The healthcare industry is currently working on a way to move health data from consumer wearable devices into official medical practice.

醫療產業目前正致力於研究如何將消費者穿戴式裝置的健康數據整合到正式的醫療實踐中。

The rise of wearable technology has led to a huge increase in health data created by patients. However, there is a gap between the constant stream of data from these devices and the occasional nature of traditional doctor visits. This problem is made worse by technical difficulties, as the private data clouds used by companies often cannot communicate with Electronic Health Records (EHRs). Furthermore, the lack of standard data formats and the need for doctors to use many different login systems make it difficult to organize patient information efficiently.

穿戴式科技的興起，導致患者產生的健康數據大幅增加。然而，這些裝置提供的持續數據流與傳統就醫的偶發性之間存在落差。由於公司使用的私有數據雲端通常無法與電子健康紀錄 (EHR) 通訊，技術困難使問題更加嚴重。此外，缺乏標準化的數據格式，加上醫生需要使用多套不同的登入系統，使得高效整理患者資訊變得困難。

From a medical point of view, this data is often less useful because the formulas used to calculate metrics like 'strain' or 'recovery' are not transparent. Consequently, doctors face a difficult choice: they may upset patients by ignoring their data, or they may make mistakes by relying on unproven metrics. While the FDA has approved some specific features for medical use, there is still not enough evidence for most functions. To solve these problems, companies are buying other firms—such as Samsung's purchase of Xealth—to improve EHR integration, while academic projects like JupyterHealth are creating open-source systems to handle this data.

從醫療角度來看，這些數據通常較不有用，因為用於計算「壓力」或「恢復」等指標的公式並不透明。因此，醫生面臨一個困難的選擇：他們可能會因為忽略數據而讓患者不滿，或者可能因為依賴未經證實的指標而犯錯。雖然 FDA 已批准部分特定功能可用於醫療用途，但大多數功能仍缺乏足夠證據。為了 l解決這些問題，企業正透過收購其他公司（例如三星收購 Xealth）來改善 EHR 整合，而像 JupyterHealth 這樣的學術項目則在開發開源系統以處理這些數據。

Healthcare professionals are generally optimistic but cautious. Some doctors admit that wearables can save lives by detecting irregular heartbeats, yet they emphasize that the 'flood' of information needs better filtering. Experts suggest that Large Language Models (LLMs) could be used to summarize this data, provided that privacy laws and regulations are updated to cover consumer devices.

醫療專業人士普遍持樂觀但謹慎的態度。部分醫生承認穿戴式裝置能透過偵測心律不整來挽救生命，但他們強調，資訊的「氾濫」需要更好的過濾機制。專家建議，只要更新隱私法律與法規以涵蓋消費者裝置，即可利用大語言模型 (LLM) 來總結這些數據。

Although technical and legal barriers still exist, the effort to include wearable data in medical workflows continues through corporate partnerships and academic development.

雖然技術與法律障礙依然存在，但透過企業合作與學術開發，將穿戴式數據納入醫療工作流程的努力仍在持續。