An Algorithm That Predicts Deadly Infections Is Often Flawed
A complication of infection known as sepsis is the number one killer in US hospitals. So it’s not surprising that more than 100 health systems use an early warning system offered by Epic Systems, the dominant provider of US electronic health records. But a new study using data from nearly 30,000 patients in University of Michigan hospitals suggests Epic’s system performs poorly. An Epic spokesperson disputed the study’s conclusions, saying the company’s system has “helped clinicians save thousands of lives.” Epic’s is not the first widely used health algorithm to trigger concerns that technology supposed to improve health care is not delivering, or even actively harmful. The models are “very widely used, and yet there’s very little published on them.” Karandeep Singh, assistant professor, University of Michigan The way sepsis stalks hospital wards has made it a special target of algorithmic aids for medical staff.
Discover Related
How UK’s ‘murder prediction’ tool could predict who might kill in future
AI can recommend if you need to be screened for cancer
Artificial Intelligence in healthcare: what lies ahead
Can AI predict when you will die? This AI app claims results are ‘pretty significant’
Scientists able to predict neonatal sepsis before symptoms show
AI could ‘revolutionise’ care for heart failure patients, say researchers
Cutting-edge tech boosting diagnostic accuracy
New AI tool ‘can rapidly rule out heart attacks in people attending A&E’
AI Model Predicts Heart Irregularities Before Onset
Chinese scientists use AI algorithm to better predict unknown tumor origins
New AI model diagnoses diseases by drawing visual maps
AI's ability to predict death may not be as scary as it sounds
New AI model Life2vec may predict human lifespan, researchers say
How Artificial Intelligence can predict, prevent sudden cardiac death?
AI algorithm ‘could improve outcomes for thousands of cancer patients a year’
AI in medicine needs to be carefully deployed to counter bias – and not entrench it
Scientists use AI to discover new antibiotic against deadly hospital superbug
AI may be on its way to your doctor’s office, but it’s not ready to see patients
While COVID raged, another deadly threat was on the rise in hospitals
How scientists trained computers to forecast COVID-19 outbreaks weeks ahead
NHS trials AI technology offering same-day diagnosis of aggressive lung cancer
Long Covid-19 link to suicide: Scientists warn of hidden crisis
Long covid's link to suicide: Scientists warn of hidden crisis
ICMR DG questions WHO\'s COVID death estimates for India
How the Pandemic Made Algorithms Go Haywire
Patients ‘more likely to discuss some health conditions with AI than a GP’