AI Enabling Tremendously Insightful Predictive Healthcare Analytics

There’s tremendous buzz in healthcare right now around AI accelerating solutions to large-scale problems that would otherwise take months, years, or decades to resolve. A key use for AI that we’re seeing is in predictive clinical analytics.

In healthcare, the precursor for any predictive analytics capability is having enough historical patient data to build models in order to identify and forecast future events. The Electronic Health Record (EHR) system is the foundation for that capability. However, to really understand how EHR’s can drive the predictive analytics of the future, let’s look back at the past to see how it all began.

The first hospital in the United States was founded in Pennsylvania in 1751, by Dr. Thomas Bond and Benjamin Franklin. While the field of medicine progressed rapidly during the intervening years, paper-based workflows were predominant in healthcare. Then from 2011 to 2017, the US government provided incentives for the adoption of EHR capabilities under Meaningful Use.  Now over 80 percent of healthcare organizations in the US have an EHR and thus also have access to the underlying base of data coming out of those EHRs.

Transforming those EHR data into AI-driven new insights is very promising. The healthcare analytics market is projecting to be worth $24.55B by 2021–up from $7.6B in 2016. Meanwhile, the global AI in Healthcare market is expecting to reach $7.9B, up from $667M in 2016.

Harnessing Healthcare Insights to Make Predictions

Rooted in the future of valuable data sets is the knowledge that AI-driven insights aren’t used just to practice medicine, but to use it in ways that allow prediction of adverse events or outcomes. Case in point, organizations like Sharp HealthCare in San Diego, have used EHR data to help identify patients who were at-risk of sudden decline and require a Rapid Response Team to react. The analytics work has shown predictability within 80 percent accuracy whether a Rapid Response call is likely to occur in the next hour. This enables Sharp Healthcare to optimize and proactively place Rapid Response Teams (RRT) at key points in hospitals and even potentially intervene before the situation becomes life-threatening.

Sharp HealthCare’s predictive analytics model, built by ProKarma, demonstrates how AI-driven models can tap into EHR data to enable predictive and proactive insights that are actionable – optimizing resources and improving patient care. The Rapid Response Team is but one example in a nearly endless list of predictive use cases:

  • Sepsis onset
  • Patients at-risk of hospital-acquired infections
  • Longer lengths of stay
  • Readmissions

Intel is passionate about harnessing AI’s potential in helping healthcare providers use data to fight disease and technology to tailor treatment. We’ve sponsored cancer-screening competitions on Kaggle using artificial intelligence to improve the precision and accuracy of those screenings. We’ve also worked with cardiologists to use machine-learning so they can rapidly discern between two serious heart conditions with similar symptoms.   And we’ve created open-source machine-learning algorithms that inform AI-driven pattern recognition and are excited to see more healthcare organizations benefit from this type of innovation.

There has never been a more exciting time for the future of healthcare than today. We’re ready to help you find the solution that’s right for your organization. Contact your Intel representative or visit today.

Published on Categories Health & Life SciencesTags , , , ,
Jennifer Esposito

About Jennifer Esposito

I believe that technology has the power to accelerate the transformation of healthcare and to improve health, quality of life, safety and security worldwide. Follow me on Twitter @Jennifer_Espo or Flipboard @jesposito. Executive with over 20 years of experience in the global healthcare IT, health and life sciences industry. Jennifer worked for over 13 years at GE Healthcare and is now General Manager of Health and Life Sciences at Intel Corporation. Jennifer has led commercial, sales, marketing and service operations, P&Ls as well as both upstream and downstream strategy and marketing. Jennifer has extensively traveled the globe, regularly meeting with top leaders in industry and government. She is active in initiatives on global health, identifying novel ways technology can be used to advance the SDGs and IHRs. Jennifer has a graduate degree in Epidemiology and Biostatistics from Dartmouth College. She is a full member of the American Association of Physicists in Medicine. Jennifer is a member of the Working Group on Digital Health for the Broadband Commission. She also serves on the Steering Committee of the Global Health Security Agenda Private Sector Roundtable and chairs their working group on Technology and Analytics.