Elbatarny Lydia, Do Richard K G, Gangai Natalie, Ahmed Firas, Chhabra Shalini, Simpson Amber L
School of Computing, Queen's University, Kingston, ON K7L 2N8, Canada.
Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
Cancers (Basel). 2023 Oct 10;15(20):4909. doi: 10.3390/cancers15204909.
Generating Real World Evidence (RWE) on disease responses from radiological reports is important for understanding cancer treatment effectiveness and developing personalized treatment. A lack of standardization in reporting among radiologists impacts the feasibility of large-scale interpretation of disease response. This study examines the utility of applying natural language processing (NLP) to the large-scale interpretation of disease responses using a standardized oncologic response lexicon (OR-RADS) to facilitate RWE collection. Radiologists annotated 3503 retrospectively collected clinical impressions from radiological reports across several cancer types with one of seven OR-RADS categories. A Bidirectional Encoder Representations from Transformers (BERT) model was trained on this dataset with an 80-20% train/test split to perform multiclass and single-class classification tasks using the OR-RADS. Radiologists also performed the classification to compare human and model performance. The model achieved accuracies from 95 to 99% across all classification tasks, performing better in single-class tasks compared to the multiclass task and producing minimal misclassifications, which pertained mostly to overpredicting the equivocal and mixed OR-RADS labels. Human accuracy ranged from 74 to 93% across all classification tasks, performing better on single-class tasks. This study demonstrates the feasibility of the BERT NLP model in predicting disease response in cancer patients, exceeding human performance, and encourages the use of the standardized OR-RADS lexicon to improve large-scale prediction accuracy.
从放射学报告中生成关于疾病反应的真实世界证据（RWE）对于理解癌症治疗效果和制定个性化治疗方案非常重要。放射科医生报告缺乏标准化会影响对疾病反应进行大规模解读的可行性。本研究探讨了应用自然语言处理（NLP），使用标准化的肿瘤反应词汇表（OR-RADS）对疾病反应进行大规模解读以促进RWE收集的效用。放射科医生用七个OR-RADS类别之一对从几种癌症类型的放射学报告中回顾性收集的3503份临床印象进行了标注。基于该数据集，以80-20%的训练/测试分割比例训练了一个来自变换器的双向编码器表征（BERT）模型，以使用OR-RADS执行多类和单类分类任务。放射科医生也进行了分类以比较人类和模型的表现。该模型在所有分类任务中的准确率达到95%至99%，在单类任务中的表现优于多类任务，并且产生的错误分类最少，这些错误分类大多是对模棱两可和混合的OR-RADS标签预测过度。在所有分类任务中，人类的准确率在74%至93%之间，在单类任务中的表现更好。本研究证明了BERT NLP模型在预测癌症患者疾病反应方面的可行性，其表现超过了人类，并且鼓励使用标准化的OR-RADS词汇表来提高大规模预测的准确性。
