healthcare technology

Olive automates repetitive tasks and can match patients across databases at different hospitals

When Sean Lane, a former NSA operative who served five tours of duty in Afghanistan and Iraq, first entered into the health care-AI arena, he was overwhelmed with data silos, systems that don’t speak to each other, and many, many portals and screens.

“I was not going to create another screen,” Lane told a packed room on Monday at ApplySci’s annual health technology conference at the MIT Media Lab in Cambridge, Mass. 

Instead, Lane and a team taught an AI system to use software that already exists in health care just like a human would use it. They named it Olive.

“Olive loves all that crappy software that health care already has,” said Lane. “Olive can look at any software program, any application for the first time she’s ever seen it, and understand how to use it.”

For example, Olive navigates electronic medical records, logs into hospital portals, creates reports, files insurance claims, and more.

Olive does so thanks to three key traits. First, using computer vision and Robotic Process Automation, or RPA, the program can interact with any software interface just as a human would, opening browsers and typing. Second, machine learning enables Olive to make decisions the way human health care workers do. The team trained Olive with historical data on how health care workers perform digital tasks, such as how to file an insurance eligibility check for a patient seeking to undergo a procedure.

Finally, Olive relies on a unique skill that Lane developed based on his work at the NSA identifying criminals across disparate government sources—the ability to match identities across databases. Just as NSA software can determine if a terrorist in the CIA database is the same as in the Homeland Security database, so Olive matches a patient across disparate databases and software, such as multiple electronic health care record programs.

Read the full article at https://spectrum.ieee.org/the-human-os/computing/software/this-healthcare-ai-loves-crappy-software

The "SOAP" -- subjective, objective, assessment, plan -- format has been in common use for decades as a way of organizing physician progress notes in medical records, but it was created during a different era, when most everything was written on paper. In the age of electronic health records, some are rethinking the order of presenting information, electing to go with the latter two elements first in what's being called an "APSO note."

An early adopter of the APSO format, C.T. Lin, MD, CMIO of Aurora, Colo.-based University of Colorado Health, explains that physicians often flip right to the assessment page of paper charts to see what previous visits or referring doctors may have found. By this reasoning, it makes more sense to put the assessment and plan first in an electronic note, according to Lin.

Lin was lead author of a paper published in JAMA Internal Medicine in January 2013 that found that SOAP "translates poorly from paper medical charts to the EHR" because it takes a lot of clicking and scrolling to find the assessment and plan. The article detailed a 2010 study at 13 University of Colorado Health ambulatory clinics that produced mostly positive results from an APSO trial.

For the study, eight of the clinics — six in primary care and two specialty clinics — mandated APSO notes, and the rest made it voluntary. All providers in the locations where it was mandatory and slightly more than half in the voluntary clinics did adopt the APSO format within the two months, according to the report.

The researchers, led by Lin, found that 73 percent of participants were "satisfied" or "very satisfied" with the APSO format when writing progress notes, and 82 percent said the same about reading APSO notes. A full 75 percent said they "preferred" or "strongly preferred" reading APSO notes, compared to just 8 percent who said SOAP was better.