# Clinical Evidence Generation from Electronic Health Records for Precision Medicine

> **NIH NIH K01** · UNIVERSITY OF COLORADO DENVER · 2020 · $53,866

## Abstract

PROJECT SUMMARY
 This career development application describes targeted coursework and mentored research
for clinical evidence generation from electronic health records for precision medicine. Although
randomized controlled trials (RCTs) are the gold standard of clinical evidence, either due to
RCTs not matching the patient seen in the clinic, the rarity of a condition, or lack of equipoise to
justify randomization, these data are often unavailable to guide a number of treatment
decisions. A clinical example is the case of management of unruptured intracranial aneurysms
(UIAs). Although an RCT was attempted to determine the benefit of preventive surgical
treatment compared to careful observation, this study failed due to patient and provider
concerns about randomization. It is clear that new methods of evidence generation are needed.
The research aims of this proposal describe a novel systematic approach to clinical evidence
generation from EHRs under the hypothesis that domain expert provided insights into the “on-
the-ground” work of clinical assessment will enable the generation of expert-informed
hypotheses, which coupled with data quality assessment and newly developed “target trial”
causal inference models will allow for robust precision evidence to support clinical decision
making. This hypothesis will be tested by: Aim 1 - Identify factors guiding clinical management
recommendations for UIAs through in-depth, semi-structured interviews of neurovascular expert
physicians; Aim 2 - Extract factors guiding clinical recommendations and clinical outcomes from
the EHR, characterize the quality and extractability of these variables, and assess their fitness
for use in clinical evidence generation; and Aim 3 - Assess the efficacy of preventive surgical
treatment vs observation for UIAs through a target-trial causal inference approach. This project
has significant potential to influence the clinical care provided for patients with UIAs, where
there is currently a paucity of evidence guiding care. The creation of a robust, and reproducible
framework for clinical evidence generation is both innovative and impactful on the field of
biomedical informatics and clinical data science. To accomplish these research aims, Dr. Wiley
will be mentored by a team of experts in clinical evidence generation (Dr. Lisa Schilling),
qualitative methodologies (Dr. Jennifer Reich), data quality assessments (Dr. Michael Kahn),
and causal inference methodologies (Dr. Debashis Ghosh). This mentorship coupled with Dr.
Wiley’s existing record of research performance, dedication to local and national education and
service, will ensure Dr. Wiley becomes an independent investigator and international leader in
clinical evidence generation from EHRs for precision medicine

## Key facts

- **NIH application ID:** 10189099
- **Project number:** 3K01LM013088-02S1
- **Recipient organization:** UNIVERSITY OF COLORADO DENVER
- **Principal Investigator:** Laura Katherine Wiley
- **Activity code:** K01 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2020
- **Award amount:** $53,866
- **Award type:** 3
- **Project period:** 2019-05-17 → 2022-04-30

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10189099

## Citation

> US National Institutes of Health, RePORTER application 10189099, Clinical Evidence Generation from Electronic Health Records for Precision Medicine (3K01LM013088-02S1). Retrieved via AI Analytics 2026-06-11 from https://api.ai-analytics.org/grant/nih/10189099. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*