Northwestern University Feinberg School of Medicine, Division of Gynecologic Oncology, Department of Obstetrics and Gynecology, Chicago, IL, USA; Robert H Lurie Comprehensive Cancer Center, Northwestern University, Chicago, IL, United States of America; Center for Health Equity Transformation, Northwestern University Feinberg School of Medicine, Chicago, IL, United States of America; Institute of Public Health and Medicine Northwestern University Feinberg School of Medicine, Chicago, IL, United States of America.
Institute of Public Health and Medicine Northwestern University Feinberg School of Medicine, Chicago, IL, United States of America.
Gynecol Oncol. 2021 Jan;160(1):182-186. doi: 10.1016/j.ygyno.2020.10.004. Epub 2020 Oct 14.
To determine if natural language processing (NLP) with machine learning of unstructured full text documents (a preoperative CT scan) improves the ability to predict postoperative complication and hospital readmission among women with ovarian cancer undergoing surgery when compared with discrete data predictors alone.
Medical records from two institutions were queried to identify women with ovarian cancer and available preoperative CT scan reports who underwent debulking surgery. Machine learning methods using both discrete data predictors (age, comorbidities, preoperative laboratory values) and natural language processing of full text reports (preoperative CT scans) were used to predict postoperative complication and hospital readmission within 30 days of surgery. Discrimination was measured using the area under the receiver operating characteristic curve (AUC).
We identified 291 women who underwent debulking surgery for ovarian cancer. Mean age was 59, mean preoperative CA125 value was 610 U/ml and albumin was 3.9 g/dl. There were 25 patients (8.6%) who were readmitted and 45 patients (15.5%) who developed postoperative complications within 30 days. Using discrete features alone, we were able to predict postoperative readmission with an AUC of 0.56 (0.54-0.58, 95% CI); this improved to 0.70 (0.68-0.73, 95% CI) (p < 0.001) with the addition of NLP of preoperative CT scans.
Natural language processing with machine learning improved the ability to predict postoperative complication and hospital readmission among women with ovarian cancer undergoing surgery.
确定在对接受手术治疗的卵巢癌女性患者进行预测时，与单独使用离散数据预测因子相比，通过使用机器学习对非结构化全文文档（术前 CT 扫描）进行自然语言处理是否能提高对术后并发症和 30 天内住院再入院的预测能力。
通过查询两个机构的病历记录，确定接受肿瘤细胞减灭术且有可用术前 CT 扫描报告的卵巢癌女性患者。使用机器学习方法，同时使用离散数据预测因子（年龄、合并症、术前实验室值）和对全文报告（术前 CT 扫描）进行自然语言处理，以预测术后 30 天内的并发症和住院再入院。使用接收者操作特征曲线下的面积（AUC）来衡量判别能力。
我们共确定了 291 名接受肿瘤细胞减灭术治疗卵巢癌的女性患者。平均年龄为 59 岁，平均术前 CA125 值为 610U/ml，白蛋白值为 3.9g/dl。有 25 名患者（8.6%）在 30 天内再次入院，45 名患者（15.5%）在术后 30 天内发生了并发症。仅使用离散特征，我们能够以 AUC 为 0.56（0.54-0.58，95%CI）来预测术后再入院；通过增加术前 CT 扫描的自然语言处理，这一数值提高到 0.70（0.68-0.73，95%CI）（p<0.001）。
通过使用机器学习对自然语言处理，可以提高对接受手术治疗的卵巢癌女性患者的术后并发症和住院再入院的预测能力。
