State-of-the-Art of Stress Prediction from Heart Rate Variability Using Artificial Intelligence

Yeaminul Haque, Rahat Shahriar Zawad, Chowdhury Saleh Ahmed Rony, Hasan Al Banna, Tapotosh Ghosh, M. Shamim Kaiser, Mufti Mahmud*

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

22 Scopus citations

Abstract

Recent advancements in the manufacturing and commercialisation of miniaturised sensors and low-cost wearables have enabled an effortless monitoring of lifestyle by detecting and analysing physiological signals. Heart rate variability (HRV) denotes the time interval between consecutive heartbeats.The HRV signal, as detected by the sensors and devices, has been popularly used as an indicative measure to estimate the level of stress, depression, and anxiety. For years, artificial intelligence (AI)-based learning systems have been known for their predictive capabilities, and in recent years, AI models with deep learning (DL) architectures have been successfully applied to achieve unprecedented accuracy. In order to determine effective methodologies applied to the collection, processing, and prediction of stress from HRV data, this work presents an in depth analysis of 43 studies reporting the application of various AI algorithms. The methods are summarised in tables and thoroughly evaluated to ensure the completeness of their findings and reported results. To make the work comprehensive, a detailed review has been conducted on sensing technologies, pre-processing methods applied on multi-modal data, and employed prediction models. This is followed by a critical examination of how various Machine Learning (ML) models, have been utilised in predicting stress from HRV data. In addition, the reported reseults from the selected studies have been carefully analysed to identify features that enable the models to perform better. Finally, the challenges of using HRV to predict stress are listed, along with some possible mitigation strategies. This work aims to highlight the impact of AI-based stress prediction methodologies from HRV data, and is expected to aid the development of more meticulous techniques.

Original languageEnglish
Pages (from-to)455-481
Number of pages27
JournalCognitive Computation
Volume16
Issue number2
DOIs
StatePublished - Mar 2024
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2023, The Author(s).

Keywords

  • Deep Learning
  • HRV
  • Machine Learning
  • Multi-modal data
  • Physiological sensors
  • Stress prediction

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'State-of-the-Art of Stress Prediction from Heart Rate Variability Using Artificial Intelligence'. Together they form a unique fingerprint.

Cite this