Bridge2AI
Bridge2AI-ChoRUS
Researchers have made great strides in improving patient care through the use of artificial intelligence (AI) in critical care environments. Studies have yielded many positive results from using AI in critical care (AICC)—for example, early detection of sepsis, organ failure, and arrythmia.
Challenges for AI in critical care
Despite these advances, problems must be addressed for AICC research to avoid being impeded by an insufficient AICC infrastructure. For example:
- Lack of a large, diverse data set. Existing large, high-resolution data sets are available only at single centers and are biased due to being specific to certain demographics or regions.
- Lack of standards that support interoperability. Waveform data (e.g., ECG, blood pressure data) are rarely recorded in sufficiently detailed samples. Privacy protection standards vary between sites nationally, and demographic information may be lost due to those varying privacy standards.
- Lack of a trained AI workforce and a public familiar with medical AI. To effectively engage in AICC research and improve algorithms, a trained medical AI workforce is needed. To make patients comfortable with AICC, the public needs exposure to medical AI and access to accurate information about potential benefits.
Therefore, the NIH Bridge2AI-funded CHoRUS project—a consortium of 18 top medical research institutions—aims to solve those three problems by creating the following:
- A 100,000-patient data set with health data from a broad sample population.
- Standards and AICC tools to facilitate interoperability.
- Training to expand the AICC research workforce, and public engagement to familiarize general audiences with medical AI.
The NIH Bridge2AI-funded CHoRUS project consists of six modules—Teaming; Ethical and Trustworthy AI; Standards; Tool Development and Optimization; Data Acquisition; and Skills and Workforce Development—each of which address a vital issue related to the advancement of medical AI research.
Beyond the four-year span of CHoRUS (2022–2026), the project’s accomplishments will continue to yield benefits for researchers and, ultimately, patients. The 100,000-patient data set, the establishment of a more robust AICC ecosystem, and the trained medical AI workforce will serve the public by providing better critical care to patients in all regions and of all backgrounds.
UF Teams
| Name | Title | Involved Modules |
|---|---|---|
| Azra Bihorac | MD, MS, Professor | Teaming, Ethics, Tools, Data Acq, SWD |
| Parisa Rashidi | PhD, Associate Professor | Tools, SWD |
| Barbara Evans | JD,PhD, Professor | Ethics |
| Elizabeth Shenkman | PhD, Professor | Ethics |
| Yulia Strekalova | PhD, Assistant Professor | Teaming, SWD |
| Benjamin Shickel | PhD, Assistant Professor | Tools, Data Acq, SWD |
| Tezcan Ozrazgat Baslanti | PhD, Assistant Professor | Ethics, Tools, Data Acq, Standards |
| Serena Guo | PhD, Assistant Professor | Ethics, Tools |
| Yi Guo | PhD, Associate Professor | Ethics, Tools |
| Brooke Armfield | PhD, Assistant Director for Clinical Research | Data Acq |
| Ziyuan Guan | MS, Senior Data Engineer | Tools, Data Acq, Standards |
Progress
Please check with Monday