging from image segmentation, lesion detection, and more. In bone and soft tissue tumor imaging, radiomics and deep learning show promise for malignancy stratification, grading, prognostication, and treatment planning. However, challenges such as standardization, data integration, and ethical concerns regarding patient data need to be addressed ahead of clinical translation. In the realm of musculoskeletal oncology, AI also faces obstacles in robust algorithm development due to limited disease incidence. While many initiatives aim to develop multitasking AI systems, multidisciplinary collaboration is crucial for successful AI integration into clinical practice. Robust approaches addressing challenges and embodying ethical practices are warranted to fully realize AI's potential for enhancing diagnostic accuracy and advancing patient care.

RESUMEN

INTRODUCTION: This study evaluates the diagnostic performance of the latest large language models (LLMs), GPT-4o (OpenAI, San Francisco, CA, USA) and Claude 3 Opus (Anthropic, San Francisco, CA, USA), in determining causes of death from medical histories and postmortem CT findings. METHODS: We included 100 adult cases whose postmortem CT scans were diagnosable for the causes of death using the gold standard of autopsy results. Their medical histories and postmortem CT findings were compiled, and clinical and imaging diagnoses of both the underlying and immediate causes of death, as well as their personal information, were carefully separated from the database to be shown to the LLMs. Both GPT-4o and Claude 3 Opus generated the top three differential diagnoses for each of the underlying or immediate causes of death based on the following three prompts: 1) medical history only; 2) postmortem CT findings only; and 3) both medical history and postmortem CT findings. The diagnostic performance of the LLMs was compared using McNemar's test. RESULTS: For the underlying cause of death, GPT-4o achieved primary diagnostic accuracy rates of 78%, 72%, and 78%, while Claude 3 Opus achieved 72%, 56%, and 75% for prompts 1, 2, and 3, respectively. Including any of the top three differential diagnoses, GPT-4o's accuracy rates were 92%, 90%, and 92%, while Claude 3 Opus's rates were 93%, 69%, and 93% for prompts 1, 2, and 3, respectively. For the immediate cause of death, GPT-4o's primary diagnostic accuracy rates were 55%, 58%, and 62%, while Claude 3 Opus's rates were 60%, 62%, and 63% for prompts 1,2, and 3, respectively. For any of the top three differential diagnoses, GPT-4o's accuracy rates were 88% for prompt 1 and 91% for prompts 2 and 3, whereas Claude 3 Opus's rates were 92% for all three prompts. Significant differences between the models were observed for prompt two in diagnosing the underlying cause of death (p = 0.03 and <0.01 for the primary and top three differential diagnoses, respectively). CONCLUSION: Both GPT-4o and Claude 3 Opus demonstrated relatively high performance in diagnosing both the underlying and immediate causes of death using medical histories and postmortem CT findings.

RESUMEN

INTRODUCTION: As artificial intelligence (AI) transforms healthcare, medical education must adapt to equip future physicians with the necessary competencies. However, little is known about the differences in AI knowledge, attitudes, and practices between undergraduate and postgraduate medical students. This study aims to assess and compare AI knowledge, attitudes, and practices among undergraduate and postgraduate medical students, and to explore the associated factors and qualitative themes. METHODS: A mixed-methods study was conducted, involving 605 medical students (404 undergraduates, 201 postgraduates) from a tertiary care center. Participants completed a survey assessing AI knowledge, attitudes, and practices. Semi-structured interviews and focus group discussions were conducted to explore qualitative themes. Quantitative data were analyzed using descriptive statistics, t-tests, chi-square tests, and regression analyses. Qualitative data underwent thematic analysis. RESULTS: Postgraduate students demonstrated significantly higher AI knowledge scores than undergraduates (38.9±4.9 vs. 29.6±6.8, p<0.001). Both groups held positive attitudes, but postgraduates showed greater confidence in AI's potential (p<0.001). Postgraduates reported more extensive AI-related practices (p<0.001). Key qualitative themes included excitement about AI's potential, concerns about job security, and the need for AI education. AI knowledge, attitudes, and practices were positively correlated (p<0.01). CONCLUSIONS: This study reveals a significant AI knowledge gap between undergraduate and postgraduate medical students, highlighting the need for targeted AI education. The findings can inform curriculum development and policies to prepare medical students for the AI-driven future of healthcare. Further research should explore the long-term impact of AI education on clinical practice.

RESUMEN

Cerebral aneurysms are abnormal dilations of blood vessels in the brain that have the potential to rupture, leading to subarachnoid hemorrhage and other serious complications. Early detection and prediction of aneurysm rupture are crucial for effective management and prevention of rupture-related morbidities and mortalities. This review aims to summarize the current knowledge on risk factors and predictive indicators of rupture in cerebral aneurysms. Morphological characteristics such as aneurysm size, shape, and location, as well as hemodynamic factors including blood flow patterns and wall shear stress, have been identified as important factors influencing aneurysm stability and rupture risk. In addition to these traditional factors, emerging evidence suggests that biological and genetic factors, such as inflammation, extracellular matrix remodeling, and genetic polymorphisms, may also play significant roles in aneurysm rupture. Furthermore, advancements in computational fluid dynamics and machine learning algorithms have enabled the development of novel predictive models for rupture risk assessment. However, challenges remain in accurately predicting aneurysm rupture, and further research is needed to validate these predictors and integrate them into clinical practice. By elucidating and identifying the various risk factors and predictive indicators associated with aneurysm rupture, we can enhance personalized risk assessment and optimize treatment strategies for patients with cerebral aneurysms.

RESUMEN

In today's information age, recommender systems have become an essential tool to filter and personalize the massive data flow to users. However, these systems' increasing complexity and opaque nature have raised concerns about transparency and user trust. Lack of explainability in recommendations can lead to ill-informed decisions and decreased confidence in these advanced systems. Our study addresses this problem by integrating explainability techniques into recommendation systems to improve both the precision of the recommendations and their transparency. We implemented and evaluated recommendation models on the MovieLens and Amazon datasets, applying explainability methods like LIME and SHAP to disentangle the model decisions. The results indicated significant improvements in the precision of the recommendations, with a notable increase in the user's ability to understand and trust the suggestions provided by the system. For example, we saw a 3% increase in recommendation precision when incorporating these explainability techniques, demonstrating their added value in performance and improving the user experience.

RESUMEN

Introduction: This study investigates the experiences of leading Chinese companies in environmental conservation under varying extreme climate conditions, focusing on the role of artificial intelligence (AI) and governmental assistance. Methods: A survey was conducted involving 200 participants to assess recognition and endorsement of AI's role in environmental protection and to explore the adoption of AI technologies by firms for enhancing environmental management practices. Results: The survey revealed widespread recognition of Tencent's green initiatives and strong support for AI's role in environmental protection. Many firms are considering adopting AI technologies to optimize energy management, deploy intelligent HVAC systems, and improve the operations of data centers and smart lighting systems. Discussion: The findings highlight a strong belief in AI's potential to advance environmental protection efforts, with a call for increased governmental support to foster this development. The study underscores the importance of a partnership between businesses and governments to leverage AI for environmental sustainability, contributing significantly to conservation efforts.

Asunto(s)

RESUMEN

Background: Recurrent and metastatic head and neck squamous cell carcinoma (HNSCC) is characterized by a complex therapeutic management that needs to be discussed in multidisciplinary tumor boards (MDT). While artificial intelligence (AI) improved significantly to assist healthcare professionals in making informed treatment decisions for primary cases, an application in the even more complex recurrent/metastatic setting has not been evaluated yet. This study also represents the first evaluation of the recently published LLM ChatGPT 4o, compared to ChatGPT 4.0 for providing therapy recommendations. Methods: The therapy recommendations for 100 HNSCC cases generated by each LLM, 50 cases of recurrence and 50 cases of distant metastasis were evaluated by two independent reviewers. The primary outcome measured was the quality of the therapy recommendations measured by the following parameters: clinical recommendation, explanation, and summarization. Results: In this study, ChatGPT 4o and 4.0 provided mostly general answers for surgery, palliative care, or systemic therapy. ChatGPT 4o proved to be 48.5% faster than ChatGPT 4.0. For clinical recommendation, explanation, and summarization both LLMs obtained high scores in terms of performance of therapy recommendations, with no significant differences between both LLMs, but demonstrated to be mostly an assisting tool, requiring validation by an experienced clinician due to a lack of transparency and sometimes recommending treatment modalities that are not part of the current treatment guidelines. Conclusion: This research demonstrates that ChatGPT 4o and 4.0 share a similar performance, while ChatGPT 4o is significantly faster. Since the current versions cannot tailor therapy recommendations, and sometimes recommend incorrect treatment options and lack information on the source material, advanced AI models at the moment can merely assist in the MDT setting for recurrent/metastatic HNSCC.