Abstract
Left ventricular ejection fraction (EF) is a key measure in the diagnosis and treatment of heart failure (HF) and many patients experience changes in EF overtime. Large-scale analysis of longitudinal changes in EF using electronic health records (EHRs) is limited. In a multi-site retrospective study using EHR data from three academic medical centers, we investigated longitudinal changes in EF measurements in patients diagnosed with HF. We observed significant variations in baseline characteristics and longitudinal EF change behavior of the HF cohorts from a previous study that is based on HF registry data. Data gathered from this longitudinal study were used to develop multiple machine learning models to predict changes in ejection fraction measurements in HF patients. Across all three sites, we observed higher performance in predicting EF increase over a 1-year duration, with similarly higher performance predicting an EF increase of 30% from baseline compared to lower percentage increases. In predicting EF decrease we found moderate to high performance with low confidence for various models. Among various machine learning models, XGBoost was the best performing model for predicting EF changes. Across the three sites, the XGBoost model had an F1-score of 87.2, 89.9, and 88.6 and AUC of 0.83, 0.87, and 0.90 in predicting a 30% increase in EF, and had an F1-score of 95.0, 90.6, 90.1 and AUC of 0.54, 0.56, 0.68 in predicting a 30% decrease in EF. Among features that contribute to predicting EF changes, baseline ejection fraction measurement, age, gender, and heart diseases were found to be statistically significant.
| Original language | English (US) |
|---|---|
| Article number | 294 |
| Journal | Scientific reports |
| Volume | 13 |
| Issue number | 1 |
| DOIs | |
| State | Published - Dec 2023 |
ASJC Scopus subject areas
- General
Access to Document
Other files and links
Fingerprint
Dive into the research topics of 'Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study'. Together they form a unique fingerprint.
View full fingerprint
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
Adekkanattu, P., Rasmussen, L. V., Pacheco, J. A., Kabariti, J., Stone, D. J., Yu, Y., Jiang, G., Luo, Y., Brandt, P. S., Xu, Z., Vekaria, V., Xu, J., Wang, F., Benda, N. C., Peng, Y., Goyal, P., Ahmad, F. S., & Pathak, J. (2023). Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study. Scientific reports, 13(1), [294]. https://doi.org/10.1038/s41598-023-27493-8
Adekkanattu, Prakash ; Rasmussen, Luke V. ; Pacheco, Jennifer A. et al. / Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records : a multi-site study. In: Scientific reports. 2023 ; Vol. 13, No. 1.
@article{d65b744ae559493285fab47d922fc3ab,
title = "Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study",
abstract = "Left ventricular ejection fraction (EF) is a key measure in the diagnosis and treatment of heart failure (HF) and many patients experience changes in EF overtime. Large-scale analysis of longitudinal changes in EF using electronic health records (EHRs) is limited. In a multi-site retrospective study using EHR data from three academic medical centers, we investigated longitudinal changes in EF measurements in patients diagnosed with HF. We observed significant variations in baseline characteristics and longitudinal EF change behavior of the HF cohorts from a previous study that is based on HF registry data. Data gathered from this longitudinal study were used to develop multiple machine learning models to predict changes in ejection fraction measurements in HF patients. Across all three sites, we observed higher performance in predicting EF increase over a 1-year duration, with similarly higher performance predicting an EF increase of 30% from baseline compared to lower percentage increases. In predicting EF decrease we found moderate to high performance with low confidence for various models. Among various machine learning models, XGBoost was the best performing model for predicting EF changes. Across the three sites, the XGBoost model had an F1-score of 87.2, 89.9, and 88.6 and AUC of 0.83, 0.87, and 0.90 in predicting a 30% increase in EF, and had an F1-score of 95.0, 90.6, 90.1 and AUC of 0.54, 0.56, 0.68 in predicting a 30% decrease in EF. Among features that contribute to predicting EF changes, baseline ejection fraction measurement, age, gender, and heart diseases were found to be statistically significant.",
author = "Prakash Adekkanattu and Rasmussen, {Luke V.} and Pacheco, {Jennifer A.} and Joseph Kabariti and Stone, {Daniel J.} and Yue Yu and Guoqian Jiang and Yuan Luo and Brandt, {Pascal S.} and Zhenxing Xu and Veer Vekaria and Jie Xu and Fei Wang and Benda, {Natalie C.} and Yifan Peng and Parag Goyal and Ahmad, {Faraz S.} and Jyotishman Pathak",
note = "Funding Information: This research is funded in part by NIH grants R01GM105688 and R00LM013001. Publisher Copyright: {\textcopyright} 2023, The Author(s).",
year = "2023",
month = dec,
doi = "10.1038/s41598-023-27493-8",
language = "English (US)",
volume = "13",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",
}
Adekkanattu, P, Rasmussen, LV, Pacheco, JA, Kabariti, J, Stone, DJ, Yu, Y, Jiang, G, Luo, Y, Brandt, PS, Xu, Z, Vekaria, V, Xu, J, Wang, F, Benda, NC, Peng, Y, Goyal, P, Ahmad, FS & Pathak, J 2023, 'Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study', Scientific reports, vol. 13, no. 1, 294. https://doi.org/10.1038/s41598-023-27493-8
Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records : a multi-site study. / Adekkanattu, Prakash; Rasmussen, Luke V.; Pacheco, Jennifer A. et al.
In: Scientific reports, Vol. 13, No. 1, 294, 12.2023.
Research output: Contribution to journal › Article › peer-review
TY - JOUR
T1 - Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records
T2 - a multi-site study
AU - Adekkanattu, Prakash
AU - Rasmussen, Luke V.
AU - Pacheco, Jennifer A.
AU - Kabariti, Joseph
AU - Stone, Daniel J.
AU - Yu, Yue
AU - Jiang, Guoqian
AU - Luo, Yuan
AU - Brandt, Pascal S.
AU - Xu, Zhenxing
AU - Vekaria, Veer
AU - Xu, Jie
AU - Wang, Fei
AU - Benda, Natalie C.
AU - Peng, Yifan
AU - Goyal, Parag
AU - Ahmad, Faraz S.
AU - Pathak, Jyotishman
N1 - Funding Information:This research is funded in part by NIH grants R01GM105688 and R00LM013001. Publisher Copyright:© 2023, The Author(s).
PY - 2023/12
Y1 - 2023/12
N2 - Left ventricular ejection fraction (EF) is a key measure in the diagnosis and treatment of heart failure (HF) and many patients experience changes in EF overtime. Large-scale analysis of longitudinal changes in EF using electronic health records (EHRs) is limited. In a multi-site retrospective study using EHR data from three academic medical centers, we investigated longitudinal changes in EF measurements in patients diagnosed with HF. We observed significant variations in baseline characteristics and longitudinal EF change behavior of the HF cohorts from a previous study that is based on HF registry data. Data gathered from this longitudinal study were used to develop multiple machine learning models to predict changes in ejection fraction measurements in HF patients. Across all three sites, we observed higher performance in predicting EF increase over a 1-year duration, with similarly higher performance predicting an EF increase of 30% from baseline compared to lower percentage increases. In predicting EF decrease we found moderate to high performance with low confidence for various models. Among various machine learning models, XGBoost was the best performing model for predicting EF changes. Across the three sites, the XGBoost model had an F1-score of 87.2, 89.9, and 88.6 and AUC of 0.83, 0.87, and 0.90 in predicting a 30% increase in EF, and had an F1-score of 95.0, 90.6, 90.1 and AUC of 0.54, 0.56, 0.68 in predicting a 30% decrease in EF. Among features that contribute to predicting EF changes, baseline ejection fraction measurement, age, gender, and heart diseases were found to be statistically significant.
AB - Left ventricular ejection fraction (EF) is a key measure in the diagnosis and treatment of heart failure (HF) and many patients experience changes in EF overtime. Large-scale analysis of longitudinal changes in EF using electronic health records (EHRs) is limited. In a multi-site retrospective study using EHR data from three academic medical centers, we investigated longitudinal changes in EF measurements in patients diagnosed with HF. We observed significant variations in baseline characteristics and longitudinal EF change behavior of the HF cohorts from a previous study that is based on HF registry data. Data gathered from this longitudinal study were used to develop multiple machine learning models to predict changes in ejection fraction measurements in HF patients. Across all three sites, we observed higher performance in predicting EF increase over a 1-year duration, with similarly higher performance predicting an EF increase of 30% from baseline compared to lower percentage increases. In predicting EF decrease we found moderate to high performance with low confidence for various models. Among various machine learning models, XGBoost was the best performing model for predicting EF changes. Across the three sites, the XGBoost model had an F1-score of 87.2, 89.9, and 88.6 and AUC of 0.83, 0.87, and 0.90 in predicting a 30% increase in EF, and had an F1-score of 95.0, 90.6, 90.1 and AUC of 0.54, 0.56, 0.68 in predicting a 30% decrease in EF. Among features that contribute to predicting EF changes, baseline ejection fraction measurement, age, gender, and heart diseases were found to be statistically significant.
UR - http://www.scopus.com/inward/record.url?scp=85145857712&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85145857712&partnerID=8YFLogxK
U2 - 10.1038/s41598-023-27493-8
DO - 10.1038/s41598-023-27493-8
M3 - Article
C2 - 36609415
AN - SCOPUS:85145857712
SN - 2045-2322
VL - 13
JO - Scientific Reports
JF - Scientific Reports
IS - 1
M1 - 294
ER -
Adekkanattu P, Rasmussen LV, Pacheco JA, Kabariti J, Stone DJ, Yu Y et al. Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study. Scientific reports. 2023 Dec;13(1):294. doi: 10.1038/s41598-023-27493-8