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.

Korean Circulation Journal 대한심장학회지 순환기 Cha JJ, et al. Korean Circ J. 2022 Feb;52:e30. https://doi.org/10.4070/kcj.2021.0342

The ex-vivo discrimination between human normal and cancer renal tissues was confirmed using μEoN (micro electrical impedance spectroscopy-on-a-needle) by measuring and comparing the electrical impedances in the frequency domain. To quantify the extent of discrimination between dissimilar tissues and to determine the optimal frequency at which the discrimination capability is at a maximum, discrimination index (DI) was employed for both magnitude and phase. The highest values of DI for the magnitude and phase were 5.15 at 1 MHz and 3.57 at 1 kHz, respectively. The mean magnitude and phase measured at the optimal frequency for normal tissues were 5013.40 ± 94.39 Ω and −68.54 ± 0.72°, respectively; those for cancer tissues were 4165.19 ± 70.32 Ω and −64.10 ± 0.52°, respectively. A statistically significant difference (p< 0.05) between the two tissues was observed at all the investigated frequencies. To extract the electrical properties (resistance and capacitance) of these bio-tissues through curve fitting with experimental results, an equivalent circuit was proposed based on the μEoN structure on the condition that the μEoN was immersed in the bio-tissues. The average and standard deviation of the extracted resistance and capacitance for the normal tissues were 6.22 ± 0.24 kΩ and 280.21 ± 32.25 pF, respectively, and those for the cancer tissues were 5.45 ± 0.22 kΩ and 376.32 ± 34.14 pF, respectively. The electrical impedance was higher in the normal tissues compared with the cancer tissues. The μEoN could clearly discriminate between normal and cancer tissues by comparing the results at the optimal frequency (magnitude and phase) and those of the curve fitting (extracted resistance and capacitance).

Korean Circulation Journal 대한심장학회지 순환기 Cha JJ, et al. Korean Circ J. 2022 Feb;52(2):123-133. https://doi.org/10.4070/kcj.2021.0246