A prognostic information system for real-time personalized care: Lessons for embedded researchers.

Embedded researchers could play a central role in developing tools to personalize care using electronic medical records (EMRs). However, few studies have described the steps involved in developing such tools, or evaluated the key factors in success and failure. This case study describes how we used an EMR-derived data warehouse to develop a prototype informatics tool to help oncologists counsel patients with pancreatic cancer about their prognosis. The tool generated real-time prognostic information based on tumor type and stage, age, comorbidity status and lab tests. Our multidisciplinary team included embedded researchers, application developers, user experience experts, and an oncologist leader.This prototype succeeded in establishing proof of principle, but did not reach adoption into actual practice. In pilot testing, oncologists succeeded in generating prognostic information in real time. A few found it helpful in patient encounters, but all identified critical areas for further development before implementation. Generalizable lessons included the need to (1) include a wide range of potential use cases and stakeholders when selecting use cases for such tools; (2) develop talking points for clinicians to explain results from predictive tools to patients; (3) develop ways to reduce lag time between events and data availability; and (4) keep the options presented in the user interface very simple. This case demonstrates that embedded researchers can lead collaborations using EMR-derived data to create systems for real-time personalized patient counseling, and highlights challenges that such teams can anticipate.

Developing a Prognostic Information System for Personalized Care in Real Time.

CONTEXT: Electronic medical records hold promise to transform clinical practice. However, technological and other barriers may preclude using them to guide care in real time. We used the Virtual Data Warehouse (VDW) to develop a tool that enables physicians to generate real-time, personalized prognostic information about survival after cancer. CASE DESCRIPTION: Patients with cancer often ask their oncologists, "Have you ever seen a patient like me?" To help oncologists answer this question, we developed a prototype Prognostic Information System (PRISM), a web-based tool that gathers data about the index patient from Kaiser Permanente's clinical information systems, selects a historical cohort of similar patients, and displays the survival curve of the similar patients relative to key points in their treatment course. FINDINGS AND MAJOR THEMES: The prototype was developed by a multidisciplinary team with expertise in oncology, research, and technology. We have completed two rounds of user testing and refinement. Successful development rested on: (1) executive support and a clinical champion; (2) collaboration among experts from multiple disciplines; (3) starting with simple cases rather than ambitious ones; (4) extensive research experience with the Virtual Data Warehouse, related databases, and an existing query tool; and (5) following agile software development principles, especially iterative user testing. CONCLUSION: Clinical data stored in health care systems' electronic medical records can be used to personalize clinical care in real time. Development of prognostic information systems can be accelerated by collaborations among researchers, technology specialists, and clinicians and by use of existing technology like the Virtual Data Warehouse.