Vision–language models can be trained to read cardiac ultrasound images with implications for improving clinical workflows, but additional development and validation will be required before such models can replace humans.

中文翻译：

---

使视觉-语言人工智能模型适应心脏病学任务

可以训练视觉语言模型来读取心脏超声图像，这对改善临床工作流程具有重要意义，但在此类模型能够取代人类之前，还需要进行额外的开发和验证。