Identifying Patients Who Meet Criteria for Genetic Testing of Hereditary Cancers Based on Structured and Unstructured Family Health History Data in the Electronic Health Record: Natural Language Processing Approach

Abstract

Background Family health history has been recognized as an essential factor for cancer risk assessment and is an integral part of many cancer screening guidelines, including genetic testing for personalized clinical management strategies. However, manually identifying eligible candidates for genetic testing is labor intensive. Objective The aim of this study was to develop a natural language processing (NLP) pipeline and assess its contribution to identifying patients who meet genetic testing criteria for hereditary cancers based on family health history data in the electronic health record (EHR). We compared an algorithm that uses structured data alone with structured data augmented using NLP. Methods Algorithms were developed based on the National Comprehensive Cancer Network (NCCN) guidelines for genetic testing for hereditary breast or ovarian and colorectal cancers. The NLP-augmented algorithm uses both structured family health history data and the associated unstructured free-text comments. The algorithms were compared with a reference standard of 100 patients with a family health history in the EHR. Results Regarding identifying the reference standard patients meeting the NCCN criteria, the NLP-augmented algorithm compared with the structured data algorithm yielded a significantly higher recall of 0.95 (95% CI 0.9-0.99) versus 0.29 (95% CI 0.19-0.40) and a precision of 0.99 (95% CI 0.96-1.00) versus 0.81 (95% CI 0.65-0.95). On the whole data set, the NLP-augmented algorithm extracted 33.6% more entities, resulting in 53.8% more patients meeting the NCCN criteria. Conclusions Compared with the structured data algorithm, the NLP-augmented algorithm based on both structured and unstructured family health history data in the EHR increased the number of patients identified as meeting the NCCN criteria for genetic testing for hereditary breast or ovarian and colorectal cancers.

A Clinical Prediction Model to Assess Risk for Pancreatic Cancer Among Patients With Acute Pancreatitis

“…In the future, incorporation of existing AP imaging results using natural language processing of radiology reports to specify true pancreatic cysts could further improve the identification of these high-risk individuals. 30 In addition, while the family history would be a useful candidate predictor, it is not always 31,32 and in the future after validation of these pipelines, we could include family history along with germline genetic risk for PC 33 as candidate predictors, as has previously been performed for other cancers. 34 Furthermore, we could also focus our risk prediction model solely on pancreatic ductal adenocarcinoma, although this already composes 90% of all PC.…”

“…In addition, while the family history would be a useful candidate predictor, it is not always available nor easily accessible in a structured format. Natural language processing has been tested in other electronic health record systems to create structured values for family history, 31,32 and in the future after validation of these pipelines, we could include family history along with germline genetic risk for PC 33 as candidate predictors, as has previously been performed for other cancers 34 . Furthermore, we could also focus our risk prediction model solely on pancreatic ductal adenocarcinoma, although this already composes 90% of all PC 30 …”

Enhanced family history-based algorithms increase the identification of individuals meeting criteria for genetic testing of hereditary cancer syndromes but would not reduce disparities on their own

“…Details of the development and evaluation of the SD + NLP algorithm are described elsewhere. [ 12 , 13 ].…”

Validation of a guidelines-based digital tool to assess the need for germline cancer genetic testing

“…A variety of such solutions have arisen in recent years. [27][28][29][30][31] This includes automated algorithms that leverage family history information already captured in the EHR 31 as well as patient-facing digital tools that perform hereditary cancer risk assessment based on patient-entered personal and family history. 27,28,30 Studies have found that such digital tools effectively identify at-risk patients who would have been overlooked.…”