Natural Language Processing to Ascertain Cancer Outcomes From Medical Oncologist Notes
Natural Language Processing to Ascertain Cancer Outcomes From Medical Oncologist Notes
复制标题
DOI：
10.1200/cci.20.00020
复制
发表时间：
2020-08-05
影响因子：
4.2
通讯作者：
Schrag, Deborah
中科院分区：
文献类型：
--
作者：
Kehl, Kenneth L.;Xu, Wenxin;Schrag, Deborah
目的：使用电子健康记录和基因组数据集的癌症研究需要临床结果数据，而这些数据可能仅由治疗肿瘤学家以非结构化文本记录。自然语言处理（NLP）可以大大加快这些信息的提取。方法选取2013年至2018年在单机构精确肿瘤学研究中接受肿瘤测序的肺癌患者。我们回顾了肿瘤内科医生对这些患者的病程记录。对于每个记录，管理员记录评估/计划是否表明任何癌症，疾病进展/恶化，和/或对治疗或改善疾病的反应。接下来，使用未标记的音符训练递归神经网络，从每个音符中提取评估/计划。最后，对卷积神经网络进行标记评估/计划训练，以预测每个策划结果存在的概率。在一组10%的患者中，使用受试者工作特征曲线下面积（AUROC）来评估模型的性能。在接受姑息性全身治疗的患者中，使用Cox模型测量了缓解或进展终点与总生存期之间的关系。结果人工整理了919例患者的肿瘤内科医师记录（n = 7597）。在10%的测试集中，NLP模型复制了人类治疗，任何癌症结果的auroc为0.94，进展结果为0.86，反应结果为0.90。使用NLP模型确定的进展/恶化事件与缩短的生存期相关（死亡率的风险比[HR]， 2.49; 95% CI， 2.00至3.09）；缓解/改善事件与改善的生存相关（HR, 0.45; 95% CI, 0.30 ~ 0.67）。结论基于神经网络的NLP模型可以大规模地从肿瘤医师笔记中提取有意义的结果。这种模型可能有助于识别与癌症治疗反应相关的临床和基因组特征。(c)美国临床肿瘤学会2020年
PURPOSE Cancer research using electronic health records and genomic data sets requires clinical outcomes data, which may be recorded only in unstructured text by treating oncologists. Natural language processing (NLP) could substantially accelerate extraction of this information.METHODS Patients with lung cancer who had tumor sequencing as part of a single-institution precision oncology study from 2013 to 2018 were identified. Medical oncologists' progress notes for these patients were reviewed. For each note, curators recorded whether the assessment/plan indicated any cancer, progression/worsening of disease, and/or response to therapy or improving disease. Next, a recurrent neural network was trained using unlabeled notes to extract the assessment/plan from each note. Finally, convolutional neural networks were trained on labeled assessments/plans to predict the probability that each curated outcome was present. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC) among a held-out test set of 10% of patients. Associations between curated response or progression end points and overall survival were measured using Cox models among patients receiving palliative-intent systemic therapy.RESULTS Medical oncologist notes (n = 7,597) were manually curated for 919 patients. In the 10% test set, NLP models replicated human curation with AUROCs of 0.94 for the any-cancer outcome, 0.86 for the progression outcome, and 0.90 for the response outcome. Progression/worsening events identified using NLP models were associated with shortened survival (hazard ratio [HR] for mortality, 2.49; 95% CI, 2.00 to 3.09); response/improvement events were associated with improved survival (HR, 0.45; 95% CI, 0.30 to 0.67).CONCLUSION NLP models based on neural networks can extract meaningful outcomes from oncologist notes at scale. Such models may facilitate identification of clinical and genomic features associated with response to cancer treatment. (c) 2020 by American Society of Clinical Oncology