According to reports, a patent filed by Google explains its plans to develop its own electronic health record (EHR) for clinicians.
Google’s EHR will use Machine Learning
The electronic health record (EHR) will use machine learning to predict clinical outcomes and gather patients’ medical records. It is a new healthcare system that provides facing interface which predicts and reviews medical events from EHRs. Reportedly, the inventors involved in the application are more than 20 Google employees, particularly from the Google Brain team, or its artificial intelligence division, including AI head Jeffrey Dean.
Electronic health record (EHR) Structure and Working
The electronic health record patent defines a system that is made up of three parts:
First part is a computer memory to store health records from millions of patients. It stores aggregated EHR data from patients of diverse ages, health conditions, and demographics. It also takes medications, laboratory values, diagnoses, vital signs, and medical notes. The second part is a computer system executing deep learning models on patients’ health records converted into a single standard data format. Last part is an interface for the computer terminal, tablet or smartphone, that displays predictions for future clinical events and suitable past medical events for patients.
Assist healthcare providers to handle overflow of information
Inventors noted, that in the application, there is a need for systems and methods to assist healthcare providers to allocate their attention efficiently among the overflow of information from diverse sources. The application also provides predictions of future clinical events and highlight relevant underlying medical events contributing to these predictions in a timely manner.
Example given by application
The patent application explains an example of how the deep learning EHR’s clinical predictions could aid physicians in patient care. In an example, a patient comes to the emergency room for abdominal pain; his alcohol withdrawal symptoms are mistaken for sepsis and he is given the wrong treatment. According to the inventors, the PC framework mentioned in the patent would most likely banner clinicians’ notes in regards to worries about liquor withdrawal and would alarm doctors’ consideration prior that the patient was in danger.
Google’s involved in healthcare
Google is getting involved in healthcare, including products such as Google Fit and Google Nest. The company selected David Feinberg, Geisinger Health System’s former CEO, M.D., to help organize its fragmented health initiatives. Toby Cosgrove, Former Cleveland Clinic CEO, M.D., has also joined Google Cloud’s healthcare and life sciences team as an executive adviser.