Health Research Implementation Services

Our research implementation services are available to all UM researchers who have developed models in need of prospective validation, workflow integration and clinical trials.

Building a machine learning model is the first step in the journey of testing your research at Michigan Medicine. You’ll need help integrating it for prospective validation, defining workflow integration, and navigating the steps needed to approve clinical testing. We have the systems, processes, and expertise needed to move your research forward!

Early Implementation Consultation

We are available to meet with you early in your research to help plan for integration.

The AI & Digital Health Innovation Research Implementation Team consults with researchers to understand their models, the expected impact of their models, identify potential challenges with translating their model prospectively and determine how to overcome those challenges. We also provide support for writing research implementation services into proposals to enhance grant proposals.

For more information, contact:
Phil Jacokes, Managing Director,
AI & Digital Health Innovation

“AI & Digital Health Innovation is playing a key role in guiding clinical workflow implementation for AI models at Michigan Medicine, providing expertise that helps deliver our innovative research to the bedside where it can have a positive impact on patients.”

Steven Kunkel, PhD
Executive Vice Dean for Research, Medical School
Chief Scientific Officer, Michigan Medicine
Peter A. Ward Distinguished University Professor

Prospective Data Integration

We deliver real time health data from Michigan Medicine to our researcher’s AI models for prospective model validation.

Our Research Implementation Services Team will help you navigate options to integrate your model with the appropriate data pipelines. A successful prospective validation can lead to next steps including:

  • - Human Centered Design Sprints

  • - Workflow Integration

  • - Clinical Trials

For more information, contact:
Phil Jacokes, Managing Director,
AI & Digital Health Innovation

“Quote”

Name, Title
Dept

Workflow Integration

AI & Digital Health Innovation is a trusted services partner for testing models within Michigan Medicine. Request our support for guiding you down the path of developing workflows to maximize the clinical impact of your model!

Integrating a model into the clinical workflow at Michigan Medicine is a complicated process with many touch points including IRB, Michigan Medicine’s Health Information Technology & Services (HITS), the Clinical Intelligence Committee (CIC), Epic, hospitalists, nurses, and more.

We are here to guide you through these challenging pathways and to leverage our evidence-based approach to implement AI models into workflows for testing at Michigan Medicine.

Our team can help with:

  • Connecting to subject matter experts and clinical champions within Michigan Medicine

  • Guiding teams down the path of developing appropriate workflows to maximize clinical impact

  • Coaching research teams prior to clinical operational governance committees

  • IRB guidance and consultation

  • Planning design sessions with clinicians, nurses, and support staff

  • Exploring options to display and alert in MiChart

For more information, contact:
Phil Jacokes, Managing Director,
AI & Digital Health Innovation

“AI & Digital Health Innovation guided me through the steps needed to develop a clinical trial within Mott’s Children’s Hospital. Their understanding of the workflows, governances, and systems needed for the clinical trial were essential to were essential for accelerating the PICTURE Pediatric trial.”

Sardar Ansari, PhD
Assistant Professor, Emergency Medicine

Clinical Impact Monitoring

After a model is integrated into the workflow, we can monitor the complex relationships between cause and effect within the ever-changing clinical environment.

Imagine the best-case scenario: your model identifies an at-risk patient. The clinician receives an alert and intervenes to prevent a bad outcome. Existing performance monitors would count that as a false positive – the model identified a patient who didn’t deteriorate. However, AI and Digital Health Innovation’s novel causal inference monitoring tools help pinpoint exactly how clinicians are responding to their model, when they are intervening, and how the model is helping impact patient care.

For more information, contact:
Phil Jacokes, Managing Director,
AI & Digital Health Innovation

“Clinical Impact Monitoring is needed to help researchers understand the impact of a model in a clinical setting. As a Data Scientist, I need to this information to help me fully understand why a model’s performance might be declining when it is put use.”

Brittany Baur, PhD
Max Harry Weil Institute for Critical Care Research and Innovation
Michigan Medicine