Background: Accurate medical advice is paramount in ensuring optimal patient care, and misinformation can lead to misguided decisions with potentially detrimental health outcomes. The emergence of large language models (LLMs) such as OpenAI’s GPT-4 has spurred interest in their potential health care applications, particularly in automated medical consultation. Yet, rigorous investigations comparing their performance to human experts remain sparse. Objective: This study aims to compare the medical accuracy of GPT-4 with human experts in providing medical advice using real-world user-generated queries, with a specific focus on cardiology. It also sought to analyze the performance of GPT-4 and human experts in specific question categories, including drug or medication information and preliminary diagnoses. Methods: We collected 251 pairs of cardiology-specific questions from general users and answers from human experts via an internet portal. GPT-4 was tasked with generating responses to the same questions. Three independent cardiologists (SL, JHK, and JJC) evaluated the answers provided by both human experts and GPT-4. Using a computer interface, each evaluator compared the pairs and determined which answer was superior, and they quantitatively measured the clarity and complexity of the questions as well as the accuracy and appropriateness of the responses, applying a 3-tiered grading scale (low, medium, and high). Furthermore, a linguistic analysis was conducted to compare the length and vocabulary diversity of the responses using word count and type-token ratio. Results: GPT-4 and human experts displayed comparable efficacy in medical accuracy (“GPT-4 is better” at 132/251, 52.6% vs “Human expert is better” at 119/251, 47.4%). In accuracy level categorization, humans had more high-accuracy responses than GPT-4 (50/237, 21.1% vs 30/238, 12.6%) but also a greater proportion of low-accuracy responses (11/237, 4.6% vs 1/238, 0.4%; P=.001). GPT-4 responses were generally longer and used a less diverse vocabulary than those of human experts, potentially enhancing their comprehensibility for general users (sentence count: mean 10.9, SD 4.2 vs mean 5.9, SD 3.7; P<.001; type-token ratio: mean 0.69, SD 0.07 vs mean 0.79, SD 0.09; P<.001). Nevertheless, human experts outperformed GPT-4 in specific question categories, notably those related to drug or medication information and preliminary diagnoses. These findings highlight the limitations of GPT-4 in providing advice based on clinical experience. Conclusions: GPT-4 has shown promising potential in automated medical consultation, with comparable medical accuracy to human experts. However, challenges remain particularly in the realm of nuanced clinical judgment. Future improvements in LLMs may require the integration of specific clinical reasoning pathways and regulatory oversight for safe use. Further research is needed to understand the full potential of LLMs across various medical specialties and conditions.

Cardiac stem cells (CSCs) were known to secrete diverse paracrine factors leading to functional improvement and beneficial left ventricular remodeling via activation of the endogenous pro-survival signaling pathway. However, little is known about the paracrine factors secreted by CSCs and their roles in cardiomyocyte survival during hypoxic condition mimicking the post-myocardial infarction environment. We established Sca-1+/CD31− human telomerase reverse transcriptase-immortalized CSCs (Sca-1+/CD31− CSCs^hTERT), evaluated their stem cell properties, and paracrine potential in cardiomyocyte survival during hypoxia-induced injury. Sca-1+/CD31− CSCs^hTERT sustained proliferation ability even after long-term culture exceeding 100 population doublings, and represented multi-differentiation potential into cardiomyogenic, endothelial, adipogenic, and osteogenic lineages. Dominant factors secreted from Sca-1+/CD31− CSCs^hTERT were EGF, TGF-β1, IGF-1, IGF-2, MCP-1, HGF R, and IL-6. Among these, MCP-1 was the most predominant factor in Sca-1+/CD31− CSCs^hTERT conditioned medium (CM). Sca-1+/CD31− CSCs^hTERT CM increased survival and reduced apoptosis of HL-1 cardiomyocytes during hypoxic injury. MCP-1 silencing in Sca-1+/CD31− CSCs^hTERT CM resulted in a significant reduction in cardiomyocyte apoptosis. We demonstrated that Sca-1+/CD31− CSCs^hTERT exhibited long-term proliferation capacity and multi-differentiation potential. Sca-1+/CD31− CSCs^hTERT CM protected cardiomyocytes from hypoxic injury partly via MCP-1-dependent mechanism. Thus, they are valuable sources for in vitro and in vivo studies in the cardiovascular field.

Background: Sca-1+ cardiac stem cells and their limited proliferative potential were major limiting factors for use in various studies. Methods: Therefore, the effects of sphere genetically engineered cardiac stem cells (S-GECS) inserted with telomerase reverse transcriptase (TERT) were investigated to examine cardiomyocyte survival under hypoxic conditions. GECS was obtained from hTERT-immortalized Sca-1+ cardiac stem cell (CSC) lines, and S-GECS were generated using poly-HEMA. Results: The optimal conditions for S-GECS was determined to be 1052 GECS cells/mm² and a 48 h culture period to produce spheroids. Compared to adherent-GECS (A-GECS) and S-GECS showed significantly higher mRNA expression of SDF-1α and CXCR4. S-GECS conditioned medium (CM) significantly reduced the proportion of early and late apoptotic cardiomyoblasts during CoCl₂-induced hypoxic injury; however, gene silencing via CXCR4 siRNA deteriorated the protective effects of S-GECS against hypoxic injury. As downstream pathways of SDF-1α/CXCR4, the Erk and Akt signaling pathways were stimulated in the presence of S-GECS CM. S-GECS transplantation into a rat acute myocardial infarction model improved cardiac function and reduced the fibrotic area. These cardioprotective effects were confirmed to be related with the SDF-1α/CXCR4 pathway. Conclusions: Our findings suggest that paracrine factors secreted from transplanted cells may protect host cardiomyoblasts in the infarcted myocardium, contributing to beneficial left ventricle (LV) remodeling after acute myocardial infarction (AMI).

Background: De-identifying personal information is critical when using personal health data for secondary research. The Observational Medical Outcomes Partnership Common Data Model (CDM), defined by the nonprofit organization Observational Health Data Sciences and Informatics, has been gaining attention for its use in the analysis of patient-level clinical data obtained from various medical institutions. When analyzing such data in a public environment such as a cloud-computing system, an appropriate de-identification strategy is required to protect patient privacy. Objective: This study proposes and evaluates a de-identification strategy that is comprised of several rules along with privacy models such as k-anonymity, l-diversity, and t-closeness. The proposed strategy was evaluated using the actual CDM database. Methods: The CDM database used in this study was constructed by the Anam Hospital of Korea University. Analysis and evaluation were performed using the ARX anonymizing framework in combination with the k-anonymity, l-diversity, and t-closeness privacy models. Results: The CDM database, which was constructed according to the rules established by Observational Health Data Sciences and Informatics, exhibited a low risk of re-identification: The highest re-identifiable record rate (11.3%) in the dataset was exhibited by the DRUG_EXPOSURE table, with a re-identification success rate of 0.03%. However, because all tables include at least one “highest risk” value of 100%, suitable anonymizing techniques are required; moreover, the CDM database preserves the “source values” (raw data), a combination of which could increase the risk of re-identification. Therefore, this study proposes an enhanced strategy to de-identify the source values to significantly reduce not only the highest risk in the k-anonymity, l-diversity, and t-closeness privacy models but also the overall possibility of re-identification. Conclusions: Our proposed de-identification strategy effectively enhanced the privacy of the CDM database, thereby encouraging clinical research involving multiple centers.

Talin is a focal adhesion protein that activates integrins and recruits other focal adhesion proteins. Talin regulates the interactions between integrins and the extracellular matrix, which are critical for endothelial cells during angiogenesis. In this study, we successfully synthesized a novel talin modulator, N-((2-(1H-indol-3-yl)ethyl)carbamoyl)-2-(benzo[d][1,3]dioxol-5-yloxy)acetamide, referred to as KCH-1521. KCH-1521 was determined to bind talin and modulate downstream signaling molecules of talin. After 24 h of treatment, KCH-1521 changed the cell morphology of human umbilical vein endothelial cells (HUVECs) and reduced focal adhesion protein expression including vinculin and paxillin. Talin downstream signaling is regulated via focal adhesion kinase (FAK), kinase B (AKT), and extracellular signal-regulated kinase (ERK) pathways, however, treatment with KCH-1521 decreased phosphorylation of FAK, AKT, and ERK, leading to reduction of cell proliferation, survival, and angiogenesis. Interestingly, the expression of various angiogenic genes was significantly decreased after treatment with KCH-1521. Also, in vitro tube forming assay revealed that KCH-1521 reduced angiogenic networks in a time-dependent manner. To investigate the reversibility of its effects, KCH-1521 was removed after treatment. HUVECs recovered their morphology through rearrangement of the cytoskeleton and the expression of angiogenic genes was also recovered. By further optimization and in vivo studies of KCH-1521, a novel drug of talin modulation could be used to achieve therapeutic anti-angiogenesis for vascular diseases and cancers.

Purpose: The purpose of this study is to construct a synthetic dataset of ECG signal that overcomes the sensitivity of personal information and the complexity of disclosure policies.Methods: The public dataset was constructed by generating synthetic data based on the deep learning model using a convolution neural network (CNN) and bi-directional long short-term memory (Bi-LSTM), and the effectiveness of the dataset was verified by developing classification models for ECG diagnoses.Results: The synthetic 12-lead ECG dataset generated consists of a total of 6000 ECGs, with normal and 5 abnormal groups. The synthetic ECG signal has a waveform pattern similar to the original ECG signal, the average RMSE between the two signals is 0.042 µV, and the average cosine similarity is 0.993. In addition, five classification models were developed to verify the effect of the synthetic dataset and showed performance similar to that of the model made with the actual dataset. In particular, even when the real dataset was applied as a test set to the classification model trained with the synthetic dataset, the classification performance of all models showed high accuracy (average accuracy 93.41%).Conclusion: The synthetic 12-lead ECG dataset was confirmed to perform similarly to the real-world 12-lead ECG in the classification model. This implies that a synthetic dataset can perform similarly to a real dataset in clinical research using AI. The synthetic dataset generation process in this study provides a way to overcome the medical data disclosure challenges constrained by privacy rights, a way to encourage open data policies, and contribute significantly to promoting cardiovascular disease research.