Breaking News
October 19, 2018 - New urea sorbent could speed up the development of wearable artificial kidney
October 19, 2018 - Intensive care patients’ muscles less able to use fats for energy
October 19, 2018 - FDA Advisory Committee Recommends Approval of Dsuvia for the Treatment of Moderate-to-Severe Acute Pain
October 19, 2018 - 48,XXXY syndrome – Genetics Home Reference
October 19, 2018 - Physical exercise improves the elimination of toxic proteins from muscles
October 19, 2018 - How a new system improved wait times for Stanford kidney transplant patients
October 19, 2018 - Nutrition has bigger positive impact on bone mass and strength than exercise
October 19, 2018 - Study finds lack of progress in media representation of nurses over last 20 years
October 19, 2018 - Many people have trouble understanding differences between OCD and OCPD
October 19, 2018 - New family planning app found to be as effective as modern methods
October 19, 2018 - Gastric Banding, Metformin Similar for Improving Glycemia
October 19, 2018 - Physiologist publishes findings on the role of the protein titin in muscle contraction
October 19, 2018 - What digital health companies need to do to succeed
October 19, 2018 - N. Carolina Sees Alarming Spike in Heart Infections Among Opioid Users
October 19, 2018 - Video monitoring of TB therapy works well in urban and rural areas
October 19, 2018 - Determining acid-neutralizing capacity for OTC antacids
October 19, 2018 - Males who spend more time taking care of kids have greater reproductive success
October 18, 2018 - Study to explore bioethics of brain organoids
October 18, 2018 - Environmental conditions may drive development of multiple sclerosis
October 18, 2018 - Genetically modifying zebrafish provides more accurate disease models
October 18, 2018 - Purdue Pharma, Eisai announce positive topline results from Phase 3 study of lemborexant
October 18, 2018 - 5 Strength-Training Mistakes to Avoid
October 18, 2018 - Immune system’s balancing act keeps bowel disease in check
October 18, 2018 - Anti-inflammatory drug effective for treating lymphedema symptoms | News Center
October 18, 2018 - Keeping Your Voice Young
October 18, 2018 - One-time universal screening recommended to tackle increase in hepatitis C
October 18, 2018 - Researchers to develop new stem cell-based strategies for treating vision disorders
October 18, 2018 - Detecting epigenetic signature may help people stay ahead of inflammatory bowel disease
October 18, 2018 - Understanding AFib: Slowing down the dancing heart
October 18, 2018 - Using NMR to Reduce Fraud
October 18, 2018 - New automated model identifies dense breast tissue in mammograms
October 18, 2018 - Mysterious polio-like illness baffles medical experts while frightening parents
October 18, 2018 - Cases of Acute Flaccid Myelitis on the rise across U.S.
October 18, 2018 - Dietary fiber reduces brain inflammation during aging
October 18, 2018 - New tool could help prioritize recovery efforts for the poorest hit by natural disasters
October 18, 2018 - Hundreds of dietary supplements shown to contain unapproved drugs
October 18, 2018 - Active Pharmaceuticals ID’d in >700 Dietary Supplements
October 18, 2018 - Cell death protein also damps inflammation
October 18, 2018 - AI pathology diagnostic tool developed using deep learning technology from Olympus
October 18, 2018 - Health Highlights: Oct. 15, 2018
October 18, 2018 - Largest study of ‘post-treatment controllers’ reveals clues about HIV remission
October 18, 2018 - Bad Blood in Silicon Valley: A conversation with John Carreyrou
October 18, 2018 - ANTRUK’s Annual Lecture sends out message on shortage of funds for antibiotic research
October 18, 2018 - NAM special publication outlines steps to ensure interoperability of health care systems
October 18, 2018 - Novel method uses just a drop of blood to monitor effect of lung cancer therapy
October 18, 2018 - New blood test could spare cancer patients from unnecessary chemotherapy
October 18, 2018 - Training young researchers to work with data volumes arising in the health sector
October 18, 2018 - New Metrohm IC method is reliable and convenient to use for zinc oxide assay
October 18, 2018 - Global AIDS, TB fight needs more money: health fund
October 18, 2018 - Understanding the forces that cause sports concussions
October 18, 2018 - Research points to new target for treating periodontitis
October 18, 2018 - New tool improves assessment of postpartum depression symptoms
October 18, 2018 - From Biopsy to Diagnosis
October 18, 2018 - Sexual harassment and assault linked to worse physical/mental health among midlife women
October 18, 2018 - Stumped by medical school? A Q&A with a learning specialist
October 18, 2018 - Report predicts life expectancy in 2040, Spain comes out on top
October 18, 2018 - Self-lubricating condoms may help raise condom usage
October 18, 2018 - Targeting immune checkpoints in microglia could reduce out-of-control neuroinflammation
October 18, 2018 - Study finds changes in antiepileptic drug metabolism during different trimesters of pregnancy
October 18, 2018 - Autonomic nervous system directly controls stem cell proliferation, study shows
October 18, 2018 - FDA Approves Talzenna (talazoparib) for gBRCAm HER2-Negative Locally Advanced or Metastatic Breast Cancer
October 18, 2018 - Sleeping Beauty technique helps identify genes responsible for NAFLD-associated liver cancer
October 18, 2018 - Many U.S. adults confused about primary care, study shows
October 18, 2018 - UC researcher focuses on light-mediated therapies to target breast cancer
October 18, 2018 - With philanthropic gifts, Stanford poised to make major advances in neurosciences | News Center
October 18, 2018 - Mice study shows antibiotics are not always necessary to cure sepsis
October 18, 2018 - Researchers discover why heart contractions are weaker in individuals with HCM
October 18, 2018 - Participation in organized sport during childhood may have long-term skeletal benefits
October 18, 2018 - Probiotic/antibiotic combination could eradicate drug-resistant bacteria
October 17, 2018 - More Socioeconomic Challenges for Hispanic Women With HIV
October 17, 2018 - 49,XXXXY syndrome – Genetics Home Reference
October 17, 2018 - Scientists uncover possible new causes of Tourette syndrome
October 17, 2018 - Girl undergoes unusual heart surgery after compassionate-use exemption | News Center
October 17, 2018 - Health Issues That Are Sometimes Mistaken for Gluten Sensitivity
October 17, 2018 - Elective induction of labor at 39 weeks may be beneficial option for women and their babies
October 17, 2018 - New smart watch algorithms can accurately monitor wearers’ sleep patterns
October 17, 2018 - Researchers demonstrate epigenetic memory transmission via sperm
October 17, 2018 - FDA, DHS announce memorandum of agreement to address cybersecurity in medical devices
October 17, 2018 - Health Tip: Know the Risks of Chicken Pox
October 17, 2018 - Immunotherapy effective against hereditary melanoma
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