An Electronic Health Record (EHR) is a digital version of a patient’s medical history that is maintained by the provider over time. It goes beyond the standard clinical data collected in a provider's office and can be inclusive of a broader view of a patient's care. EHRs are designed to contain and share information from all providers involved in a patient’s care. This can include demographics, progress notes, problems, medications, vital signs, past medical history, immunizations, laboratory data, and radiology reports.
primary goal of EHRs is to support efficient, accurate, and informed patient care. They enable quick access to patient records for more coordinated, efficient care and secure sharing of information with patients and other clinicians. EHRs also help providers improve productivity and work-life balance by automating workflows. Additionally, they facilitate outcomes reporting, disease surveillance, and potentially quality management and cost-reduction efforts..
An Electronic Health Record (EHR) is a digital version of a patient’s medical history that is maintained by the provider over time. It goes beyond the standard clinical data collected in a provider's office and can be inclusive of a broader view of a patient's care. EHRs are designed to contain and share information from all providers involved in a patient’s care. This can include demographics, progress notes, problems, medications, vital signs, past medical history, immunizations, laboratory data, and radiology reports.
EHR archives can be used to generate insights, test hypotheses, and develop predictive models. Most applications using the EHR models for decision support manifest as risk stratification models, or early warning systems. hese applications ingest hand-identified and crafted EHR features to make a binary decision, which can be implemented as a flag
+
+
What are Electronic Health
+
+
+
+
+
+ Multiple Embedding Model for EHR (MEME) Architecture
+
+
+ 
+
+
+
+
+
+
+ Our second main contribution is the Multiple Embedding Model for EHR architecture. We designed a methodology that takes pre-trained language models as representation models to generate multiple embeddings for our varying EHR input (e.g. medication, vitals, demographics). We then concatenate these embeddings and send this "patient embedding" through an additional self-attention layer where it learns the most important part of the inputs from the entire patient embedding. This model then gets fed to a MLP where it will be used for various downstream tasks in the Emergency Department.
+
+
+
+
+
+
Multiple Embedding Model for EHR (MEME) Architecture
+ +
+ + Our second main contribution is the Multiple Embedding Model for EHR architecture. We designed a methodology that takes pre-trained language models as representation models to generate multiple embeddings for our varying EHR input (e.g. medication, vitals, demographics). We then concatenate these embeddings and send this "patient embedding" through an additional self-attention layer where it learns the most important part of the inputs from the entire patient embedding. This model then gets fed to a MLP where it will be used for various downstream tasks in the Emergency Department. +
+