Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Effective Machine Learning Needs Leadership — Not AI Hype
 Originally published in BigThink, Feb 12, 2024.  Excerpted from The...
Today’s AI Won’t Radically Transform Society, But It’s Already Reshaping Business
 Originally published in Fast Company, Jan 5, 2024. Eric...
Calculating Customer Potential with Share of Wallet
 No question about it: We, as consumers have our...
A University Curriculum Supplement to Teach a Business Framework for ML Deployment
    In 2023, as a visiting analytics professor...
SHARE THIS:

This excerpt is from Health IT News. To view the whole article click here.  

9 years ago
Healthcare Challenges: Where Big Data Falls Short

 

Big data and analytic tools have not yet been harnessed to bring meaningful improvement to the healthcare industry.


Use code: PATIMES15 for 15% of a two-day Conference pass to Predictive Analytics World for Healthcare.

That’s according to a new report from the National Quality Forum outlining the challenges to making health data and analytics more usable and available in real time for providers and consumers.

Whereas big data has supported improvement in certain settings, such as reducing ventilator-acquired pneumonia, data analytics has been largely overlooked in the area of healthcare costs, even though this data can inform and assess efforts to improve the affordability and quality of care.

What’s more, effective data management is necessary for the success of other incentives to enhance care, such as payment programs, as providers need timely information to understand where to improve and track their progress.

NQF found multiple challenges to making better use of health information, such as interoperability and linking disparate data sources, leveraging data for benchmarking, providing the ability to gather data directly from patients and de-identify it to generate knowledge, and the need to ensure that the data itself is trustworthy.

Then there’s the matter of electronic health records software. “While greater EHR adoption is positive, these records do not contain all of the data needed for improvement,” the report said. NQF pointed to operational or clinical data not captured in an EHR, such as the time a nurse spends caring for a particular patient or the time to transfer a patient from surgery to a post-operative recovery unit to a hospital room, as common examples.

The report noted there have been many ongoing attempts to develop interoperability between EHRs and clinical data sources recording patients’ experiences and outcomes. Beyond linking healthcare data, however, “there is a need to learn from data spanning other determinants of health, as the most significant and sustained individual and population health improvements occur when healthcare organizations collaborate with community or public health organizations.”

By: Jack McCarthy, Health IT News
Originally published at
www.healthcareitnews.com

Leave a Reply