Neutropenia Prediction Based on First-Cycle Blood Counts Using a FOS-3NN Classifier.

Area of Science:

• Oncology
• Hematology
• Biostatistics

Background:

• Adjuvant chemotherapy delivery is crucial for breast cancer treatment success.
• Neutropenia, a common chemotherapy complication, often leads to treatment delays or dose reductions.
• Predicting neutropenic risk in breast cancer patients remains challenging.

Purpose of the Study:

• To develop and validate a predictive model for neutropenic events in early-stage breast cancer patients undergoing adjuvant chemotherapy.
• To stratify patients into low- and high-risk groups for neutropenia based on early treatment response.

Main Methods:

• A cohort of 35 early-stage breast cancer patients receiving adjuvant chemotherapy was analyzed.
• The FOS-3NN model was developed to stratify patient risk using complete blood count data after the first chemotherapy cycle.
• Risk classification was independent of breast cancer subtype and clinical markers, focusing on blood count kinetics.

Main Results:

• The FOS-3NN model demonstrated high accuracy in an independent test set.
• 19 out of 21 unseen patients were correctly classified (P < 0.00023, Matthews' correlation coefficient +0.83).
• The model effectively predicted neutropenic events based on early chemotherapy response.

Conclusions:

• A novel model, FOS-3NN, accurately predicts neutropenic events in breast cancer patients during adjuvant chemotherapy.
• This predictive capability aids in managing treatment schedules and optimizing patient outcomes.
• The model offers a reliable method for classifying neutropenic risk early in the treatment course.