Call 413.540.1234 to
schedule an appointment
CONCERN/EAP: 413.534.2625
Billing questions? Call: 413.540.1212
CRISIS: 413.733.6661

Health Policy & Advocacy
Resources
Basic InformationMore InformationLatest News
Opioid Rxs Decreasing, But Not for All DoctorsAfter Chinese Infant Gene-Editing Scandal, U.S. Health Officials Join Call for a BanAre 'Inactive' Ingredients in Your Drugs Really So Harmless?Need to Be Vaccinated? Try Your Local PharmacyBystanders Key to Cutting Cardiac Arrest DeathsMany Black Americans Live in Trauma Care 'Deserts'FDA Issues Asbestos Warning About Some Claire's Cosmetic ProductsFDA to Crack Down on Retailers That Keep Selling Tobacco to KidsBlood Donation by Teen Girls May Raise Anemia RiskNurses' Long Hours, Moonlighting Could Pose Patient Safety RiskBerkeley's Efforts Suggest Soda Taxes Do Cut Soda SalesOpioid Overdose Deaths Quadruple, Centered in 8 StatesPayments for Research Can Lead to Lies: StudyFDA Aims to Strengthen Sunscreen RulesAre Primary Care Doctors Prepared to Discuss Cancer Treatment?FDA Fell Short in Preventing Fentanyl Abuse Crisis, Report ClaimsPrimary Care Doctors Help Boost Life Spans, But More Are NeededMore Car Crashes Tied to Drivers High on OpioidsPoor Whites Bear the Brunt of U.S. Opioid Crisis, Studies FindFDA to Tighten Oversight of SupplementsAs U.S. Measles Outbreaks Spread, Why Does 'Anti-Vax' Movement Persist?Even Brief EMS Delay Can Cost Lives After Car CrashHealth Tip: Know Your Family's Medical HistoryPatients With Primary Care Docs May Get Better Health CareMany Paramedics Ignore Hand Hygiene Rules, Study FindsIs Brexit a Health Hazard?Blood Donors Needed as Cold Weather Freezes U.S. SupplyMedical Scribes Could Help Improve ER CareAHA: Medical Experts 'Sound the Alarm' on Medical MisinformationWhite House Plan to Disclose Drug Prices May Not Drive Down Costs: StudyCan Artificial Intelligence Read X-Rays?Virtual Doctor Visits Get High Marks in New SurveyBig Pharma's Marketing to Docs Helped Trigger Opioid Crisis: StudyDisrupted Sleep Plagues Hospital Patients, But New Program Might HelpOpioid Prescriptions Almost Twice as Likely for Rural vs. Urban AmericansClimate Change Already Hurting Human Health, Review ShowsCalling All Blood Donors …Even Older Drugs Are Getting Steep Price Hikes, Study FindsAs Medical Marketing Soars, Is Regulation Needed?Radiation Doses From CT Scans Vary WidelyU.S. Leads Health Care Spending Among Richer Nations, But Gets LessIs Your State a Hotspot for Obesity-Linked Cancers?Health Tip: Choose the Right DoctorFDA Warns Companies on Dangerous, Unapproved Stem Cell TreatmentsMore U.S. Kids Dying From Guns, Car AccidentsRoad Rules on Smartphone Use Are Saving Bikers' Lives, TooAHA: Should Pacemakers, Defibrillators Be Recycled -- and Reused in Others?California Farm Tied to E. coli Outbreak Expands Recall Beyond Romaine LettuceHealth Tip: Use Medical Devices SafelyCalifornia Farm Implicated in Outbreak of E. coli Tied to Romaine Lettuce
Questions and AnswersLinksBook Reviews
Related Topics

Can Artificial Intelligence Read X-Rays?

HealthDay News
by -- Robert Preidt
Updated: Jan 23rd 2019

new article illustration

WEDNESDAY, Jan. 23, 2019 (HealthDay News) -- An artificial intelligence (AI) system can analyze chest X-rays and spot patients who should receive immediate care, researchers report.

The system could also reduce backlogs in hospitals someday. Chest X-rays account for 40 percent of all diagnostic imaging worldwide, and there can be large backlogs, according to the researchers.

"Currently, there are no systematic and automated ways to triage chest X-rays and bring those with critical and urgent findings to the top of the reporting pile," explained study co-author Giovanni Montana. He is formerly of King's College London and is now at the University of Warwick in Coventry, England.

Montana and his colleagues used more than 470,300 adult chest X-rays to develop an AI system that could identify unusual results.

The system's performance in prioritizing X-rays was assessed in a simulation using a separate set of 15,887 chest X-rays. All identifying information was removed from the X-rays to protect patient privacy.

The system was highly accurate in distinguished abnormal from normal chest X-rays, researchers said. Simulations showed that with the AI system, critical findings received an expert radiologist opinion within an average of 2.7 days, compared with an average of 11.2 days in actual practice.

The study results were published Jan. 22 in the journal Radiology.

"The initial results reported here are exciting as they demonstrate that an AI system can be successfully trained using a very large database of routinely acquired radiologic data," Montana said in a journal news release.

"With further clinical validation, this technology is expected to reduce a radiologist's workload by a significant amount by detecting all the normal exams, so more time can be spent on those requiring more attention," he added.

The researchers said the next step is to test a much larger number of X-rays and to conduct a multi-center study to assess the AI system's performance.

More information

The U.S. National Heart, Lung, and Blood Institute has more on chest X-rays.