Dataset Information

Deep Learning to Estimate RECIST in Patients with NSCLC Treated with PD-1 Blockade.

ABSTRACT: Real-world evidence (RWE), conclusions derived from analysis of patients not treated in clinical trials, is increasingly recognized as an opportunity for discovery, to reduce disparities, and to contribute to regulatory approval. Maximal value of RWE may be facilitated through machine-learning techniques to integrate and interrogate large and otherwise underutilized datasets. In cancer research, an ongoing challenge for RWE is the lack of reliable, reproducible, scalable assessment of treatment-specific outcomes. We hypothesized a deep-learning model could be trained to use radiology text reports to estimate gold-standard RECIST-defined outcomes. Using text reports from patients with non-small cell lung cancer treated with PD-1 blockade in a training cohort and two test cohorts, we developed a deep-learning model to accurately estimate best overall response and progression-free survival. Our model may be a tool to determine outcomes at scale, enabling analyses of large clinical databases. SIGNIFICANCE: We developed and validated a deep-learning model trained on radiology text reports to estimate gold-standard objective response categories used in clinical trial assessments. This tool may facilitate analysis of large real-world oncology datasets using objective outcome metrics determined more reliably and at greater scale than currently possible.This article is highlighted in the In This Issue feature, p. 1.

SUBMITTER: Arbour KC

PROVIDER: S-EPMC7981277 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning to Estimate RECIST in Patients with NSCLC Treated with PD-1 Blockade.

Arbour Kathryn C KC Luu Anh Tuan AT Luo Jia J Rizvi Hira H Plodkowski Andrew J AJ Sakhi Mustafa M Huang Kevin B KB Digumarthy Subba R SR Ginsberg Michelle S MS Girshman Jeffrey J Kris Mark G MG Riely Gregory J GJ Yala Adam A Gainor Justin F JF Barzilay Regina R Hellmann Matthew D MD

Cancer discovery 20200921 1

Real-world evidence (RWE), conclusions derived from analysis of patients not treated in clinical trials, is increasingly recognized as an opportunity for discovery, to reduce disparities, and to contribute to regulatory approval. Maximal value of RWE may be facilitated through machine-learning techniques to integrate and interrogate large and otherwise underutilized datasets. In cancer research, an ongoing challenge for RWE is the lack of reliable, reproducible, scalable assessment of treatment- ...[more]

PMID: 32958579

Similar Datasets

Project description:The interaction between programmed cell death protein 1 (PD-1) and its ligand programmed death-ligand 1 (PD-L1) induces exhaustions of cytotoxic lymphocytes in the tumor microenvironment, which facilitates tumor immune evasion. PD-1/PD-L1 blockade therapy, which prevents the receptors and ligands from binding to each other, disrupts the T-cell exhaustion signaling, thereby increasing antitumor immunity. Inspiringly, it has revolutionized the treatment of many different types of cancers including non-small-cell lung carcinoma, melanoma, lymphoma, and so on. However, with the intention of generating an antitumor immune response, PD-1/PD-L1 blockade may also lead to a spectrum of side effects. The profile of adverse events (AEs) of PD-1/PD-L1 blockade is not exactly the same with other immune checkpoint blockades, such as blockade of cytotoxic T-lymphocyte-associated protein 4. Although cutaneous, gastrointestinal, and pulmonary systems are common victims, AEs of PD-1/PD-L1 blockade might occur in any other organ system of the human body. These toxicities can be life-threatening if not managed promptly, and proper treatment intervention is imperative for optimal control and prevention of severe damage. Currently, clinical practice for the management of AEs in PD-1/PD-L1 blockade remains sporadic and variable. The majority of initial clinical trials were carried out in Caucasians. The trials of multiple races usually included a small portion of Asian participants, and results were calculated and interpreted for the entire included subjects without any race-specific conclusions. Therefore, the information on PD-1/PD-L1 blockade in Asians is far from systematic or comprehensive. Recently, as the results of clinical trials of anti-PD-1/PD-L1 agents in Asian populations have been gradually released, we summarized current evidence with a specific focus on the Asian population, hoping to outline strategies and offer guidance on the management of AEs in cancer patients treated with PD-1/PD-L1 blockade in the Asian world.

Project description:ObjectivesThis study aims to establish nomograms to accurately predict the overall survival (OS) and progression-free survival (PFS) in patients with non-small cell lung cancer (NSCLC) who received chemotherapy alone as the first-line treatment.Materials and methodsIn a training cohort of 121 NSCLC patients, radiomic features were extracted, selected from intra- and peri-tumoral regions, and used to build signatures (S1 and S2) using a Cox regression model. Deep learning features were obtained from three convolutional neural networks and utilized to build signatures (S3, S4, and S5) that were stratified into over- and under-expression subgroups for survival risk using X-tile. After univariate and multivariate Cox regression analyses, a nomogram incorporating the tumor, node, and metastasis (TNM) stages, radiomic signature, and deep learning signature was established to predict OS and PFS, respectively. The performance was validated using an independent cohort (61 patients).ResultsTNM stages, S2 and S3 were identified as the significant prognosis factors for both OS and PFS; S2 (OS: (HR (95%), 2.26 (1.40-3.67); PFS: (HR (95%), 2.23 (1.36-3.65)) demonstrated the best ability in discriminating patients with over- and under-expression. For the OS nomogram, the C-index (95% CI) was 0.74 (0.70-0.79) and 0.72 (0.67-0.78) in the training and validation cohorts, respectively; for the PFS nomogram, the C-index (95% CI) was 0.71 (0.68-0.81) and 0.72 (0.66-0.79). The calibration curves for the 3- and 5-year OS and PFS were in acceptable agreement between the predicted and observed survival. The established nomogram presented a higher overall net benefit than the TNM stage for predicting both OS and PFS.ConclusionBy integrating the TNM stage, CT radiomic signature, and deep learning signatures, the established nomograms can predict the individual prognosis of NSCLC patients who received chemotherapy. The integrated nomogram has the potential to improve the individualized treatment and precise management of NSCLC patients.

Dataset Information

Deep Learning to Estimate RECIST in Patients with NSCLC Treated with PD-1 Blockade.

Publications

Deep Learning to Estimate RECIST in Patients with NSCLC Treated with PD-1 Blockade.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets