Breaking News
May 23, 2018 - Malaria-causing parasite seeks refuge inside the liver to replicate and survive
May 23, 2018 - Slower rates of stimulation may be more effective in brain therapy, suggests research
May 23, 2018 - Study finds connection between one partner’s BMI and other spouse’s risk of developing diabetes
May 23, 2018 - Mapping the Genes Responsible for Pluripotency
May 23, 2018 - FDA Alert: Homeopathic Teething Drops, Nausea Drops, Intestinal Colic Drops, Stomach Calm, Expectorant Cough Syrup, Silver-Zinc Throat Spray, and Argentum Elixir by MBI Distributing: Recall
May 23, 2018 - Genetic fixer-uppers may predict bladder cancer prognosis
May 23, 2018 - Investigational technology could increase donor organ supply for lung transplants
May 23, 2018 - Prediabetic patients with OSA could lower their resting heart rates by using CPAP
May 23, 2018 - Schizophrenics’ blood samples feature genetic material from more types of microorganisms
May 23, 2018 - Subtle hearing deficits can change the brains of young people
May 23, 2018 - New study shows increased rates of hospitalization for suicide among youths
May 23, 2018 - Proportion of Drug-Intoxicated Organ Donors on the Rise in U.S.
May 23, 2018 - Using virtual biopsies to improve melanoma detection
May 23, 2018 - Compassion meditation training may increase brain’s resilience to suffering of other people
May 23, 2018 - New AAD PSA uses social media imagery to highlight tanning hazards
May 23, 2018 - Medicaid expansion linked to reduction in ICU utilization
May 23, 2018 - Proteins moderating nicotine dependence may help fat cells burn energy
May 23, 2018 - Researchers identify mechanisms that regulate mammary gland development
May 23, 2018 - ‘Low-Alcohol’ Booze Labels May Backfire
May 23, 2018 - New research shows that children with autism are able to create imaginary friends
May 23, 2018 - New technology could make prosthetic use more intuitive and reliable
May 23, 2018 - Researchers develop injectable bandage to stop fatal blood loss, activate wound healing
May 23, 2018 - Exercising for 4-5 days per week is needed to keep the heart young
May 23, 2018 - Porvair Sciences offers wide range of reagent reservoirs for use with automated liquid handling systems
May 23, 2018 - New study unravels secrets of HIV’s persistence
May 23, 2018 - IDF launches initiative to improve health services for displaced people with diabetes
May 23, 2018 - Maintaining healthy weight between early adulthood and middle age could help avoid diabetes
May 23, 2018 - DNA vaccine shows promise for colorectal cancer
May 23, 2018 - Abnormal brain connections seen in preschoolers with autism
May 23, 2018 - Study finds increase in number of calls to US Poison Control Centers about ADHD medication exposures
May 23, 2018 - Yoghurt before a meal packed with health benefits
May 23, 2018 - New tool predicts the lifetime risk of Alzheimer’s
May 23, 2018 - Scientists reveal mechanisms that may help preterm infants extend nephron development window
May 23, 2018 - Unnecessary antibiotic use for asthma exacerbations linked to increased hospital stays, costs
May 23, 2018 - Quitting cigarettes linked to better lung health than long-term light smoking
May 23, 2018 - Researchers shed light on how androgen deprivation therapy increases risk for cardiovascular mortality
May 23, 2018 - Ingesting blue dye tablet during colonoscopy aids in detecting difficult-to-see polyps
May 23, 2018 - Patients with low-back pain benefit from early physical therapy
May 23, 2018 - Researchers discover link between tuberculosis and Parkinson’s disease
May 23, 2018 - FDA Approves Doptelet (avatrombopag) for Chronic Liver Disease Patients with Thrombocytopenia who are Undergoing a Medical Procedure
May 23, 2018 - Is knee pain linked to depression?
May 23, 2018 - Research team uncovers new information that more accurately explains formation of tumors
May 23, 2018 - Brain stimulation shows promise in treating obesity by reducing food cravings
May 23, 2018 - Mediterranean diet may protect people from negative effects of air pollution
May 23, 2018 - Researcher aims to develop virtual biopsy tool for early melanoma detection
May 23, 2018 - Medical centers more willing to perform lung transplants for severe alcoholic hepatitis patients
May 23, 2018 - The brain may tune to social learning even at rest, finds study
May 23, 2018 - Eczema drug alleviates asthma symptoms and improves lung function
May 23, 2018 - Researchers to test two-pronged approach in humans to treat advanced colorectal cancer
May 23, 2018 - FDA Alert: Juluca, Tivicay, Triumeq (dolutegravir): FDA to Evaluate
May 23, 2018 - Neuroscientists say daily ibuprofen can prevent Alzheimer’s disease
May 23, 2018 - Scientists decipher workings of little-understood bacterial riboswitch
May 23, 2018 - Investigational drug offers hope of relief for celiac disease patients exposed to gluten
May 23, 2018 - PCI along with prescribed drugs better than medication alone for treating for people with heart disease
May 23, 2018 - ToolGen’s CRISPR/Cas9 gene editing platform improves T-cell anti-tumor activity in mouse model
May 22, 2018 - FDA approves new drug to treat thrombocytopenia in adults with chronic liver disease
May 22, 2018 - CSIRO study urges Australians to avoid junk protein foods for healthy weight loss
May 22, 2018 - Breath Test Shows Promise for Diagnosis of Esophagogastric CA
May 22, 2018 - Common class of drugs linked to dementia even when taken 20 years before diagnosis
May 22, 2018 - Optimal Biomarker Frequency for Biosensors
May 22, 2018 - Ethics of conducting clinical research during public health emergencies
May 22, 2018 - FDA Approves Aimovig (erenumab), The First Drug Aimed at Preventing Migraines
May 22, 2018 - Warning labels on alcohol containers highly deficient, new research shows
May 22, 2018 - Doctors publish comprehensive proposal to ensure universal access to safe, affordable medications
May 22, 2018 - When is insurance not really insurance? When you need pricey dental care.
May 22, 2018 - Thyroid tumors may be more susceptible to precisely targeted radiation treatment, suggests study
May 22, 2018 - Researchers uncover clues to early lung transplant failure
May 22, 2018 - Coagulation Factor Tests: MedlinePlus Lab Test Information
May 22, 2018 - Booze ads cause risky drinking in young people
May 22, 2018 - Are you and your primary care doc ready to talk about your DNA?
May 22, 2018 - UCI research team uncovers new unexpected mode of neurotransmitter-based communication
May 22, 2018 - Researcher develops nanoparticle-based tags to detect viruses and cancer with high sensitivity
May 22, 2018 - Researchers highlight need for transgender-inclusive healthcare providers
May 22, 2018 - Celgene to share new and updated data around novel hematological therapies
May 22, 2018 - Scientists identify cell types underlying schizophrenia
May 22, 2018 - ACR urges legislative action on access and cost barriers in rheumatologic care
May 22, 2018 - Study examines link between nicotine dependence and likelihood to quit smoking after lung cancer screening
May 22, 2018 - Experts highlight the need to move beyond conventional cost-effectiveness analysis
May 22, 2018 - PanOptica doses first patient in Phase 1/2 dose-ranging clinical trial of PAN-90806
May 22, 2018 - New report highlights danger of childhood drowning in open water
AI better than most human experts at detecting cause of preemie blindness

AI better than most human experts at detecting cause of preemie blindness

image_pdfDownload PDFimage_print
This image of an eye shows how twisted and dilated vessels of the retina can indicate retinopathy of prematurity, or ROP, the leading cause of childhood blindness. Credit: Michael Chiang/OHSU

An algorithm that uses artificial intelligence can automatically and more accurately diagnose a potentially devastating cause of childhood blindness than most expert physicians, a paper published in JAMA Ophthalmology suggests.

The finding could help prevent blindness in more babies with the disease, called retinopathy of prematurity, or ROP. Musician Stevie Wonder went blind due to this condition.

The algorithm accurately diagnosed the condition in images of infant eyes 91 percent of the time. On the other hand, a team of eight physicians with ROP expertise who examined the same images had an average accuracy rate of 82 percent.

“There’s a huge shortage of ophthalmologists who are trained and willing to diagnose ROP. This creates enormous gaps in care, even in the United States, and sadly leads too many children around the world to go undiagnosed,” said the study’s co-lead researcher, Michael Chiang, M.D., a professor of ophthalmology and medical informatics & clinical epidemiology in the OHSU School of Medicine and a pediatric ophthalmologist at the Elks Children’s Eye Clinic in the OHSU Casey Eye Institute.

“This algorithm distills the knowledge of ophthalmologists who are skilled at identifying ROP and puts it into a mathematical model so clinicians who may not have that same wealth of experience can still help babies receive a timely, accurate diagnosis,” said the other lead researcher, Jayashree Kalpathy-Cramer, Ph.D., of the Athinoula A. Martinos Center for Biomedical Imaging at Massachusetts General Hospital, who is also an associate professor of radiology at Harvard Medical School.

Leading cause of childhood blindness

Retinopathy of prematurity is caused by abnormal blood vessel growth near the retina, the light-sensitive portion in the back of an eye. The condition is common in premature babies and is the leading cause of childhood blindness globally.

The National Eye Institute of the National Institutes of Health reports that up to 16,000 U.S. babies experience retinopathy of prematurity to some degree, but only up to 600 become legally blind each year as a result. The condition is becoming more common as medical care for premature babies improves.

The disease is diagnosed by visually inspecting a baby’s eye. Physicians typically use a magnifying device that shines light into a baby’s dilated eye, but that approach can lead to variable and subjective diagnoses.

Computational smarts

Artificial intelligence, also called AI, enables machines to think like humans and is a growing field in health care. Last month, the FDA approved an AI device that detects diabetes-related eye disease. Others have tried developing computerized systems to diagnose retinopathy of prematurity, but none have been able to match the accuracy of visual diagnosis by physicians.

This algorithm specifically uses deep learning, a form of AI that mimics how humans perceive the world through vision, including identifying objects. The MGH researchers combined two existing AI models to create the algorithm, while the OHSU researchers developed extensive reference standards to train it.

They first trained the algorithm to identify retinal vessels in more than 5,000 pictures taken during infant visits to an ophthalmologist. Next, they trained it to differentiate between healthy and diseased vessels. Afterward, they compared the algorithm’s accuracy with that of trained experts who viewed the same images and discovered it performed better than most of the expert physicians.

The full research team is now working with a collaborator in India to see if the algorithm can diagnose ROP in Indian babies as well as it did for the group of primarily Caucasian babies involved in this study. They are also exploring whether the algorithm can diagnose the condition in images of other parts of the retina besides vessels. The ultimate goal is to enable physicians to incorporate the technology into their clinical practices.


Explore further:
Telemedicine provides accurate diagnosis of rare cause of blindness in preemies

More information:
James M. Brown et al, Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks, JAMA Ophthalmology (2018). DOI: 10.1001/jamaophthalmol.2018.1934

Journal reference:
JAMA Ophthalmology

Provided by:
Oregon Health & Science University

Tagged with:

About author

Related Articles