Upgrade to Pro — share decks privately, control downloads, hide ads and more …

The Droid Will See You Now: Intelligent Systems and the Future of Healthcare

The Droid Will See You Now: Intelligent Systems and the Future of Healthcare

n this talk we will explore how Artificial Intelligence has and is being utilised in healthcare and medicine with a focus on how technology can help tackle the growing threat of chronic disease.

Nader Al-Shamma

September 05, 2016
Tweet

More Decks by Nader Al-Shamma

Other Decks in Technology

Transcript

  1. The Droid* Will See You Now. Intelligent Systems and the

    Future of Healthcare * A talk which has nothing to do with robots, droids or robotics… Nader Al-Shamma @nadershamma
  2. What to expect • About Me • Chronic Disease: Why

    We Should Care. • Artificial Intelligence (AI) and Machine Learning (ML) in Medicine and Healthcare. • The potential for AI to help us deal with Chronic Disease. • What the future holds.
  3. Why care about chronic disease? Long term chronic disease is

    one of the biggest challenges health systems, globally, will face during the twenty-first century.
  4. Why care about chronic disease? • What is a Chronic

    Disease? • 15 Million people in England have a long term incurable chronic disease. • UK has recognised threat of chronic Illness
  5. The many faces of chronic disease Most Common Illnesses: •

    cardiovascular diseases, mainly heart disease and stroke; • cancer; • chronic respiratory diseases; • diabetes; • others, such as mental disorders, vision and hearing • impairment, oral diseases, bone and joint disorders, and genetic disorders.
  6. The many faces of chronic disease Less Common but equally

    problematic diseases • Multiple sclerosis (MS) • Chronic fatigue syndrome (CFS) AKA Myalgic encephalomyelitis (ME) • Inflammatory Bowel Disease (IBD): ulcerative colitis and Crohn's disease • The list goes on…
  7. Artificial Intelligence and Medicine • Medicine application postulated since the

    1950s. • First used an assistive tool in 1976. • Tested for general clinical care and for specific ailments. • Can aid in diagnostics, prognostics and clinical decision making and management.
  8. AI in Clinical Care Johnson et al. (2016) conducted a

    thorough review of Machine Learning in critical care (ICU). The challenge: • Data comes from a variety of different departments • Data is often missing or corrupted • It’s an environment that lends itself to human error The Benefit • Machine Learning is effective in gathering, analysing, interpreting and presenting a wide range of clinical data in a relevant and useable format.
  9. AI in Clinical Care Bennet and Hauser (2013) AI in

    action: • AI framework built to determine the outcome of various treatments and policy decisions. • Laid the grounds for a clinical AI that could provide real time analysis and assistance with clinical decisions.
  10. AI in Diagnostics AI and ML is an effective diagnostic

    tool • Used to diagnose a wide variety of illnesses • Widely used in the diagnosis of cancer Machine Vision is used to asses biopsies
  11. AI in Diagnostics AI in action: • Artificial Neural Network

    (ANN) and a Probabilistic Neural Network (PNN) used to diagnose IBD. • The system had a 98.31% rate of accuracy.
  12. AI in Prognostics ANN in action • Used to determine

    the prognosis of patients prostate cancer. • Used to determine the outcome of treating Ulcerative Colitis with Cytoapheresis therapy.
  13. AI in Prognostics Machine Learning in action Machine Learning and

    medication • Random Forest used to determine success of thioprine treatments • Hidden Markov and Fuzzy logic can help determine proper antibiotic dosage. • Linear regression models used to determine heparin dose in ICU