Big Data & Analytics in Healthcare Summit 2014 Philadelphia: Day 1 Highlights

Highlights from the presentations by Healthcare Analytics leaders from GlaxoSmithKline, Excellus BlueCross BlueShield, Adventist Health and Mayo Clinic on day 1 of Big Data & Analytics in Healthcare Summit 2014 in Philadelphia.

The Healthcare industry is at a turning point. Huge amounts of analytical talent is flowing into healthcare and by 2016 half of hospitals will be using advanced analytics software, compared to 10% today. This trend is driven by the realization that the best way to help physicians make better treatment decisions while decreasing cost is by leveraging data and predictive modeling. With data and data scientists at the core, the healthcare industry is evolving. Healthcare providers and payers are increasingly turning to big data and analytics, to help them understand their patients and the contexts of their illnesses in more detail.

The Healthcare Summit 2014Big Data & Analytics in Healthcare Summit (May 15 & 16, 2014) was organized by the Innovation Enterprise at Philadelphia. A wide range of topics were discussed including clinical decision support, high cost patient treatment, creating physician friendly systems, consumer healthcare engagement, bundled payments, health information exchanges, clinical integration and improving patient safety, genomics & personalized medicine and population healthcare management.

We provide here a summary of selected talks along with the key takeaways.

Here are highlights from Day 1 (Thursday, May 15, 2014):

Jesse SturinoJesse Sturino, Head of Data and Analytics Architecture for R&D IT, GlaxoSmithKline delivered a highly insightful talk on "Innovation, Agility & Generating Value Through Data Integration". Currently, the major industry challenges are patent cliff / generic pressures, reimbursement requirements becoming more stringent, increased regulatory complexity, and increasing costs to develop new medicines. At the same time, there are disruptive data opportunities because we now have more data than ever before, more efficient and affordable tools to process the data, and open collaboration opportunities.

Despite such enormous opportunities, the process of extracting business value from data has been far from easy, particularly due to problems such as data complexity, return on investment (ROI) concerns, unconnected infrastructure, ethical concerns(privacy), economies of scale, lack of data standards and lack of holistic patient understanding. He stressed on connecting to the community to overcome problems such as "I don't want to share my data, but I would like everyone else to share their data"; "I don't really trust the data other people generated, I guess I'll do it myself"; and "I spend most of my time pulling data together instead of analyzing the data". Knowledge is a commodity, which can be used to broker relationships with partners.

Establish a bold, yet credible strategic plan that delivers incremental value over time towards business goals with measured investment. He asked firms to establish a simple framework to inspire, identify, incubate and industrialize innovation, thus, quickly moving from ideas to solutions. During incubation, stay focused on a question of value, keep costs low and undergo quick iterations for continual improvement. This approach reduces risk of strategic investments and enables innovation by making it okay to 'fail'.

He discussed principles and practices GSK has followed to quickly mobilize the necessary capabilities (people, processes, systems and data) to enable 6 key business and scientific areas of investigation across the R&D value chain, each focused on a different area of data analytics. No matter how great, monolithic solutions would not work. An information ecosystem needs to be set up to harness data. Be aware of vendors re-branding their legacy products as 'big data' solutions when they really aren't. In the end, he summarized the learning through the following three points:
  1. Integration drives value
  2. Agility enables innovation
  3. Business problems drive analytics

Leo BarellaLeo Barella, Chief Technology Officer, Excellus BlueCross BlueShield talked about current state of healthcare and Big Data opportunities in his presentation "Leveraging Big Data for Improving Population Health Management". Health Care reform redefined how individuals can obtain health insurance. Providers will receive incentives on positive outcomes which will lead to their increased interest in improving the health not only of the patients they visit in their offices but the patients they seldom see. The information available about their patients is growing rapidly and can be harvested from sources that are not typically linked to medical records.

Demographic, technological and economic forces are changing the face of health care. Buyers expect greater value, improved quality and better outcomes - at a more affordable cost. Volumes of data create an opportunity for deeper insight, earlier intervention and engagement (1 billion health-related apps will be downloaded by the year 2016). Demand to connect health care and social services is driving formation of new partnerships ($500 billion in avoidable costs with medication adherence).

In the healthcare industry, enterprise analytics and Big Data has moved to center stage. Healthcare deals with a variety of data such as machine-to-machine data, transaction data, biometric data, human-generated data, etc. In order to deliver efficient solutions, healthcare needs a 360-degree view of the customer which should include all relevant details such as living conditions, diet, education, social behaviors, driving, sleep schedule, physical health, family medical history, physical activity, and more.

The immense growth in personal, portable and affordable bio-sensors is creating a new era of unprecedented opportunities. Big Data and Analytics can lead to the proactive improvement of population health and wellness by helping healthcare industry improve quality & efficiency, detect diseases early, detect frauds, deliver personalized solutions, and manage population health. His key recommendations were: engage providers, foster transparency, provide for flexibility in information transference, prefer in-house solutions over vendor-generated solutions, and close the quality loop.

Raj GopalanRaj Gopalan, Regional CMIO, Adventist Health gave an interesting talk on "Healthcare Analytics Driven Optimization for Patient Safety and Physician Experience". The major healthcare initiative that is predicted for 2014 is healthcare analytics to drive quality efficiency and revenue. The drastic changes in the healthcare payment systems from fee for service, to payments for quality, preventive care and population health drives this initiative.

Hospital mergers are sky rocketing to leverage economies of scale to boost efficiency and effectiveness. A staggering 43% of physician's time is being taken up by data entry. There is a threefold increase in EMR adoption in the past 2 years. About 40% of the US hospitals have some form of EMR in place and have been collecting data for the past few years. He described how Adventist Health System is leveraging their data to improve patient safety, quality, cost, physician efficiency and experience.

The number of patients that die of preventable medical errors is similar to having a 747 plane crash every day. Analytics can help identify these errors in time by raising alerts. Monitoring physicians' response to these alerts should be recorded and reported back to help understand what is going wrong. The Analytics system must fine tune the alerts to reduce false positives. The alerts should identify the physicians to engage in a dialogue, and when possible, also recommend the next steps. Data Analytics helps explore opportunities for improving efficiency by engineering time stamp probes in the EMR (Electronic Medical Record). Concluding his talk, he recommended a Physician Dashboard with key metrics such as total number of orders written, total number of notes documented, order set utilization and evidence based order set usage against LOS (Length Of Stay) and cost of care.

Jyoti PathakJyoti Pathak, Associate Professor, Medical Informatics, Mayo Clinic talked about relevance of Big Data to clinical research in his talk titled "The Era of Big Data Informatics for Clinical and Translational Research". Despite considerable progress in prevention and treatment, cancer remains the second leading cause of death in the United States. Cancer researchers around the world are generating massive amounts of clinical and genetic data, although due to its volume, complexity and lack of centralization, much is left unanalyzed.

Big Data backed by powerful analytics holds the key to gain important insights from such high volume, variety and velocity data enabling a new understanding of cancer from molecular biology through clinical management. It provides opportunities to ask complex questions and identify novel knowledge from existing data including the study of genetics of an individual’s cancer cells, on her response to treatment and sensitivity to side effects.

He talked about the recent developments in Big Data Analytics platforms at Mayo Clinic and how this transformative technology can be harnessed to leverage multidimensional data for developing new preventive measures, diagnostic tools and interventions in cancer research. He stated Mayo Clinic's vision to move away from the current application-centric approach for managing data to data-as-a-service/unified data approach. The initial focus for Big Data efforts is Clinical NLP(Natural Language Processing), which is highly data and process intensive. In conclusion, he stated that Big Data approaches allow us to quantify the biological and non-biological determinants of health and disease. Big Data creates actionable information, particularly for personalizing treatment interventions and identifying new therapeutic potential.

Highlights from day 2.