Automatic detection algorithm for establishing standard to identify \u201csurge blood pressure\u201d

Ayako Kokubo,Toshikazu Shiga,Hiroshi Nakajima,Shingo Yamashita,Naoko Tomitani,Mitsuo Kuwabara,Kazuomi Kario

doi:10.1007/s11517-020-02162-4

Ayako Kokubo, Toshikazu Shiga + Show 5 more

Open Access

https://doi.org/10.1007/s11517-020-02162-4

Copy DOI

Abstract

Blood pressure (BP) variability is one of the important risk factors of cardiovascular disease (CVD). “Surge BP,” which represents short-term BP variability, is defined as pathological exaggerated BP increase capable of triggering cardiovascular events. Surge BP is effectively evaluated by our new BP monitoring device. To the best of our knowledge, we are the first to develop an algorithm for the automatic detection of surge BP from continuous “beat-by-beat” (BbB) BP measurements. It enables clinicians to save significant time identifying surge BP in big data from their patients’ continuous BbB BP measurements. A total of 94 subjects (74 males and 20 females) participated in our study to develop the surge BP detection algorithm, resulting in a total of 3272 surges collected from the study subjects. The surge BP detection algorithm is a simple classification model based on supervised learning which formulates shape of surge BP as detection rules. Surge BP identified with our algorithm was evaluated against surge BP manually labeled by experts with 5-fold cross validation. The recall and precision of the algorithm were 0.90 and 0.64, respectively. Processing time on each subject was 11.0 ± 4.7 s. Our algorithm is adequate for use in clinical practice and will be helpful in efforts to better understand this unique aspect of the onset of CVD.Graphical abstractSurge blood pressure (surge BP) which is defined as pathological short-term (several tens of seconds) exaggerated BP increase capable of triggering cardiovascular events. We have already developed a wearable continuous beat-by-beat (bBb) BP monitoring device and observed surge BPs successfully in obstructive sleep apnea patients. In this, we developed an algorithm for the automatic detection of surge BP from continuous BbB BP measurements to save significant time identifying surge BP among > 30,000 BbB BP measurements. Our result shows this algorithm can correctly detect surge BPs with a recall of over 0.9.

Highlights

Management of 24 h blood pressure (BP) is important for preventing the progress of hypertensive target organ damage and onset of cardiovascular disease (CVD) such as stroke or heart disease [1, 2]
We developed the algorithm by using the BbB BP data obtained from these 94 study subjects as described in Fig. 3 and below, in the “Collection of surge BP labeled by CV experts” and “Development of the algorithm” sections
Number of surge BPs detected or not by the algorithm, namely 2950 cases were successfully detected by the algorithm, 322 cases were not detected by the algorithm, and 1698 cases were overdetection cases

Summary

Introduction

Management of 24 h blood pressure (BP) is important for preventing the progress of hypertensive target organ damage and onset of cardiovascular disease (CVD) such as stroke or heart disease [1, 2]. To resolve the unmet need to detect cases of surge BP during sleep apnea episodes in OSA patients, we developed hypoxia-trigger nocturnal HBPM and have studied the clinical implication and management of surge BPs in OSA patients [1, 2, 11,12,13,14,15,16,17]. As this HBPM is based on the oscillometric method, the peak of surge BP might be underestimated. We found that the peak of surge BP detected by our BbB BP monitoring device was higher than that detected by hypoxia-trigger BP monitoring [2, 11]

Methods

Results

Discussion

Conclusion