Using artificial intelligence tools in answering important clinical questions: The KEYNOTE-183 multiple myeloma experience.

The phase III, randomized, active-controlled, multicenter, open-label KEYNOTE-183 study (NCT02576977) evaluating pomalidomide and low dose dexamethasone (standard-of-care [SOC]) with or without pembrolizumab in patients with refractory or relapsed and refractory multiple myeloma (rrMM) was placed on full clinical hold by the US FDA on July 03, 2017 due to an imbalance in the number of deaths between arms. Clinically-led subgroup analyses are typically used to shed light on clinical findings. However, this approach is not always successful. We propose a systematic approach using the artificial intelligence tools to identifying risk factors and subgroups contributing to the overall death (prognostic) or to the excess death observed in the pembrolizumab plus SOC arm (predictive) of the KEYNOTE-183 study. In KEYNOTE-183, with a data cutoff date of June 02, 2017, we identified plasmacytoma as a prognostic factor, and ECOG performance status as a predictive factor of death. In addition, a qualitative interaction was observed between ECOG performance status and the treatment arm. The subsequent subgroup analysis based on ECOG performance status confirmed that more deaths were associated with pembrolizumab plus SOC versus SOC alone in patients with ECOG performance status 1.

A randomized phase II trial of ridaforolimus, dalotuzumab, and exemestane compared with ridaforolimus and exemestane in patients with advanced breast cancer.

PURPOSE: To evaluate whether adding humanized monoclonal insulin growth factor-1 receptor (IGF-1R) antibody (dalotuzumab) to mammalian target of rapamycin (mTOR) inhibitor (ridaforolimus) plus aromatase inhibitor (exemestane) improves outcomes in patients with estrogen receptor (ER)-positive advanced/metastatic breast cancer. METHODS: This randomized, open-label, phase II trial enrolled 80 postmenopausal women with high-proliferation (Ki67 index staining ≥15%), ER-positive breast cancer that progressed after a non-steroidal aromatase inhibitor (NCT01605396). Randomly assigned patients were given oral ridaforolimus 10 mg QD 5 ×/week, intravenous dalotuzumab 10 mg/kg/week, and oral exemestane 25 mg/day (R/D/E, n = 40), or ridaforolimus 30 mg QD 5 ×/week and exemestane 25 mg/day (R/E; n = 40). Primary end point was progression-free survival (PFS). RESULTS: Median PFS was 23.3 weeks for R/D/E versus 31.9 weeks for R/E (hazard ratio 1.18; 80% CI 0.81-1.72; P = 0.565). Grade 3-5 adverse events were reported in 67.5% of patients in the R/E arm and 59.0% in the R/D/E arm. Stomatitis (95.0 vs. 76.9%; P = 0.021) and pneumonitis (22.5 vs. 5.1%; P = 0.027) occurred more frequently in the R/E than the R/D/E arm; hyperglycemia (27.5 vs. 28.2%) occurred at a similar rate. CONCLUSIONS: R/D/E did not improve PFS compared with R/E. Because the PFS reported for R/E was similar to that reported for everolimus plus exemestane in patients with advanced breast cancer, it is possible that lower-dose ridaforolimus in the R/D/E arm (from overlapping toxicities with IGF1R inhibitor) contributed to lack of improved PFS.

The BATTLE trial: a bold step toward improving the efficiency of biomarker-based drug development.

Successful completion of the Biomarker-integrated Approaches of Targeted Therapy for Lung Cancer Elimination (BATTLE) trial, reported in this issue of Cancer Discovery, is an important advance in the effort to improve clinical trial approaches to the simultaneous development of new therapeutics with matching diagnostic tests so that patients most likely to benefit from these therapies can be identified.

Impact of a prophylactic quadrivalent human papillomavirus (types 6, 11, 16, 18) L1 virus-like particle vaccine in a sexually active population of North American women.

OBJECTIVE: The purpose of this study was to inform policy regarding human papillomavirus (HPV) vaccination in North America. We measured the clinical impact of HPV-6/-11/-16/-18 vaccination in North American women. STUDY DESIGN: The study enrolled 21,954 women, the majority aged 16-25, across 5 studies of a quadrivalent HPV vaccine or its HPV-16 vaccine prototype. The North American subjects (n = 5996) were pooled from these trials, and the prevalence of HPV-6/-11/-16/-18 exposure was measured. The impact of vaccination on the burden of anogenital HPV lesions in an intention-to-treat population (regardless of enrollment HPV status) was calculated. RESULTS: At enrollment, the median age was 20 years; 13% of the women had had a Papanicolaou test abnormality, and 76% of the women had negative tests results for all 4 vaccine HPV types. With approximately 3 years of follow-up evaluations in the intention-to-treat population (regardless of enrollment HPV status), vaccination reduced the rate of HPV-16- and -18-related precancers and HPV-6/-11/-16/-18-related genital lesions by 66.4% (95% CI, 42.7%-81.1%) and 57.7% (95% CI, 27.3%-76.3%), respectively. CONCLUSION: The administration of HPV vaccine to sexually active North American women reduced the burden of HPV-6/-11/-16/-18-related disease. Catch-up vaccination programs in this population are warranted.