Multimodal ChatGPT-4V for Electrocardiogram Interpretation: Promise and Limitations.

This study evaluated the capabilities of the newly released ChatGPT-4V, a large language model with visual recognition abilities, in interpreting electrocardiogram waveforms and answering related multiple-choice questions for assisting with cardiovascular care.

Multimodal Approach in the Diagnosis of Urologic Malignancies: Critical Assessment of ChatGPT-4V's Image-Reading Capabilities.

ChatGPT-4V model with image interpretation tested for distinguishing kidney & prostate tumors from normal tissue.

Multifunctional MXene-doped photothermal microneedles for drug-resistant bacteria-infected wound healing.

Skin injuries and drug-resistant bacterial infections pose serious challenges to human health. It is essential to establish a novel multifunctional platform with good anti-infection and wound-healing abilities. In this study, a new MXene-doped composite microneedle (MN) patch with excellent mechanical strength and photothermal antibacterial and ROS removal properties has been developed for infected wound healing. When the MN tips carrying the MXene nanosheets are inserted into the cuticle of the skin, they will quickly dissolve and subsequently release the nanomaterials into the subcutaneous infection area. Under 808 nm NIR irradiation, the MXene, as a "nano-thermal knife", sterilizes and inhibits bacterial growth through synergistic effects of sharp edges and photothermal antibacterial activity. Furthermore, ROS caused by injury and infection can be cleared by MXene-doped MNs to avoid excessive inflammatory responses. Based on the synergistic antibacterial and antioxidant strategy, the MXene-doped MNs have demonstrated excellent wound-healing properties in an MRSA-infected wound model, such as promoting re-epithelialization, collagen deposition, and angiogenesis and inhibiting the expression of pro-inflammatory factors. Therefore, the multifunctional MXene-doped MN patches provide an excellent alternative for clinical drug-resistant bacteria-infected wound management.

Integrating single-cell and bulk sequencing data to identify glycosylation-based genes in non-alcoholic fatty liver disease-associated hepatocellular carcinoma.

Background: The incidence of non-alcoholic fatty liver disease (NAFLD) associated hepatocellular carcinoma (HCC) has been increasing. However, the role of glycosylation, an important modification that alters cellular differentiation and immune regulation, in the progression of NAFLD to HCC is rare. Methods: We used the NAFLD-HCC single-cell dataset to identify variation in the expression of glycosylation patterns between different cells and used the HCC bulk dataset to establish a link between these variations and the prognosis of HCC patients. Then, machine learning algorithms were used to identify those glycosylation-related signatures with prognostic significance and to construct a model for predicting the prognosis of HCC patients. Moreover, it was validated in high-fat diet-induced mice and clinical cohorts. Results: The NAFLD-HCC Glycogene Risk Model (NHGRM) signature included the following genes: SPP1, SOCS2, SAPCD2, S100A9, RAMP3, and CSAD. The higher NHGRM scores were associated with a poorer prognosis, stronger immune-related features, immune cell infiltration and immunity scores. Animal experiments, external and clinical cohorts confirmed the expression of these genes. Conclusion: The genetic signature we identified may serve as a potential indicator of survival in patients with NAFLD-HCC and provide new perspectives for elucidating the role of glycosylation-related signatures in this pathologic process.

The Evaluation of Generative AI Should Include Repetition to Assess Stability.

The increasing interest in the potential applications of generative artificial intelligence (AI) models like ChatGPT in health care has prompted numerous studies to explore its performance in various medical contexts. However, evaluating ChatGPT poses unique challenges due to the inherent randomness in its responses. Unlike traditional AI models, ChatGPT generates different responses for the same input, making it imperative to assess its stability through repetition. This commentary highlights the importance of including repetition in the evaluation of ChatGPT to ensure the reliability of conclusions drawn from its performance. Similar to biological experiments, which often require multiple repetitions for validity, we argue that assessing generative AI models like ChatGPT demands a similar approach. Failure to acknowledge the impact of repetition can lead to biased conclusions and undermine the credibility of research findings. We urge researchers to incorporate appropriate repetition in their studies from the outset and transparently report their methods to enhance the robustness and reproducibility of findings in this rapidly evolving field.

ChatGPT's ability to generate realistic experimental images poses a new challenge to academic integrity.

The rapid advancements in large language models (LLMs) such as ChatGPT have raised concerns about their potential impact on academic integrity. While initial concerns focused on ChatGPT's writing capabilities, recent updates have integrated DALL-E 3's image generation features, extending the risks to visual evidence in biomedical research. Our tests revealed ChatGPT's nearly barrier-free image generation feature can be used to generate experimental result images, such as blood smears, Western Blot, immunofluorescence and so on. Although the current ability of ChatGPT to generate experimental images is limited, the risk of misuse is evident. This development underscores the need for immediate action. We suggest that AI providers restrict the generation of experimental image, develop tools to detect AI-generated images, and consider adding "invisible watermarks" to the generated images. By implementing these measures, we can better ensure the responsible use of AI technology in academic research and maintain the integrity of scientific evidence.

Step into the era of large multimodal models: a pilot study on ChatGPT-4V(ision)'s ability to interpret radiological images.

BACKGROUND: The introduction of ChatGPT-4V's 'Chat with images' feature represents the beginning of the era of large multimodal models (LMMs), which allows ChatGPT to process and answer questions based on uploaded images. This advancement has the potential to transform how surgical teams utilize radiographic data, as radiological interpretation is crucial for surgical planning and postoperative care. However, a comprehensive evaluation of ChatGPT-4V's capabilities in interpret radiological images and formulating treatment plans remains to be explored. PATIENTS AND METHODS: Three types of questions were collected: (1) 87 USMLE-style questions, submitting only the question stems and images without providing options to assess ChatGPT's diagnostic capability. For questions involving treatment plan formulations, a five-point Likert scale was used to assess ChatGPT's proposed treatment plan. The 87 questions were then adapted by removing detailed patient history to assess its contribution to diagnosis. The diagnostic performance of ChatGPT-4V was also tested when only medical history was provided. (2) We randomly selected 100 chest radiography from the ChestX-ray8 database to test the ability of ChatGPT-4V to identify abnormal chest radiography. (3) Cases from the 'Diagnose Please' section in the Radiology journal were collected to evaluate the performance of ChatGPT-4V in diagnosing complex cases. Three responses were collected for each question. RESULTS: ChatGPT-4V achieved a diagnostic accuracy of 77.01% for USMLE-style questions. The average score of ChatGPT-4V's treatment plans was 3.97 (Interquartile Range: 3.33-4.67). Removing detailed patient history dropped the diagnostic accuracy to 19.54% (P<0.0001). ChatGPT-4V achieved an AUC of 0.768 (95% CI: 0.684-0.851) in detecting abnormalities in chest radiography, but could not specify the exact disease due to the lack of detailed patient history. For cases from 'Diagnose Please' ChatGPT provided diagnoses consistent with or very similar to the reference answers. CONCLUSION: ChatGPT-4V demonstrated an impressive ability to combine patient history with radiological images to make diagnoses and directly design treatment plans based on images, suggesting its potential for future application in clinical practice.

Harnessing artificial intelligence for prostate cancer management.

Prostate cancer (PCa) is a common malignancy in males. The pathology review of PCa is crucial for clinical decision-making, but traditional pathology review is labor intensive and subjective to some extent. Digital pathology and whole-slide imaging enable the application of artificial intelligence (AI) in pathology. This review highlights the success of AI in detecting and grading PCa, predicting patient outcomes, and identifying molecular subtypes. We propose that AI-based methods could collaborate with pathologists to reduce workload and assist clinicians in formulating treatment recommendations. We also introduce the general process and challenges in developing AI pathology models for PCa. Importantly, we summarize publicly available datasets and open-source codes to facilitate the utilization of existing data and the comparison of the performance of different models to improve future studies.

Artificial intelligence-aided detection for prostate cancer with multimodal routine health check-up data: an Asian multi-center study.

BACKGROUND: The early detection of high-grade prostate cancer (HGPCa) is of great importance. However, the current detection strategies result in a high rate of negative biopsies and high medical costs. In this study, the authors aimed to establish an Asian Prostate Cancer Artificial intelligence (APCA) score with no extra cost other than routine health check-ups to predict the risk of HGPCa. PATIENTS AND METHODS: A total of 7476 patients with routine health check-up data who underwent prostate biopsies from January 2008 to December 2021 in eight referral centres in Asia were screened. After data pre-processing and cleaning, 5037 patients and 117 features were analyzed. Seven AI-based algorithms were tested for feature selection and seven AI-based algorithms were tested for classification, with the best combination applied for model construction. The APAC score was established in the CH cohort and validated in a multi-centre cohort and in each validation cohort to evaluate its generalizability in different Asian regions. The performance of the models was evaluated using area under the receiver operating characteristic curve (ROC), calibration plot, and decision curve analyses. RESULTS: Eighteen features were involved in the APCA score predicting HGPCa, with some of these markers not previously used in prostate cancer diagnosis. The area under the curve (AUC) was 0.76 (95% CI:0.74-0.78) in the multi-centre validation cohort and the increment of AUC (APCA vs. PSA) was 0.16 (95% CI:0.13-0.20). The calibration plots yielded a high degree of coherence and the decision curve analysis yielded a higher net clinical benefit. Applying the APCA score could reduce unnecessary biopsies by 20.2% and 38.4%, at the risk of missing 5.0% and 10.0% of HGPCa cases in the multi-centre validation cohort, respectively. CONCLUSIONS: The APCA score based on routine health check-ups could reduce unnecessary prostate biopsies without additional examinations in Asian populations. Further prospective population-based studies are warranted to confirm these results.

Trends and Frontiers of Research on Cancer Gene Therapy From 2016 to 2020: A Bibliometric Analysis.

Background: With rapid development in molecular biology techniques and a greater understanding of cancer pathogenesis, the growing attention has been concentrated on cancer gene therapy, with numerous articles on this topic published in recent 5 years. However, there is lacking a bibliometric analysis of research on cancer gene therapy. Therefore, the aim of the present study was to conduct a bibliometric analysis to provide the trends and frontiers of research on cancer gene therapy during 2016-2020. Methods: We utilized CiteSpace 5.7.R5 software to conduct a bibliometric analysis of publications on cancer gene therapy published during 2016-2020. The bibliometric records were obtained from the Web of Science Core Collection. Results: A total of 4,392 papers were included in the bibliometric analysis. Materials Science and Nanoscience and Nanotechnology took an increasing part in the field of cancer gene therapy. Additionally, WANG W was the most productive author, while ZHANG Y ranked top in terms of citations. Harvard Medical School and Sichuan University ranked top in the active institutions. P NATL ACAD SCI USA was identified as the core journal in the field of cancer gene therapy. "Ovarian cancer" was found to be the latest keyword with the strongest burst. The keyword analysis suggested that the top three latest clusters were labeled "gene delivery," "drug delivery," and "gene therapy." In the reference analysis, cluster#2 labeled "gene delivery" held a dominant place considering both the node volume and mean year. Conclusion: The academic attention on cancer gene therapy was growing at a dramatically high speed. Materials Science and Nanoscience and Nanotechnology might become promising impetus for the development of this field. "Gene delivery" was thought to best reflect the research frontier on cancer gene therapy. The top-cited articles on gene delivery were focused on several novel non-viral vectors due to their specialty compared with viral vectors. "Ovarian cancer" was likely to be the potential research direction. These findings would help medical workers conduct further investigations on cancer gene therapy.