Predicting likelihood of in vivo chemotherapy response in canine lymphoma using ex vivo drug sensitivity and immunophenotyping data in a machine learning model

• Published in: Veterinary & comparative oncology 2021-03, Vol.19 (1), p.160-171
• Main Authors: Bohannan, Zach, Pudupakam, Raghavendra Sumanth, Koo, Jamin, Horwitz, Harrison, Tsang, Josephine, Polley, Amanda, Han, Enyang James, Fernandez, Elmer, Park, Stanley, Swartzfager, Deanna, Qi, Nicholas Seah Xi, Tu, Chantal, Rankin, Wendi Velando, Thamm, Douglas H., Lee, Hye‐Ryeon, Lim, Sungwon
• Format: Article
• Language: English
• Subjects: chemosensitivity; dog; lymphosarcoma; machine learning; Original; precision medicine
• ISSN: 1476-5810; 1476-5829
• DOI: 10.1111/vco.12656

We report a precision medicine platform that evaluates the probability of chemotherapy drug efficacy for canine lymphoma by combining ex vivo chemosensitivity and immunophenotyping assays with computational modelling. We isolated live cancer cells from fresh fine needle aspirates of affected lymph nodes and collected post‐treatment clinical responses in 261 canine lymphoma patients scheduled to receive at least 1 of 5 common chemotherapy agents (doxorubicin, vincristine, cyclophosphamide, lomustine and rabacfosadine). We used flow cytometry analysis for immunophenotyping and ex vivo chemosensitivity testing. For each drug, 70% of treated patients were randomly selected to train a random forest model to predict the probability of positive Veterinary Cooperative Oncology Group (VCOG) clinical response based on input variables including antigen expression profiles and treatment sensitivity readouts for each patient's cancer cells. The remaining 30% of patients were used to test model performance. Most models showed a test set ROC‐AUC > 0.65, and all models had overall ROC‐AUC > 0.95. Predicted response scores significantly distinguished (P 50% showed a statistically significant reduction (log‐rank P