Women identified as high-risk for breast cancer may benefit from personalized risk-reducing strategies; however, barriers exist, including the time required to conduct a risk assessment of each woman in a population. Electronic health records (EHRs), a common source for populating risk assessment models, present challenges, including missing data, and data types more accurate when provided by patients compared to EHRs. We previously extracted EHR data on age, race/ethnicity, family history of BC, benign breast disease, and breast density to calculate BC risk according to the Breast Cancer Surveillance Consortium (BCSC) model among 9,514 women. Comparing self-reported and EHR data, more women with a first-degree family history of BC (14.6% vs. 4.4%) and benign breast biopsies (21.3% vs. 11.3%) were identified with patient-reported data, but EHR data identified more women with atypia or lobular carcinoma in situ (1.1% vs. 2.3%). The EHR had missing data on race/ethnicity for 26.8% of women and on first-degree family history of BC for 87.2%. Opportunely, Fast Healthcare Interoperability Resources (FHIR), application programming interfaces (APIs), and new legislation offer an elegant solution for automated BC risk assessment that integrates both patient-generated health data and EHR data to harness the strengths of each approach. To increase the likelihood of developing disseminatable and equitable strategies that integrate EHR and patient-generated health data for risk assessment and personalized BC risk reduction, the focus of this project is to refine and test our approach among diverse multiethnic women. Our aims are: 1) upgrade FHIR integration of a patient decision aid, parse EHR data pulled by patients, develop a user interface to enable women to view and augment their EHR data, conduct user evaluations of the user interface; 2) assess the effect of the FHIR-enhanced patient decision aid on patient activation, risk perception, and usability in a pilot study of multiethnic high-risk women; and 3) identify multilevel barriers to implementing FHIR-enhanced patient decision aid into clinical care.

This project is eligible for a matching fund stipend from the Data Science Institute. This is not a guarantee of payment, and the total amount is subject to available funding.

Faculty Advisor

  • Professor: Rita, Kukafka
  • Center/Lab: Department of Biomedical Informatics
  • My research interests focus on patient, provider, and community engagement technologies, risk communication, behavioral and decision science, and implementation of technologies. I apply quantitative and qualitative methods to design, implement and study the effects of technology on decision-making. My current work integrates multiple levels of patient-derived and electronic health record (EHR) data to develop and implement decision support for precision cancer prevention.

Project Timeline

  • Earliest starting date: 10/15/2022
  • End date: 5/6/2023
  • Number of hours per week of research expected during Fall 2022: ~10

Candidate requirements

  • Skill sets: Fluency in programming languages (e.g., R/Python, SQL, JAVA, PHP), some experience or interest in conducting usability testing, ability to work in teams and with senior programmers, software developers, data scientists, and medical/healthcare professionals.
  • Student eligibility: freshman, sophomore, junior, senior, master’s
  • International students on F1 or J1 visa: eligible
  • Academic Credit Possible: Yes