# Explainable, Fair, Reproducible and Collaborative Surgical Artificial Intelligence: Integrating data, algorithms and clinical reasoning for surgical risk assessment (XAIIDEALIST)

> **NIH NIH R01** · UNIVERSITY OF FLORIDA · 2024 · $249,124

## Abstract

Project Summary
In the United States, the average American will undergo seven surgical operations during their lifetime. Each year
150,000 surgical patients die, and 1.5 million develop a complication after surgery. Progress in medical Artificial
Intelligence (AI) remains halted by limited datasets and models with insufficient interpretability, transparency, fairness,
and reproducibility that are difficult to implement and share across institutions. The overall objective of this
administrative equipment supplement is to develop a new conceptual framework that includes digital pathological
images from surgical biopsies for “Explainable, Fair, Reproducible, and Collaborative Medical AI”. The widespread
adoption of electronic health records (EHR) leading to digital data has enabled the proliferation of AI/ML tools for risk
surveillance and diagnosis. However, progress in the field remains halted by limited datasets (such as lack of digital
pathological images) and models with insufficient interpretability, fairness, and reproducibility that are difficult to
implement and share across institutions. The lack of explainability and transparency of black-box AI models is
challenging for the high-risk medical environment and has delayed clinical implementation of AI on a large scale.
The overall objective will be achieved by incorporating digital pathology images into three specific aims: (1) External and
prospective validation of novel interpretable, dynamic, actionable, fair and reproducible algorithmic toolkit for real-time
surgical risk surveillance. (2) Developing and evaluating explainable AI platform (XAI-IDEALIST) for real-time surgical risk
surveillance using human-grounded benchmarks. (3) Implementing and evaluating a federated learning approach with
advanced privacy features for collaborative surgical risk model training. Ultimately, the results are expected to improve
patient outcomes and decrease hospitalization costs, as well as lifelong complications.
With the requested equipment, Leica Versa 200 we will aim to scan 500 pathology slides per week for our retrospective
data and approximately 3700 slides that will be used during our validation stage. Additional institutional resources
provided by the University of Florida College of Medicine Office of Research will pay for a trained technician, equipment
maintenance, and digital storage fees for the life of the grant.

## Key facts

- **NIH application ID:** 11097804
- **Project number:** 3R01GM110240-08S1
- **Recipient organization:** UNIVERSITY OF FLORIDA
- **Principal Investigator:** Azra Bihorac
- **Activity code:** R01 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $249,124
- **Award type:** 3
- **Project period:** 2016-03-01 → 2026-05-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/11097804

## Citation

> US National Institutes of Health, RePORTER application 11097804, Explainable, Fair, Reproducible and Collaborative Surgical Artificial Intelligence: Integrating data, algorithms and clinical reasoning for surgical risk assessment (XAIIDEALIST) (3R01GM110240-08S1). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/11097804. Licensed CC0.

---

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