Breaking News
December 12, 2018 - Study provides new information regarding microRNA function in cellular homeostasis of zebrafish
December 12, 2018 - Study provides new understanding of mysterious ‘hereditary swelling’
December 12, 2018 - Researchers shed new light on how to combat Shiga and ricin toxins
December 12, 2018 - Pregnant Women Commonly Refuse Vaccines
December 12, 2018 - Drug treatment could offer new hope for some patients with brain bleeding
December 12, 2018 - Health care financial burden of animal-related injuries is growing, study says
December 12, 2018 - Macrophage cells could help repair the heart following a heart attack, study finds
December 12, 2018 - Researchers develop new system for efficiently producing human norovirus
December 12, 2018 - New artificial intelligence-based system to differentiate between different types of cancer cells
December 11, 2018 - Healthy Lifestyle Lowers Odds of Breast Cancer’s Return
December 11, 2018 - New research identifies two genes linked to serious congenital heart condition
December 11, 2018 - NIH Director talks science, STEM careers with preteens
December 11, 2018 - Disabling a Cellular Antivirus System Could Improve Gene Therapy
December 11, 2018 - New tool swiftly provides accurate measure of patients’ cognitive difficulties
December 11, 2018 - NICE releases new guidelines for diagnosis and management of COPD
December 11, 2018 - Without Obamacare penalty, think it’ll be nice to drop your plan? Better think twice
December 11, 2018 - Researchers capture high-resolution X-ray and NMR image of key immune regulator
December 11, 2018 - Natural flavonoid is effective at treating leishmanisis infections, study shows
December 11, 2018 - Avoidant grievers unconsciously monitor and block mind-wandering contents, study shows
December 11, 2018 - Study identifies how hantaviruses infect lung cells
December 11, 2018 - Improving PTSD care through genetics
December 11, 2018 - Dermatology providers show interest in recommending cannabinoids to patients
December 11, 2018 - Researchers to study effects of electroconvulsive therapy on Alzheimer’s patients with aggression
December 11, 2018 - Four dried fruits have lower glycemic index than starchy foods, study finds
December 11, 2018 - Optimization of drug dose sizes can reduce pharmaceutical wastage
December 11, 2018 - Ultrarestrictive opioid prescribing strategy linked with reduction in number of pills dispensed
December 11, 2018 - PET scans to optimize tuberculosis meningitis treatments and personalize care, study finds
December 11, 2018 - Researchers aim to identify and target high blood pressure indicators
December 11, 2018 - Researchers identify immune cell subset that may drive chronic inflammation
December 11, 2018 - Ezogabine treatment reduces motor neuron excitability in ALS patients, study shows
December 11, 2018 - One implant, two prices. It depends on who’s paying.
December 11, 2018 - Standardizing feeding practices improves growth trends for micro-preemies
December 11, 2018 - COPD Tied to Obesity in Male, Female Never-Smokers
December 11, 2018 - Flossing: Information for Caregivers
December 11, 2018 - Does breastfeeding hormone protect against type 2 diabetes?
December 11, 2018 - Educating future doctors to prescribe physical activity for their patients
December 11, 2018 - Krystal 2000 microplate design improves fluorescence and luminescence measurement
December 11, 2018 - FDA clears mobile medical app to help increase retention in recovery program for opioid use disorder
December 11, 2018 - Overcoming Challenges in High-Speed Centrifugation Experiments
December 11, 2018 - Study shows link between neighborhoods’ socioeconomic status and dietary choices
December 11, 2018 - Lower BMI before obesity surgery predicts greater post-operative weight loss, study finds
December 11, 2018 - Obesity May Be Driving Rise in Uterine Cancers
December 11, 2018 - Antioxidants may prevent cognitive impairment in diabetes
December 11, 2018 - Study discovers link between meditation and how individuals respond to feedback
December 11, 2018 - Researchers identify potential diagnostic tool for Alzheimer’s disease
December 11, 2018 - Oral cancer prognostic signature identified
December 11, 2018 - How Can I Find Out What Caused My Miscarriage?
December 11, 2018 - Novel personalized medicine tool for assessing inherited colorectal cancer syndrome risk developed
December 11, 2018 - Study uncovers 11 new genes associated with epilepsy
December 11, 2018 - Filling research gaps could help develop more disability-inclusive workplaces
December 11, 2018 - Cartilage tissue engineering brings good news for patients with cartilage defects
December 11, 2018 - Novel 3D printing workflow helps predict leaky heart valves
December 11, 2018 - Imagination can help overcome fear and anxiety-related disorders, shows study
December 11, 2018 - Are caries linked to political regime?
December 11, 2018 - Leader in Diabetes Clinical Trials Wins Naomi Berrie Award
December 11, 2018 - Scientists discover cellular mechanism that triggers pneumonia in humans
December 11, 2018 - Increasing mental health problems related to drug use in over 55’s
December 11, 2018 - High-intensity interval exercise could help combat cognitive dysfunction in obese people
December 11, 2018 - Annual flu shot can save lives of heart failure patients
December 11, 2018 - Researchers compare health outcomes for VA and non-VA hospitals
December 11, 2018 - Recommendations Developed for Psoriatic Arthritis Treatment
December 11, 2018 - Genetic analysis links obesity with diabetes, coronary artery disease
December 11, 2018 - Study shows that having genetic information can affect how the body responds
December 11, 2018 - UNAIDS Report: 9 Million Are Likely HIV Positive And Don't Know It
December 11, 2018 - Lund University researchers succeed in obtaining dendritic cells by direct reprogramming
December 11, 2018 - Breast tumors recruit bone marrow cells to boost their growth, study reveals
December 11, 2018 - Updated breast cancer screening guideline highlights importance of shared decision-making
December 11, 2018 - EHR-related stress associated with physician burnout
December 11, 2018 - AHA: 12-Year-Old Heart Defect Survivor Inspires NFL Player’s Foundation
December 11, 2018 - Breast cancer patients who take heart drug with trastuzumab have less heart damage
December 11, 2018 - Providing aid to those humans – and animals – affected by the California fires
December 11, 2018 - Even without proof, CBD is finding a niche as a cure-all
December 11, 2018 - Drawing leads to better memory than writing
December 11, 2018 - Researchers report novel findings on plant hormone
December 10, 2018 - A Tale of Two Labels
December 10, 2018 - Triple combination cancer immunotherapy improves outcomes in preclinical melanoma model
December 10, 2018 - A 14-year-old explains what it’s like to get a new heart
December 10, 2018 - Team Players Honored with 2018 Baton Awards
December 10, 2018 - Global report highlights how the changing world is affecting children’s physical activity levels
December 10, 2018 - Genes play a role in physical activity and sleep
AI could help veterinarians code their notes

AI could help veterinarians code their notes

image_pdfDownload PDFimage_print

As artificial intelligence continues to find inlets into human medicine, James Zou, PhD, assistant professor of biomedical data science, has found another use for AI: animal medicine.

When pets visit a veterinarian, doctors type out notes in paragraph form to document the visit — there’s no systematic or widespread infrastructure in place for pet electronic health records. And while hand-captured notes work fine to document that one visit, in that one clinic, it limits how the data can be used and shared.

“Unlike human electronic health records, there aren’t standardized ways to map free text typed on a computer into codes that denote a specific type of disease,” said Zou. “So there are millions of vet clinical records that are essentially wasted because they’re so cumbersome to work with. Clinics don’t have the infrastructure to extract information from these medical records, but there’s a lot of really interesting information in them and they might even come to bear on human health.”

Now, Zou and his team have devised a solution rooted in artificial intelligence, called DeepTag. DeepTag is an algorithm that essentially reads the typed-out notes from a vet and predicts specific diseases that are relevant for the animal. It boils the paragraph of medical notes into codes that represent certain ailments, symptoms or diseases.

A paper describing DeepTag appears in npg Digital Medicine. Allen Nie, a machine learning researcher, is the lead author.

There’s been a tremendous amount of progress in AI understanding and applying natural language, said Zou. “AI is now much better at understanding human languages and being able to respond to them, and we’re leveraging that progress to build algorithms that can scan across the paragraph to actually read the clinical notes and interpret each word,” explained Zou. “We’re not explicitly telling the algorithm what words are associated with what disease, instead, it’s finding the key words that are associated with specific diagnoses.”

In training the algorithm, Zou collaborated with the College of Veterinary Medicine at Colorado State University, where a group of veterinary experts annotated more than 100,000 clinical notes, assigning disease codes to each case. Nie used that dataset to “teach” the algorithm the types of notes that paired with a particular disease. Then, the group further validated the algorithm’s accuracy by testing it on pet clinical data collected from private veterinarian offices.

Broadly speaking, DeepTag would allow veterinarians to track the prevalence of disease in pets, and in the future, could even be a tool to track pet clinical drug trials. After all, we can learn a lot from the maladies of a malamute or disorders of a dachshund, Zou said.

Before a drug makes it to clinical trial in humans, it’s typically tested in mice or rats for efficacy and safety. But the biology of small rodents can be quite different from that of a person, whereas a larger mammal, like a dog, can more accurately reflect how a human might respond to a treatment.

Likewise, just as is the case for sick people, there’s sometimes a lack of sanctioned options to treat disease in pets, and clinical trials would be their best bet at recovery. But until now there’s little infrastructure to keep tabs on how animals fair on new therapies. This, Zou hopes, is where DeepTag could open up new options.

“Dogs, which were the majority of patients that we documented using DeepTag, are a very good candidates for many of the drugs scientists develop for humans,” he said. “And there’s a growing interest in pharmacology and biotechnology to try to test, for example, new cancer treatments in dogs — it could be a win for both humans and their pets.”

Since the paper published, Zou’s been discussing applying the DeepTag algorithm to large vet clinics around the country, and locally in the San Francisco Bay Area. Soon, Zou said, their team will have a publicly-available platform that veterinarians anywhere in the world can use. “Once the platform is online, any veterinarian could go and use the platform to annotate their notes and see the results in real time.”

Photo by U.S. Air Force Senior Airman Rito Smith

Tagged with:

About author

Related Articles