Breaking News
August 18, 2018 - Microscopic insect odour detecting mechanisms discovered
August 18, 2018 - Researchers develop new approach to study how tuberculosis infects people
August 18, 2018 - FDA Approves Kalydeco (ivacaftor) for Cystic Fibrosis in Children Ages 12 to
August 18, 2018 - An ion channel differentiates newborn and mature neurons in the adult brain
August 18, 2018 - Socio-economic position associated with pregnant women’s exposure to environmental hazards
August 18, 2018 - Voters to settle dispute over ambulance employee break times
August 18, 2018 - AGA urges policymakers and stakeholders to improve affordability of drugs
August 18, 2018 - Increasing dietary protein may lower risk of diabetes in people with NAFLD
August 18, 2018 - New HIV therapy suppresses viral replication and increases immune cells in drug-resistant patients
August 18, 2018 - Broad Genetic Testing for NSCLC May Not Improve Survival
August 18, 2018 - Discovery opens door for synthetic opioids with less addictive qualities
August 18, 2018 - Transgenic rice plant extracts could help stop the spread of HIV
August 18, 2018 - Hologic’s Cynosure division partners with Porter Instrument to distribute nitrous oxide and oxygen system
August 18, 2018 - Two thyroid medications recalled by FDA
August 18, 2018 - Forecast Sees Abnormal Heat Worldwide Through 2022
August 18, 2018 - Childhood absence epilepsy – Genetics Home Reference
August 18, 2018 - Fearing hard Brexit, UK drugmakers stockpile to protect lives
August 18, 2018 - Discovery may help broaden the scope of defenses against HPV
August 18, 2018 - When they start thinking green, they see green
August 18, 2018 - Scientists introduce microfluidics-based chip for manipulation and analysis of single cells
August 18, 2018 - Researchers design new way to grow nose cells for treating spinal cord injuries
August 18, 2018 - New light shed on relationship between calorie-burning fat and muscle function
August 18, 2018 - Surgery Saturday Instagram series takes you inside Stanford’s OR
August 18, 2018 - Researchers uncover surprising new role for inhibition in the cerebellum
August 18, 2018 - Children have better nutrition when they live near forests, global study shows
August 18, 2018 - OHSU professor conducts clinical trial with artificial pancreas using Xeris’ liquid glucagon
August 18, 2018 - HSS takes young patients with physical challenges on a surfing trip
August 18, 2018 - Study shows electronic health records leave doctors and patients unsatisfied
August 18, 2018 - Study uncovers mechanism that affects multiplication of dengue virus lineage
August 18, 2018 - Theravance Biopharma Reports Positive Top-Line Four-Week Data from Phase 2 Trial of TD-9855 for the Treatment of Symptomatic Neurogenic Orthostatic Hypotension
August 18, 2018 - Animations prove effective in accurately measuring pain
August 18, 2018 - Three faculty members appointed to endowed positions | News Center
August 18, 2018 - New technique detects, measures, analyzes unevenly charged biomolecules
August 18, 2018 - Brief exposures to stressors can be beneficial to cells, shows study
August 18, 2018 - UTHealth-led survey shows much work remains to increase safety of e-health records
August 18, 2018 - Researchers use super-resolution microscope to unravel secrets of deadly Nipah virus
August 18, 2018 - Scientists identify pathways that reveal insights into mechanism of lung cancer etiology
August 18, 2018 - FDA approves marketing of brainsway deep transcranial magnetic stimulation system for OCD
August 17, 2018 - OUHSC gets $20 million grant to advance research and patient care for Oklahomans
August 17, 2018 - Sperm morphology differs depending on qualities of male bird
August 17, 2018 - Texas A&M researchers develop clay-based platform to grow blood vessels
August 17, 2018 - FDA Approves Expanded Indication for Orkambi (lumacaftor/ivacaftor) in Children Ages 2-5 Years
August 17, 2018 - Caring for Concussions | NIH News in Health
August 17, 2018 - Team explores diabetes drug’s ability to treat RSV infection
August 17, 2018 - New imaging technique can spot tuberculosis infection in an hour | News Center
August 17, 2018 - PolyU researchers design new self-fitting scaffold to induce bone regeneration
August 17, 2018 - CartiHeal and LSU Health successfully enroll first two patients in Agili-C IDE pivotal study
August 17, 2018 - Less-invasive options are slowing disease progression in glaucoma patients
August 17, 2018 - Researchers discover new promising target point for cancer and diabetes therapies
August 17, 2018 - Podcast: KHN’s ‘What the Health?’ See you in court!
August 17, 2018 - New mobile phone application enables early detection of cerebral ictus
August 17, 2018 - UK’s leading sight loss charity invites applications from brightest minds in ophthalmic research
August 17, 2018 - Alternative devices can help when autoinjectors are unavailable
August 17, 2018 - Researchers produce artificial placenta model that closely resembles natural organ
August 17, 2018 - Study offers possibility of squelching a focal epilepsy seizure before symptoms appear
August 17, 2018 - FDA Alert: Temporary Total Artificial Heart Companion 2 Driver System by SynCardia Systems: Letter to Health Care Providers
August 17, 2018 - New statewide program in North Dakota aims to stem opioid misuse
August 17, 2018 - Researchers discover why sepsis from a staph infection causes organ failure
August 17, 2018 - Stony Brook University’s new medical students start a transformative journey
August 17, 2018 - Revealed: The molecular mechanism underlying hypertrophic cardiomyopathy | News Center
August 17, 2018 - New modeling studies highlight urgent need for effective drug policy reforms to prevent HIV
August 17, 2018 - Research explores relationship between personal history of infectious fever and cancer risk
August 17, 2018 - Study finds rise in cases of progressive massive fibrosis among U.S. coal miners
August 17, 2018 - NEDBELS project examines impact of neurodiversity concept on legal systems
August 17, 2018 - Seeking solutions to treat scleroderma
August 17, 2018 - Statins may improve conditions of people with rare lung disease
August 17, 2018 - Study finds why some people with brain markers of Alzheimer’s never develop dementia
August 17, 2018 - Life Biosciences contributes $100,000 to fund its biomedical innovation course on aging
August 17, 2018 - Researchers develop a set of health outcome measures for children with complex medical situations
August 17, 2018 - Many Americans Not Being Assessed for Depression
August 17, 2018 - Scientists report setbacks in quest for AIDS cure
August 17, 2018 - Christopher Gardner busts myths about milk | News Center
August 17, 2018 - Bacterial activity in child’s mouth may serve as biomarkers for autism spectrum disorder
August 17, 2018 - Scripps Research scientists uncover new approach for treating thrombocytopenia
August 17, 2018 - Mathematical model shows the influence of human behavior on spread of infectious diseases
August 17, 2018 - Valley Hospital achieves Magnet recognition for fourth consecutive time
August 17, 2018 - Researchers describe link between poor oocyte development and oxidative stress in obese mice
August 17, 2018 - Hospitals battle for control over fast-growing heart-valve procedure
August 17, 2018 - AHA: Home-Delivered Meals Keep Heart Failure Patients Out of Hospital
August 17, 2018 - In Southern Mozambique, only half of people diagnosed with HIV enroll in medical care
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