Comparing DeepSeek and GPT-4o in ECG interpretation: Is AI improving over time?

<h3 dir="ltr">Background</h3><p dir="ltr">DeepSeek is a recently launched large language model (LLM), whereas GPT-4o is an advanced ChatGPT version whose electrocardiography (ECG) interpretation capabilities have been previously studied. However, DeepSeek’s perf...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Serkan GÜNAY (23072548) (author)
مؤلفون آخرون: Ahmet ÖZTÜRK (23072551) (author), Anılcan Tahsin KARAHAN (23072554) (author), Mert BARINDIK (23072557) (author), Seval KOMUT (23072560) (author), Yavuz YİĞİT (23072563) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص:<h3 dir="ltr">Background</h3><p dir="ltr">DeepSeek is a recently launched large language model (LLM), whereas GPT-4o is an advanced ChatGPT version whose electrocardiography (ECG) interpretation capabilities have been previously studied. However, DeepSeek’s performance in this domain remains unexplored. </p><h3 dir="ltr">Objectives</h3><p dir="ltr">This study aims to evaluate DeepSeek’s accuracy in ECG interpretation and compare it with GPT-4o, emergency medicine specialists, and cardiologists. A secondary aim is to assess any performance changes in GPT-4o over one year. </p><h3 dir="ltr">Methods</h3><p dir="ltr">Between February 9 and March 1, 2025, 40 ECG images (20 daily routine, 20 more challenging) from the book 150 ECG Cases were evaluated by both GPT-4o and DeepSeek, each model tested 13 times. The accuracy of their responses was compared with previously collected answers from 12 cardiologists and 12 emergency medicine specialists. GPT-4o’s 2025 performance was compared to its 2024 results on identical ECGs. </p><h3 dir="ltr">Results</h3><p dir="ltr">GPT-4o outperformed DeepSeek with higher median correct answers on daily routine (14 vs. 12), more challenging (13 vs. 10), and total ECGs (27 vs. 22) with statistically significant differences (p=0.048, p<0.001, p<0.001). A moderate agreement was observed between the responses provided by GPT-4o (p<0.001, Fleiss Kappa=0.473), while a substantial agreement was observed in the responses provided by DeepSeek (p<0.001, Fleiss Kappa=0.712). No significant year-over-year improvement was observed in GPT-4o’s performance. </p><h3 dir="ltr">Conclusion</h3><p dir="ltr">This first evaluation of DeepSeek in ECG interpretation reveals its performance is lower than that of GPT-4o and human experts. While GPT-4o demonstrates greater accuracy, both models fall short of expert-level performance, underscoring the need for caution and further validation before clinical integration.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: Heart & Lung<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.hrtlng.2025.08.007" target="_blank">https://dx.doi.org/10.1016/j.hrtlng.2025.08.007</a></p>