Healthcare Innovation Bridging Research, Informatics & Design Lab Projects | NYU Langone Health

Skip to Main Content
Healthcare Innovation Bridging Research, Informatics & Design Lab Healthcare Innovation Bridging Research, Informatics & Design Lab Projects

Healthcare Innovation Bridging Research, Informatics & Design Lab Projects

The Healthcare Innovation Bridging Research, Informatics, and Design (HiBRID) Lab collaborates with researchers across NYU Langone on a variety of research and operational projects. We aim to improve healthcare delivery and patient care by supporting user-centered design in digital health applications and electronic health record (EHR) innovations.

Our unique interdisciplinary research group currently manages a portfolio of seven federally sponsored grants and multiple enterprise digital innovation initiatives. We represent core members of critical digital innovation teams at NYU Langone including Clinical Decision Support, FuturePractice, Patient Digital Experience, and Clinical Digital Experience.

Learn more about our current projects below.

Behavioral Economics in the EHR to Promote Choosing Wisely Guidelines Adherence for Older Adults

This randomized clinical trial will test a new EHR module to improve guideline-compliant care of older adults with diabetes. The module incorporates effective behavioral economics principles to improve the degree to which care of older adults is compliant with Choosing Wisely guidelines; this generally involves less aggressive targets for HbA1c and the reduction of medications other than metformin. The implementation of the module is triggered by patient scheduling and medication prescribing in Epic. The behavioral economics principles include suggesting alternatives to medications, requiring justification, setting of appropriate default order sets, and incorporation of anchoring and checklists to guide behavior.

Digital Diabetes Prevention Integration Tool

This project seeks to set the standard for how data from new digital behavior change interventions are integrated into the EHR and clinical workflow. The project leverages a National Institutes of Health (NIH)–funded prototype integration tool with the goal of conducting a large-scale hybrid effectiveness and implementation study. Ongoing activities include piloting of the new tool within the NYU Langone ambulatory primary care network and partnering with digital health companies to determine best practices.


Led by Devin Mann, MD, MS, in collaboration with NYU Langone’s Medical Center Information Technology team, the FuturePractice team explores, designs, and tests potential healthcare solutions. In partnership with our multidisciplinary colleagues, we solve problems, inspire change, and explore applications of emerging technology. Together with the HiBRID Lab, we are a part of the larger NYU Langone digital health ecosystem.

Effects of Nurse-Driven Integrated Clinical Prediction Tool on Antibiotic Prescribing

This study evaluates the effects of a novel integrated clinical decision prediction tool, ICPR3, on antibiotic prescription patterns of nurses for acute respiratory infections (ARIs). The intervention is an EHR-integrated risk calculator and order set to help guide appropriate, evidence-based antibiotic prescriptions for patients presenting with ARI symptoms.

iMatter Modern Journaling System

In this project, we will evaluate the effect of a technology-based patient-reported outcome tool called iMatter for care of patients with uncontrolled type 2 diabetes. The iMatter tool uses text messaging to capture patient-reported outcome data on behaviors such as medication and dietary compliance, physical activity, and quality of life in real time. It enhances patient engagement through data-driven feedback and motivational messages and creates dynamic visualizations of the data in a personal journal report that is sent directly to patients. The monthly journal report includes key insights and evidence-based recommendations to help patients reflect on changes in their response overtime, and to help them better manage their type 2 diabetes.

Addressing Antihypertensive Medication Adherence Through EHR-Enabled Teamlets in Primary Care

This project will fill a critical gap in the evidence base to answer the question of whether a clinic-based intervention that includes use of pharmacy fill data, health coaching by medical assistants, and EHR-based clinical decision support can improve medication adherence and improve blood pressure. To answer this question, we will perform a pragmatic, type I hybrid comparative effectiveness–implementation study.

National Cancer Institute’s Cancer Moonshot Initiative: Broadening the Research, Impact, and Delivery of Genetic Services

We collaborate across NYU Langone to build and integrate a process for identification, education, and testing of patients that meet hereditary cancer screening guidelines. Our tool uses an evidence-based algorithm to screen our entire patient population for people at high risk for hereditary cancers. The system continuously runs the algorithm and creates a dynamic list of high-risk patients. The genetic counseling team will reach out to the people on the list via the NYU Langone Health MyChart portal and engage them in a conversation about their risk. At-risk patients will also be supported by a genetic counseling chatbot developed by an outside company (Clear Genetics) to support the genetic counseling team.

Smart Clinical Decision Support: Using Machine Learning to Suppress the Noise Generated by Clinical Decision Support

We are building a machine learning model and corresponding data architecture to suppress inappropriate clinical decision support alerts in our EHR system, Epic. With the insertion of a machine learning system that could predict when physicians were likely to ignore EHR alerts (a type of clinical decision support) and if that risk is high, automatically suppressing the alert, we aim to mitigate the alert fatigue, which is a significant contributor to the larger burnout phenomenon. This study proposes to reduce the alert quantity with high confidence and maintain the volume of vaccine orders with minimal decrease.