Breaking News
December 10, 2018 - Scientists find answers to how cancer spreads
December 10, 2018 - Study explores why older people read more slowly
December 10, 2018 - Asbestos found in most NHS hospitals finds BBC inquiry
December 10, 2018 - Researchers use new technique to probe hydrogen bonds
December 10, 2018 - Music improves social communication in autistic children
December 10, 2018 - Some Brain Tumors May Respond to Immunotherapy, New Study Suggests
December 10, 2018 - Banning junk food ads to combat childhood obesity
December 10, 2018 - Skin Autofluorescence Predicts T2DM, Heart Disease, Mortality
December 10, 2018 - Largest autism sequencing study to date yields 102 genes associated with ASD
December 10, 2018 - Statins associated with low risk of side effects
December 10, 2018 - Study explores how schools address adolescent self-harming practices
December 10, 2018 - Pregnancy in adolescence linked to increased risks of complications in young mothers
December 10, 2018 - Risk Analysis publishes special issue on communicating about Zika virus
December 10, 2018 - Botox May Help Prevent Post-Op A-Fib
December 10, 2018 - African-American mothers rate boys higher for ADHD
December 10, 2018 - Graphic warning labels cancel out cigarettes’ appeal to young people
December 10, 2018 - Australian researchers to study gas inhalational anaesthetic and likelihood of cancer return
December 10, 2018 - Individual neurons located within the brain have implications for psychiatric diseases
December 10, 2018 - Researchers improve bariatric surgery scoring system to extend prediction time for diabetic remission
December 10, 2018 - HPV type 16 or 18 associated with cervical cancer risk in young women
December 10, 2018 - Cervical cancer risk is higher in women with positive HPV, but no cellular abnormalities
December 10, 2018 - Combo therapy not needed if low RA disease activity achieved
December 10, 2018 - Novel therapeutic targets based on biology of aging show promise for Alzheimer’s disease
December 10, 2018 - UC San Diego professor receives NCI Outstanding Investigator Award for cancer research
December 10, 2018 - Study evaluates placental mesenchymal stem cell sheets for myocardial repair and regeneration
December 10, 2018 - Blueprint Medicines Announces Updated Results from Ongoing EXPLORER Clinical Trial of Avapritinib Demonstrating Broad Clinical Activity and Significant Symptom Reductions in Patients with Systemic Mastocytosis
December 10, 2018 - Study clarifies ApoE4’s role in dementia
December 10, 2018 - Eating disorders now a top priority with Australian Government
December 10, 2018 - Neuronal activity in the brain allows prediction of risky or safe decisions
December 10, 2018 - FDA Alerts Health Care Professionals and Patients Not to Use Drug Products Intended to be Sterile from Promise Pharmacy
December 10, 2018 - Improving dementia care and treatment saves thousands of pounds in care homes
December 10, 2018 - Heroin-assisted treatment can offer benefits, reduce harms
December 10, 2018 - People covered by Michigan’s expanded Medicaid program report improvements in health, finds study
December 10, 2018 - Hazelnuts improve micronutrient levels in older adults
December 9, 2018 - History of Partner Violence Tied to Menopause Symptoms
December 9, 2018 - Clean Up Safely After a Disaster|Natural Disasters and Severe Weather
December 9, 2018 - Drug wholesalers drove fentanyl’s deadly rise, report concludes
December 9, 2018 - Deprescribing could help manage polypharmacy in older adults
December 9, 2018 - Retraction of article “Joy of cooking too much” from journal
December 9, 2018 - FDA Warns of Rare Stroke Risk With MS Drug Lemtrada (Alemtuzumab)
December 9, 2018 - Feds say heroin, fentanyl remain biggest drug threat to US
December 9, 2018 - Eliminating microglia can reverse some aspects of stress sensitization, study shows
December 9, 2018 - New genetic insight could help treat rare debilitating heart and lung condition
December 9, 2018 - MiRagen Therapeutics Announces Final Safety, Biodistribution and Clinical Efficacy Data From Phase 1 Cobomarsen Clinical Trial in Patients With Mycosis Fungoides
December 9, 2018 - Work with your doctor to weigh pros, cons of treatment options for hyperthyroidism
December 9, 2018 - CWRU researcher secures $14.6 million funding for genetic study into Alzheimer’s disease
December 9, 2018 - High intensity statin treatment and adherence could save more lives
December 9, 2018 - Surgery patients use only 1/4 of prescribed opioids, and prescription size matters
December 9, 2018 - AXT offers Phi Optics upgrade to QPI systems for inverted light microscopes
December 9, 2018 - New booklet could help improve conditions of young pupils with albinism
December 9, 2018 - Few Physicians Work in Practices That Use Telemedicine
December 9, 2018 - Older Adults and Oral Health
December 9, 2018 - Health utility values improve after septorhinoplasty
December 9, 2018 - New EU-funded project provides insight into how the brain develops
December 9, 2018 - Expanded use of tele-emergency services can help strengthen rural hospitals
December 9, 2018 - Infections in the Young May Be Tied to Risk for Mental Illness: Study
December 9, 2018 - Profile: Native Hawaiians and Pacific Islanders
December 9, 2018 - Snoring poses greater cardiac risk to women
December 9, 2018 - Researcher takes further steps in understanding how and why cute aggression occurs
December 9, 2018 - Researchers create new light-activated tools for controlling neurons
December 9, 2018 - Spinal cord injury disrupts the body’s internal clock, study shows
December 9, 2018 - Babies recognize nested structures similar to our grammar
December 9, 2018 - UT Austin researcher receives $2.5 million CZI grant for neurodegenerative disease research
December 9, 2018 - Sleep problems found to be prevalent and increasing among college students
December 9, 2018 - Study reveals why some children are susceptible to the effects of maltreatment
December 9, 2018 - Study investigates influence of different opioids on driving performance
December 9, 2018 - Jazz Pharmaceuticals Announces First Patient Enrolled in Phase 3 Clinical Trial Evaluating JZP-258 for the Treatment of Idiopathic Hypersomnia
December 9, 2018 - Eliminating microglia prevents heightened immune sensitivity after stress
December 9, 2018 - Boys with social difficulties are at greatest risk of early substance use
December 9, 2018 - ‘Wrong’ connective tissue cells linked to worse prognosis in breast cancer patients
December 8, 2018 - Chronic, refractory schizophrenia patients benefit from targeted cognitive training
December 8, 2018 - Advertising in kids’ apps more prevalent than parents may realize
December 8, 2018 - New way to trace the transmission histories of rare genetic diseases
December 8, 2018 - ASH: A+CHP Bests CHOP for Peripheral T-Cell Lymphoma
December 8, 2018 - Results of pediatric genomic epilepsy tests often reclassified
December 8, 2018 - New way of controlling HIV latency to completely eradicate the virus
December 8, 2018 - Phasefocus to showcase the Livecyte 2 at ASCB
December 8, 2018 - KHN’s ‘What the Health?’ Is health spending the next big political issue?
December 8, 2018 - Mussels take in microplastic pollution fibers and flush most of them out again
December 8, 2018 - AHA: How to Stop Smoking … for Good
AI matched, outperformed radiologists in screening X-rays for certain diseases | News Center

AI matched, outperformed radiologists in screening X-rays for certain diseases | News Center

image_pdfDownload PDFimage_print

“Usually, we see AI algorithms that can detect a brain hemorrhage or a wrist fracture — a very narrow scope for single-use cases,” said Matthew Lungren, MD, MPH, assistant professor of radiology. “But here we’re talking about 14 different pathologies analyzed simultaneously, and it’s all through one algorithm.”

The goal, Lungren said, is to eventually leverage these algorithms to reliably and quickly scan a wide range of image-based medical exams for signs of disease without the backup of professional radiologists. And while that may sound disconcerting, the technology could eventually serve as high-quality digital “consultations” to resource-deprived regions of the world that wouldn’t otherwise have access to a radiologist’s expertise. Likewise, there’s an important role for AI in fully developed health care systems too, Lungren added. Algorithms like CheXNeXt could one day expedite care, empowering primary care doctors to make informed decisions about X-ray diagnostics faster, without having to wait for a radiologist.

“We’re seeking opportunities to get our algorithm trained and validated in a variety of settings to explore both its strengths and blind spots,” said graduate student Pranav Rajpurkar. “The algorithm has evaluated over 100,000 X-rays so far, but now we want to know how well it would do if we showed it a million X-rays — and not just from one hospital, but from hospitals around the world.”

A paper detailing the findings of the study was published online Nov. 20 in PLOS Medicine. Lungren and Andrew Ng, PhD, adjunct professor of computer science at Stanford, share senior authorship. Rajpurkar and fellow graduate student Jeremy Irvin are the lead authors.

Practice makes perfect

Lungren and Ng’s diagnostic algorithm has been in development for more than a year. It builds on their work on a previous iteration of the technology that could outperform radiologists when diagnosing pneumonia from a chest X-ray. Now, they’ve boosted the abilities of the algorithm to flag 14 ailments, including masses, enlarged hearts and collapsed lungs. For 11 of the 14 pathologies, the algorithm made diagnoses with the accuracy of radiologists or better.

Back in the summer of 2017, the National Institutes of Health released a set of hundreds of thousands of X-rays. Since then, there’s been a mad dash for computer scientists and radiologists working in artificial intelligence to deliver the best possible algorithm for chest X-ray diagnostics.

We need to be thinking about how far we can push these AI models to improve the lives of patients anywhere in the world.

The scientists used about 112,000 X-rays to train the algorithm. A panel of three radiologists then reviewed a different set of 420 X-rays, one by one, for the 14 pathologies. Their conclusions served as a “ground truth”— a diagnosis that experts agree is the most accurate assessment — for each scan. This set would eventually be used to test how well the algorithm had learned the telltale signs of disease in an X-ray. It also allowed the team of researchers to see how well the algorithm performed compared to the radiologists.

“We treated the algorithm like it was a student; the NIH data set was the material we used to teach the student, and the 420 images were like the final exam,” Lungren said. To further evaluate the performance of the algorithm compared with human experts, the scientists asked an additional nine radiologists from multiple institutions to also take the same “final exam.”

“That’s another factor that elevates this research,” Lungren said. “We weren’t just comparing this against other algorithms out there; we were comparing this model against practicing radiologists.”

What’s more, to read all 420 X-rays, the radiologists took about three hours on average, while the algorithm scanned and diagnosed all pathologies in about 90 seconds.

Next stop: the clinic

Now, Lungren said, his team is working on a subsequent version of CheXNeXt that will bring the researchers even closer to in-clinic testing. The algorithm isn’t ready for that just yet, but Lungren hopes that it will eventually help expedite the X-ray-reading process for doctors diagnosing urgent care or emergency patients who come in with a cough.

“I could see this working in a few ways. The algorithm 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. For example, if a patient’s physical exam and lab results were consistent with pneumonia, and the algorithm diagnosed pneumonia on the patient’s X-ray, then that’s a pretty high-confidence diagnosis and the physician could provide care right away for the condition. Importantly, in this scenario, there would be no need to wait for a radiologist. But if the algorithm came up with a different diagnosis, the primary care doctor could take a closer look at the X-ray or consult with a radiologist to make the final call.

“We should be building AI algorithms to be as good or better than the gold standard of human, expert physicians. Now, I’m not expecting AI to replace radiologists any time soon, but we are not truly pushing the limits of this technology if we’re just aiming to enhance existing radiologist workflows,” Lungren said. “Instead, we need to be thinking about how far we can push these AI models to improve the lives of patients anywhere in the world.”

Other Stanford authors of the study are biostatistician Robyn Ball, PhD; undergraduate student Kaylie Zhu; former research assistant Brandon Yang; data scientist Hershel Mehta; research assistants Tony Duan and Daisy Ding; former research assistant Aarti Bagul; professor of radiology and of medicine Curtis Langlotz, PhD; assistant professor of radiology Bhavik Patel, MD; associate professor of radiology Kristen Yeom, MD; research associate Katie Shpanskaya; associate professor of radiology Francis Blackenberg, MD; clinical assistant professor of radiology Jayne Seekins, MD; clinical associate professor of radiology Safwan Halabi, MD; and clinical assistant professor of radiology Evan Zucker, MD.

Researchers from Duke University and from the University of Colorado also contributed to the study.

Lungren is a member of Stanford Bio-X, the Stanford Child Health Research Institute and the Stanford Cancer Institute.

Stanford’s departments of Radiology and of Computer Science along with the Stanford Center for Artificial Intelligence in Medicine & Imaging supported the work.

Tagged with:

About author

Related Articles