Abstract: For those of you who have visited a doctor at least a few times, you had probably noticed that the time waiting for a doctor is typically much greater than the time you spend with the doctor. Several days after actual doctor’s visit, you are often surprised with the amount that you need to pay for the service provided. To add to frustration, you typically do not have any clue how much the service will cost before or during the doctor’s visit. It is all between your health care provider and your insurance carrier, and you do not have any control over it.
For an average American family, health care is one of the largest household expenses. In addition, the United States government spends more than $3.4 trillion annually on health care. According to the Institute of Medicine, one third of that money is wasted. At the same time, our population is becoming older and sicker. Almost 60% of US population has at least one chronic condition, and almost 90% of entire health care spending is due to treating individuals with chronic conditions. Despite all this spending, US is still ranked last in health care quality among 34 OECD (Organization for Economic Co-operation and Development) countries. Our healthcare system is simply reaching a breaking point!
We need to broaden the definition of health to the one given by World Health Organization as a “state of complete physical, mental and social well-being and not merely the absence of disease or infirmity”. In this definition, healthcare actually becomes what happens between doctor’s visits, not what happens in the clinic. In other words, it is far more important where do you live and how you live your life than what kind of health care is provided to you. So, in order to make proper health decisions, we do not only need medical claims and EHR data, but also data from outside the doctor’s office.
With emergence of all new these new data sources (e.g., IoT, blockchain) as well as Big Data and AI technologies, one question remains: Could these technologies help in fixing our broken health care system? The speaker will cover what are the biggest challenges in achieving this goal ranging from addressing enormous volume and veracity of health care data to implementation challenges and finally to change management techniques that require engagement on patient, provider and insurance carrier side. The speaker will cover several use cases how machine learning and AI helped health care organizations in detecting fraud, waste and abuse, early prediction of chronic conditions, predicting readmission rate and medication adherence. The speaker will talk how we can use this first level of simpler analytics and convert it into real insights and data driven recommendations. The speaker will finally address how health care organizations could address ever growing consumerism in health care by leveraging big data and AI to provide more personalized health care, and how analyzing human behavior and socio-economic determinants can help patients have better overall life.
Bio: Aleksandar is responsible for overall predictive analytics solution in health care fraud, waste and abuse detection at Aetna. He is passionate about applying big data technologies and AI within health care and helping people live better overall life. In addition to health care industry, he has extensive experience in various analytics projects ranging from banking, credit and insurance industry to fault diagnostics and computer security applications. He is a frequent speaker at data science conferences. He has co-edited a book on cyber security threats, written 8 book chapters and published over 50 research articles, which were cited more than 4,000 times. He holds a PhD degree in data mining / machine learning from Temple University.