The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation
Objective: Although many clinical metrics are associated with proximity to decompensation in heart failure (HF), none are individually accurate enough to risk-stratify HF patients on a patient-by-patient basis. The dire consequences of this inaccuracy in risk stratification have profoundly lowered t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-12-01
|
| Series: | Frontiers in Digital Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fdgth.2020.576945/full |
| _version_ | 1819071504372989952 |
|---|---|
| author | Aixia Guo Randi E. Foraker Randi E. Foraker Robert M. MacGregor Faraz M. Masood Brian P. Cupps Michael K. Pasque |
| author_facet | Aixia Guo Randi E. Foraker Randi E. Foraker Robert M. MacGregor Faraz M. Masood Brian P. Cupps Michael K. Pasque |
| author_sort | Aixia Guo |
| collection | DOAJ |
| description | Objective: Although many clinical metrics are associated with proximity to decompensation in heart failure (HF), none are individually accurate enough to risk-stratify HF patients on a patient-by-patient basis. The dire consequences of this inaccuracy in risk stratification have profoundly lowered the clinical threshold for application of high-risk surgical intervention, such as ventricular assist device placement. Machine learning can detect non-intuitive classifier patterns that allow for innovative combination of patient feature predictive capability. A machine learning-based clinical tool to identify proximity to catastrophic HF deterioration on a patient-specific basis would enable more efficient direction of high-risk surgical intervention to those patients who have the most to gain from it, while sparing others. Synthetic electronic health record (EHR) data are statistically indistinguishable from the original protected health information, and can be analyzed as if they were original data but without any privacy concerns. We demonstrate that synthetic EHR data can be easily accessed and analyzed and are amenable to machine learning analyses.Methods: We developed synthetic data from EHR data of 26,575 HF patients admitted to a single institution during the decade ending on 12/31/2018. Twenty-seven clinically-relevant features were synthesized and utilized in supervised deep learning and machine learning algorithms (i.e., deep neural networks [DNN], random forest [RF], and logistic regression [LR]) to explore their ability to predict 1-year mortality by five-fold cross validation methods. We conducted analyses leveraging features from prior to/at and after/at the time of HF diagnosis.Results: The area under the receiver operating curve (AUC) was used to evaluate the performance of the three models: the mean AUC was 0.80 for DNN, 0.72 for RF, and 0.74 for LR. Age, creatinine, body mass index, and blood pressure levels were especially important features in predicting death within 1-year among HF patients.Conclusions: Machine learning models have considerable potential to improve accuracy in mortality prediction, such that high-risk surgical intervention can be applied only in those patients who stand to benefit from it. Access to EHR-based synthetic data derivatives eliminates risk of exposure of EHR data, speeds time-to-insight, and facilitates data sharing. As more clinical, imaging, and contractile features with proven predictive capability are added to these models, the development of a clinical tool to assist in timing of intervention in surgical candidates may be possible. |
| first_indexed | 2024-12-21T17:22:53Z |
| format | Article |
| id | doaj.art-a7f63ca34c1d49a68a8b6cf7190e92ff |
| institution | Directory Open Access Journal |
| issn | 2673-253X |
| language | English |
| last_indexed | 2024-12-21T17:22:53Z |
| publishDate | 2020-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Digital Health |
| spelling | doaj.art-a7f63ca34c1d49a68a8b6cf7190e92ff2022-12-21T18:56:07ZengFrontiers Media S.A.Frontiers in Digital Health2673-253X2020-12-01210.3389/fdgth.2020.576945576945The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic DecompensationAixia Guo0Randi E. Foraker1Randi E. Foraker2Robert M. MacGregor3Faraz M. Masood4Brian P. Cupps5Michael K. Pasque6Institute for Informatics (I2), Washington University School of Medicine, St. Louis, MO, United StatesInstitute for Informatics (I2), Washington University School of Medicine, St. Louis, MO, United StatesDepartment of Internal Medicine, Washington University School of Medicine, St. Louis, MO, United StatesDepartment of Surgery, Washington University School of Medicine, St. Louis, MO, United StatesDepartment of Surgery, Washington University School of Medicine, St. Louis, MO, United StatesDepartment of Surgery, Washington University School of Medicine, St. Louis, MO, United StatesDepartment of Surgery, Washington University School of Medicine, St. Louis, MO, United StatesObjective: Although many clinical metrics are associated with proximity to decompensation in heart failure (HF), none are individually accurate enough to risk-stratify HF patients on a patient-by-patient basis. The dire consequences of this inaccuracy in risk stratification have profoundly lowered the clinical threshold for application of high-risk surgical intervention, such as ventricular assist device placement. Machine learning can detect non-intuitive classifier patterns that allow for innovative combination of patient feature predictive capability. A machine learning-based clinical tool to identify proximity to catastrophic HF deterioration on a patient-specific basis would enable more efficient direction of high-risk surgical intervention to those patients who have the most to gain from it, while sparing others. Synthetic electronic health record (EHR) data are statistically indistinguishable from the original protected health information, and can be analyzed as if they were original data but without any privacy concerns. We demonstrate that synthetic EHR data can be easily accessed and analyzed and are amenable to machine learning analyses.Methods: We developed synthetic data from EHR data of 26,575 HF patients admitted to a single institution during the decade ending on 12/31/2018. Twenty-seven clinically-relevant features were synthesized and utilized in supervised deep learning and machine learning algorithms (i.e., deep neural networks [DNN], random forest [RF], and logistic regression [LR]) to explore their ability to predict 1-year mortality by five-fold cross validation methods. We conducted analyses leveraging features from prior to/at and after/at the time of HF diagnosis.Results: The area under the receiver operating curve (AUC) was used to evaluate the performance of the three models: the mean AUC was 0.80 for DNN, 0.72 for RF, and 0.74 for LR. Age, creatinine, body mass index, and blood pressure levels were especially important features in predicting death within 1-year among HF patients.Conclusions: Machine learning models have considerable potential to improve accuracy in mortality prediction, such that high-risk surgical intervention can be applied only in those patients who stand to benefit from it. Access to EHR-based synthetic data derivatives eliminates risk of exposure of EHR data, speeds time-to-insight, and facilitates data sharing. As more clinical, imaging, and contractile features with proven predictive capability are added to these models, the development of a clinical tool to assist in timing of intervention in surgical candidates may be possible.https://www.frontiersin.org/articles/10.3389/fdgth.2020.576945/fullelectronic health record (EHR)machine/deep learningheart failuresynthetic datasurgical intervention |
| spellingShingle | Aixia Guo Randi E. Foraker Randi E. Foraker Robert M. MacGregor Faraz M. Masood Brian P. Cupps Michael K. Pasque The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation Frontiers in Digital Health electronic health record (EHR) machine/deep learning heart failure synthetic data surgical intervention |
| title | The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation |
| title_full | The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation |
| title_fullStr | The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation |
| title_full_unstemmed | The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation |
| title_short | The Use of Synthetic Electronic Health Record Data and Deep Learning to Improve Timing of High-Risk Heart Failure Surgical Intervention by Predicting Proximity to Catastrophic Decompensation |
| title_sort | use of synthetic electronic health record data and deep learning to improve timing of high risk heart failure surgical intervention by predicting proximity to catastrophic decompensation |
| topic | electronic health record (EHR) machine/deep learning heart failure synthetic data surgical intervention |
| url | https://www.frontiersin.org/articles/10.3389/fdgth.2020.576945/full |
| work_keys_str_mv | AT aixiaguo theuseofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT randieforaker theuseofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT randieforaker theuseofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT robertmmacgregor theuseofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT farazmmasood theuseofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT brianpcupps theuseofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT michaelkpasque theuseofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT aixiaguo useofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT randieforaker useofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT randieforaker useofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT robertmmacgregor useofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT farazmmasood useofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT brianpcupps useofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation AT michaelkpasque useofsyntheticelectronichealthrecorddataanddeeplearningtoimprovetimingofhighriskheartfailuresurgicalinterventionbypredictingproximitytocatastrophicdecompensation |