Diagnostics

When assisted by an AI tool designed to organize and display digitized patient referral records, gastroenterologists cut their time to answer relevant clinical questions by 2.3 minutes.

Going on a year and a half since its debut as a COVID symptom checker, one virtual health assistant is now trained on 17 million patient interactions. 

Early on in the development of digital image recognition, the technology showed a penchant for taking logical but potentially problematic shortcuts: It would look to image artifacts and incidental “asides” such as background features to distinguish between two visually similar subjects.

Psychology researchers have used machine learning to wring useful two-year dementia trajectory predictions from more than 500 potentially contributing risk factors.

Before colonoscopy AI can progress from lab to clinic on a broad scale—and win regulatory approvals along the way—it has to show its diagnostic mettle in numerous large clinical trials conducted at multiple facilities.

Not so fast with explainable AI in healthcare, warns an international and multidisciplinary team of academics.

As machine learning progresses from research settings to clinical practice, how are clinicians to know they can trust the machine’s conclusions to guide care for actual patients?

Emergency physicians have a tough time identifying patients who have Crohn’s disease and truly need a CT scan to pinpoint the cause of acute abdominal distress.

Many cases will be handled by primary-care providers, eye technicians and even patients themselves connected by telehealth and armed with commercial test kits and AI.

The deep learning models had nothing more to go on than routine abdominal CT scans acquired preoperatively.

Working with 9/11 responders as retrospective subjects, researchers in mental health and computer science have shown AI language tools can help predict the course of PTSD.

Comparing four methods for predicting septic shock in children hospitalized with sepsis, Johns Hopkins researchers have found a newer machine-learning approach superior to an older one as well as to two conventional methods.

   
   
   
   
   
Trimed Popup