Assessing disparities through missing race and ethnicity data: results from a juvenile arthritis registry.

Introduction: Ensuring high-quality race and ethnicity data within the electronic health record (EHR) and across linked systems, such as patient registries, is necessary to achieving the goal of inclusion of racial and ethnic minorities in scientific research and detecting disparities associated with race and ethnicity. The project goal was to improve race and ethnicity data completion within the Pediatric Rheumatology Care Outcomes Improvement Network and assess impact of improved data completion on conclusions drawn from the registry. Methods: This is a mixed-methods quality improvement study that consisted of five parts, as follows: (1) Identifying baseline missing race and ethnicity data, (2) Surveying current collection and entry, (3) Completing data through audit and feedback cycles, (4) Assessing the impact on outcome measures, and (5) Conducting participant interviews and thematic analysis. Results: Across six participating centers, 29% of the patients were missing data on race and 31% were missing data on ethnicity. Of patients missing data, most patients were missing both race and ethnicity. Rates of missingness varied by data entry method (electronic vs. manual). Recovered data had a higher percentage of patients with Other race or Hispanic/Latino ethnicity compared with patients with non-missing race and ethnicity data at baseline. Black patients had a significantly higher odds ratio of having a clinical juvenile arthritis disease activity score (cJADAS10) of ≥5 at first follow-up compared with White patients. There was no significant change in odds ratio of cJADAS10 ≥5 for race and ethnicity after data completion. Patients missing race and ethnicity were more likely to be missing cJADAS values, which may affect the ability to detect changes in odds ratio of cJADAS ≥5 after completion. Conclusions: About one-third of the patients in a pediatric rheumatology registry were missing race and ethnicity data. After three audit and feedback cycles, centers decreased missing data by 94%, primarily via data recovery from the EHR. In this sample, completion of missing data did not change the findings related to differential outcomes by race. Recovered data were not uniformly distributed compared with those with non-missing race and ethnicity data at baseline, suggesting that differences in outcomes after completing race and ethnicity data may be seen with larger sample sizes.

Uses of Electronic Health Record Data to Measure the Clinical Learning Environment of Graduate Medical Education Trainees: A Systematic Review.

PURPOSE: This study systematically reviews the uses of electronic health record (EHR) data to measure graduate medical education (GME) trainee competencies. METHOD: In January 2022, the authors conducted a systematic review of original research in MEDLINE from database start to December 31, 2021. The authors searched for articles that used the EHR as their data source and in which the individual GME trainee was the unit of observation and/or unit of analysis. The database query was intentionally broad because an initial survey of pertinent articles identified no unifying Medical Subject Heading terms. Articles were coded and clustered by theme and Accreditation Council for Graduate Medical Education (ACGME) core competency. RESULTS: The database search yielded 3,540 articles, of which 86 met the study inclusion criteria. Articles clustered into 16 themes, the largest of which were trainee condition experience (17 articles), work patterns (16 articles), and continuity of care (12 articles). Five of the ACGME core competencies were represented (patient care and procedural skills, practice-based learning and improvement, systems-based practice, medical knowledge, and professionalism). In addition, 25 articles assessed the clinical learning environment. CONCLUSIONS: This review identified 86 articles that used EHR data to measure individual GME trainee competencies, spanning 16 themes and 6 competencies and revealing marked between-trainee variation. The authors propose a digital learning cycle framework that arranges sequentially the uses of EHR data within the cycle of clinical experiential learning central to GME. Three technical components necessary to unlock the potential of EHR data to improve GME are described: measures, attribution, and visualization. Partnerships between GME programs and informatics departments will be pivotal in realizing this opportunity.

Auditing Learned Associations in Deep Learning Approaches to Extract Race and Ethnicity from Clinical Text.

Complete and accurate race and ethnicity (RE) patient information is important for many areas of biomedical informatics research, such as defining and characterizing cohorts, performing quality assessments, and identifying health inequities. Patient-level RE data is often inaccurate or missing in structured sources, but can be supplemented through clinical notes and natural language processing (NLP). While NLP has made many improvements in recent years with large language models, bias remains an often-unaddressed concern, with research showing that harmful and negative language is more often used for certain racial/ethnic groups than others. We present an approach to audit the learned associations of models trained to identify RE information in clinical text by measuring the concordance between model-derived salient features and manually identified RE-related spans of text. We show that while models perform well on the surface, there exist concerning learned associations and potential for future harms from RE-identification models if left unaddressed.

Implementation of pharmacogenomic clinical decision support for health systems: a cost-utility analysis.

We constructed a cost-effectiveness model to assess the clinical and economic value of a CDS alert program that provides pharmacogenomic (PGx) testing results, compared to no alert program in acute coronary syndrome (ACS) and atrial fibrillation (AF), from a health system perspective. We defaulted that 20% of 500,000 health-system members between the ages of 55 and 65 received PGx testing for CYP2C19 (ACS-clopidogrel) and CYP2C9, CYP4F2 and VKORC1 (AF-warfarin) annually. Clinical events, costs, and quality-adjusted life years (QALYs) were calculated over 20 years with an annual discount rate of 3%. In total, 3169 alerts would be fired. The CDS alert program would help avoid 16 major clinical events and 6 deaths for ACS; and 2 clinical events and 0.9 deaths for AF. The incremental cost-effectiveness ratio was $39,477/QALY. A PGx-CDS alert program was cost-effective, under a willingness-to-pay threshold of $100,000/QALY gained, compared to no alert program.

Using a Constraint-Based Method to Identify Chronic Disease Patients Who Are Apt to Obtain Care Mostly Within a Given Health Care System: Retrospective Cohort Study.

BACKGROUND: For several major chronic diseases including asthma, chronic obstructive pulmonary disease, chronic kidney disease, and diabetes, a state-of-the-art method to avert poor outcomes is to use predictive models to identify future high-cost patients for preemptive care management interventions. Frequently, an American patient obtains care from multiple health care systems, each managed by a distinct institution. As the patient's medical data are spread across these health care systems, none has complete medical data for the patient. The task of building models to predict an individual patient's cost is currently thought to be impractical with incomplete data, which limits the use of care management to improve outcomes. Recently, we developed a constraint-based method to identify patients who are apt to obtain care mostly within a given health care system. Our method was shown to work well for the cohort of all adult patients at the University of Washington Medicine for a 6-month follow-up period. It is unknown how well our method works for patients with various chronic diseases and over follow-up periods of different lengths, and subsequently, whether it is reasonable to perform this predictive modeling task on the subset of patients pinpointed by our method. OBJECTIVE: To understand our method's potential to enable this predictive modeling task on incomplete medical data, this study assesses our method's performance at the University of Washington Medicine on 5 subgroups of adult patients with major chronic diseases and over follow-up periods of 2 different lengths. METHODS: We used University of Washington Medicine data for all adult patients who obtained care at the University of Washington Medicine in 2018 and PreManage data containing usage information from all hospitals in Washington state in 2019. We evaluated our method's performance over the follow-up periods of 6 months and 12 months on 5 patient subgroups separately-asthma, chronic kidney disease, type 1 diabetes, type 2 diabetes, and chronic obstructive pulmonary disease. RESULTS: Our method identified 21.81% (3194/14,644) of University of Washington Medicine adult patients with asthma. Around 66.75% (797/1194) and 67.13% (1997/2975) of their emergency department visits and inpatient stays took place within the University of Washington Medicine system in the subsequent 6 months and in the subsequent 12 months, respectively, approximately double the corresponding percentage for all University of Washington Medicine adult patients with asthma. The performance for adult patients with chronic kidney disease, adult patients with chronic obstructive pulmonary disease, adult patients with type 1 diabetes, and adult patients with type 2 diabetes was reasonably similar to that for adult patients with asthma. CONCLUSIONS: For each of the 5 chronic diseases most relevant to care management, our method can pinpoint a reasonably large subset of patients who are apt to obtain care mostly within the University of Washington Medicine system. This opens the door to building models to predict an individual patient's cost on incomplete data, which was formerly deemed impractical. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/13783.

A Novel Food Record App for Dietary Assessments Among Older Adults With Type 2 Diabetes: Development and Usability Study.

BACKGROUND: More than 1 in 4 people in the United States aged 65 years and older have type 2 diabetes. For diabetes care, medical nutrition therapy is recommended as a clinically effective intervention. Previous researchers have developed and validated dietary assessment methods using images of food items to improve the accuracy of self-reporting over traditional methods. Nevertheless, little is known about the usability of image-assisted dietary assessment methods for older adults with diabetes. OBJECTIVE: The aims of this study were (1) to create a food record app for dietary assessments (FRADA) that would support image-assisted dietary assessments, and (2) to evaluate the usability of FRADA for older adults with diabetes. METHODS: For the development of FRADA, we identified design principles that address the needs of older adults and implemented three fundamental tasks required for image-assisted dietary assessments: capturing, viewing, and transmitting images of food based on the design principles. For the usability assessment of FRADA, older adults aged 65 to 80 years (11 females and 3 males) were assigned to interact with FRADA in a lab-based setting. Participants' opinions of FRADA and its usability were determined by a follow-up survey and interview. As an evaluation indicator of usability, the responses to the survey, including an after-scenario questionnaire, were analyzed. Qualitative data from the interviews confirmed the responses to the survey. RESULTS: We developed a smartphone app that enables older adults with diabetes to capture, view, and transmit images of food items they consumed. The findings of this study showed that FRADA and its instructions for capturing, viewing, and transmitting images of food items were usable for older adults with diabetes. The survey showed that participants found FRADA easy to use and would consider using FRADA daily. The analysis of the qualitative data from interviews revealed multiple categories, such as the usability of FRADA, potential benefits of using FRADA, potential features to be added to FRADA, and concerns of older adults with diabetes regarding interactions with FRADA. CONCLUSIONS: This study demonstrates in a lab-based setting not only the usability of FRADA by older adults with diabetes but also potential opportunities using FRADA in real-world settings. The findings suggest implications for creating a smartphone app for an image-assisted dietary assessment. Future work still remains to evaluate the feasibility and validity of FRADA with multiple stakeholders, including older adults with diabetes and dietitians.

Leaf: an open-source, model-agnostic, data-driven web application for cohort discovery and translational biomedical research.

OBJECTIVE: Academic medical centers and health systems are increasingly challenged with supporting appropriate secondary use of clinical data. Enterprise data warehouses have emerged as central resources for these data, but often require an informatician to extract meaningful information, limiting direct access by end users. To overcome this challenge, we have developed Leaf, a lightweight self-service web application for querying clinical data from heterogeneous data models and sources. MATERIALS AND METHODS: Leaf utilizes a flexible biomedical concept system to define hierarchical concepts and ontologies. Each Leaf concept contains both textual representations and SQL query building blocks, exposed by a simple drag-and-drop user interface. Leaf generates abstract syntax trees which are compiled into dynamic SQL queries. RESULTS: Leaf is a successful production-supported tool at the University of Washington, which hosts a central Leaf instance querying an enterprise data warehouse with over 300 active users. Through the support of UW Medicine (https://uwmedicine.org), the Institute of Translational Health Sciences (https://www.iths.org), and the National Center for Data to Health (https://ctsa.ncats.nih.gov/cd2h/), Leaf source code has been released into the public domain at https://github.com/uwrit/leaf. DISCUSSION: Leaf allows the querying of single or multiple clinical databases simultaneously, even those of different data models. This enables fast installation without costly extraction or duplication. CONCLUSIONS: Leaf differs from existing cohort discovery tools because it does not specify a required data model and is designed to seamlessly leverage existing user authentication systems and clinical databases in situ. We believe Leaf to be useful for health system analytics, clinical research data warehouses, precision medicine biobanks, and clinical studies involving large patient cohorts.

Personalized Medicine Implementation with Non-traditional Data Sources: A Conceptual Framework and Survey of the Literature.

OBJECTIVES: With the explosive growth in availability of health data captured using non-traditional sources, the goal for this work was to evaluate the current biomedical literature on theory- driven studies investigating approaches that leverage non- traditional data in personalized medicine applications. METHODS: We conducted a literature assessment guided by the personalized medicine unsolicited health information (pUHl) conceptual framework incorporating diffusion of innovations and task-technology fit theories. RESULTS: The assessment provided an oveiview of the current literature and highlighted areas for future research. In particular, there is a need for: more research on the relationship between attributes of innovation and of societal structure on adoption; new study designs to enable flexible communication channels; more work to create and study approaches in healthcare settings; and more theory-driven studies with data-driven interventions. CONCLUSION: This work introduces to an informatics audience an elaboration on personalized medicine implementation with non-traditional data sources by blending it with the pUHl conceptual framework to help explain adoption. We highlight areas to pursue future theory-driven research on personalized medicine applications that leverage non-traditional data sources.

Clinical exome sequencing vs. usual care for hereditary colorectal cancer diagnosis: A pilot comparative effectiveness study.

BACKGROUND: Clinical exome sequencing (CES) provides the advantage of assessing genetic variation across the human exome compared to a traditional stepwise diagnostic approach or multi-gene panels. Comparative effectiveness research methods offer an approach to better understand the patient-centered and economic outcomes of CES. PURPOSE: To evaluate CES compared to usual care (UC) in the diagnostic work-up of inherited colorectal cancer/polyposis (CRCP) in a randomized controlled trial (RCT). METHODS: The primary outcome was clinical sensitivity for the diagnosis of inherited CRCP; secondary outcomes included psychosocial outcomes, family communication, and healthcare resource utilization. Participants were surveyed 2 and 4 weeks after results return and at 3-month intervals up to 1 year. RESULTS: Evolving outcome measures and standard of care presented critical challenges. The majority of participants in the UC arm received multi-gene panels [94.73%]. Rates of genetic findings supporting the diagnosis of hereditary CRCP were 7.5% [7/93] vs. 5.4% [5/93] in the CES and UC arms, respectively (P = 0.28). Differences in privacy concerns after receiving CRCP results were identified (0.88 in UC vs 0.38 in CES, P = 0.05); however, healthcare resource utilization, family communication and psychosocial outcomes were similar between the two arms. More participants with positive results (17.7%) intended to change their life insurance 1  month after the first return visit compared to participants returned a variant of uncertain significance (9.1%) or negative result (4.8%) (P = 0.09). CONCLUSION: Our results suggest that CES provides similar clinical benefits to multi-gene panels in the diagnosis of hereditary CRCP.

The Feelings About genomiC Testing Results (FACToR) Questionnaire: Development and Preliminary Validation.

The purpose of this study was to develop a brief instrument, the Feelings About genomiC Testing Results (FACToR), to measure the psychosocial impact of returning genomic findings to patients in research and clinical practice. To create the FACToR, we modified and augmented the Multidimensional Impact of Cancer Risk Assessment (MICRA) questionnaire based on findings from a literature review, two focus groups (N = 12), and cognitive interviews (N = 6). We evaluated data from 122 participants referred for evaluation for inherited colorectal cancer or polyposis from the New EXome Technology in (NEXT) Medicine Study, an RCT of exome sequencing versus usual care. We assessed floor and ceiling effects of each item, conducted principal component analysis to identify subscales, and evaluated each subscale's internal consistency, test-retest reliability, and construct validity. After excluding items that were ambiguous or demonstrated floor or ceiling effects, 12 items forming four distinct subscales were retained for further analysis: negative emotions, positive feelings, uncertainty, and privacy concerns. All four showed good internal consistency (0.66-0.78) and test-retest reliability (0.65-0.91). The positive feelings and the uncertainty subscales demonstrated known-group validity. The 12-item FACToR with four subscales shows promising psychometric properties on preliminary evaluation in a limited sample and needs to be evaluated in other populations.

Identifying Patients Who Are Likely to Receive Most of Their Care From a Specific Health Care System: Demonstration via Secondary Analysis.

BACKGROUND: In the United States, health care is fragmented in numerous distinct health care systems including private, public, and federal organizations like private physician groups and academic medical centers. Many patients have their complete medical data scattered across these several health care systems, with no particular system having complete data on any of them. Several major data analysis tasks such as predictive modeling using historical data are considered impractical on incomplete data. OBJECTIVE: Our objective was to find a way to enable these analysis tasks for a health care system with incomplete data on many of its patients. METHODS: This study presents, to the best of our knowledge, the first method to use a geographic constraint to identify a reasonably large subset of patients who tend to receive most of their care from a given health care system. A data analysis task needing relatively complete data can be conducted on this subset of patients. We demonstrated our method using data from the University of Washington Medicine (UWM) and PreManage data covering the use of all hospitals in Washington State. We compared 10 candidate constraints to optimize the solution. RESULTS: For UWM, the best constraint is that the patient has a UWM primary care physician and lives within 5 miles of at least one UWM hospital. About 16.01% (55,707/348,054) of UWM patients satisfied this constraint. Around 69.38% (10,501/15,135) of their inpatient stays and emergency department visits occurred within UWM in the following 6 months, more than double the corresponding percentage for all UWM patients. CONCLUSIONS: Our method can identify a reasonably large subset of patients who tend to receive most of their care from UWM. This enables several major analysis tasks on incomplete medical data that were previously deemed infeasible.

Automating Electronic Clinical Data Capture for Quality Improvement and Research: The CERTAIN Validation Project of Real World Evidence.

BACKGROUND: The availability of high fidelity electronic health record (EHR) data is a hallmark of the learning health care system. Washington State's Surgical Care Outcomes and Assessment Program (SCOAP) is a network of hospitals participating in quality improvement (QI) registries wherein data are manually abstracted from EHRs. To create the Comparative Effectiveness Research and Translation Network (CERTAIN), we semi-automated SCOAP data abstraction using a centralized federated data model, created a central data repository (CDR), and assessed whether these data could be used as real world evidence for QI and research. OBJECTIVES: Describe the validation processes and complexities involved and lessons learned. METHODS: Investigators installed a commercial CDR to retrieve and store data from disparate EHRs. Manual and automated abstraction systems were conducted in parallel (10/2012-7/2013) and validated in three phases using the EHR as the gold standard: 1) ingestion, 2) standardization, and 3) concordance of automated versus manually abstracted cases. Information retrieval statistics were calculated. RESULTS: Four unaffiliated health systems provided data. Between 6 and 15 percent of data elements were abstracted: 51 to 86 percent from structured data; the remainder using natural language processing (NLP). In phase 1, data ingestion from 12 out of 20 feeds reached 95 percent accuracy. In phase 2, 55 percent of structured data elements performed with 96 to 100 percent accuracy; NLP with 89 to 91 percent accuracy. In phase 3, concordance ranged from 69 to 89 percent. Information retrieval statistics were consistently above 90 percent. CONCLUSIONS: Semi-automated data abstraction may be useful, although raw data collected as a byproduct of health care delivery is not immediately available for use as real world evidence. New approaches to gathering and analyzing extant data are required.

Sustainability considerations for clinical and translational research informatics infrastructure.

A robust biomedical informatics infrastructure is essential for academic health centers engaged in translational research. There are no templates for what such an infrastructure encompasses or how it is funded. An informatics workgroup within the Clinical and Translational Science Awards network conducted an analysis to identify the scope, governance, and funding of this infrastructure. After we identified the essential components of an informatics infrastructure, we surveyed informatics leaders at network institutions about the governance and sustainability of the different components. Results from 42 survey respondents showed significant variations in governance and sustainability; however, some trends also emerged. Core informatics components such as electronic data capture systems, electronic health records data repositories, and related tools had mixed models of funding including, fee-for-service, extramural grants, and institutional support. Several key components such as regulatory systems (e.g., electronic Institutional Review Board [IRB] systems, grants, and contracts), security systems, data warehouses, and clinical trials management systems were overwhelmingly supported as institutional infrastructure. The findings highlighted in this report are worth noting for academic health centers and funding agencies involved in planning current and future informatics infrastructure, which provides the foundation for a robust, data-driven clinical and translational research program.

Automating Construction of Machine Learning Models With Clinical Big Data: Proposal Rationale and Methods.

BACKGROUND: To improve health outcomes and cut health care costs, we often need to conduct prediction/classification using large clinical datasets (aka, clinical big data), for example, to identify high-risk patients for preventive interventions. Machine learning has been proposed as a key technology for doing this. Machine learning has won most data science competitions and could support many clinical activities, yet only 15% of hospitals use it for even limited purposes. Despite familiarity with data, health care researchers often lack machine learning expertise to directly use clinical big data, creating a hurdle in realizing value from their data. Health care researchers can work with data scientists with deep machine learning knowledge, but it takes time and effort for both parties to communicate effectively. Facing a shortage in the United States of data scientists and hiring competition from companies with deep pockets, health care systems have difficulty recruiting data scientists. Building and generalizing a machine learning model often requires hundreds to thousands of manual iterations by data scientists to select the following: (1) hyper-parameter values and complex algorithms that greatly affect model accuracy and (2) operators and periods for temporally aggregating clinical attributes (eg, whether a patient's weight kept rising in the past year). This process becomes infeasible with limited budgets. OBJECTIVE: This study's goal is to enable health care researchers to directly use clinical big data, make machine learning feasible with limited budgets and data scientist resources, and realize value from data. METHODS: This study will allow us to achieve the following: (1) finish developing the new software, Automated Machine Learning (Auto-ML), to automate model selection for machine learning with clinical big data and validate Auto-ML on seven benchmark modeling problems of clinical importance; (2) apply Auto-ML and novel methodology to two new modeling problems crucial for care management allocation and pilot one model with care managers; and (3) perform simulations to estimate the impact of adopting Auto-ML on US patient outcomes. RESULTS: We are currently writing Auto-ML's design document. We intend to finish our study by around the year 2022. CONCLUSIONS: Auto-ML will generalize to various clinical prediction/classification problems. With minimal help from data scientists, health care researchers can use Auto-ML to quickly build high-quality models. This will boost wider use of machine learning in health care and improve patient outcomes.

A Knowledge-based System for Intelligent Support in Pharmacogenomics Evidence Assessment: Ontology-driven Evidence Representation and Retrieval.

Pharmacogenomics holds promise as a critical component of precision medicine. Yet, the use of pharmacogenomics in routine clinical care is minimal, partly due to the lack of efficient and effective use of existing evidence. This paper describes the design, development, implementation and evaluation of a knowledge-based system that fulfills three critical features: a) providing clinically relevant evidence, b) applying an evidence-based approach, and c) using semantically computable formalism, to facilitate efficient evidence assessment to support timely decisions on adoption of pharmacogenomics in clinical care. To illustrate functionality, the system was piloted in the context of clopidogrel and warfarin pharmacogenomics. In contrast to existing pharmacogenomics knowledge bases, the developed system is the first to exploit the expressivity and reasoning power of logic-based representation formalism to enable unambiguous expression and automatic retrieval of pharmacogenomics evidence to support systematic review with meta-analysis.

Design Recommendations for Pharmacogenomics Clinical Decision Support Systems.

The use of pharmacogenomics (PGx) in clinical practice still faces challenges to fully adopt genetic information in targeting drug therapy. To incorporate genetics into clinical practice, many support the use of Pharmacogenomics Clinical Decision Support Systems (PGx-CDS) for medication prescriptions. This support was fueled by new guidelines to incorporate genetics for optimizing drug dosage and reducing adverse events. In addition, the complexity of PGx led to exploring CDS outside the paradigm of the basic CDS tools embedded in commercial electronic health records. Therefore, designing the right CDS is key to unleashing the full potential of pharmacogenomics and making it a part of clinicians' daily workflow. In this work, we 1) identify challenges and barriers of the implementation of PGx-CDS in clinical settings, 2) develop a new design approach to CDS with functional characteristics that can improve the adoption of pharmacogenomics guidelines and thus patient safety, and 3) create design guidelines and recommendations for such PGx-CDS tools.

Practical considerations for implementing genomic information resources. Experiences from eMERGE and CSER.

OBJECTIVES: To understand opinions and perceptions on the state of information resources specifically targeted to genomics, and approaches to delivery in clinical practice. METHODS: We conducted a survey of genomic content use and its clinical delivery from representatives across eight institutions in the electronic Medical Records and Genomics (eMERGE) network and two institutions in the Clinical Sequencing Exploratory Research (CSER) consortium in 2014. RESULTS: Eleven responses representing distinct projects across ten sites showed heterogeneity in how content is being delivered, with provider-facing content primarily delivered via the electronic health record (EHR) (n=10), and paper/pamphlets as the leading mode for patient-facing content (n=9). There was general agreement (91%) that new content is needed for patients and providers specific to genomics, and that while aspects of this content could be shared across institutions there remain site-specific needs (73% in agreement). CONCLUSION: This work identifies a need for the improved access to and expansion of information resources to support genomic medicine, and opportunities for content developers and EHR vendors to partner with institutions to develop needed resources, and streamline their use - such as a central content site in multiple modalities while implementing approaches to allow for site-specific customization.

Modeling the costs of clinical decision support for genomic precision medicine.

Clinical decision support (CDS) within the electronic health record represents a promising mechanism to provide important genomic findings within clinical workflows. To better understand the current and possible future costs of genomic CDS, we leveraged our local CDS experience to assemble a simple model with inputs such as initial cost and numbers of patients, rules, and institutions. Our model assumed efficiencies of scale and allowed us to perform a one-way sensitivity analysis of the impact of each model input. The number of patients with genomic results per institution was the only single variable that could decrease the cost of CDS per useful alert below projected genomic sequencing costs. Because of the prohibitive upfront cost of sequencing large numbers of individuals, increasing the number of institutions using genomic CDS and improving the efficiency of sharing CDS infrastructure represent the most promising paths to making genomic CDS cost-effective.

Harnessing next-generation informatics for personalizing medicine: a report from AMIA's 2014 Health Policy Invitational Meeting.

The American Medical Informatics Association convened the 2014 Health Policy Invitational Meeting to develop recommendations for updates to current policies and to establish an informatics research agenda for personalizing medicine. In particular, the meeting focused on discussing informatics challenges related to personalizing care through the integration of genomic or other high-volume biomolecular data with data from clinical systems to make health care more efficient and effective. This report summarizes the findings (n = 6) and recommendations (n = 15) from the policy meeting, which were clustered into 3 broad areas: (1) policies governing data access for research and personalization of care; (2) policy and research needs for evolving data interpretation and knowledge representation; and (3) policy and research needs to ensure data integrity and preservation. The meeting outcome underscored the need to address a number of important policy and technical considerations in order to realize the potential of personalized or precision medicine in actual clinical contexts.