Tag Archives: EHR

New framework developed at U-M helps streamline EHR data extraction

By | October 14, 2020

A cross-disciplinary team of researchers from U-M have developed an open-source framework that streamlines the preprocessing of data extracted from the electronic health record. The framework, which the researchers call FIDDLE (Flexible Data-Driven Pipeline), has the power to greatly speed up EHR data preprocessing and assist machine learning (ML) practitioners working with health data, according to a study published in… Read More »

Electronic health records: More demands, same amount of time

By | August 24, 2020

A team of researchers from U-M recently published a paper in the Journal of General Internal Medicine documenting electronic medical record time demands faced by general internists at Michigan Medicine. The findings build on other studies showing that primary care providers nationwide face the highest number of incoming tasks on electronic health records systems. Lead author Laurence McMahon, chief of general medicine at U-M,… Read More »

Beyond the hype, what are the risks and rewards of Artificial Intelligence in health care?

By | February 15, 2019

Artificial Intelligence has received tremendous attention for its ability to transform how health care uses Electronic Health Records. EHR are already an invaluable tool for organizing a patient’s demographic information and their past and current medical data. EHR can support physician decision-making, help increase the efficiency of administrative processes, and make clinical data available to researchers for advancing… Read More »

EMERSE: Michigan Medicine’s powerful medical record search engine

Any note or document that is written by a medical professional (like a doctor, pharmacist, nurse, or social worker) is called free text, meaning anything goes—from syntax errors to misspellings to abbreviations, and more. That’s tough for a search engine to navigate. To get any information at all for things like research studies or billing information, users would have… Read More »

To fight fatal infections, hospitals may turn to algorithms

By | February 14, 2018

Jenna Wiens, a computer scientist and assistant professor of engineering at U-M, helped create an algorithm to predict a patient’s risk of developing a C-diff infection (CDI), one of the deadliest killers in American hospitals. The algorithm uses a form of artificial intelligence called machine learning to extract warning signs of disease from patients’ vital signs and other health records—constellations of symptoms, circumstances,… Read More »

Michigan Medicine CIO looks back in time for answers to today’s dilemmas

A majority of U.S. hospitals and health systems implemented electronic health records (EHR) over the last decade, thanks in large part to federal government incentive programs. But not everyone is happy about it. According to a 2016 Survey by Deloitte, seven out of 10 U.S. physicians believe EHRs reduce their  productivity. In a talk titled, “Solving the EHR… Read More »

HITS hosts successful electronic health records conference

Nearly 350 health care IT professionals from 11 different health systems recently gathered in Ann Arbor to share ideas and knowledge to improve patient care. The EHR Michigan User Group, or eMUG, is a collection of health systems in Michigan that use Epic electronic health records software. The 2017 eMUG conference was hosted by Michigan Medicine Health Information Technology &… Read More »

EHR improves patient care

By | April 11, 2017

According to U-M researchers, hospitals that voluntarily participated in value-based health care reforms, such as the Meaningful Use of Electronic Health Records program, were better at keeping patients from returning to the hospital within 30 days for three common diagnoses than the government’s mandatory program that penalizes acute care facilities for high readmission rates. Andrew Ryan, associate professor in the School… Read More »

Fuzzy records

By | February 6, 2017

Symptoms that patients describe to doctors may not always be documented in electronic medical records, a small study suggests. To test out how well the records match reality, researchers compared symptoms that 162 patients checked off on paper-based questionnaires with the information entered in patients’ electronic charts at eye clinics. Roughly one-third of the time, data on blurry… Read More »