External Validation of Radiation-Induced Dyspnea Models on Esophageal Cancer Radiotherapy Patients

Abstract

Purpose: Radiation-induced lung disease (RILD), defined as dyspnea in this study, is a risk for patients receiving high-dose thoracic irradiation. This study is a TRIPOD (Transparent Reporting of A Multivariable Prediction Model for Individual Prognosis or Diagnosis) Type 4 validation of previously-published dyspnea models via secondary analysis of esophageal cancer SCOPE1 trial data. We quantify the predictive performance of these two models for predicting the maximal dyspnea grade ≥ 2 within 6 months after the end of high-dose chemo-radiotherapy for primary esophageal cancer. Materials and methods: We tested the performance of two previously published dyspnea risk models using baseline, treatment and follow-up data on 258 esophageal cancer patients in the UK enrolled into the SCOPE1 multi-center trial. The tested models were developed from lung cancer patients treated at MAASTRO Clinic (The Netherlands) from the period 2002 to 2011. The adverse event of interest was dyspnea ≥ Grade 2 (CTCAE v3) within 6 months after the end of radiotherapy. As some variables were missing randomly and cannot be imputed, 212 patients in the SCOPE1 were used for validation of model 1 and 255 patients were used for validation of model 2. The model parameter Forced Expiratory Volume in 1 s (FEV 1), as a predictor to both validated models, was imputed using the WHO performance status. External validation was performed using an automated, decentralized approach, without exchange of individual patient data. Results: Out of 258 patients with esophageal cancer in SCOPE1 trial data, 38 patients (14.7%) developed radiation-induced dyspnea (≥ Grade 2) within 6 months after chemo-radiotherapy. The discrimination performance of the models in esophageal cancer patients treated with high-dose external beam radiotherapy was moderate, area under curve (AUC) of 0.68 (95% CI 0.55-0.76) and 0.70 (95% CI 0.58-0.77), respectively. The curves and AUCs derived by distributed learning were identical to the results from validation on a local host. Shi et al. Dyspnea Model for EC Patients Conclusion: We have externally validated previously published dyspnea models using an esophageal cancer dataset. FEV 1 that is not routinely measured for esophageal cancer was imputed using WHO performance status. Prediction performance was not statistically different from previous training and validation sets. Risk estimates were dominated by WHO score in Model 1 and baseline dyspnea in Model 2. The distributed learning approach gave the same answer as local processing, and could be performed without accessing a validation site's individual patients-level data.

FAIR‐compliant clinical, radiomics and DICOM metadata of RIDER, interobserver, Lung1 and head‐Neck1 TCIA collections

“…As has been shown in other publications, the proposed methodology here can be used prospectively for exchanging radiomics prediction models for training or validation, in accordance with a paradigm known as distributed (or equivalently, federated) machine learning 41–43 …”

“…As has been shown in other publications, the proposed methodology here can be used prospectively for exchanging radiomics prediction models for training or validation, in accordance with a paradigm known as distributed (or equivalently, federated) machine learning. [41][42][43] We have provided examples of SPARQL queries, primarily as a form of guidance notes on how to use this data submission. We would encourage the academic community to adjust them according to their own questions and potentially utilize this methodology for multicenter studies.…”

Automatic Tumor Grading on Colorectal Cancer Whole-Slide Images: Semi-Quantitative Gland Formation Percentage and New Indicator Exploration

“…Although the rate of false positives (normal tissue being misclassified as GF1, GF2, or GF3) appears low in this study, it is important to note that such errors can happen. Therefore, cautious clinical commissioning and routine quality assurance of such classification models are needed if they are included in clinical practice ( 22 – 24 ). Although this model has not yet been deployed into routine clinical practice, it has been designed and developed in close collaboration between data scientists and highly experienced clinicians; therefore, it is hoped that a clinical translation gap will be more easily bridged through future work.…”

Methodological quality of machine learning-based quantitative imaging analysis studies in esophageal cancer: a systematic review of clinical outcome prediction after concurrent chemoradiotherapy

“…Alternatively, privacy-preserving federated learning [ 78 ] (also known as distributed learning) may be a feasible solution for modelling private data between institutions without physically exchanging individual patient data. Federated learning has been shown to be feasible in the radiomics domain [ 79 , 80 ], and also for EC in particular [ 81 ].…”