Join us for some of the most innovative best practices sessions yet. This year, we have expanded the type and quantity of breakout sessions. Clinical outcomes improvement sessions are only the start. We will highlight the data-driven innovation that is expanding across the health system and beyond the 4 walls of the hospital. We will begin to explore how we will reach the full digitization of the patient and patient experience. We’ll share examples from both the leadership, analyst, and frontline staff perspective. The following are the breakout sessions we will be featuring this year.
Vice President of Lean Promotion, University of Kansas Health System
It’s all about the data. The ability to quickly and effectively assemble timely, accurate, and comprehensive data for strategic decision making and operational execution is an imperative in our era of: increasing at-risk payment models, reduced reimbursements, costs pressures, consumer demands, and evolving healthcare technologies like predictive analytics and precision medicine. The University of Kansas Health System’s advanced analytics team will discuss how it partners with its users to quickly develop insights, predictions, and interventions to solve strategic problems: generating new revenue, improving operational efficiencies, and delivering safe, quality care.
7 – Using Machine Learning and Big Data to Drive Patient Engagement and Better Health Outcomes (analyst, AI)
Principal, EY Analytics
Customer Analytics Lead, Cigna Information Management & Analytics
For many years, companies in the retail, telecom, insurance, and banking industries have used machine learning (ML) techniques to analyze terabytes of real-time data representing a wide range of customer interactions (across all channels), demographic characteristics, and lifestyle events. This session will explain how CIGNA has leveraged some of the ML techniques used to influence consumer behavior in other industries for their own purpose of influencing consumer behaviors towards lower medical costs and better healthcare outcomes. One example to be discussed is how they used a combination of claims, demographic, lab, call center, and click-stream data from web-interactions and mobile phone interactions to improve the timing, channel, and content they use to engage members with chronic conditions in coaching that lowers medical costs and improves healthcare outcomes for those patients.
8 – Real-World Examples Leveraging NLP, Big Data, and Data Science to Improve Population Health and Individual Care Outcomes (AI, technical)
Director, Regenstrief Center for Biomedical Informatics, Associate Professor of Family Medicine, Indiana University School of Medicine
With the unrelenting exponential growth in the volume of health and health-related electronic data, the potential to rapidly and accurately monitor, predict, intervene, and ultimately improve human health and care processes has never been more promising. However, real-world examples leveraging these technologies in an operational context are nascent, and care must be taken to realize the benefits of these resources and methods. Dr. Grannis will share outcomes and lessons learned from recent initiatives supporting precision and population health in the context of one of the country’s largest and longest-tenured health information exchanges. Real world examples will include leveraging Natural Language Processing (NLP) and machine learning to identifying patients at risk for high resource utilization, early identification of cancer cases, managing patients in need of social determinants of health wrap-around services, and automated notifiable disease case identification.
Associate Chief Quality Officer, Partners Healthcare; Harvard Medical School Faculty
Healthcare suffers from a deficit of quality measures that matter to patients, things like how well patients can function, work, and perform activities of daily living, and clinicians are increasingly frustrated by measurement systems that aren’t working and distract them from providing high-quality patient care. To succeed in population health outcomes and clinician buy-in, Partners HealthCare embarked on a comprehensive revamp of its quality measures. By eliminating clinically-irrelevant “noise”, Partners was able to identify meaningful quality insights that are being deployed to improve patient outcomes. This session outlines Partners’ methodologies for choosing the right metrics and extracting actionable insights to improve patient and clinician experience.
10 – Integrating Data and Analytics Into Provider Workflows Improves ACO Quality and Financial Performance (operations, financial)
Executive Vice President, Visiting Physician Association, USMM
Chief Information Officer, US Medical Management
President & Chief Executive Officer, Thibodaux Regional Medical Center
Director, HIM and Clinical Documentation Improvement, Thibodaux Regional Medical Center
In today’s healthcare market, financial challenges rank as the number one issue hospitals face. To maintain a margin to support its mission, hospital CEOs are always looking for opportunities to boost revenue through improved reimbursement. Managing discharged not final billed (DNFB) cases, where bills remain incomplete due to coding or documentation gaps, is one important way hospitals can improve financial performance. By expanding the use of analytics to every aspect of its billing services, Thibodaux Regional Medical Center has achieved impressive, sustained results. Three years after Thibodaux Regional launched its initial DNFB redesign effort, it continues to sustain and add to its improvement, realizing $2.4M in additional annual reimbursement and a 61% relative reduction in DNFB dollars, significantly improving its cash flow.
Executive Director, Strategic Analytics, UnityPoint Health
Data Scientist, UnityPoint Health
Far too often analytics efforts have fallen short of making a tangible impact on outcomes because they haven’t been successfully implemented in real workflows. Predictive models remain at risk of becoming isolated in their use along the continuum of care where their integration may provide benefits larger than the sum of each silo. UnityPoint Health (UPH) focused on integrating analytical models within the same readmission reduction strategy and coaching the care team to facilitate their adoption. Using this approach, one of UPH hospital’s risk-adjusted readmission indexes improved 40 percent over three years, surpassing internal system targets in performance and becoming the top performer in the health system. This session will provide an overview of the analytics tools and methods UPH used, including innovative individualized risk heat-maps generated for each patient, strategies for analytics adoption, and lessons learned along the way.
14 – Using a Real-Time Data Science Platform to Drive Perioperative Quality and Efficiency (analyst, AI, clinical)
Director and Associate Professor, University of Washington
Perioperative care for surgery patients contribute to more than 50% of a hospital’s revenue. However, due to the complexity and dynamic nature of the perioperative environment, delivering optimal and efficient care is challenging. Real-time perioperative data science platforms support a wide ecosystem of data and technology solutions including real-time decision support, machine learning predictive models, and robotic business intelligence. Learn about solutions built on these platforms that have: delivered a return on investment (ROI) of $1.2 million per 10,000 surgeries in terms of quality of care using the real-time decision support and guidance system in over 400,000 surgeries; improved efficiencies, resulting in a potential to reduce overage by $263,000 using machine learning models to predict operating room and post-anesthesia care unit occupancy times; reduced surgical supplies cost by $565,000 using robotic business intelligence algorithms.
Vice President, Medical Operations, Allina Health
Senior Performance Improvement Consultant, Allina Health
The Hierarchical Condition Category (HCC) risk adjustment model is used by CMS to estimate predicted costs for Medicare beneficiaries, and the results directly impact the reimbursement healthcare organizations receive. CMS requires that all qualifying conditions be identified each year by provider organizations. Documentation that is linked to a non-specific diagnosis, as well as incomplete documentation, negatively affects reimbursement. Despite providing care to a patient population that is not significantly less complex than the national population, Allina Health’s HCC coding for CMS risk adjustment was historically lower than both national and regional averages for Medicare ACO cohorts. Discover how it optimized its EMR, data, analytics, and provided widespread education to enable better documentation of care for patients with chronic diseases, leading to more accurate HCC risk adjustment coding—and more appropriate compensation for the quality care it provides.
Vice President, Surgery and Procedural Care, Allina Health
Improvement Specialist, Health Catalyst at Allina Health
President & Co-Founder of Protenus
A person’s medical record can be sold for ten times what their credit card goes for on the black market, making it a common target for attacks. This session takes you through a Johns Hopkins Case Study and their journey to implement privacy analytics. This practical application of AI resulted in a highly accurate model that reviewed every access to patient data and detected when the EHR was potentially exposed to a privacy violation, attack, or breach. Specific techniques, including supervised and unsupervised machine learning and explainability of AI techniques, advanced Johns Hopkins toward their current state—a predictive, analytics-based, collaborative privacy analytics infrastructure.
This session will enable users to:
- Define the cultural shift and identify stakeholders critical to a privacy analytics implementation
- Describe how to measure privacy and security outcomes
- Identify methods for demonstrating privacy and security ROI
24 – How Automating and Virtualizing the Hell Out of Healthcare Is the Only Way to Save It (strategy, innovation)
Chief Medical Officer and EVP of Product, MDLIVE, President, MDLIVE Medical Group
The statistics are staggering: 40% of Americans do not have a primary care physician (PCP); of those who do, 50% don’t get even the basic care they need due to issues with time, distance, cost, and appointment inavailability. Problems with primary care accessibility to patients are regularly blamed on a severe shortage of PCPs. But, we don’t really have a PCP shortage—just a shortage of efficiency in using them. Saving our primary care system requires the “double whammy” of automation and virtualization.
Virtualization is critical to providing care to patients who can’t easily get into a PCP office easily due to distance, time, and cost. But, it is not scalable by itself—scalability requires automation. Together, automation and virtualization allow one doctor to take care of at least twice as many patients in a significantly higher-quality manner. Combining automation and virtualization will lead to the rise of the virtualist—the Netflix of Healthcare—where 80% of care can and should be done online (where patients want it delivered), so that the 20% who really need to see a doctor in the office will have the ability to easily get an appointment and the time they deserve with their PCP.
Join in this lively discussion to learn about the automated and virtual future of primary care delivery with Lyle Berkowitz, MD, FACP, FHIMSS, a PCP, digital healthcare innovator and health tech entrepreneur, and Chief Medical Officer and EVP of Product for MDLIVE, as well as President of the MDLIVE Medical Group, one of the largest virtual primary care groups in the nation.
25 – Towards Proactive, Predictive, and Personalized Care: How Startups are Using Data Science to Build a Better Future for Healthcare (innovation, AI)
Chief Executive Officer, MATTER
The healthcare system is moving from one where patients interact with care episodically and reactively, toward a future where healthcare is proactive, predictive, and personalized. Currently, patients wait to see a doctor when they are sick—soon, healthcare will come to the patient before they even realize they have a medical problem. The technology and analytics capabilities needed to make this future happen are rapidly advancing as innovative healthcare startups work toward a new healthcare model where proactive, predictive, and personalized care is a reality for all patients.
Join Steven Collens, CEO of MATTER, to learn about trends in healthcare startup innovations, current focuses of healthcare digital entrepreneurs, and examples of how cutting-edge companies are harnessing healthcare data in new and novel ways. MATTER is the premier health technology collaborative that includes more than 200 start-ups and 70 industry partners committed to improving health and care for every patient. MATTER start-ups have raised $528 million in financing and their solutions have thus far benefited 76 million patients.
This presentation will provide attendees with:
- Insight into how healthcare entrepreneurs are leveraging data and digital technology to build the future of healthcare.
- Tips for working effectively with startups and building internal innovation capacity to create real value for patients.
26 – Adding Capacity Without Construction: A Collaboration of Analytics and Frontline Operations (operations, analyst)
Chief Analytics Officer, Stanford HealthCare
Administrative Director of the Hospital Operations Center, Stanford HealthCare
- Enhanced situational awareness across Stanford Hospital – monitoring clinical and non-clinical support departments and their impact on patient flow
- Develop tools to track patients through their expected care path, early recognition of variation including both affiliated and integrated sites
- Maximize data management to enhance the organizational decision-making process to maximize capacity, including predictive modeling
The value of predictive analytics in healthcare settings is well-established. In fact, 47 percent of health system CIOs say they plan to increase predictive analytics spending in the coming months. But how can you get a great return on that investment? The most common strategy is to hire data scientists. While data scientists are critical to any predictive analytics program, they are also difficult to find and expensive to hire. And new hires always take a long time to become productive. What if there were another solution — one that already exists in your organization? With the latest technology advancements, you can now effectively turn your encumbent data analysts into citizen data scientists. By focusing on a small set of artificial intelligence (AI) problems with known solutions, learning some basic data science principles and tools, and following the lead of an in-house or consulting data scientist, your data analysts can lead the way on your organization’s AI journey.
This session, designed for data analysts and their managers, covers a seven-step program for easily incorporating key data science principles and tools into analysts’ everyday actions. Starting with the use case of predicting readmissions, we’ll walk through how to organize the data, apply AI algorithms to generate predictions, and present the predictions to clinicians in the right way so that they are accepted.
28 – Population Health Innovations Deliver Significant Cost Savings and Improved Health Outcomes (pop health)
Director Digital Operations, Airdrie & Area Health Co-op
Executive Director, Crowfoot Village Family Practice
Crowfoot Village Family Practice (CVFP), a medical home to over 25,000 people in Calgary, Alberta, and the Airdrie & Area Health Cooperative (AAHC), an organization serving the city of Airdrie and surrounding areas, will share their population health innovations. Discover how CVFP’s leadership, vision, and values-driven culture resulted in population-based quality improvements: same day access (reduced wait times from 15 to zero days); an estimated $6M in cost savings associated with reduced emergency department usage and hospital length of stay; and improved health outcomes. And, learn how AAHC’s “Smart Healthy Community Project” is expanding beyond just the medical home to the entire community—the municipality, physicians, businesses, schools, churches, and other community organizations. AAHC will discuss how it will leverage and connect its existing infrastructure, and add new technologies and applications to create an open data platform for the community.
29 – Integrating Clinical Improvement and Activity Based Costing Identifies Pathway to Healthier Moms and Babies (clinical, financial)
Executive Vice Chair, Obstetrical Services, UPMC
Program Director, Women’s Health Services, UPMC
Nationally, one in ten pregnant women develops gestational diabetes (GDM), increasing the chance of negative outcomes for both mom and baby. Clinical leaders know early treatment will impact the outcomes, but early identification of these patients poses its own set of challenges. To address these challenges, The University of Pittsburgh Medical Center (UPMC) uses a service line management approach, coupled with an activity-based costing solution. An advantage of this organizational structure is the ability to easily access integrated clinical and financial information for a specific patient population. Come and learn how an interdisciplinary team, including clinicians and finance, developed an improvement proposal with a return on investment (ROI) projection to gain executive sponsorship and clinician engagement. Providing clinicians with detailed information about the effectiveness of the interventions resulted in the development of a pathway for clinical screening and interventions to benefit moms and babies.
The Machine Learning Marketplace is a unique 2-hour breakout that will provide attendees a broad exposure to a wide variety of innovative use cases for machine learning in healthcare. This session will be divided into two segments
- The first hour segment will consist of 10 health systems presenting 5-minute overviews of how they are using machine learning. The audience will be seated and able to see a broad array of use cases, and determine which of the use cases they would like to investigate further.
- The second hour segment will consist of the audience walking around and conversing directly with the 10 health systems in individual walkabout stations. Each of the 10 health systems will be available to explain more in depth about their machine learning projects, including results and key lessons learned.
- Case studies included in this session include using machine learning to assist in real-time inpatient care, detecting errors in medical data (comorbidities), optimizing no-show rates, determining risk modeling in falls, maintaining machine learning models after launching, predicting no-show patients, determining opioid risk, assessing readmission risks, and analyzing unstructured data, VOC data, and social media data to create actionable insights. Click for more detailed information.
Senior Vice President of Client Engagement, Health Catalyst
Good surfers are the consummate analysts. They dynamically process streams of seemingly unrelated information bypassing lesser opportunities, then surgically select the perfect wave.
The ability to tease out genuine opportunities amidst a tumult of noise is a hallmark of great analysts. In this session, John will:
- Explore the human elements of a great analyst
- Re-frame the role of technology in analysis
- Highlight healthcare knowledge required to maximize the value of the healthcare analyst
John has presented every year at the Healthcare Analytic Summit. His sessions fill up fast because attendees consistently rate his session as a conference highlight. His engaging presentation style leverages simple and fun analogies to galvanize key concepts for technical, clinical, and executive audiences alike. This year, he brings principles from the world of surfing and applies them to healthcare analytics.
Chief Strategy Officer, Community Care & Systems Chair, Super-Utilizer Care, Intermountain Healthcare
The top 5% of patients—sometimes referred to as “hotspotters”—account for more than 50% of total healthcare costs in the U.S. Intermountain’s quantitative assessment, initiated in 2011, identified hotspotters to engage patients in their own care and provide higher quality of care at lower cost. The session will delve into what Intermountain learned during their journey as an integrated delivery system as they initiated three interventions across five geographies. The session also summarizes the quantitative and qualitative outcomes of the interventions, such as reduction in utilization.
This session will enable users to:
- Define “hotspotting” and how it can impact a healthcare system’s outcomes
- Identify specific tactics for initiating hotspotting in an integrated healthcare system
- Review patient feedback and patient engagement in their care
- Review lessons learned
Vice President, Quality and Safety, Mission Health System
Executive Director, Emergency Services, Mission Health
35 – Innovative Analytics: Using Analytics to Evaluate Emerging Technologies (innovation, operations)
Manager, CV Clinical Programs/Services, Allina Health
Senior Analytics Engineer, Health Catalyst at Allina Health
Clinical Program Director, Cardiovascular Clinical Service Line, Allina Health
General Cardiologist, Minneapolis Hearth Institute
36 – Data, Insights, Action! Little-Known Principles and Skills Needed for Making Analytics Actionable (analyst, operations)
Senior Vice President, Professional Services, Health Catalyst
What critical factor guarantees your analytics will lead to actual improvements and an increased ROI? Actionability! Russ has made actionability a key indicator of success for his team of analytic professionals embedded in 40 different healthcare systems across the country. If their insights are not actionable, if they don’t achieve sustained improvements, they have failed. In this session, Russ dives into hands-on techniques for raising insight quantity, quality, clarity, and above all, actionability. Participants will learn:
- How to overcome the recurring barriers to “mission accomplished”
- How to avoid team time wasters by delineating between interesting and actionable
- How to make analytics actively drive value and raise ROI
This session is tailored for heavy analytics consumers and leaders of analytics teams. All participants will leave the session with a set of skills and guiding principles to elevate their analytic focus from just achieving “great analytics” to truly driving value.
Finance Manager, Allina Health
Director, Analytics, Allina Health with Health Catalyst
In the current healthcare environment, understanding per member per month (PMPM) cost drivers, and recognizing opportunities to optimize both reimbursement and patient outcomes, are critical to the financial viability of a healthcare organization. Integrated Health Partnerships (IHP) is an accountable care model that incentivizes healthcare providers to take on more financial accountability for the cost of care for Medicaid patients in Minnesota. Allina Health has three IHP contracts which cover approximately 90,000 members, half of which live within a three-county metro area.
Using its analytics platform made it possible for Allina Health to integrate internal and external data sources to deliver insight into PMPM cost drivers and produce a comprehensive evaluation of the drivers of PMPM payment performance. Coupling this PMPM insight with information from data-driven opportunity analysis has given Allina Health insight into its IHP patient population, supporting informed at-risk contracting and the creation of interventions to decrease the total cost of care and improve both financial and clinical outcomes.
38 – Proactive Patient and Leadership Engagement Delivers an Improved Care Experience (operations, innovation)
Chief Quality Officer, UPMC
Senior Product Manager, UPMC Enterprises
New this year is our first-ever, two-hour Machine Learning Marketplace. Selected from over sixty submissions, we have chosen ten innovative machine learning projects to share their approach and best practices. During the first hour, each system will present a 5 minute Rapid Review summary of their machine learning project to the entire audience. During the second hour, we will feature their projects in ten different stations where the audience walk around, select, and learn more about these projects with face-to-face interactions. The featured machine learning projects include…
- Real-time inpatient care
- Detecting errors in medical data (patient comorbidities)
- Predicting targeted nursing turnover
- Optimizing no-show rates
- NLP falls analytics
- Sustaining machine learning models over time
- No-show patient analytics
- Opioid risk prediction tool
- Heart failure readmission risks, closed-loop analytics
- NLP analytics from VOC surveys and social media
New this year…
If you could pick anyone’s brain, who would it be? Join the conversations that will happen on Braindate
What's a braindate?
This is the best conference I’ve ever been to in all my years in healthcare…and that’s over 20 years
I can’t imagine a better summit. My brain is buzzing with all these new tools, resources, case studies, and innovative ideas and software. I’ll be back next year, and if next year is as good as this year, you’ll definitely have made a follower for life out of me.
This is by far the best conference I have attended. It was well planned and coordinated. Great job to the team for putting this amazing event together.
Same place, same time next year!! The best conference I’ve attended, fabulous job!
It definitely exceeded my expectations. A lot of conferences I go to, you take a lot information but it doesn’t have a practical application. This is completely different because I feel like I have a lot of information I’m excited about and can apply to my situation.
We talk about value -based care…this is a value-based conference. Considering what other conferences costs, the value I get out of this is tremendous.