AI Tool Could Identify Serious Illnesses through Photographs

AI Tool Could Identify Serious Illnesses through Photographs

An AI tool might be the new way to identify cancer types and genetic changes in lung tumors, according to a recent study by researchers at NYU School of Medicine. The tool can use just a photograph to identify serious diseases.

A new AI technology can identify cancer types and genetic changes in lung tumors, potentially speeding up the diagnosis and treatment process.

According to ANSI, this tool can use machine learning to analyze images of patients’ lung tumors and differentiate adenocarcinoma and squamous cell carcinoma with 97 percent accuracy. Interestingly enough, the study that tested this technology showed that the patients that the AI often mistyped were the ones that pathologists had also misdiagnosed, showing the difficulty in differentiating between these two lung cancer types.

With slightly less accurate, but still impressive accuracy, it was also able to identify the presence of abnormal versions of six genes linked to lung cancer in cells with 73 to 86 percent accuracy. The computer technology used the same technique — machine learning. This could significantly speed up the time before diagnosis, as current genetic tests can take weeks to return results.

AI is continuing to become more accepted in the medical field, as it creates opportunities for the medical field to be expand to underdeveloped areas and potentially improve outcomes of patients. This acceptance is relatively new, with the FDA issued their first approval of marketing a technology that uses AI to detect diabetes-related eye problems in 2018.

After the adoption of a new policy on the use of AI in healthcare, the American Medical Association said the policy aligns with their main principal – advancing the quadruple aim. This means it should “enhance the patient experience of care and outcomes, improve population health, reduce overall costs for the health care system while increasing value, and support the professional satisfaction of physicians and the health care team.”

While general AI standards have been around for a while, standards for AI in healthcare are in recent development along with the technology. AAMI recently released a position paper on the importance of standardization of AI in healthcare. “The emergence of artificial and machine learning in healthcare: Recommendations to support governance and regulation” analyzes AI standardization in healthcare techniques and provides recommendations for future standardization activities.

Download Center

HTML - No Current Item Deck
  • Safety Management Software - Free Demo

    IndustrySafe Safety Software’s comprehensive suite of modules help organizations to record and manage incidents, inspections, hazards, behavior based safety observations, and much more. Improve safety with an easy to use tool for tracking, notifying and reporting on key safety data.

  • The Top 5 Safety and Technology Trends to Watch in 2020

    Get the latest on trends you can expect to hear more about in 2020, including continued growth of mobile safety applications, wearable technology, and smart PPE; autonomous vehicles; and increased adoption of international safety standard, ISO 45001.

  • Get the Ultimate Guide to OSHA Recordkeeping

    OSHA’s Form 300A posting deadline is February 1! Are you prepared? To help answer your key recordkeeping questions, IndustrySafe put together this guide with critical compliance information.

  • The 4 Stages of an Incident Investigation

    So, your workplace has just experienced an incident resulting in the injury or illness of a worker. Now what? OSHA recommends that you conduct investigations of workplace incidents using a four-step system.

  • Why Is Near Miss Reporting Important?

    A near miss is an accident that's waiting to happen. Learn how to investigate these close calls and prevent more serious incidents from occurring in the future.

  • Industry Safe
comments powered by Disqus

OH&S Digital Edition

  • OHS Magazine Digital Edition - November December 2019

    November / December 2019


      Redefining Compliance for the Gas Detection Buyer
      Don't Trip Over the Basics
      What to Look for in Head-to-Toe PPE Solutions
      Effective PPE for Flammable Dust
    View This Issue