Breaking News
February 21, 2019 - Gaming system helps with autism diagnosis
February 21, 2019 - Heart Disease: Six Things Women Should Know
February 21, 2019 - More States Say Doctors Must Offer Overdose Reversal Drug Along With Opioids
February 21, 2019 - Researchers explore case studies focused on industries that kill more people than employed
February 21, 2019 - Intense exercise, fasting and hormones can enhance waste-protein removal, study shows
February 21, 2019 - Scientists can monitor brain activity to predict epileptic seizures few minutes in advance
February 21, 2019 - Study quantifies hepatic and intestinal mRNA expression of Ugt isoforms in rats
February 21, 2019 - ‘Apple-Shaped’ Body? ‘Pear-Shaped’? Your Genes May Tell
February 21, 2019 - Can we repair the brain? The promise of stem cell technologies for treating Parkinson’s disease
February 21, 2019 - Trump Plan To Beat HIV Hits Rough Road In Rural America
February 21, 2019 - PENTAX Medical introduces new electrosurgical and argon plasma coagulation platforms
February 21, 2019 - Trump plan to beat HIV hits rough road in rural America
February 21, 2019 - Eating blueberries every day could help decrease blood pressure
February 21, 2019 - ‘No Second Chances’ report calls for new measures to combat cardiovascular disease in Australia
February 21, 2019 - Mayo clinic researchers discuss local case studies of leprosy
February 21, 2019 - Scientists demonstrate key role of salt in allergic immune reactions
February 21, 2019 - Experts propose revising the criteria for diagnosis of Parkinson’s disease
February 21, 2019 - The med student and the machine
February 21, 2019 - Hey, Hey! Ho, Ho! Is Striking For School Nurses The Way To Go?
February 21, 2019 - Latest research encourages children to move out and learn through physical activity
February 21, 2019 - Proper oral hygiene and regular visits to dentist can promote heart health
February 21, 2019 - New, versatile technique for remote control of transplanted cells in Parkinson’s
February 21, 2019 - Why melanoma tumors in the brain may be worse?
February 21, 2019 - New project aims to improve lung disease care in Appalachia
February 21, 2019 - Drug increases melanin production in some people with albinism
February 21, 2019 - Over 1 in 3 adults miss the mark on protein, finds study
February 21, 2019 - CymaBay Therapeutics Announces Seladelpar Granted Breakthrough Therapy Designation by the FDA for the Treatment of Primary Biliary Cholangitis
February 21, 2019 - A correlation between obesity and income has only developed in the past 30 years
February 21, 2019 - Baby, then work: An effort to help resident-parents in emergency medicine
February 21, 2019 - Heavy cigarette smoking could damage vision, say researchers
February 21, 2019 - Some drug combinations may be more effective than others for schizophrenic patients
February 21, 2019 - Combination of common antibiotics can eliminate multi-drug resistant E. coli
February 21, 2019 - Number of calls to U.S. Poison Control regarding kratom exposure increased
February 21, 2019 - New computational tool searches for factors that cause specific diseases
February 21, 2019 - New method to assess effectiveness of psychotherapies for social anxiety disorder
February 21, 2019 - New technology measures hormones that influence reproductive health efficiently
February 21, 2019 - Bat influenza viruses could potentially attack the cells of humans and livestock
February 21, 2019 - Immunotherapeutic antibody therapy to kill cancer has now progressed to patient testing
February 21, 2019 - Johns Hopkins scientists find new compound that may prevent reperfusion injury
February 21, 2019 - Researchers develop new way to deliver treatment for cartilage regeneration
February 21, 2019 - Study sheds new light on left ventricular dysfunction in ischemic heart disease
February 21, 2019 - New technique could expedite cancer diagnosis, lead to better patient outcomes
February 21, 2019 - New map of infant brain may aid early diagnosis of autism
February 21, 2019 - Human consciousness depends on the brain’s ability to maintain dynamics of neural activity
February 21, 2019 - Harmony Biosciences Announces File Acceptance Of Its New Drug Application For Pitolisant
February 21, 2019 - Medications could fill treatment gap for adolescents with obesity
February 21, 2019 - New antibiotics are desperately needed: Machine learning could help | News Center
February 21, 2019 - Researchers develop new computer game for dementia carers
February 21, 2019 - University of Dundee partners with Takeda to develop new treatments for tau pathology
February 21, 2019 - Influenza vaccine may be less effective in elderly patients, finds study
February 21, 2019 - Researchers explain why T cells lose their protective ability in inflamed tissues
February 21, 2019 - New optimization method rapidly analyzes nanomedicines for cancer treatment
February 21, 2019 - Viruses in the intestinal tracts can lead to islet autoimmunity and Type 1 diabetes
February 21, 2019 - Link between dietary fatty acid intake and hypertension found to be influenced by diabetes status
February 21, 2019 - FDA Approves Esperoct (turoctocog alfa pegol, N8-GP) for Hemophilia A
February 21, 2019 - ‘Boy erased’—why conversion therapies and ex-gay ministries should be outlawed
February 21, 2019 - Titia de Lange to give annual McCormick Lecture on March 8 | News Center
February 21, 2019 - Study reveals how helper T cells support memory cells to function optimally
February 21, 2019 - Autistic children with co-occurring ADHD have greater adaptive behavior impairments
February 21, 2019 - Elevated levels of key cellular process implicated in intestinal inflammation and IBD
February 20, 2019 - Over Half of Hip Replacements Expected to Last 25 Years
February 20, 2019 - Microscopic eye movements affect how we see contrast
February 20, 2019 - Computer vs. patient: Fighting for residents’ attention | News Center
February 20, 2019 - New “Smart Drug” Shows Promise for Metastatic Triple-Negative Breast Cancer
February 20, 2019 - Researchers develop large-scale window material for high-efficiency PM2.5 capture
February 20, 2019 - Widespread confusion among consumers on food date labels lead to unnecessary discards
February 20, 2019 - Researchers unlock plant’s secret of producing specialized metabolites
February 20, 2019 - Newly released national framework identifies obstacles to improving EMS systems
February 20, 2019 - Exercise can shift human body clock depending on time when people work out
February 20, 2019 - Female adolescent blood donors more likely to have iron deficiency and related anemia
February 20, 2019 - Rubicon level linked to inhibition of autophagic process
February 20, 2019 - Researchers find potential therapeutic strategy to treat Alzheimer’s
February 20, 2019 - New forms of older anti-cancer agent appear to enhance immune response to fight melanoma
February 20, 2019 - Health Tip: Eat Less Saturated Fat
February 20, 2019 - Sleeping in contact lenses puts you at risk of dangerous infection
February 20, 2019 - “We should study that!”: How a nurse-scientist found her passion
February 20, 2019 - Cervical microbiome may influence HPV infection more than previously thought
February 20, 2019 - Sausage mislabeling in Canada is down, new study finds
February 20, 2019 - Study shows blood pressure benefits of morning exercise for older overweight/obese adults
February 20, 2019 - New screening method could catch organ rejection much earlier without a biopsy needle
AI, doctors team up to improve, expedite diagnoses

AI, doctors team up to improve, expedite diagnoses

image_pdfDownload PDFimage_print

As the role of artificial intelligence in medicine continues to evolve, doctors and robots are often seen as pitted against each other. But two new studies suggest that it’s not man versus machine, it’s man and machine.

The research harnesses artificial intelligence to “read” medical images, from X-rays to more advanced scans such as magnetic resonance imaging, or MRI, scans. The ultimate goal is not to replace physicians, says co-senior author Matthew Lungren, PhD, it’s instead to provide all clinicians with tools to make faster, more accurate imaging diagnoses and treatment plans  — something that could one day benefit patients across the world.

A team of scientists led by Lungren, an assistant professor of radiology, and Andrew Ng, PhD, an adjunct professor of computer science, have devised two algorithms poised to do just that. One of the latest algorithms, which diagnoses knee injuries by automatically reading MRI scans, has already made its way into the hands of Stanford clinicians for preliminary testing.

The results were published today in PLOS Medicine. Graduate students Nicholas Bien and Pranav Rajpurkar are the first authors.

“One of the main goals of this paper is to figure out how doctors, both radiologists and non-radiologist clinicians, would work with algorithms that read medical scans,” said Lungren. “Does it make them better? Worse?”

So far, it’s one of the first studies to investigate how the physician-and-machine dynamic might work. The preliminary results show that the algorithm, called MRNet, not only performed at about the same level as radiologists on its own (although sometimes it performed just below depending on the MRI), it actually helped radiologists more accurately diagnose MRI scans of knee injuries.

“We developed MRNet for knee MRIs, but the same algorithm could also potentially classify other types of MRI,” said Bien. After the algorithm has been trained on a large dataset, it can generate predictions for a new MRI scan in a matter of seconds.”

MRNet was trained on a dataset of 1,370 MRI scans. Such image-based diagnostics comes down to pattern recognition, and in this case, the scientists trained the algorithm to recognize visual patterns associated with ligament and meniscal tears in the knee, as well as anything else that looks iffy. A panel of expert radiologists then sifted through a separate set of 120 knee MRIs to find a “ground truth,” for each scan, or diagnoses that the radiologists agreed was the right call. This set of images served to establish MRNet’s accuracy.

To answer if MRNet helped or hindered doctors diagnosing MRIs, a group of seven radiologists and two orthopedic surgeons took turns reading MRI scans with and without the algorithm. When reading the scans with the help of MRNet, they diagnosed fewer false positives (meaning they were less likely to say a patient had a serious knee injury, when they in fact were healthy) compared to their performance without the algorithm.

The results of the study, although still very early, are encouraging to physicians like Gary Fanton, MD, a clinical professor of orthopedic surgery at Stanford. He was one of the first doctors to give MRNet a try.

“As a clinician, having immediate and accurate data-driven information will allow us to make clinical decisions and mobilize a treatment plan with greater efficiency, especially in urgent care facilities or the emergency room,” Fanton said. “MRNet takes us closer to a more efficient, accurate and cost-effective means of delivering the most important first step in patient management — a diagnosis.”

Lungren and Ng likewise have plans to move another one of their diagnostic algorithms into the clinic to test how it fairs among doctors. The algorithm, called CheXNeXt, can simultaneously recognize 10 different pathologies from chest X-rays as well as radiologists; for one disease, it even outdid the experts.

It was featured in a recent video.

Lungren speaks to its potential in our release:

‘I could see [CheXNeXt] working in a few ways. [It] could triage the X-rays, sorting them into prioritized categories for doctors to review, like normal, abnormal or emergent,’ Lungren said. Or the algorithm could sit bedside with primary care doctors for on-demand consultation, he said.

In this case, Lungren said, the algorithm could step in to help confirm or cast doubt on a diagnosis.

Eventually, the scientists hope that algorithms like MRNet and CheXNeXt could stand alone, efficiently and effectively scanning for a wide range of diseases or injuries typically diagnosed through image-based medical exams. Such a feat could one day even be used as a sort of digital consultation for resource-deprived regions of the world that don’t typically have access to professional radiologists.

Photo by Kurt Hickman

Tagged with:

About author

Related Articles