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.

BACKGROUND: We previously reported the use of minimal stent area to predict angiographic in-stent restenosis after drug-eluting stent implantation for unprotected left main (LM) disease. We aimed to evaluate the optimal minimal stent area criteria for up-front LM 2-stenting based on long-term clinical outcomes. METHODS: We identified 292 consecutive patients with LM bifurcation stenosis who were treated using the crush technique. The final minimal stent area was measured in the ostial left anterior descending artery (LAD), ostial left circumflex artery (LCX), and distal LM. The primary outcome was 5-year major adverse cardiac events, including all-cause death, myocardial infarction, and target lesion revascularization. RESULTS: The minimal stent area cutoff values that best predicted the 5-year major adverse cardiac events were 11.8 mm ² for distal LM (area under the curve, 0.57; P =0.15), 8.3 mm ² for LAD ostium (area under the curve, 0.62; P =0.02), and 5.7 mm ² for LCX ostium (area under the curve, 0.64; P =0.01). Using these criteria, the risk of 5-year major adverse cardiac events was significantly associated with stent underexpansion in the LAD ostium (hazard ratio, 3.14; [95% CI, 1.23–8.06]; P =0.02) and LCX ostium (hazard ratio, 2.60 [95% CI, 1.11–6.07]; P =0.03) but not in the distal LM (hazard ratio, 0.81 [95% CI, 0.34–1.91]; P =0.63). Patients with stent underexpansion in both ostial LAD and LCX had a significantly higher rate of 5-year major adverse cardiac events than those with no or 1 underexpanded stent of either ostium ( P <0.01). CONCLUSIONS: Stent underexpansion in the LAD and LCX ostium was significantly associated with long-term outcomes in patients who underwent up-front 2-stenting for LM bifurcation stenosis.

The generation of mature and vascularized human pluripotent stem cell-derived cardiac organoids (hPSC-COs) is necessary to ensure the validity of drug screening and disease modeling. This study investigates the effects of cellular aggregate (CA) stemness and self-organization on the generation of mature and vascularized hPSC-COs and elucidates the mechanisms underlying cardiac organoid (CO) maturation and vascularization. COs derived from 2-day-old CAs with high stemness (H-COs) and COs derived from 5-day-old CAs with low stemness (L-COs) were generated in a self-organized microenvironment via Wnt signaling induction. This study finds that H-COs exhibit ventricular, structural, metabolic, and functional cardiomyocyte maturation and vessel networks consisting of endothelial cells, smooth muscle cells, pericytes, and basement membranes compared to L-COs. Transcriptional profiling shows the upregulation of genes associated with cardiac maturation and vessel formation in H-COs compared with the genes in L-COs. Through experiments with LIMK inhibitors, the activation of ROCK-LIMK-pCofilin via ECM–integrin interactions leads to cardiomyocyte maturation and vessel formation in H-COs. Furthermore, the LIMK/Cofilin signaling pathway induces TGFβ/NODAL and PDGF pathway activation for the maturation and vascularization of H-COs. The study demonstrates for the first time that LIMK/Cofilin axis activation plays an important role in the generation of mature and vascularized COs.

In recent years, a wealth of clinical data has emerged regarding intravascular imaging involving either intravascular ultrasound or optical coherence tomography. This surge in data has propelled the adoption of intravascular imaging–guided percutaneous coronary intervention (PCI) in daily clinical practice. The findings of current randomized clinical trials regarding imaging guidance have lent strong support to the benefits of intravascular imaging–guided PCI. This holds especially true for the diagnosis and treatment of complex lesions, such as left main disease, diffuse long lesions, chronic total occlusion, severely calcified lesions, bifurcations, and in-stent restenosis, as well as in high-risk patients such as those with acute myocardial infarction or chronic kidney disease. During intravascular imaging–guided PCI, operators attempt to achieve stent optimization for maximized benefits of imaging guidance. This paper provides a comprehensive review on the updated clinical data of intravascular imaging–guided PCI and intravascular ultrasound/optical coherence tomography–derived stent optimization criteria.

Korean Circulation Journal 대한심장학회지 순환기 Yoon YH, et al. Korean Circ J. 2021 Nov;52:e5. https://doi.org/10.4070/kcj.2021.0240

Introduction Clinical trial evidence supports early low-density lipoprotein cholesterol (LDL-C) goal achievement in patients with atherosclerotic cardiovascular disease (ASCVD), but real-world evidence in Asia is lacking. We investigated the effects of early LDL-C goal achievement on recurrent major cardiovascular events (MACEs) among patients with very-high-risk ASCVD in South Korea. Methods We included adult patients hospitalized with ASCVD (acute coronary syndrome [ACS], stable angina, ischemic stroke, transient ischemic attack, peripheral arterial disease, or asymptomatic coronary artery disease) at a major Korean tertiary hospital from 2000 to 2020. Patients were categorized into early or non-early target LDL-C groups based on LDL-C measured 4–12 weeks post-discharge (< 55 vs. ≥ 55 mg/dl). The primary outcome was recurrent MACEs, including myocardial infarction, ischemic stroke, all-cause mortality, hospitalization for unstable angina, and coronary revascularization. The secondary outcome was health resource use (frequency/length of stay [LOS]). Results During follow-up (mean: 5 years), the early target LDL-C group (n = 5702) had a lower risk of recurrent MACEs compared with the non-early target LDL-C group (n = 11,232; adjusted hazard ratio [95% CI]: 0.89 [0.82–0.96]). The effect was most pronounced in patients with ACS (0.73 [0.63–0.85]), particularly for recurrent MACEs within 6 months (0.61 [0.44–0.87]). The early target LDL-C group had 19% lower frequency and 31% shorter LOS for cardiovascular-related hospitalizations than the non-early group. Conclusions Early LDL-C goal achievement was associated with lower recurrent MACEs in patients with very-high-risk ASCVD in South Korea, especially in patients with ACS. These findings underscore the importance of early LDL-C management in improving cardiovascular outcomes.