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

Abstract

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.

Can synthetic data be a proxy for real clinical trial data? A validation study

“…In fact, we are already starting to see published (observational) health research using synthetic derivatives only. 40 While we found that there were very little differences between the real and synthetic data on the bivariate comparisons, one may hypothesise that this was influenced by the fact that the effect sizes were small. However, that was not the case for the multivariate models where the effect sizes were larger and the differences between the real and synthetic datasets remained small.…”

“…In addition to offering more options for addressing privacy concerns, sharing synthetic versions of clinical trial datasets can potentially alleviate the need for obtaining ethics board reviews for such analysis projects, 40 simplifying and accelerating research studies.…”

“…While we are already starting to see published (observational) health research using synthetic data only, 40 there will be situations where there is a requirement for additional verification that the model parameters produced from synthetic data are numerically similar to the those from the real data, and that the conclusions are the same. This step can be achieved by implementing a verification server.…”

“…39 Furthermore, there are recent examples of research studies using synthetic data not requiring ethics review because they are considered to contain no patient information. 40 To the extent that this becomes a common practice, it would accelerate data access.…”

Predicting mortality among patients with liver cirrhosis in electronic health records with machine learning

“…In this study, we utilized electronic health record (EHR) data from a large academic liver transplant center. Our institution partnered with MDClone [ 18 , 19 ] (Beer Sheva, Israel) for the data storage and retrieval. MDClone platform is a data engine by storing EHR medical events in a time order for each patient.…”