National Institutes of Health, National Cancer Institute R01CA277782: Multi-institutional validation of a multi-modal machine learning algorithm to predict and reduce acute care during cancer therapy
Patients with cancer undergoing cancer treatments such as radiation therapy or chemotherapy may require emergency department (ED) visits or hospitalization, a public health need that affects treatment outcomes, quality of life, and costs to patients and the healthcare system. We have developed artificial intelligence (AI) models using routine electronic health record data and mobile device step count data that have been demonstrated to predict and reduce ED visits and hospitalizations. The goal of this work is to assess and improve how well these approaches work across a network of diverse hospitals and make the benefits of this AI-supported care apply more broadly and ensure access and equal healthcare to all patients.
Prostate Cancer Foundation Special Challenge Award 22CHAS02: Advancing the Drug Development Process in Metastatic Prostate Cancer through Machine Learning
The identification of intermediate clinical endpoints which can be used much earlier in clinical trials to determine the impact of a new treatment on patients’ overall survival will greatly speed the development of new treatments. Our team will use a machine learning approach to identify novel kinetic, multi-dimensional biomarkers that can serve as accurate predictors of overall survival, which will accelerate the “readout” timeline for late phase studies in metastatic prostate cancer, and lead to faster patient access to effective new therapies.
American Society for Radiation Oncology and Prostate Cancer Foundation Early Career Development Award to End Prostate Cancer: Artificial Intelligence Approaches for the Diagnosis and Treatment of Oligometastatic Prostate Cancer
The objective of this study is to develop AI-based approaches to combine a patient’s prior history, cancer-related information, and imaging data to identify if they are a good candidate for a PSMA PET scan and if they are likely to benefit from radiation therapy. The resulting AI-based tools developed in this study will improve the quality of life for patients with prostate cancer by improving the identification of patients at risk of oligometastatic cancer and by guiding the use of the most effective treatments for those patients.
Conquer Cancer Foundation (American Society of Clinical Oncology) Career Development Award: Accessible and equitable computational approaches to reduce acute care for cancer patients
Patient Centered Outcomes Research Institute Improving Methods for Conducting Patient-Centered Outcomes Research: Diagnostic Tools for Quality Improvement of Machine Learning-Based Clinical Decision Support Systems
