Consensus Statement on Electronic Health Predictive Analytics: A Guiding Framework to Address Challenges.

CONTEXT: The recent explosion in available electronic health record (EHR) data is motivating a rapid expansion of electronic health care predictive analytic (e-HPA) applications, defined as the use of electronic algorithms that forecast clinical events in real time with the intent to improve patient outcomes and reduce costs. There is an urgent need for a systematic framework to guide the development and application of e-HPA to ensure that the field develops in a scientifically sound, ethical, and efficient manner. OBJECTIVES: Building upon earlier frameworks of model development and utilization, we identify the emerging opportunities and challenges of e-HPA, propose a framework that enables us to realize these opportunities, address these challenges, and motivate e-HPA stakeholders to both adopt and continuously refine the framework as the applications of e-HPA emerge. METHODS: To achieve these objectives, 17 experts with diverse expertise including methodology, ethics, legal, regulation, and health care delivery systems were assembled to identify emerging opportunities and challenges of e-HPA and to propose a framework to guide the development and application of e-HPA. FINDINGS: The framework proposed by the panel includes three key domains where e-HPA differs qualitatively from earlier generations of models and algorithms (Data Barriers, Transparency, and ETHICS) and areas where current frameworks are insufficient to address the emerging opportunities and challenges of e-HPA (Regulation and Certification; and Education and Training). The following list of recommendations summarizes the key points of the framework: Data Barriers: Establish mechanisms within the scientific community to support data sharing for predictive model development and testing.Transparency: Set standards around e-HPA validation based on principles of scientific transparency and reproducibility. ETHICS: Develop both individual-centered and society-centered risk-benefit approaches to evaluate e-HPA.Regulation and Certification: Construct a self-regulation and certification framework within e-HPA.Education and Training: Make significant changes to medical, nursing, and paraprofessional curricula by including training for understanding, evaluating, and utilizing predictive models.

Toward a science of learning systems: a research agenda for the high-functioning Learning Health System.

OBJECTIVE: The capability to share data, and harness its potential to generate knowledge rapidly and inform decisions, can have transformative effects that improve health. The infrastructure to achieve this goal at scale--marrying technology, process, and policy--is commonly referred to as the Learning Health System (LHS). Achieving an LHS raises numerous scientific challenges. MATERIALS AND METHODS: The National Science Foundation convened an invitational workshop to identify the fundamental scientific and engineering research challenges to achieving a national-scale LHS. The workshop was planned by a 12-member committee and ultimately engaged 45 prominent researchers spanning multiple disciplines over 2 days in Washington, DC on 11-12 April 2013. RESULTS: The workshop participants collectively identified 106 research questions organized around four system-level requirements that a high-functioning LHS must satisfy. The workshop participants also identified a new cross-disciplinary integrative science of cyber-social ecosystems that will be required to address these challenges. CONCLUSIONS: The intellectual merit and potential broad impacts of the innovations that will be driven by investments in an LHS are of great potential significance. The specific research questions that emerged from the workshop, alongside the potential for diverse communities to assemble to address them through a 'new science of learning systems', create an important agenda for informatics and related disciplines.

Rapid learning: a breakthrough agenda.

A "rapid-learning health system" was proposed in a 2007 thematic issue of Health Affairs. The system was envisioned as one that uses evidence-based medicine to quickly determine the best possible treatments for patients. It does so by drawing on electronic health records and the power of big data to access large volumes of information from a variety of sources at high speed. The foundation for a rapid-learning health system was laid during 2007-13 by workshops, policy papers, large public investments in databases and research programs, and developing learning systems. Challenges now include implementing a new clinical research system with several hundred million patients, modernizing clinical trials and registries, devising and funding research on national priorities, and analyzing genetic and other factors that influence diseases and responses to treatment. Next steps also should aim to improve comparative effectiveness research; build on investments in health information technology to standardize handling of genetic information and support information exchange through apps and software modules; and develop new tools, data, and information for clinical decision support. Further advances will require commitment, leadership, and public-private and global collaboration.

Rapid, responsive, relevant (R3) research: a call for a rapid learning health research enterprise.

Our current health research enterprise is painstakingly slow and cumbersome, and its results seldom translate into practice. The slow pace of health research contributes to findings that are less relevant and potentially even obsolete. To produce more rapid, responsive, and relevant research, we propose approaches that increase relevance via greater stakeholder involvement, speed research via innovative designs, streamline review processes, and create and/or better leverage research infrastructure. Broad stakeholder input integrated throughout the research process can both increase relevance and facilitate study procedures. More flexible and rapid research designs should be considered before defaulting to the traditional two-arm randomized controlled trial (RCT), but even traditional RCTs can be designed for more rapid findings. Review processes for grant applications, IRB protocols, and manuscript submissions can be better streamlined to minimize delays. Research infrastructures such as rapid learning systems and other health information technologies can be leveraged to rapidly evaluate new and existing treatments, and alleviate the extensive recruitment delays common in traditional research. These and other approaches are feasible but require a culture shift among the research community to value not only methodological rigor, but also the pace and relevance of research.

Creating a high-performance system for comparative effectiveness research.

Enactment of the federal stimulus and health reform legislation heralds the beginning of a national comparative effectiveness research program. This article suggests how the Department of Health and Human Services (HHS) can, with collaborators, build a high-performing comparative effectiveness research system. New policies and investments should exploit the rapid-learning potential of electronic health records, computerized databases, data sharing, and research networks. A national database for effectiveness research studies should be established by presidential order. HHS will need to support all of these pieces and take the lead in creating a rapid-learning culture for the US health system.

Rapid-learning system for cancer care.

Compelling public interest is propelling national efforts to advance the evidence base for cancer treatment and control measures and to transform the way in which evidence is aggregated and applied. Substantial investments in health information technology, comparative effectiveness research, health care quality and value, and personalized medicine support these efforts and have resulted in considerable progress to date. An emerging initiative, and one that integrates these converging approaches to improving health care, is "rapid-learning health care." In this framework, routinely collected real-time clinical data drive the process of scientific discovery, which becomes a natural outgrowth of patient care. To better understand the state of the rapid-learning health care model and its potential implications for oncology, the National Cancer Policy Forum of the Institute of Medicine held a workshop entitled "A Foundation for Evidence-Driven Practice: A Rapid-Learning System for Cancer Care" in October 2009. Participants examined the elements of a rapid-learning system for cancer, including registries and databases, emerging information technology, patient-centered and -driven clinical decision support, patient engagement, culture change, clinical practice guidelines, point-of-care needs in clinical oncology, and federal policy issues and implications. This Special Article reviews the activities of the workshop and sets the stage to move from vision to action.

Medicare's future: cancer care.

This paper proposes a national initiative for Medicare patients with cancer. It would include (1) a rapid-learning system for comparative effectiveness; (2) a quality measurement system; and (3) payment reforms to reward high-quality care. In implementing this strategy, the U.S. Department of Health and Human Services (HHS) would make extensive use of new computerized databases for clinical research and quality measurement. Legislation will be needed for full national implementation. Similar initiatives could be started for other priority areas in Medicare. Medicare could become a national leader in advancing high-quality, effective care.

Technologies of health policy.

Major factors in adoption of new national health policies include (1) a crisis or perceived opportunity; (2) a persuasive diagnosis of what is needed; (3) a prescription for new policies; and (4) new technologies that are ready to go. The past twenty-five years illustrate that the development of new policy ideas to where they can be implemented as major nationwide reforms can take a decade or more. Many national policy ideas for evidence-based medicine--such as electronic health records, rapid-learning networks, predictive modeling, Medicare/Medicaid disease management, widespread pay-for-performance, and large consumer-information databases--are in a development phase.

A rapid-learning health system.

Private- and public-sector initiatives, using electronic health record (EHR) databases from millions of people, could rapidly advance the U.S. evidence base for clinical care. Rapid learning could fill major knowledge gaps about health care costs, the benefits and risks of drugs and procedures, geographic variations, environmental health influences, the health of special populations, and personalized medicine. Policymakers could use rapid learning to revitalize value-based competition, redesign Medicare's payments, advance Medicaid into national health care leadership, foster national collaborative research initiatives, and design a national technology assessment system.

Massachusetts reform plus President Bush's tax credits: a national model?

The Massachusetts health reform offers an important opportunity for a new federal-state strategy to cover the uninsured. President George Bush's proposed health insurance tax credits could be added to the Massachusetts health reform. The combined plan would include Medicaid expansions; offer workers affordable coverage through competitive insurance markets; and provide federal, state, employer, and individual financing. Many other states might be interested in similar federal-state partnerships for the forty-five million uninsured Americans. Ending the national impasse on coverage needs this kind of bold initiative.

The need for evidence-based health policy to address health care variations.

Medicare policy making now deals mostly with price-setting issues. However, as Warren Buffet has noted: "Price is what you pay. Value is what you get." Victor Fuchs's studies raise fundamental issues for a value-oriented Medicare program. Florida offers one of many regional patterns of Medicare mortality that are not yet adequately explained. Valued-oriented, evidence-based Medicare policies would target opportunities to improve population health and would foster greater use of evidence-based medicine.

A new Medicaid program.

This paper suggests a new federal-state partnership--a new Medicaid program--for coverage of the uninsured and long-term care. It discusses national eligibility standards, based on financial need (rather than categorical eligibility); buy-ins and reinsurance for high-risk populations; a national strategy of "Medicaid plus tax credits" to cover the uninsured; Medicaid long-term care with expanded eligibility, better financial protection, and home and community-based care benefits; quality initiatives; administration; and possible financing sources (such as estate taxes and an increased Social Security Disability Insurance wage base). Without a new mission and national standards, Medicaid will continue to grow in a patchwork fashion with huge gaps and inequities.

Strategies to improve consumer health information services.

Consumer health information is important in two respects. It helps individuals improve their own health and creates pressure on the healthcare system to produce higher quality care. Initiatives to strengthen consumer health information services are underway in many public and private-sector organizations nationwide. This paper describes some trends in the field and opportunities to spur further progress nationally and at the community level over the next few years.

Quality incentives for Medicare+Choice plans.

The Medicare program should be a leader in national efforts to improve quality of care. This paper proposes a new system of quality bonuses for Medicare+Choice plans and lays out a framework of key issues and options to promote discussion about such an initiative.

A flexible benefits tax credit for health insurance and more.

This essay outlines a concept for a "flexible benefits" tax credit for expanding health insurance coverage and other purposes such as retirement savings plans (with potential withdrawals for higher education, first-home ownership, and catastrophic medical expenses). Two examples are presented. The advantages of a flexible benefits tax credit are considered in terms of efficient use of the budget surplus to help meet the varied (and changing) needs of American families, to eliminate major national gaps in health insurance and pension coverage, and to advance other objectives. If the budget surplus is used wisely, political decisionmakers could achieve health insurance coverage for most uninsured workers and children and assure a future with real economic security for American families.