Shreve, Jacob

7543 Background: Total metabolic tumor volume (TMTV) and maximum standardized uptake value (SUVmax) may improve upon standard 18F-fluorodeoxyglucose positron emission tomography/computed tomography (PET-CT)-based assessment of advanced DLBCL during treatment. We report the association of TMTV and SUVmax changes at interim PET-CT (PET2) on survival outcomes in patients with primary refractory DLBCL (prDLBCL) and early relapsing DLBCL (erDLBCL). Methods: Adult patients with prDLBCL (less than a complete response (CR) or progression by the end of treatment (EOT)) or erDLBCL (CR at EOT with relapse within 12 months) between 2005 and 2019 at Mayo Clinic Rochester were included. The % change (Δ) from baseline to PET2 (after 2 cycles of 1L therapy) of TMTV and SUVmax were measured. A PET segmentation threshold of 1.5 liver mean SUV + two standard deviations with a minimum volume constraint of 0.5 mL was utilized (MIM Software, Inc., Cleveland OH, USA) with manual input as needed. Functional splines analysis determined SUVmax and TMTV threshold for analysis. Results: 131 patients had complete PET-CT data (N=79 prDLBCL, N=52 erDLBCL). Baseline median TMTV and SUVmax were 767.4 cm3 (range 0.9-6840.4) and 20.5 (2.0-52.6), respectively. At a median follow up of 77.6 months, 81 patients had died. 2-year OS rate was 53% (95% CI: 42-67) for patients with a PET2 ΔSUVmax decline ≥65% compared to 15% (95% CI: 7-29) for patients with a PET2 ΔSUVmax decline <65%(p<0.001). PrDLBCL had a 2-year OS rate of 48% (95% CI: 31-74) for a ΔSUVmax ≥65% compared to 7% (95% CI: 2-21) for a ΔSUVmax <65%(p<0.001), which captured 58% of prDLBCL patients (N=46). Two-year OS rate was 43% (95% CI: 34-54) for patients with a ΔTMTV ≥75% compared to 5% (95% CI: 1-35) for patients with ΔTMTV <75% (p<0.001). All patients with a ΔTMTV <75% had prDLBCL. PrDLBCL had a 2-year OS rate of 28% (95% CI: 18-44) for a ΔTMTV ≥75%. The outcomes for ΔSUVmax <65% and ΔTMTV <75% at PET2 remained significant in a cox regression model adjusted for IPI and bulky disease (>10cm)(Table). Conclusions: A ΔTMTV decline <75% or a ΔSUVmax decline <65% at PET2 identified an ultra-high-risk subgroup of DLBCL with particularly poor outcomes, that captured a high percentage of prDLBCL patients, and was significant after adjusting for IPI and bulky baseline disease. These patients may benefit from clinical trials evaluating alternative PET-adapted treatment strategies, but further evaluation among all patients with DLBCL is needed. [Table: see text]

1552 Background: Immune checkpoint inhibitor therapy-related (ICI) pneumonitis poses a significant challenge in patients with cancer. There is a need for predictive modeling to identify those at high risk of developing serious adverse events of ICI pneumonitis. Methods: A newly created database of cancer patients diagnosed with ICI pneumonitis seen at Mayo Clinic from 2014-2022 was utilized for exploratory data analysis. Modeling was used to determine if three clinical outcomes could be predicted, namely risk of death from: pneumonitis prior to starting immunotherapy, pneumonitis at time of diagnosis of ICI pneumonitis, and any cause at time of ICI pneumonitis diagnosis. The data consisted of 170 patients with annotation for 71 clinical features. Data was divided into features available at time of cancer diagnosis and at time of ICI pneumonitis diagnosis. Exploratory modeling was performed using the gradient boosting technique Xgboost (Chen, 2015) and conducted using k-fold balanced cross validation best practices as well as a train/test/validate schema with 70%/20%/10% data proportions, respectively. Model reverse engineering was done with Shapley statistics (Lundberg, 2017) to determine which features had the largest contribution per model. Once identified, only those highly weighted features were used for logistic regression analysis providing more reproducible predictions by decreasing model variance. Results: Risk of death from pneumonitis prior to starting immunotherapy was modeled with an area under the curve of the receiver operator characteristic (AUC-ROC) of 0.79 with the most contributory features including lymphocyte count, oxygen dependence, PFT values, and PD-L1 expression. Logistic regression produced an AUC-ROC of 0.87 (95% CI 0.72-1.0, p < 0.0013). Risk of death from pneumonitis at the time of ICI pneumonitis diagnosis was modeled with an AUC-ROC of 0.85 and the most contributory features were similar to the list described in the previous endpoint. Logistic regression produced an AUC-ROC of 0.89 (95% CI 0.81-0.96, p < 0.0001). Risk of death from any cause at the time of ICI pneumonitis diagnosis until follow up concluded by 12/2022 produced a model with an AUC-ROC of 0.75 with the most contributory features including supplemental oxygen, PFT values, basic laboratory values, and PD-L1 expression, among others. Logistic regression produced an AUC-ROC of 0.85 (95% CI 0.76-0.93, p < 0.0001). Conclusions: We demonstrate that commonly available clinical data can be used to identify patients at high risk of death from ICI pneumonitis. This study identified clinical features that were predictive in each scenario from which further concerted effort could produce a new clinical model to provide clinician decision support when considering immunotherapy. Further studies should be done to further elucidate feature interdependence and generalizability.

The promise of highly personalized oncology care using artificial intelligence (AI) technologies has been forecasted since the emergence of the field. Cumulative advances across the science are bringing this promise to realization, including refinement of machine learning– and deep learning algorithms; expansion in the depth and variety of databases, including multiomics; and the decreased cost of massively parallelized computational power. Examples of successful clinical applications of AI can be found throughout the cancer continuum and in multidisciplinary practice, with computer vision–assisted image analysis in particular having several U.S. Food and Drug Administration–approved uses. Techniques with emerging clinical utility include whole blood multicancer detection from deep sequencing, virtual biopsies, natural language processing to infer health trajectories from medical notes, and advanced clinical decision support systems that combine genomics and clinomics. Substantial issues have delayed broad adoption, with data transparency and interpretability suffering from AI’s “black box” mechanism, and intrinsic bias against underrepresented persons limiting the reproducibility of AI models and perpetuating health care disparities. Midfuture projections of AI maturation involve increasing a model’s complexity by using multimodal data elements to better approximate an organic system. Far-future positing includes living databases that accumulate all aspects of a person’s health into discrete data elements; this will fuel highly convoluted modeling that can tailor treatment selection, dose determination, surveillance modality and schedule, and more. The field of AI has had a historical dichotomy between its proponents and detractors. The successful development of recent applications, and continued investment in prospective validation that defines their impact on multilevel outcomes, has established a momentum of accelerated progress.