Abstract 515P
Background
Anlotinib is a multitarget anti-angiogenic drug that combined with temozolomide (TMZ) can effectively prolongs the overall survival (OS) of recurrent malignant glioma(rMG), but some patients do not respond to anlotinib combined with TMZ. These patients were associated with a worse prognosis and lack effective identification methods. Therefore, there is a great need to differentiate patients who are likely to have a good response to anlotinb in combination with TMZ from those who are not, so as to provide more personalized targeted therapy and free patients who might have a poor treatment response from risk of those severe side effects and high cost.
Methods
A total of 53 rMG patients (42 in training cohort and 11 in validation cohort) receiving anlotinib combined with TMZ were enrolled. A total of 3668 radiomics features were extracted from the recurrent MRI images. Radiomics features are reduced and filtered by hypothesis testing and LASSO regression. Eight machine learning models construct the radiomics model, and then screen out the optimal model. The performance of the model was assessed by its discrimination, calibration, and clinical usefulness with validation.
Results
53 patients with rMG were enrolled in our study. 34 patients displayed effective treatment response, showed a higher survival benefits than non-response group, the median PFS was 8.53 months versus 5.33 months(P=0.06) and the median OS was 19.9 months and 7.33 months (P=0.029), respectively. Three radiomics features were incorporated into the model construction as final variables after LASSO regression analysis. Compared with other models, LR model has the best performance with an AUC of 0.929 in validation cohort, which can effectively predict the response of rMG patients to anlotinib in combination with TMZ. The calibration curve confirmed the agreement between the observed actual and prediction probability. Within the reasonable threshold probability range (0.38-0.88), the radiomics model shows good clinical utility.
Conclusions
The above-described radiomics modle performed well, which can serve as a clinical tool for individualized prediction of the response to anlotinb combined with TMZ in rMG patients.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
S. Zhou.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
14P - Peripheral immune kinetics in survival prediction of small cell lung cancer patients treated with immune checkpoint blockade therapy
Presenter: MIGUEL GALINDO CAMPOS
Session: Poster session 09
15P - CBL E3 ubiquitin ligases are key inhibitory regulators in PD-1/LAG-3 co-signaling in human cancers, targeted through bispecific co-blockade
Presenter: Luisa Chocarro
Session: Poster session 09
16P - Terminally exhausted CD8+ T cells and increased immunosuppressive soluble factors in malignant ascites of patients with gastric cancer with peritoneal metastasis
Presenter: Hye Sook Han
Session: Poster session 09
17P - Continued expansion of long-lived effect CD8+ T cells associates with durable response post-PD-1 blockade
Presenter: Robert Watson
Session: Poster session 09
18P - Exposure of calreticulin is required for vitamin C immunomediated cancer surveillance
Presenter: Alessandro Cavaliere
Session: Poster session 09
19P - Preclinical and clinical significance of VEGF deprivation in ovarian cancer through a specific active immunotherapy
Presenter: Yanelys Morera
Session: Poster session 09
20P - The essential role of DNA repair in the pharmacological activities of AST-3424
Presenter: Fanying Meng
Session: Poster session 09
21P - Implications of KMT2C knockdown for DNA damage repair in breast cancer
Presenter: Philip Bredin
Session: Poster session 09
22P - Clinical significance of DNA damage response mutations in early stage NSCLC
Presenter: Haoran Zhang
Session: Poster session 09
23P - PMC-309: A highly selective anti-VISTA antibody reverses immunosuppressive TME to immune-supportive
Presenter: Cheon Ho Park
Session: Poster session 09