基于睡眠传感器的心率变异性三角指数数据

以智能床用户心率变异性三角指数数据为基础，可以应用于多个领域和场景：1)个人健康管理：通过智能床采集到的心率变异性三角指数数据，可量化评估自主神经系统的调节能力，为用户提供精准健康管理支持，帮助改善睡眠质量。2)医疗研究和诊断：心率变异性三角指数数据可以用于医疗研究和诊断，心率变异性三角指数数据为慢性病研究和临床诊断提供关键指标。医学上通过分析大量用户的心率变异性三角指数数据，研究显示，糖尿病患者HRVI<18时，3年内神经病变风险增加2.3倍。临床中，医生可通过对比患者用药前后HRVI变化（如服用β受体阻滞剂后HRVI提升5-8点）量化治疗效果，或评估心脏术后患者康复进度。智能床的传感器，收集夜间用户的睡眠原始信号数据。这些信号数据经过异常值处理并计算后，得到若干个RR间期的数据集。输入连续RR间期序列（单位：毫秒），剔除异常值（<300ms或>1200ms）及相邻差值超过均值20%的突变值，缺失数据采用线性插值填补。按非重叠的5分钟窗口分割数据，每个窗口包含若干个有效的RR间期。首先，以固定bin宽度（bin 宽度常用值：7.8125 ms）生成RR间期的概率密度分布图，每个bin统计其中落入的RR值数量，从而构建频数分布直方图。其次，统计总有效数（N），即所有落入有效bin中的RR数目以及最高频区间计数（C_max），即直方图的最大柱高。最后，按公式HRVI = N / C_max计算结果，N越大表示采样充分，C_max越大表示集中度高，输出心率变异性三角指数数值（HRVI）。HRVI越高，表明心率分布越分散、变异性越强；HRVI越低，表示心律集中、波动性差。

Based on the triangular index of heart rate variability (HRVI) data from smart bed users, this dataset can be applied to multiple fields and scenarios:
1) Personal Health Management: The HRVI data collected by smart beds can quantitatively evaluate the regulatory ability of the autonomic nervous system, provide precise health management support for users, and help improve sleep quality.
2) Medical Research and Diagnosis: HRVI data can be used for medical research and diagnosis, serving as a key indicator for chronic disease research and clinical diagnosis. Through analysis of HRVI data from a large number of users, medical studies have shown that when the HRVI of diabetic patients is less than 18, the risk of neuropathy within 3 years increases by 2.3 times. In clinical practice, doctors can quantify treatment effects by comparing changes in patients' HRVI before and after medication (e.g., a 5-8 point increase in HRVI after taking beta-blockers), or evaluate the rehabilitation progress of post-cardiac surgery patients.
The sensors of smart beds collect the original sleep signal data of users at night. After outlier processing and calculation, these signal data are converted into a dataset of multiple RR intervals. First, input the continuous RR interval sequence (unit: millisecond), eliminate outliers (less than 300ms or greater than 1200ms) and abrupt values where the difference between adjacent RR intervals exceeds 20% of the mean, and fill missing data with linear interpolation. Next, split the data into non-overlapping 5-minute windows, each containing several valid RR intervals. First, generate a probability density distribution map of RR intervals with a fixed bin width (common bin width value: 7.8125 ms), count the number of RR values falling into each bin to construct a frequency distribution histogram. Second, calculate the total valid number (N), which is the total number of RR values falling into valid bins, and the maximum frequency bin count (C_max), which is the height of the tallest bar in the histogram. Finally, compute the result using the formula HRVI = N / C_max: a larger N indicates sufficient sampling, while a larger C_max indicates higher concentration. The final output is the triangular index of heart rate variability (HRVI). A higher HRVI indicates a more dispersed heart rate distribution and stronger variability; a lower HRVI indicates concentrated heart rhythm and poor variability.

搜集汇总

背景与挑战

背景概述

该数据集包含基于睡眠传感器采集的心率变异性三角指数（HRVI）数据，规模为1001条，每日更新，用于评估自主神经系统功能和睡眠质量。数据应用于个人健康管理和医疗研究场景，如糖尿病风险预测和临床治疗效果量化，通过算法处理RR间期序列计算HRVI指标。