By Mitali Maheshwari, Clinical Analyst
MD Buyline
With health care moving more toward value-based payment and shared risk, there is a need to become proactive, identifying disease conditions at an early stage and keeping the population healthier. While still an emerging field, health care analytics appears promising in promoting earlier diagnosis of disease, providing real-time insights about conditions, helping in cost reduction, and improving quality.
Analytical solutions range from traditional descriptive and predictive, to prescriptive modeling with artificial intelligence (AI) and machine learning. Many organizations have already adopted some form of descriptive (retrospective) analytics and are able to determine their sickest, highest-risk patient, and areas that need improvement. However, such analytics do not help in determination of evidence-based best practices.
Ad Statistics
Times Displayed: 173689
Times Visited: 3172 For those who need to move fast and expand clinical capabilities -- and would love new equipment -- the uCT 550 Advance offers a new fully configured 80-slice CT in up to 2 weeks with routine maintenance and parts and Software Upgrades for Life™ included.
Ginni Rometty, CEO of IBM, observed
in her HIMSS17 opening keynote that this is a cognitive era, and industry needs to make every effort to move toward more advanced forms of analytics and artificial intelligence that can provide insights about interventions. She also insisted that AI is not there to replace caregivers, but rather to help them by providing the right information at the right time in the right format. “It is not AI or caregiver, but AI and caregiver,” she said.
More and more data is becoming available in digital format with the adoption of electronic health records (EHR). Data is also becoming available from health/activity monitoring devices and wearable items. Now that health care has fuel to build analytical models, industry needs to find the best ways to derive value from this collected data and transform it into actionable clinical and operational information. HIMSS17 showcased how industry is making efforts to make use of this available data to build up algorithms and machine learning. Industry is also recognizing a need for collaborations and an open AI platform to optimize collective efforts.
Availability of usable structured data and a platform capable of analyzing big data are still big challenges in applying advanced analytics to health care. Some vendors have built their own data warehouse to store and process the normalized actionable data available from their member organizations, while others are participating in or forming a Health Information Exchange (HIE) to make the data available to train their models and develop algorithms.
One challenge to adoption of analytics is the lack of standard terminology. Different interpretations of the same data can result from failure to provide proper context, and data aggregation from different sources can be challenging. Skepticism of caregivers toward AI is another hurdle in the way of analytics.
ABOUT THE AUTHOR: Mitali Maheshwari joined MD Buyline in 2016 with a background in health care information technology. Prior to coming to MD Buyline, she was an Epic Analyst at OCHIN, Inc., and an International Regulatory Affairs Associate for Claris Lifesciences Ltd. At MD Buyline, Ms. Maheshwari has responsibility for several technologies, including Electronic Health Records. Ms. Maheshwari graduated from Gujarat University in Ahmedabad, India, with a Bachelor of Pharmacy in 2011. She earned her Master of Science in health care management in 2016 from the University of Texas at Dallas. In addition to being certified in health care IT and Six Sigma, she has Prelude and Cadence certifications in Epic 2015.
