Wilding, George

686 Background: Immune checkpoint inhibitors (ICI) have been used to treat advanced muscle invasive and/or metastatic bladder cancer. However, ICIs are only effective in 30-40% of cases. In light of potentially significant IRAE’s, tools to predict individual patient level benefits are desirable. AI technology offers the opportunity to apply computational methods to predict outcomes from readily available digitized pathology slides. We investigated the utility of an AI platform integrating computational biomarkers based on morphological characterization of digitized H&E slide whole images (WSI) to predict response to ICI. Methods: We analyzed H&E-stained whole slide images (WSI) of bladder tumor tissue collected from transurethral resection of bladder tumor (TURBT) from 116 patients with advanced or metastatic bladder cancer at a single institution between 2015-2020. Adjacent multiplex IHC stained specimens were analyzed myeloid and lymphoid marker panels. 20 patients from the overall cohort treated with ICI were designated ‘responders’ (complete response, partial response, stable disease) and 20 patients were identified as non-responders (progressive disease) based on ICI best clinical/radiographic response. WSIs were divided into small non-overlapping image patches. These image tiles were processed into multiple AI encoder models to extract morphological features. The tile morphological features, represented by high dimensional vectors, were combined by an aggregation model to represent the whole slide morphology and then used to classify the patients into responders vs non-responders to immunotherapy. Area-under-the-receiver operating characteristic (AUC) was used to measure the performance of response prediction. Results: Our method shows AUC of 0.708 at classification of the patients (n=40) into responder and non-responder groups. With a cutoff that identifies the top 50% patients (n=20) of high probability of responding to immunotherapy predicted by our models, 75% of them are responders. In the bottom 50% patients (n=20) of the low scores, 75% of them are non-responders. . Multiplex IHC (myeloid and lymphoid panel) was performed using adjacent sections and were characterized yielding deeper mechanistic insight into the inflammatory populations driving predictive morphologic patterns. Conclusions: By applying innovative AI morphological analysis on patient WSIs, we generated a computational biomarker that shows promising ability to predict patient response to immunotherapy in bladder cancer. This approach merits future prospective validation and additional patient level analysis in broader cohorts. [Table: see text]

Abstract Purpose: To define the toxicities, pharmacodynamics, and clinical activity of the proteasome inhibitor, PS-341 (bortezomib), in patients with advanced malignancies. Patients and Methods: Twenty-eight patients (14 male and 14 female) received PS-341 twice weekly for 4 of 6 weeks (schedule I). Because toxicity necessitated dose omissions on this schedule, 16 additional patients (12 male and 4 female) received PS-341 twice weekly for 2 of every 3 weeks (schedule II). A total of 73 courses of treatment was given (median, 2; range, 1-4). Inhibition of 20S proteasome activity in peripheral blood mononuclear cells (PBMC) and accumulation of proteasome-targeted polypeptides in tumor tissue were evaluated as pharmacodynamic markers of PS-341 activity. Results: The most common toxicity was thrombocytopenia, which was dose limiting at 1.7 mg/m2 (schedule I) and 1.6 mg/m2 (schedule II), respectively. Sensory neuropathy was dose-limiting in a patient in schedule I. Grade ≥3 toxicities for schedule I were constipation, fatigue, myalgia, and sensory neuropathy. Grade ≥3 toxicities for schedule II were dehydration resulting from diarrhea, nausea and vomiting, fatigue, hypoglycemia, and hypotension. The maximum tolerated dose was 1.5 mg/m2 for both schedules. Reversible dose-dependent decreases in 20S proteasome activity in PBMCs were observed, with 36% inhibition at 0.5 mg/m2, 52% at 0.9 mg/m2, and 75% at 1.25 mg/m2. Accumulation of proteasome-targeted polypeptides was detected in tumor samples after treatment with PS-341. A patient with multiple myeloma had a partial response. Conclusion: PS-341 given 1.5 mg/m2 twice weekly for 2 of every 3 weeks is well tolerated and should be further studied.

Purpose: To evaluate the role of adjuvant interferon alfa after complete resection of locally extensive renal cell carcinoma. Patients and Methods: A total of 283 eligible patients with pT3–4a and/or node-positive disease were randomly assigned after radical nephrectomy and lymphadenectomy to observation or to interferon alfa-NL (Wellferon, Burroughs-Wellcome, Research Park, NC) given daily for 5 days every 3 weeks for up to 12 cycles. Patients were stratified on the basis of pathologic stage. Patients remained on treatment until documented recurrence, excessive toxicity, or patient/physician preference deemed removal appropriate. Results: At median follow-up of 10.4 years, median survival was 7.4 years in the observation arm and 5.1 year in the treatment arm (log-rank P = .09). Median recurrence-free survival was 3.0 years in the observation arm and 2.2 years in the interferon arm (P = .33). Performance status (P = .003), nodal status (N2 v N0, P < .0001), and tumor stage (P = .0002) were significant prognostic factors in multivariate analysis. A proportional hazards model examining the effects of treatment arm and time to recurrence on survival after recurrence among patients who recurred found that random assignment to interferon treatment (P = .009) and shorter time to recurrence (P < .0001) were independent predictors of shorter survival after recurrence. Although no lethal toxicities were observed, severe (grade 4) toxicities including neutropenia, myalgia, fatigue, depression, and other neurologic toxicities occurred in 11.4% of those randomly assigned to interferon treatment. Conclusion: Adjuvant treatment with interferon did not contribute to survival or relapse-free survival in this group of patients.