System and method for prediction of artificial intelligence model generalizability for unseen data
TS-075229 — Problem
Artificial intelligence models often perform well during development but show unpredictable drops in accuracy and reliability when deployed on data that differ from their training sets. In high‑risk settings such as clinical care, these shifts can arise from changes in hardware, protocols…
- College: College of Medicine (COM)
- Inventors: Dikici, Engin; Nguyen, Xuan; Prevedello, Luciano
- Licensing Officer: Hampton, Andrew
A novel machine learning model for prediction of ICI responsive patients based on ICI pharmacokinetics
TS-075183 — Problem
Current eligibility biomarkers for Immune checkpoint inhibitors (ICIs) poorly predict patient’s response. Drug clearance, both at baseline and over time, is a stronger predictor of ICI effectiveness, however the current non-linear mixed effects modeling (NLME) approach for estimating …
- College: College of Pharmacy
- Inventors: Phelps, Mitchell "Mitch"; Adeluola, Adeoluwa; Coss, Christopher; Kim, Kyeongmin; Mo, Xiaokui "Molly"; Owen, Dwight
- Licensing Officer: Hampton, Andrew
EmitGCL: Prediction of Future Metastasis based on Graph Contrastive Learning
TS-075168 — Problem
Metastasis is the primary driver of cancer-related deaths, yet accurately predicting its onset is a major clinical challenge. Current diagnostic tools often fail to detect occult metastatic cells and metastatic precursor cells, resulting in either overdiagnosis, with unnecessary treatments,…
- College: College of Medicine (COM)
- Inventors: Ma, Qin; Wang, Xiaoying
- Licensing Officer: Hampton, Andrew
A Regularized Conditional GAN for Posterior Sampling in Inverse Problems
TS-063238 — A novel regularization technique applicable for medical imaging applications that leverages conditional generative adversarial networks (cGANs) to generate reconstructed images in significantly shorter timeframes.
The Need
Several techniques are used for image reconstruction in the medical aren…
- College: College of Engineering (COE)
- Inventors: Bendel, Matthew; Ahmad, Rizwan; Schniter, Philip "Phil"
- Licensing Officer: Hampton, Andrew
Hybrid Collaborative Filtering Methods for Recommending Search Terms to Clinicians
TS-063237 — Electronic Health Records (EHR) are used in over 88% of all US medical clinics to improve care and streamline data. In addition, they enable sharing of data to multiple providers dealing with the same patient, thereby enhancing efficiency and care.
The Need
In the last decade, medical practices…
- College: College of Medicine (COM)
- Inventors: Ning, Xia; Peng, Bo; Ren, Zhiyun
- Licensing Officer: Hampton, Andrew
Convolutional Neural Network to Assess Phayngeal and Laryngeal Pathology and Function on Nasopharyngolaryngoscopy
TS-063154 — Worldwide, 686,000 new head and neck (H&N) cancers are diagnosed yearly, and 375,000 people will die annually. Human papillomavirus (HPV) is responsible for an increasing subset of H&N malignancies called oropharyngeal squamous cell carcinomas (OPSCC). Although it has a better prognosis than…
- College: College of Engineering (COE)
- Inventors: Krening, Samantha; Gifford, Ryan; Jhawar, Sachin; VanKoevering, Kyle
- Licensing Officer: Hampton, Andrew
Method for Prediction of Artificial Intelligence Model Generalizability for Unseen Data
TS-063039 — Medical-based AI systems have seen increased use in recent years across a range of applications (e.g., diagnostics, prognostics, treatment response prediction). Their widespread adoption by the medical community is still restricted, primarily due to their limited ability to realize a high degree of …
- College: College of Medicine (COM)
- Inventors: Dikici, Engin; Nguyen, Xuan; Prevedello, Luciano
- Licensing Officer: Hampton, Andrew
Transforming PAH Management with PHORA: Empowering Physicians for Better Patient Care
TS-062764 — The Pulmonary Hypertension Outcomes Risk Assessment (PHORA): a PAH risk stratification tool.
Pulmonary Arterial Hypertension (PAH) demands precise risk stratification for effective patient management. Clinical decision support tools can help inform treatment decisions made by physicians and other healthcare providers, usually at the point of care.
The Need
Current methods for assistin…
- College: College of Medicine (COM)
- Inventors: Benza, Ray; Lin, Shili; Mathur, Puneet
- Licensing Officer: Hampton, Andrew
Show More Technologies
