跳到正文
原文
Nature 健康护理主题·· 24 天前AI 评分36

基于边缘AI与IoT技术的生命体征分析及生理参数相关性研究

Vital sign analysis and correlation of physiological parameters using edge AI and IoT technology

AI 导读

研究团队设计了一种基于边缘AI与IoT的医疗设备,用于测量心率、体温、SpO2和血压并进行临床风险分层。在MIMIC-IV-ED v2.2和真实临床数据集上,量化梯度提升模型准确率达99.84%、精确率99.40%、假阳性率0.06%。INT8量化模型部署于ARM Cortex-A72处理器,延迟为0.596 ms。

正文

Scientific Reports (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

Individuals encounter discomfort in their lifestyle with vital signs and problems that lie in their ability to identify and respond to life-saving situations with advanced health care technologies. Vital signs are essential parameters that provide an early warning of a diagnosis before further deterioration in health. Progress in health care technologies, such as automated health monitoring systems and telehealth systems, which can detect, collect real-time data, and diagnose remotely. The present article aims to measure vital signs such as heart rate (HR), temperature (T), oxygen saturation (SpO2), and blood pressure (BP) using a designed medical device by implementing a quantized Gradient Boosting (GB) model deployed on the ARM Cortex-A72 processor for automated clinical risk stratification. The proposed system was evaluated on two benchmark datasets: The Medical Information Mart for Intensive Care for Emergency Department (MIMIC-IV-ED v2.2) dataset and a real-world clinical dataset. The accuracy of measured parameters was evaluated using parametric statistical analysis of baseline metrics and Gaussian distribution fitting of the recorded data from MIMIC-IV-ED. The (GB) algorithm achieved an accuracy of 99.84%, precision of 99.40%, and attained a lower false positive rate (FPR) of 0.06%. The quantized edge AI (INT8) model, when deployed on the processor, attained a latency of 0.596 ms. Hence, the designed system provides an efficient, low-latency solution for real-time vital sign monitoring and clinical risk-based classification.

Acknowledgements

The authors extended sincere thanks to Great Eastern Medical School and Hospital for recording data of vital signs

Funding

This research received no specific grant from any funding agency, commercial organization, or not-for-profit sector. No funding is provided for the research work performed.

Author information

Authors and Affiliations

  1. Department of Physics, GITAM University, Visakhapatnam, India

    P. Manikanta, Ch. Ravi Shankar Kumar & Manikumar Chimpineni

Authors

  1. P. Manikanta
  2. Ch. Ravi Shankar Kumar
  3. Manikumar Chimpineni

Corresponding authors

Correspondence to Ch. Ravi Shankar Kumar or Manikumar Chimpineni.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval

This study was reviewed and approved by the Ethics Committee of Great Eastern Medical School and Hospital under reference number [197/IEC/GEMS&H/2024]. All participants voluntarily participated in the sample collection with full awareness and informed consent. This study confirms that all experiments were performed in accordance with relevant guidelines and regulations.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Manikanta, P., Kumar, C.R.S. & Chimpineni, M. Vital sign analysis and correlation of physiological parameters using edge AI and IoT technology. Sci Rep (2026). https://doi.org/10.1038/s41598-026-77362-3

Download citation

  • Received: 07 May 2026

  • Accepted: 19 October 2026

  • Published: 27 October 2026

  • DOI: https://doi.org/10.1038/s41598-026-77362-3

Keywords

来源:Nature 健康护理主题 · nature.com