Watson for Oncology and breast cancer treatment recommendations: agreement with an expert multidisciplinary tumor board.

Background: Breast cancer oncologists are challenged to personalize care with rapidly changing scientific evidence, drug approvals, and treatment guidelines. Artificial intelligence (AI) clinical decision-support systems (CDSSs) have the potential to help address this challenge. We report here the results of examining the level of agreement (concordance) between treatment recommendations made by the AI CDSS Watson for Oncology (WFO) and a multidisciplinary tumor board for breast cancer. Patients and methods: Treatment recommendations were provided for 638 breast cancers between 2014 and 2016 at the Manipal Comprehensive Cancer Center, Bengaluru, India. WFO provided treatment recommendations for the identical cases in 2016. A blinded second review was carried out by the center's tumor board in 2016 for all cases in which there was not agreement, to account for treatments and guidelines not available before 2016. Treatment recommendations were considered concordant if the tumor board recommendations were designated 'recommended' or 'for consideration' by WFO. Results: Treatment concordance between WFO and the multidisciplinary tumor board occurred in 93% of breast cancer cases. Subgroup analysis found that patients with stage I or IV disease were less likely to be concordant than patients with stage II or III disease. Increasing age was found to have a major impact on concordance. Concordance declined significantly (P ≤ 0.02; P < 0.001) in all age groups compared with patients <45 years of age, except for the age group 55-64 years. Receptor status was not found to affect concordance. Conclusion: Treatment recommendations made by WFO and the tumor board were highly concordant for breast cancer cases examined. Breast cancer stage and patient age had significant influence on concordance, while receptor status alone did not. This study demonstrates that the AI clinical decision-support system WFO may be a helpful tool for breast cancer treatment decision making, especially at centers where expert breast cancer resources are limited.

Phase I study of panobinostat in combination with bevacizumab for recurrent high-grade glioma.

Bevacizumab is frequently used to treat patients with recurrent high-grade glioma (HGG), but responses are generally not durable. Panobinostat is a histone deacetylase inhibitor with anti-neoplastic and anti-angiogenic effects and may work synergistically with VEGF inhibitors. We performed a phase I study to evaluate the safety and tolerability of the combination of orally administered panobinostat with bevacizumab in patients with recurrent HGG. Patients with recurrent HGG were treated on a 3 + 3 trial design. Patients received bevacizumab 10 mg/kg every other week in combination with oral panobinostat. The starting dose of panobinostat was 20 mg three times per week, weekly (cohort 1). Due to concerns for thrombocytopenia with the weekly dosing regimen, the protocol was amended to examine an every other week regimen. Cohort 2 received panobinostat 20 mg three times per week, every other week, and cohort 3 received 30 mg three times per week, every other week. Dose-limiting toxicity during the first 30 days was used to determine the maximum-tolerated dose. Twelve patients (median age 50, median KPS 90) with recurrent HGG were enrolled. One dose-limiting toxicity (DLT) (Grade 3 thrombocytopenia) was observed in cohort 1. No DLTs were observed in cohorts 2 and 3. The following grade 3 toxicities were seen in one patient each: thrombocytopenia, hypophosphatemia, esophageal hemorrhage, and deep venous thrombosis. There were no grade 4 or 5 toxicities. There were three patients with partial responses and seven with stable disease. The recommended doses for further study are oral panobinostat 30 mg three times per week, every other week, in combination with bevacizumab 10 mg/kg every other week. A phase II clinical trial in recurrent HGG is underway.

Retrospective study of dasatinib for recurrent glioblastoma after bevacizumab failure.

There is no effective treatment for recurrent glioblastoma (GBM) after bevacizumab failure. Putative mechanisms of resistance to bevacizumab include increased pericyte coverage, mediated partly by platelet-derived growth factor receptor (PDGFR) signaling, and an infiltrative tumor growth pattern potentially dependent on SRC. We explored the efficacy of dasatinib, a SRC, BCR-ABL, c-KIT, EPHA2, and PDGFRß inhibitor, in patients with recurrent GBM after bevacizumab failure. Adult patients with histologically confirmed GBM who failed bevacizumab therapy were treated with dasatinib 70-100 mg twice daily in combination with bevacizumab (n = 14), until tumor progression or unacceptable toxicity. Fourteen patients were treated. Median age was 55 years (range 32-66) and median KPS was 80 (range 50-90). All patients (100%) had glioblastomas. The median number of prior regimens was 4 (range from 2 to 6). Of the thirteen evaluable patients, none had a complete or partial response. Only one patient had stable disease after an 8 week interval. Median progression-free survival (PFS) was 28 days (95% confidence interval [CI] 26-35 days). Six month progression-free survival (PFS6) was 0%. Median overall survival (OS) was 78 days (95% CI 41-137 days). Treatment was moderately well-tolerated, although one patient sustained a grade 4 intracerebral hemorrhage. Dasatinib in conjunction with bevacizumab does not appear to have activity in patients with recurrent, heavily pretreated GBM.

Bevacizumab for recurrent malignant gliomas: efficacy, toxicity, and patterns of recurrence.

BACKGROUND: Bevacizumab, a humanized monoclonal antibody against vascular endothelial growth factor, may have activity in recurrent malignant gliomas. At recurrence some patients appear to develop nonenhancing infiltrating disease rather than enhancing tumor. METHODS: We retrospectively reviewed 55 consecutive patients with recurrent malignant gliomas who received bevacizumab and chemotherapy to determine efficacy, toxicity, and patterns of recurrence. Using a blinded, standardized imaging review and quantitative volumetric analysis, the recurrence patterns of patients treated with bevacizumab were compared to recurrence patterns of 19 patients treated with chemotherapy alone. RESULTS: A total of 2.3% of patients had a complete response, 31.8% partial response, 29.5% minimal response, and 29.5% had stable disease. Median time to radiographic progression was 19.3 weeks. Six-month progression-free survival (PFS) was 42% for patients with glioblastoma and 32% for patients with anaplastic glioma. In 23 patients who progressed on their initial therapy, bevacizumab was continued and the concurrent chemotherapy agent changed. In no case did the change produce a radiographic response, but two patients had prolonged PFS of 20 and 31 weeks. Recurrence pattern analysis identified a significant increase in the volume of infiltrative tumor relative to enhancing tumor in bevacizumab responders. CONCLUSIONS: Combination therapy with bevacizumab and chemotherapy is well-tolerated and active against recurrent malignant gliomas. At recurrence, continuing bevacizumab and changing the chemotherapy agent provided long-term disease control only in a small subset of patients. Bevacizumab may alter the recurrence pattern of malignant gliomas by suppressing enhancing tumor recurrence more effectively than it suppresses nonenhancing, infiltrative tumor growth.