Mahajan Arjun, Powell Dylan
Harvard Medical School, Boston, MA, USA.
Faculty of Health Sciences & Sport, University of Stirling, Stirling, UK.
NPJ Digit Med. 2025 Jan 15;8(1):31. doi: 10.1038/s41746-024-01374-4.
Enabled by the rapid rise in data collected by technologies, Digital Biomarkers (DBx) have emerged as a novel mechanism for assessment, diagnosis, and monitoring. However, the exponential growth and ability to generate new data has also raised questions about ways of ensuring the authenticity and accuracy of digital data. A recent study highlights how Large Language Models (LLMs) generating human-like content amplify these risks, and propose watermarking as a scalable solution to ensure data integrity. This article examines the potential of digital watermarking to help safeguard the reliability and provenance of DBx data, whilst also addressing broader challenges in health systems.
随着技术收集的数据迅速增加，数字生物标志物（DBx）已成为一种用于评估、诊断和监测的新机制。然而，数据的指数级增长以及生成新数据的能力也引发了有关确保数字数据真实性和准确性方法的问题。最近的一项研究强调了生成类人文本的大语言模型（LLM）如何放大这些风险，并提出水印作为确保数据完整性的可扩展解决方案。本文探讨了数字水印在帮助保障DBx数据的可靠性和来源方面的潜力，同时也应对卫生系统中更广泛的挑战。
