Surya Vishnubhatt1, George Courcoubetis1 , Ilona Holcomb1, Sungwon Lim1,2 , Jamin Koo1,2,3
1ImpriMed, Inc., 3980 Fabian Way, Palo Alto, CA 94303, USA
2ImpriMedKorea, Inc., Seoul 03920, Republic of Korea
3Department of Chemical Engineering, Hongik University, Seoul 04066, Republic of Korea
High-grade canine T-cell lymphoma is an aggressive malignancy with limited treatment options and poor prognosis. This study evaluates the clinical utility of ImpriMed’s AI-driven single drug response prediction (SDRP) to determine whether treatment selection aligned with SDRP predictions improves patient outcomes in T-cell lymphoma.
A retrospective analysis was performed on 136 patients with T-cell lymphoma, including 68 treatment-naïve and 68 previously treated patients, for 13 chemotherapeutic and corticosteroid agents. Patients were classified as high- or low-matching if administered therapies were predicted to be effective (>50% response probability). Clinical responses were assessed using Veterinary Cooperative Oncology Group (VCOG) criteria, and overall survival (OS), progression-free survival (PFS), and remission rates were compared between groups.
Patients receiving SDRP-aligned therapies experienced significantly improved outcomes. Median OS was 271 days in the high-matching group compared with 117 days in the low-matching group (hazard ratio [HR] = 2.05, p = 0.0078). Complete remission rates were also significantly higher among high-matching patients (72% versus 34%, p = 1.4 × 10⁻⁵). Overall, the SDRP model achieved an ROC-AUC of 0.76, demonstrating good discrimination between responders and non-responders.
These findings support the clinical utility of the SDRP platform in treating canine T-cell lymphoma. Patients receiving treatments aligned with positive predictions experienced significantly longer overall survival and markedly higher complete remission rates within high matching groups compared to low matching groups.
While prospective validation is warranted, this analysis provides strong evidence that SDRP-guided treatment selection can enhance clinical decision-making and improve outcomes in canine T-cell lymphoma.