Personalized medicine can be defined broadly as a model of healthcare that is predictive, personalized, preventive and participatory. Two US President’s Council of Advisors on Science and Technolog...

Background: In a multisite clinical research collaboration, institutions may or may not use the same common data model (CDM) to store clinical data. To overcome this challenge, we proposed to use Health Level 7’s Fast Healthcare Interoperability Resources (FHIR) as a meta-CDM—a single standard to represent clinical data. Objective: In this study, we aimed to create an open-source application termed the Clinical Asset Mapping Program for FHIR (CAMP FHIR) to efficiently transform clinical data to FHIR for supporting source-agnostic CDM-to-FHIR mapping. Methods: Mapping with CAMP FHIR involves (1) mapping each source variable to its corresponding FHIR element and (2) mapping each item in the source data’s value sets to the corresponding FHIR value set item for variables with strict value sets. To date, CAMP FHIR has been used to transform 108 variables from the Informatics for Integrating Biology & the Bedside (i2b2) and Patient-Centered Outcomes Research Network data models to fields across 7 FHIR resources. It is designed to allow input from any source data model and will support additional FHIR resources in the future. Results: We have used CAMP FHIR to transform data on approximately 23,000 patients with asthma from our institution’s i2b2 database. Data quality and integrity were validated against the origin point of the data, our enterprise clinical data warehouse. Conclusions: We believe that CAMP FHIR can serve as an alternative to implementing new CDMs on a project-by-project basis. Moreover, the use of FHIR as a CDM could support rare data sharing opportunities, such as collaborations between academic medical centers and community hospitals. We anticipate adoption and use of CAMP FHIR to foster sharing of clinical data across institutions for downstream applications in translational research.

Opportunities for genomic clinical decision support interventions

This study assessed physician attitudes toward adopting genome-guided prescribing through clinical decision support (CDS), prior to enlisting in the Clinical Implementation of Personalized Medicine through Electronic Health Records and Genomics pilot pharmacogenomics project (CLIPMERGE PGx). We developed a survey instrument that includes the Evidence Based Practice Attitude Scale, adapted to measure attitudes toward adopting genome-informed interventions (EBPAS-GII). The survey also includes items to measure physicians’ characteristics (awareness, experience, and perceived usefulness), attitudes about personal genome testing (PGT) services, and comfort using technology. We surveyed 101 General Internal Medicine physicians from the Icahn School of Medicine at Mount Sinai (ISMMS). The majority were residency program trainees (~88%). Prior to enlisting into CLIPMERGE PGx, most physicians were aware of and had used decision support aids. Few physicians, however, were aware of and had used genome-guided prescribing. The majority of physicians viewed decision support aids and genotype data as being useful for making prescribing decisions. Most physicians had not heard of, but were willing to use, PGT services and felt comfortable interpreting PGT results. Most physicians were comfortable with technology. Physicians who perceived genotype data to be useful in making prescribing decisions, had more positive attitudes toward adopting genome-guided prescribing through CDS. Our findings suggest that internal medicine physicians have a deficit in their familiarity and comfort interpreting and using genomic information. This has reinforced the importance of gathering feedback and guidance from our enrolled physicians when designing genome-guided CDS and the importance of prioritizing genomic medicine education at our institutions.

Incorporating expert knowledge at the time machine learning models are trained holds promise for producing models that are easier to interpret. The main objectives of this study were to use a feature engineering approach to incorporate clinical expert knowledge prior to applying machine learning techniques, and to assess the impact of the approach on model complexity and performance. Four machine learning models were trained to predict mortality with a severe asthma case study. Experiments to select fewer input features based on a discriminative score showed low to moderate precision for discovering clinically meaningful triplets, indicating that discriminative score alone cannot replace clinical input. When compared to baseline machine learning models, we found a decrease in model complexity with use of fewer features informed by discriminative score and filtering of laboratory features with clinical input. We also found a small difference in performance for the mortality prediction task when comparing baseline ML models to models that used filtered features. Encoding demographic and triplet information in ML models with filtered features appeared to show performance improvements from the baseline. These findings indicated that the use of filtered features may reduce model complexity, and with little impact on performance.