Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications
<italic>Goal:</italic> To establish Pulse2AI as a reproducible data preprocessing framework for pulsatile signals that generate high-quality machine-learning-ready datasets from raw wearable recordings. <italic>Methods:</italic> We proposed an end-to-end data preprocessing fr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10522883/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582315925045248 |
|---|---|
| author | Sicong Huang Roozbeh Jafari Bobak J. Mortazavi |
| author_facet | Sicong Huang Roozbeh Jafari Bobak J. Mortazavi |
| author_sort | Sicong Huang |
| collection | DOAJ |
| description | <italic>Goal:</italic> To establish Pulse2AI as a reproducible data preprocessing framework for pulsatile signals that generate high-quality machine-learning-ready datasets from raw wearable recordings. <italic>Methods:</italic> We proposed an end-to-end data preprocessing framework that adapts multiple pulsatile signal modalities and generates machine-learning-ready datasets agnostic to downstream medical tasks. <italic>Results:</italic> a dataset preprocessed by Pulse2AI improved systolic blood pressure estimation by 29.58%, from 11.41 to 8.03 mmHg in root-mean-square-error (RMSE) and its diastolic counterpart by 26.01%, from 7.93 to 5.87 mmHg in RMSE. For respiration rate (RR) estimation, Pulse2AI boosted performance by 19.69%, from 1.47 to 1.18 breaths per minute (BrPM) in mean-absolute-error (MAE). <italic>Conclusion:</italic> Pulse2AI turns pulsatile signals into machine learning (ML) ready datasets for arbitrary remote health monitoring tasks. We tested Pulse2AI on multiple pulsatile modalities and demonstrated its efficacy in two medical applications. This work bridges valuable assets in remote sensing and internet of medical things to ML-ready datasets for medical modeling. |
| format | Article |
| id | doaj-art-83ae2e3e5af44f9fa8560b1b7ad09656 |
| institution | Kabale University |
| issn | 2644-1276 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-83ae2e3e5af44f9fa8560b1b7ad096562025-01-30T00:03:33ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762024-01-01533033810.1109/OJEMB.2024.339844410522883Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical ApplicationsSicong Huang0https://orcid.org/0009-0009-3596-5244Roozbeh Jafari1https://orcid.org/0000-0002-6358-0458Bobak J. Mortazavi2https://orcid.org/0000-0002-2655-2095Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USALincoln Laboratory, Massachusetts Institute of Technology, Lexington, MA, USADepartment of Computer Science and Engineering, Texas A&M University, College Station, TX, USA<italic>Goal:</italic> To establish Pulse2AI as a reproducible data preprocessing framework for pulsatile signals that generate high-quality machine-learning-ready datasets from raw wearable recordings. <italic>Methods:</italic> We proposed an end-to-end data preprocessing framework that adapts multiple pulsatile signal modalities and generates machine-learning-ready datasets agnostic to downstream medical tasks. <italic>Results:</italic> a dataset preprocessed by Pulse2AI improved systolic blood pressure estimation by 29.58%, from 11.41 to 8.03 mmHg in root-mean-square-error (RMSE) and its diastolic counterpart by 26.01%, from 7.93 to 5.87 mmHg in RMSE. For respiration rate (RR) estimation, Pulse2AI boosted performance by 19.69%, from 1.47 to 1.18 breaths per minute (BrPM) in mean-absolute-error (MAE). <italic>Conclusion:</italic> Pulse2AI turns pulsatile signals into machine learning (ML) ready datasets for arbitrary remote health monitoring tasks. We tested Pulse2AI on multiple pulsatile modalities and demonstrated its efficacy in two medical applications. This work bridges valuable assets in remote sensing and internet of medical things to ML-ready datasets for medical modeling.https://ieeexplore.ieee.org/document/10522883/IoMTML for HealthcareBridge2AIwearable pulsatile signalssignal processing |
| spellingShingle | Sicong Huang Roozbeh Jafari Bobak J. Mortazavi Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications IEEE Open Journal of Engineering in Medicine and Biology IoMT ML for Healthcare Bridge2AI wearable pulsatile signals signal processing |
| title | Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications |
| title_full | Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications |
| title_fullStr | Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications |
| title_full_unstemmed | Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications |
| title_short | Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications |
| title_sort | pulse2ai an adaptive framework to standardize and process pulsatile wearable sensor data for clinical applications |
| topic | IoMT ML for Healthcare Bridge2AI wearable pulsatile signals signal processing |
| url | https://ieeexplore.ieee.org/document/10522883/ |
| work_keys_str_mv | AT siconghuang pulse2aianadaptiveframeworktostandardizeandprocesspulsatilewearablesensordataforclinicalapplications AT roozbehjafari pulse2aianadaptiveframeworktostandardizeandprocesspulsatilewearablesensordataforclinicalapplications AT bobakjmortazavi pulse2aianadaptiveframeworktostandardizeandprocesspulsatilewearablesensordataforclinicalapplications |