AI Tool Predicts Infection Risks for Stem Cell Transplant Patients with Oral Mucositis

Groundbreaking Research on Oral Mucositis Risks

Researchers from the University at Buffalo and collaborators have conducted a series of studies that shed light on the infection risks associated with oral mucositis in stem cell transplant patients. The findings, published in the journal Cancers, reveal that patients undergoing hematopoietic stem cell transplants (HSCT) for blood cancers who develop oral mucositis are at nearly four times the risk of developing a severe infection compared to those without the condition 1

1

Dr. Satheeshkumar Poolakkad Sankaran, the corresponding author and research scientist at the Jacobs School of Medicine and Biomedical Sciences at UB, emphasizes the significance of oral mucositis: "Oral mucositis is not simply a source of discomfort; it serves as a significant portal for infections in immunocompromised patients" 2

2

Identifying Risk Factors and Developing Predictive Tools

Source: Medical Xpress

The research team has compiled the most comprehensive synthesis to date of recent findings on individual risk factors for oral mucositis. These factors include specific drugs like methotrexate, high-dose chemotherapy, female gender, younger age, kidney issues, and reactivation of the herpes simplex virus .

To better assess patient risk, the researchers developed a nomogram tool, which was described in a paper published in Support Cancer Care. This statistical instrument uses variables such as age, gender, race, total body irradiation, and fluid/electrolyte disorders to estimate the risks of developing ulcerative mucositis, a severe form of oral mucositis 2

2

Harnessing AI for Enhanced Prediction

At the Multinational Association of Supportive Care in Cancer 2025 meeting, Dr. Poolakkad Sankaran presented findings on an advanced nomogram-based model that utilizes explainable AI to predict adverse events more accurately. This AI model employs machine learning algorithms to assess complex clinical and demographic data 1

1

"The AI model exhibited enhanced predictive accuracy, recognizing patterns linked to toxicities that conventional nomograms failed to detect," explains Dr. Poolakkad Sankaran. "By synthesizing demographic and clinical data, the system can predict adverse events, facilitating individualized therapy modifications to reduce toxicities" 2

2

Related Stories

AI Tool Analyzes Bone Marrow Slides to Personalize Multiple Myeloma Treatment for Newly Diagnosed Patients

Mayo Clinic's AI Tool UNISOM Detects Early Signs of Cancer-Linked Blood Mutations

AI-Powered Saliva Test Shows Promise in Identifying Chemotherapy Risks

AI Tool SCORPIO Predicts Cancer Immunotherapy Response Using Routine Blood Tests

Implications for Cancer Care and Future Directions

The researchers are now validating the AI model with other cancer-related adverse events, including immune-related complications. Their ultimate goal is to achieve widespread clinical adoption of the model in assessing cancer patients 1

1

Dr. Poolakkad Sankaran emphasizes the importance of these interconnected studies: "These tools promise reduced complications, shorter hospitalizations, and lower costs. As cancer management such as HSCT and immunotherapy grows -- particularly for older patients -- the need for accurate prediction and prevention becomes increasingly crucial" 2

2

Collaborative Efforts and Funding

The research team includes members from various institutions, including the University at Buffalo, Boston Medical Center, the University of Connecticut Health Center, and the City of Hope National Cancer Center. They are part of the Worldwide Extension of Buffalo's Research Innovation Group in Hem/Onc Talent (WE-BRIGHT) Network, which aims to inspire transformation in oncology care and research 2

2

Some of the work was partially funded by the Kaleida Health Foundation, highlighting the importance of continued support for innovative medical research in improving patient outcomes and advancing cancer care 2

2