Automating the Capture of Structured Pathology Data for Prostate Cancer Clinical Care and Research

Abstract

Purpose Cancer pathology findings are critical for many aspects of care but are often locked away as unstructured free text. Our objective was to develop a natural language processing (NLP) system to extract prostate pathology details from postoperative pathology reports and a parallel structured data entry process for use by urologists during routine documentation care and compare accuracy when compared with manual abstraction and concordance between NLP and clinician-entered approaches. Materials and Methods From February 2016, clinicians used note templates with custom structured data elements (SDEs) during routine clinical care for men with prostate cancer. We also developed an NLP algorithm to parse radical prostatectomy pathology reports and extract structured data. We compared accuracy of clinician-entered SDEs and NLP-parsed data to manual abstraction as a gold standard and compared concordance (Cohen’s κ) between approaches assuming no gold standard. Results There were 523 patients with NLP-extracted data, 319 with SDE data, and 555 with manually abstracted data. For Gleason scores, NLP and clinician SDE accuracy was 95.6% and 95.8%, respectively, compared with manual abstraction, with concordance of 0.93 (95% CI, 0.89 to 0.98). For margin status, extracapsular extension, and seminal vesicle invasion, stage, and lymph node status, NLP accuracy was 94.8% to 100%, SDE accuracy was 87.7% to 100%, and concordance between NLP and SDE ranged from 0.92 to 1.0. Conclusion We show that a real-world deployment of an NLP algorithm to extract pathology data and structured data entry by clinicians during routine clinical care in a busy clinical practice can generate accurate data when compared with manual abstraction for some, but not all, components of a prostate pathology report.

Electronic case report forms generation from pathology reports by ARGO, automatic record generator for onco-hematology

“…In comparison with other applications in oncology, ARGO confirmed super-imposable performances in data field detection 6 , 11 , 14 , 16 , 21 , 22 , while overcoming some limitations. For instance, in the work by Nguyen et al, each metric decreases as the number of classes describing a certain data field increases 11 .…”

“…Finally, our system takes advantage from two levels of personalization related to REDCap, i) the designing of graphic interfaces directly by the clinical investigators according to specific clinical endpoints; and ii) the easily population of eCRFs via Application Programming Interface (API). Therefore, ARGO appeared as a valid tool for a precise and time-saving recording of clinical data when compared to manual abstraction 16 . Our approach results feasible in the daily practice, facilitating consultation, filtering, and management of RW data.…”

“…Natural Language Processing (NLP) is a consolidated technique to extract essential unstructured data from text, e.g. from diagnostic and prognostic notes 6 – 10 , widely adopted also in onco-hematology 11 – 16 . REDCap (Research Electronic Data CAPture) is a recognized platform of electronic case report forms (eCRFs) enabling rapid, high-quality and standardized annotation of data 17 , 18 .…”

A Natural Language Processing–Assisted Extraction System for Gleason Scores: Development and Usability Study

“…Currently, there are not many publicly available NLP solutions for adequate extraction of GS. Two previous projects were implemented but were limited to extraction of GS from pathology notes alone [ 6 , 7 ]. However, in the real world, pathology notes are often unavailable for a proportion of patients, especially patients who switch hospital systems during the course of their oncologic care, which happens more frequently for prostate cancer patients due to their longer survival times.…”

“…However, GS is often unavailable in research databases because it is stored as unstructured data within clinical and pathology notes, which require human extraction. There is currently a paucity of NLP solutions for extracting GS from both clinical and pathology notes, and these existing options are limited by either accuracy or scope [5][6][7][8].…”