Applying Natural Language Processing to Single-Report Prediction of Metastatic Disease Response Using the OR-RADS Lexicon.
Applying Natural Language Processing to Single-Report Prediction of Metastatic Disease Response Using the OR-RADS Lexicon.
复制标题
使用OR-RADS词典将自然语言处理应用于转移性疾病反应的单报告预测。
DOI：
10.3390/cancers15204909
复制
发表时间：
2023-10-10
期刊：
影响因子：
5.2
通讯作者：
Simpson, Amber L.
中科院分区：
文献类型：
--
作者：
Elbatarny, Lydia;Do, Richard K. G.;Gangai, Natalie;Ahmed, Firas;Chhabra, Shalini;Simpson, Amber L.
放射科医生在撰写放射报告方面缺乏标准化，影响了大规模解释癌症对治疗反应的能力。这是一个问题，因为大规模的数据收集是必要的，以产生真实世界的证据（RWE），以了解癌症治疗的有效性和制定个性化的患者治疗决策。本研究旨在研究应用自然语言处理（NLP）大规模解释疾病反应的效用，使用标准化的肿瘤反应类别（称为OR-RADS）来促进RWE收集。本研究证明了应用NLP预测癌症患者疾病反应的可行性，超越了人类的表现，从而鼓励放射科医生和研究人员使用标准化的OR-RADS类别来提高大规模反应预测的准确性。从放射学报告中产生疾病反应的真实世界证据（RWE）对于了解癌症治疗效果和制定个性化治疗非常重要。放射科医师报告缺乏标准化影响了大规模解释疾病反应的可行性。本研究考察了使用标准化肿瘤反应词典（OR-RADS）将自然语言处理（NLP）应用于疾病反应的大规模解释的效用，以促进RWE的收集。放射科医生注释了3503回顾性收集了几种癌症类型的放射报告的临床印象，其中有七种OR-RADS类别之一。在此数据集上以80-20%的训练/测试分割训练了来自变压器的双向编码器表示（BERT）模型，以使用OR-RADS执行多类和单类分类任务。放射科医生还进行了分类，以比较人类和模型的表现。该模型在所有分类任务中实现了95%到99%的准确率，在单类任务中比在多类任务中表现更好，并且产生最小的错误分类，这主要与过度预测模棱两可和混合OR-RADS标签有关。人类在所有分类任务中的准确率从74到93%不等，在单类任务中表现更好。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，超越了人类的表现，并鼓励使用标准化的OR-RADS词典来提高大规模预测的准确性。
Lack of standardization among radiologists in writing radiological reports impacts the ability to interpret cancer response to treatment at a large-scale. This is an issue since large-scale data collection is necessary to generate Real World Evidence (RWE) towards understanding the effectiveness of cancer treatments and developing personalized patient treatment decisions. This study aims to examine the utility of applying natural language processing (NLP) for large-scale interpretation of disease response using the standardized oncologic response categories known as the OR-RADS to facilitate RWE collection. This study demonstrates the feasibility of applying NLP to predict disease response in cancer patients, exceeding human performance, thus encouraging use of the standardized OR-RADS categories among radiologists and researchers to improve large-scale response prediction accuracy. 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.
登录
查看更多内容
影响因子：
4.7
作者：
Nobel JM;Puts S;Weiss J;Aerts HJWL;Mak RH;Robben SGF;Dekker ALAJ
通讯作者：
Dekker ALAJ
影响因子：
3.1
作者：
Groot, Olivier Q.;Bongers, Michiel E. R.;Schwab, Joseph H.
通讯作者：
Schwab, Joseph H.
DOI：
10.1158/1078-0432.ccr-12-2935
发表时间：
2013-05-15
期刊：
Clinical cancer research : an official journal of the American Association for Cancer Research
影响因子：
--
作者：
Villaruz LC;Socinski MA
通讯作者：
Socinski MA
影响因子：
4.2
作者：
Kehl, Kenneth L.;Xu, Wenxin;Schrag, Deborah
通讯作者：
Schrag, Deborah
影响因子：
4.7
作者：
通讯作者：
--