Rebecca Vesely is AHCJ's topic leader on health information technology and a freelance writer. She has written about health, science and medicine for AFP, the Bay Area News Group, Modern Healthcare, Wired, Scientific American online and many other news outlets.
Hospitals and health systems are jumping into artificial intelligence (AI) in an effort to help physicians better analyze images and other clinical data. But reporters should be careful about overstating the value that these new tools can bring to clinical decision-making.
Radiology is the medical specialty probably most associated with AI today because of the tantalizing possibility that computers could help radiologists read images more quickly, enabling earlier diagnoses and treatment.
Carla K. Johnson (@CarlaKJohnson) is a medical writer at The Associated Press and has covered health and medicine since 2001. A former member of AHCJ's board of directors, she leads the Chicago AHCJ chapter.
Photo: Carla K. Johnson(from left) Paul Epner of the Society to Improve Diagnosis in Medicine, Dr. Karen Cosby of Rush University Medical School, and Dr. David Liebovitz of Northwestern Memorial Healthcare. spoke to Chicago’s AHCJ chapter.
If you’ve read Dr. Lisa Sanders’ “Diagnosis” column in The New York Times Magazine, you know the process of identifying a patient’s problem can be fraught with opportunities for error. You also know diagnosis is rich territory for dramatic storytelling.
Not the inevitable tragic things that can happen to a patient – but the ones that we know how to avoid, the lives that should not be at risk. Kliff spent several months on one story – actually a story and accompanying video and graphics – that combined insights about how hospitals think central line infections and a gripping narrative about the death of a 3-year-old girl. You can find the story here.
Kliff wrote a “How I did It” essay for AHCJ that addresses a lot of the nuts and bolts of a vast project like this. She outlines how she reached out to patients/families, how she organized the voluminous – initially not searchable – medical records, how she found researchers who could elucidate things she did not fully understand in those records.
And she talks about the power of a good analogy to both organize a 5000-word narrative and give readers an accessible entry point to her work. Read about how she did it.
To draw attention to its ongoing monitoring of the incidence of adverse events in US hospitals and the accurate reporting thereof, the HHS Office of Inspector General is highlighting a roundup of reports on the subject.
If you get a chance to read it, you’ll probably see why I decided to distill it to a bulleted list of somewhat remarkable numbers.
In a one-month period, 27 percent of Medicare recipients experienced “care-related harm.”
In that month, these events cost Medicare an estimated $324 million.
Half of them were adverse events, half were “temporary” events such as allergic reactions.
44 percent of the adverse events were deemed “preventable.”
“Hospital staff did not report 86 percent of events to incident reporting systems.”
That is partly because only 12 percent of incidents of care-related harm met requirements for being reported in the state in which they occurred.
“Many of the events not reported as required involved serious harm, including six patient deaths.”
For those looking to dig deeper and better understand the adverse events and how they’re reported, the OIG refers to a number of relevant reports. Journalists will be particularly interested in reports explaining how reporting requirements have failed, as it helps explain the limitations of currently available data sets.
“At the moment, we kind of say, ‘Well, we do it this way.’ Everybody thinks they know really what happens, but not everyone does,” (lead author Ken Catchpole, PhD) said. “There is lots of individual variation that creeps into these things. Sometimes that’s good, and it’s responsive to individual patients. But often that creates these uncertainties that increase the opportunities for errors to happen.”
Catchpole has helped physicians at London’s Great Ormond Street Hospital for Children use F1 techniques to improve their handoff of pediatric heart surgery patients to intensive care, with results first published in the May 2007 issue of Pediatric Anesthesia. New protocols developed in response to video examination of pit stops and visits with F1 racing crews helped cut the duration of patient handoffs and reduced omissions of critical information and technical errors by 67%, the study showed.