Neural Networks Used to Predict Patient Outcomes Using Electronic Health Record Data

Monday, May 14, 2018

Neural Networks Used to Predict Patient Outcomes Using Electronic Health Record Data

⯀ A new deep learning model developed by Google uses big data from electronic health records and predicts clinical outcomes more accurately than traditional models. This paper represents the beginning of the work that is needed to test the hypothesis that machine learning can be used to improve healthcare.

One of the main promises of digital medicine supposes that, by digitizing health data, we might more easily leverage computer information systems to understand and improve patient care. Today, routinely collected patient healthcare data is now approaching the genomic scale in volume and complexity.

Now,  a deep learning approach that incorporates big data from electronic health records (EHRs) has been able to predict inpatient mortality, unexpected re-admissions, and long length of stay more accurately than traditional predictive models, according to a study conducted by researchers at Google.

The deep learning tool was able to analyze more than 46 billion individual data points drawn from the EHRs of over 216,000 patients in two hospitals. The data set included unstructured data, such as free-text clinical notes. The results are published with UC San Francisco, Stanford Medicine, and The University of Chicago Medicine, in a study titled, “Scalable and Accurate Deep Learning with Electronic Health Records” in Nature Partner Journals: Digital Medicine.

“EHRs are tremendously complicated,” writes Alvin Rajkomar MD, Research Scientist and Eyal Oren PhD, Product Manager, Google AI, in a blog post.

“For each prediction, a deep learning model reads all the data-points from earliest to most recent and then learns which data helps predict the outcome,” Rajkomar and Oren said.

To ensure data interoperability between the two hospitals, the team incorporated Fast Healthcare Interoperability Resources (FHIR) into the deep learning model.

"Since there are thousands of data points involved, we had to develop some new types of deep learning modeling approaches based on recurrent neural networks (RNNs) and feedforward networks," they write.

The group then compared the accuracy of the deep learning model to that of a traditional prediction model.

"This paper represents just the beginning of the work that is needed to test the hypothesis that machine learning can be used to make healthcare better."
Researchers found that in terms of predicting inpatient mortality, the deep learning model produced an area-under-the-receiver-operator curve (AUROC) score of 0.95 for Hospital A and 0.93 for Hospital B. In comparison, the traditional predictive model produced a score of 0.85 for Hospital A and 0.86 for Hospital B.

Related articles
The deep learning model also showed significantly higher AUROC scores for unexpected readmissions. The model produced an AUROC of 0.77 for Hospital A and 0.76 for Hospital B, while the traditional predictive model produced a score of 0.70 for Hospital A and 0.68 for Hospital B.

For predicting long length of stay, the AUROCs of the deep learning model were 0.86 for Hospital A and 0.85 for Hospital B, compared to the traditional model’s AUROCs of 0.76 for Hospital A and 0.74 for Hospital B.

“This predictive performance was achieved without hand-selection of variables deemed important by an expert, similar to other applications of deep learning to EHR data,” the group said.

deep learning patient data

“Instead, our model had access to tens of thousands of predictors for each patient, including free-text notes, and identified which data were important for a particular prediction.”

The team also noted that there were several limitations to the study, including the fact that it was retrospective and that prospective trials will be needed to demonstrate that these models can improve care delivery.

These results show the potential for deep learning to transform healthcare delivery. Deep learning has previously shown success in predicting seizures and breast cancer. Although unlikely to replace human clinicians, these models could help providers verify their work.

"Because we were interested in understanding whether deep learning could scale to produce valid predictions across divergent healthcare domains, we used a single data structure to make predictions for an important clinical outcome (death), a standard measure of quality of care (readmissions), a measure of resource utilization (length of stay), and a measure of understanding of a patient’s problems (diagnoses)," write the researchers.

SOURCE  Google AI Blog

By  33rd Square