Search

9067 Background: Second-generation (gen) ALK tyrosine kinase inhibitors (TKIs) are standard first- and second-line therapies in patients (pts) with advanced ALK+ non-small cell lung cancer (NSCLC). After progression on second-gen TKI(s), standard options include platinum (PT)-based chemotherapy (chemo) or the third-gen ALK TKI lorlatinib. The efficacy of PT-based chemo is established in treatment-naive pts but is undefined in pts who have failed prior ALK TKIs. Here we evaluate the efficacy of PT/pemetrexed (pem)-based chemo in pts with ALK+ NSCLC refractory to second-gen TKIs. Methods: A retrospective study was performed at three institutions. Pts were eligible if they had advanced ALK+ NSCLC refractory to ≥1 second-gen TKI, and received PT-pem-based chemo. Medical records and imaging were reviewed to determine outcomes. Results: Among 55 eligible pts, chemo regimens included: PT/pem (31/55, 56%), PT/pem/bevacizumab (bev) (6/55, 11%), PT/pem/PD-1 inhibitor (3/55, 5%), PT/pem with ALK TKI (8/55, 15%), PT/pem/bev with TKI (6/55, 11%), and PT/pem/PD-1 inhibitor with TKI (1/55, 2%). Pts had received one (6/55, 11%), two (38/55, 69%), or more (11/55, 20%) prior TKIs. Six pts (11%) previously received adjuvant or neoadjuvant chemo. Radiographic data for response evaluation was available for 39 pts. Among 36 pts with measurable baseline disease, confirmed ORR was 31% (11/36; 95% CI, 16-48%); 13 (36%) had stable disease. The median duration of response was 5.4 months (95% CI, 1.5-7.1 months). The median progression-free survival (PFS) for the entire cohort was 4.0 months (95% CI, 2.8-4.6 months). Chemo (PT/pem +/- bev or PD-1 inhibitor) plus ALK TKI (n = 15) was associated with a significant increase in PFS compared to chemo without TKI (n = 40) (median PFS 6.8 vs 3.2 months; HR 0.306; p = 0.002). Similarly, PT/pem plus ALK TKI (n = 8) was associated with increased PFS compared to PT/pem without TKI (n = 31) (median PFS 6.8 vs 2.9 months; HR 0.358; p = 0.036). Conclusions: The efficacy of PT-pem-based chemo is limited after failure of second-gen ALK TKIs but may be higher in pts who receive chemo plus ALK TKI, suggesting a potential role for ongoing ALK inhibition. The modest benefit of PT-pem-based chemo highlights the need for other therapeutic strategies for pts refractory to second-gen TKIs.

3079 Background: ALK tyrosine kinase inhibitors (TKIs) are effective in treating advanced anaplastic lymphoma kinase (ALK) fusion-positive non-small-cell lung cancers (NSCLC), and specific ALK variants are associated with the development of resistance to specific TKIs. Humans struggle to harness the full potential of the highly complex next-generation sequencing bioinformatics pipeline output. As a consequence, the decision to report a variant remains difficult, and we considered the discrete nature of the data and the binary decision (report vs. not-report) as an ideal setting to apply an artificial intelligence (AI) approach for variant reporting. Methods: We assessed diagnostic performance of an AI model in calling ALK-resistance mutations in n = 50 consecutive ALK fusion positive patients who relapsed on TKI-therapy and underwent repeat biopsy at MGH. The random forest model was derived from independent datasets (training and validation) capturing the reporting decision on > 36,000 variants with ~500 features per variant resulting in a matrix of > 18 million data points. The model output is a contiguous prediction score from 0 (not report) to 1 (report) and a visual drill-down functionality allows exploration of the underlying features that contributed to the decision. Results: Examination of n = 76 tests from n = 50 patients with a total of n = 130 reported variants (and = 115 not reported variants) included a total of n = 31 ALK point mutations: p.1156(n = 2), p.1171(n = 8), p.1174(n = 2), p.1180(n = 2), p.1196(n = 1), p.1198(n = 1), p.1202(n = 8), p.1203(n = 1), p.1204(n = 1), p.1206(n = 1), p.1269(n = 4). Setting a screening threshold of the model at > 10% for reporting showed only one false-negative (p.Ile1171Asn) variant and 96.7% sensitivity. The average model score for ALK variants was 0.664 (range: 0.08–0.98; median 0.8) and did not show significant differences from other reported variants (0.636; 0–1; 0.7; t-test 0.66). The model would have called n = 18 of the non-reported control variants (average 0.07; range < 0.001–0.64; P < 0.0001) and was 84% specific. Review of the drill-down function identified prior call frequency, allelic ratio, and predicted transcript consequences as common model features. Importantly, the model is currently agnostic to the medical literature and does not take clinical parameters (e.g. TKI type) into account, which may further improve performance. Conclusions: Applying artificial intelligence to large discrete datasets is one approach to help identify clinically relevant variants in the setting of ALK resistance in ALK-fusion positive NSCLC.