Pop Health Analytics
Predictive Analytics • Actionable Insights • Culture Built on Data and Outcomes
To successfully manage risk-based care, organizations must develop competencies and capabilities in the areas of patient experience, clinical outcomes, population health management, and financial accountability. Integrating and mining clinical, financial, and outcomes data to gain actionable insights to prevent readmissions, reduce costs, and improve overall patient care is critical.
The 15th Annual Population Health Analytics Track at WHCC convenes health plan and provider executives to discuss strategies to optimize technology and analytics in a population health approach – improving the quality and reducing the cost of health care. Attendees gain insight into how leading organizations leverage technology tools to forecast and analyze their populations’ most pressing needs so that care can be delivered at the right time and in the right place.
Top Reasons to Attend:
- Proactively identify the rising risk population and develop programs in coordination with the community
- Launch last mile strategies to engage the care management team around data and outcomes
- Take an in-depth look at predictive analytics use cases
- Adopt machine learning and AI technology to transform health care
- Develop predictive and prescription algorithms to gauge disease progression and an effective course of action
Session Spotlight:
Predictive Analytics Use Cases: Identify, Stratify, Manage, and Intervene with Rising Risk Patients
- How do you develop the capabilities to lead in this area?
- What is the best algorithm/model? Which data are useful or negligible?
- How can you help clinicians better understand data and why metrics are valuable indicators?
- What are the right processes to implement so a patient’s predictive score can be worked out as early as possible?
- What strategies should you implement for your highest-risk versus rising risk patients?
Moderator:
Editor-in-Chief
Healthcare Informatics
Panelists:
Chief Analytics Officer
Rush Health
Chief Analytics Officer
UPMC Health Plan & UPMC Enterprises
Chief Medical Informatics Officer
AMGA Analytics
Distinguished Speakers Include:
Attendee Acclaim
WHCC is a ‘can’t miss’ event for those seeking an in-depth understanding of where the industry is headed; The thought leadership, networking, and content is unparalleled
Featured Pre-Conference Workshop on Sunday, April 29, 2018
Machine Learning (ML) and Artificial Intelligence (AI) for Payer and Provider Analytics
This workshop is an in-depth technology and application overview of ML and AI applications in health care analytics. It is designed to help payers and providers understand the role and use cases of machine learning for data analytics and their applications to health care. There is broad agreement in the industry and among research communities that AI will significantly alter and improve health care. However, there is a large gap between the generic optimism for revolutionary AI applications in the distant future such as cyborg physicians, fully automated clinics and care supported by robotics, and the current, near-term feasibility of ML and AI use cases from both business and technology points of view.
In this workshop, attendees explore both concepts/applications and implementation:
- Explore practical and theoretical applications of AI and ML
- Adopt diverse viewpoints - payer, provider, employer, and consumer – and deconstruct how ML and AI can enrich analytics in health care
- Gain an in-depth introduction to Machine Learning
- Essential methods, algorithms, and tools
- Relationship between ML, AI, statistics, and business intelligence
- Understand the essential innovative value and novelty of ML and AI methods in the context of HIT
- Hands-on implementation module using R ML
- Converting payer and provider use cases to ML Questions
- Constructing data frames from data sets as ingest to ML platforms (R, Spark MLLib)
- Implementation of core ML Algorithms:
- Supervised Learning (Regression, Classification: SVM, NN, Decision Trees)
- Unsupervised Learning (Clustering, KNN, Text Mining)
- Open Discussion: How do we critically evaluate the ML and AI use cases, apps, and start-ups for health care?
- What factors identify MI and AI that can be profitably deployed in the near-term, intermediate-, and long-term?
Professor of Practice - Data Science
University of the Pacific & University of Washington Continuum College