English
Arabic
Chinese (Simplified)
Dutch
Esperanto
French
German
Greek
Italian
Japanese
Korean
Portuguese
Russian
Spanish
UrduThe first step of the effort involves fine-tuning a large language model using approximately 100,000 inpatient clinical notes from Moffitt in a proof-of-concept tailored to address key operational challenges such as optimizing billing coding processes related to cancer and comorbidity.
The application will leverage Moffitt’s private Oracle Cloud Infrastructure AI infrastructure, including bare metal compute, and NVIDIA NeMo. Deloitte will work with Moffitt on model training and overall project implementation.
Moffitt aims to enhance the accuracy of clinical documentation specific to conditions other than cancer that may impact cancer care. This information will ultimately be leveraged to improve clinical quality, automate medical coding, match patients to clinical trials and conduct downstream cancer research.
“This collaboration represents a significant step forward in our mission to provide our patients with the highest quality cancer care. By leveraging artificial intelligence and machine learning technologies, we can unlock new insights, streamline workflows and ultimately improve patient outcomes,” said Dana Rollison, Ph.D., Vice President, Chief Data Officer and Associate Center Director of Data Science at Moffitt.
The insights gained from this initiative will be integrated into Moffitt’s overarching AI/machine learning strategy in natural language processing, with a focus on driving continuous improvement in clinical documentation and medical coding accuracy, enhancing governance through data quality analysis, and optimizing revenue cycle management through the reduction of claim denials.
“We are delighted to be a part of this transformative initiative alongside Moffitt Cancer Center,” said Dan Spellman, Global AI Cloud Director at Oracle. “With the robust AI platform and built-in security capabilities of Oracle Cloud Infrastructure, alongside esteemed partners NVIDIA and Deloitte, we look forward to helping Moffitt accelerate innovation and push the boundaries in cancer care delivery.”
“The depth of insights within cancer patient records surpasses general clinical notes, demanding specialized tools for extraction,” said Dr. Mona Flores, Global Head of Medical AI at NVIDIA. “Only through domain-specific large language models, trained on cancer data, can we illuminate the intricacies of each stage, paving the way for tailored and effective treatments.”
“This project marks an important milestone in the application of large language models to health care delivery, enabling us to augment complex, resource-intensive tasks that are ubiquitous pain points for hospitals and health systems. Tackling this challenge requires a diverse group of technicians, clinicians and thought leaders in health care delivery — it truly takes a village. Our data scientists and clinical informaticians are excited to be a part of this pioneering project in collaboration with Moffitt, NVIDIA and Oracle,” added Dr. Matthew Crowson, Health Care AI Leader at SFL Scientific, a Deloitte Business.
About Moffitt Cancer Center
Moffitt is dedicated to one lifesaving mission: to contribute to the prevention and cure of cancer. The Tampa-based facility is one of only 56 National Cancer Institute-designated Comprehensive Cancer Centers, a distinction that recognizes Moffitt’s scientific excellence, multidisciplinary research, and robust training and education. Moffitt’s expert nursing staff is recognized by the American Nurses Credentialing Center with Magnet® status, its highest distinction. With more than 9,000 team members, Moffitt has an economic impact in the state of $2.4 billion. For more information, call 1-888-MOFFITT (1-888-663-3488), visit MOFFITT.org, and follow the momentum on Facebook, Twitter, Instagram and YouTube.
*As used in this document, “Deloitte” means Deloitte Consulting LLP, a subsidiary of Deloitte LLP. Please see www.deloitte.com/us/about for a detailed description of our legal structure. Certain services may not be available to attest clients under the rules and regulations of public accounting.
###
