Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC)
Thanks to wearable devices joint with AI algorithms, it is possible to record and analyse physiological parameters such as heart rate variability (HRV) in ambulatory environments. The main downside to such setups is the bad quality of recorded data due to movement, noises, and data losses. These err...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/5/1984 |
| _version_ | 1797473696170901504 |
|---|---|
| author | Mouna Benchekroun Baptiste Chevallier Dan Istrate Vincent Zalc Dominique Lenne |
| author_facet | Mouna Benchekroun Baptiste Chevallier Dan Istrate Vincent Zalc Dominique Lenne |
| author_sort | Mouna Benchekroun |
| collection | DOAJ |
| description | Thanks to wearable devices joint with AI algorithms, it is possible to record and analyse physiological parameters such as heart rate variability (HRV) in ambulatory environments. The main downside to such setups is the bad quality of recorded data due to movement, noises, and data losses. These errors may considerably alter HRV analysis and should therefore be addressed beforehand, especially if used for medical diagnosis. One widely used method to handle such problems is interpolation, but this approach does not preserve the time dependence of the signal. In this study, we propose a new method for HRV processing including filtering and iterative data imputation using a Gaussian distribution. The particularity of the method is that many physiological aspects are taken into consideration, such as HRV distribution, RR variability, and normal boundaries, as well as time series characteristics. We study the effect of this method on classification using a random forest classifier (RF) and compare it to other data imputation methods including linear, shape-preserving piecewise cubic Hermite (pchip), and spline interpolation in a case study on stress. Features from reconstructed HRV signals of 67 healthy subjects using all four methods were analysed and separately classified by a random forest algorithm to detect stress against relaxation. The proposed method reached a stable F1 score of 61% even with a high percentage of missing data, whereas other interpolation methods reached approximately 54% F1 score for a low percentage of missing data, and the performance drops to about 44% when the percentage is increased. This suggests that our method gives better results for stress classification, especially on signals with a high percentage of missing data. |
| first_indexed | 2024-03-09T20:20:07Z |
| format | Article |
| id | doaj.art-1aec3b0c5367490fa4c6cd4591c68d9a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T20:20:07Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1aec3b0c5367490fa4c6cd4591c68d9a2023-11-23T23:49:19ZengMDPI AGSensors1424-82202022-03-01225198410.3390/s22051984Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC)Mouna Benchekroun0Baptiste Chevallier1Dan Istrate2Vincent Zalc3Dominique Lenne4Biomechanics and Bioengineering Lab, University of Technology of Compiègne (UMR CNRS 7338), 60200 Compiègne, FranceBiomechanics and Bioengineering Lab, University of Technology of Compiègne (UMR CNRS 7338), 60200 Compiègne, FranceBiomechanics and Bioengineering Lab, University of Technology of Compiègne (UMR CNRS 7338), 60200 Compiègne, FranceBiomechanics and Bioengineering Lab, University of Technology of Compiègne (UMR CNRS 7338), 60200 Compiègne, FranceHeudiasyc Lab (Heuristics and Diagnosis of Complex Systems), University of Technology of Compiègne (UMR CNRS 7338), 60200 Compiègne, FranceThanks to wearable devices joint with AI algorithms, it is possible to record and analyse physiological parameters such as heart rate variability (HRV) in ambulatory environments. The main downside to such setups is the bad quality of recorded data due to movement, noises, and data losses. These errors may considerably alter HRV analysis and should therefore be addressed beforehand, especially if used for medical diagnosis. One widely used method to handle such problems is interpolation, but this approach does not preserve the time dependence of the signal. In this study, we propose a new method for HRV processing including filtering and iterative data imputation using a Gaussian distribution. The particularity of the method is that many physiological aspects are taken into consideration, such as HRV distribution, RR variability, and normal boundaries, as well as time series characteristics. We study the effect of this method on classification using a random forest classifier (RF) and compare it to other data imputation methods including linear, shape-preserving piecewise cubic Hermite (pchip), and spline interpolation in a case study on stress. Features from reconstructed HRV signals of 67 healthy subjects using all four methods were analysed and separately classified by a random forest algorithm to detect stress against relaxation. The proposed method reached a stable F1 score of 61% even with a high percentage of missing data, whereas other interpolation methods reached approximately 54% F1 score for a low percentage of missing data, and the performance drops to about 44% when the percentage is increased. This suggests that our method gives better results for stress classification, especially on signals with a high percentage of missing data.https://www.mdpi.com/1424-8220/22/5/1984heart rate variability (HRV)stress monitoringe-healthwearablesbiosensorsambulatory |
| spellingShingle | Mouna Benchekroun Baptiste Chevallier Dan Istrate Vincent Zalc Dominique Lenne Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC) Sensors heart rate variability (HRV) stress monitoring e-health wearables biosensors ambulatory |
| title | Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC) |
| title_full | Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC) |
| title_fullStr | Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC) |
| title_full_unstemmed | Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC) |
| title_short | Preprocessing Methods for Ambulatory HRV Analysis Based on HRV Distribution, Variability and Characteristics (DVC) |
| title_sort | preprocessing methods for ambulatory hrv analysis based on hrv distribution variability and characteristics dvc |
| topic | heart rate variability (HRV) stress monitoring e-health wearables biosensors ambulatory |
| url | https://www.mdpi.com/1424-8220/22/5/1984 |
| work_keys_str_mv | AT mounabenchekroun preprocessingmethodsforambulatoryhrvanalysisbasedonhrvdistributionvariabilityandcharacteristicsdvc AT baptistechevallier preprocessingmethodsforambulatoryhrvanalysisbasedonhrvdistributionvariabilityandcharacteristicsdvc AT danistrate preprocessingmethodsforambulatoryhrvanalysisbasedonhrvdistributionvariabilityandcharacteristicsdvc AT vincentzalc preprocessingmethodsforambulatoryhrvanalysisbasedonhrvdistributionvariabilityandcharacteristicsdvc AT dominiquelenne preprocessingmethodsforambulatoryhrvanalysisbasedonhrvdistributionvariabilityandcharacteristicsdvc |