AI-based preeclampsia detection and prediction with electrocardiogram data
IntroductionMore than 76,000 women die yearly from preeclampsia and hypertensive disorders of pregnancy. Early diagnosis and management of preeclampsia can improve outcomes for both mother and baby. In this study, we developed artificial intelligence models to detect and predict preeclampsia from el...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2024.1360238/full |
| _version_ | 1797279186632572928 |
|---|---|
| author | Liam Butler Fatma Gunturkun Lokesh Chinthala Ibrahim Karabayir Mohammad S. Tootooni Berna Bakir-Batu Turgay Celik Oguz Akbilgic Robert L. Davis |
| author_facet | Liam Butler Fatma Gunturkun Lokesh Chinthala Ibrahim Karabayir Mohammad S. Tootooni Berna Bakir-Batu Turgay Celik Oguz Akbilgic Robert L. Davis |
| author_sort | Liam Butler |
| collection | DOAJ |
| description | IntroductionMore than 76,000 women die yearly from preeclampsia and hypertensive disorders of pregnancy. Early diagnosis and management of preeclampsia can improve outcomes for both mother and baby. In this study, we developed artificial intelligence models to detect and predict preeclampsia from electrocardiograms (ECGs) in point-of-care settings.MethodsTen-second 12-lead ECG data was obtained from two large health care settings: University of Tennessee Health Science Center (UTHSC) and Atrium Health Wake Forest Baptist (AHWFB). UTHSC data was split into 80% training and 20% holdout data. The model used a modified ResNet convolutional neural network, taking one-dimensional raw ECG signals comprising 12 channels as an input, to predict risk of preeclampsia. Sub-analyses were performed to assess the predictive accuracy for preeclampsia prediction within 30, 60, or 90 days before diagnosis.ResultsThe UTHSC cohort included 904 ECGs from 759 females (78.8% African American) with a mean ± sd age of 27.3 ± 5.0 years. The AHWFB cohort included 817 ECGs from 141 females (45.4 African American) with a mean ± sd age of 27.4 ± 5.9 years. The cross-validated ECG-AI model yielded an AUC (95% CI) of 0.85 (0.77-0.93) on UTHSC holdout data, and an AUC (95% CI) of 0.81 (0.77-0.84) on AHWFB data. The sub-analysis of different time windows before preeclampsia prediction resulted in AUCs (95% CI) of 0.92 (0.84-1.00), 0.89 (0.81-0.98) and 0.90 (0.81-0.98) when tested on ECGs 30 days, 60 days and 90 days, respectively, before diagnosis. When assessed on early onset preeclampsia (preeclampsia diagnosed at <34 weeks of pregnancy), the model's AUC (95% CI) was 0.98 (0.89-1.00).DiscussionWe conclude that preeclampsia can be identified with high accuracy via application of AI models to ECG data. |
| first_indexed | 2024-03-07T16:21:41Z |
| format | Article |
| id | doaj.art-5954843b2eba404ea2b5289092f51f33 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-03-07T16:21:41Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-5954843b2eba404ea2b5289092f51f332024-03-04T04:53:30ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2024-03-011110.3389/fcvm.2024.13602381360238AI-based preeclampsia detection and prediction with electrocardiogram dataLiam Butler0Fatma Gunturkun1Lokesh Chinthala2Ibrahim Karabayir3Mohammad S. Tootooni4Berna Bakir-Batu5Turgay Celik6Oguz Akbilgic7Robert L. Davis8Department of Internal Medicine, Section on Cardiovascular Medicine, Wake Forest University School of Medicine, Winston-Salem, NC, United StatesQuantitative Sciences Unit, Stanford School of Medicine, Stanford University, Stanford, CA, United StatesCenter for Biomedical Informatics, UTHSC, Memphis, TN, United StatesDepartment of Internal Medicine, Section on Cardiovascular Medicine, Wake Forest University School of Medicine, Winston-Salem, NC, United StatesParkinson School of Health Sciences and Public Health, Loyola University Chicago, Chicago, IL, United StatesCenter for Biomedical Informatics, UTHSC, Memphis, TN, United StatesDepartment of Internal Medicine, Section on Cardiovascular Medicine, Wake Forest University School of Medicine, Winston-Salem, NC, United StatesDepartment of Internal Medicine, Section on Cardiovascular Medicine, Wake Forest University School of Medicine, Winston-Salem, NC, United StatesCenter for Biomedical Informatics, UTHSC, Memphis, TN, United StatesIntroductionMore than 76,000 women die yearly from preeclampsia and hypertensive disorders of pregnancy. Early diagnosis and management of preeclampsia can improve outcomes for both mother and baby. In this study, we developed artificial intelligence models to detect and predict preeclampsia from electrocardiograms (ECGs) in point-of-care settings.MethodsTen-second 12-lead ECG data was obtained from two large health care settings: University of Tennessee Health Science Center (UTHSC) and Atrium Health Wake Forest Baptist (AHWFB). UTHSC data was split into 80% training and 20% holdout data. The model used a modified ResNet convolutional neural network, taking one-dimensional raw ECG signals comprising 12 channels as an input, to predict risk of preeclampsia. Sub-analyses were performed to assess the predictive accuracy for preeclampsia prediction within 30, 60, or 90 days before diagnosis.ResultsThe UTHSC cohort included 904 ECGs from 759 females (78.8% African American) with a mean ± sd age of 27.3 ± 5.0 years. The AHWFB cohort included 817 ECGs from 141 females (45.4 African American) with a mean ± sd age of 27.4 ± 5.9 years. The cross-validated ECG-AI model yielded an AUC (95% CI) of 0.85 (0.77-0.93) on UTHSC holdout data, and an AUC (95% CI) of 0.81 (0.77-0.84) on AHWFB data. The sub-analysis of different time windows before preeclampsia prediction resulted in AUCs (95% CI) of 0.92 (0.84-1.00), 0.89 (0.81-0.98) and 0.90 (0.81-0.98) when tested on ECGs 30 days, 60 days and 90 days, respectively, before diagnosis. When assessed on early onset preeclampsia (preeclampsia diagnosed at <34 weeks of pregnancy), the model's AUC (95% CI) was 0.98 (0.89-1.00).DiscussionWe conclude that preeclampsia can be identified with high accuracy via application of AI models to ECG data.https://www.frontiersin.org/articles/10.3389/fcvm.2024.1360238/fullpreeclampsiaelectrocardiogramECG-AIpredictiondetectiongestational age |
| spellingShingle | Liam Butler Fatma Gunturkun Lokesh Chinthala Ibrahim Karabayir Mohammad S. Tootooni Berna Bakir-Batu Turgay Celik Oguz Akbilgic Robert L. Davis AI-based preeclampsia detection and prediction with electrocardiogram data Frontiers in Cardiovascular Medicine preeclampsia electrocardiogram ECG-AI prediction detection gestational age |
| title | AI-based preeclampsia detection and prediction with electrocardiogram data |
| title_full | AI-based preeclampsia detection and prediction with electrocardiogram data |
| title_fullStr | AI-based preeclampsia detection and prediction with electrocardiogram data |
| title_full_unstemmed | AI-based preeclampsia detection and prediction with electrocardiogram data |
| title_short | AI-based preeclampsia detection and prediction with electrocardiogram data |
| title_sort | ai based preeclampsia detection and prediction with electrocardiogram data |
| topic | preeclampsia electrocardiogram ECG-AI prediction detection gestational age |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2024.1360238/full |
| work_keys_str_mv | AT liambutler aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT fatmagunturkun aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT lokeshchinthala aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT ibrahimkarabayir aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT mohammadstootooni aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT bernabakirbatu aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT turgaycelik aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT oguzakbilgic aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata AT robertldavis aibasedpreeclampsiadetectionandpredictionwithelectrocardiogramdata |