CASE STUDY

Unlocking the Potential of a Hospital’s Data Reserves

Client: Baylor College of Medicine

# 0

In Best Medical Schools: Research

0 +

Clinical residents

At a glance

Challenge

Enable a college of medicine to utilize massive amounts of data locked away in unstructured, free-form, text medical notes — without costly manual extraction.

Result

The team built a data pipeline using a combination of on-premises and cloud-based technologies to de-identify patient records, extract usable data, and utilize results across the organization.

Impact

When fully implemented, the platform exposed missing revenue opportunities, reduced costs, increased the quality of care for patients, and saved clinicians valuable time.

TECHNOLOGIES USED

AWS Comprehend Medical

Baylor College of Medicine is a medical school and research facility sitting within the world’s largest medical center.

As a health sciences university, Baylor creates knowledge and applies scientific discoveries to further education, healthcare, and community services locally and globally. When facing a major data challenge, they jumped on the opportunity to build a data pipeline and harness the power of Medical Machine Learning and Artificial Intelligence.

Empowering a major medical school by harnessing their information with a data pipeline.

Baylor College of Medicine, a large academic medical hospital, was facing a challenge: massive amounts of its data were locked away in unstructured, free-form, text medical notes. Without costly manual extraction, Baylor’s researchers, clinicians, and administration personnel were prevented from fully utilizing this invaluable source of information. A team from Pariveda designed a cutting-edge, natural language processing pilot to extract the data.

The Pariveda team built a data pipeline using a combination of on-premises and cloud-based technologies to accomplish the following objectives:

De-identified patient records by removing all 18 categories of personal health information, or PHI, to comply with HIPAA regulations.
Used the cutting-edge cloud-based AWS Comprehend Medical Machine Learning/Artificial Intelligence algorithm to perform natural language processing on the notes to extract usable, structured data from the previously unstructured text and make it available to the hospital’s existing analytics toolchain.
Showcase results across the organization to increase excitement around Machine Learning technologies and determine value driven use cases to explore.

When fully implemented, the platform helped the Baylor organization and its patients by exposing missed revenue opportunities by finding over or under-coded billing claims, which led to higher revenue and lower risks of fraudulent claims.

The solution also reduced the costs associated with using symptoms, signs, medication, and medical history in cohort identification for clinical trials — in turn, this led to finding more eligible participants in days rather than months, accelerated study timelines, increased time and funds available for analysis and, ultimately, higher quality studies translate into improved healthcare for patients. Baylor was also able to increase patients’ quality of care through the facilitation of iterative reduction and avoidance of side effects through data-driven quality efforts using information that was previously difficult to access. There was also benefit for the clinicians who reduced the time required to write referral notes or populate a charge screen by predicting diagnoses and billing codes from the progress/encounter notes.