How Natural Language Processing Can Aid With Pulmonary Oncology Tumor Node Metastasis Staging From Free-Text Radiology Reports: Algorithm Development and Validation

Abstract

Background Natural language processing (NLP) is thought to be a promising solution to extract and store concepts from free text in a structured manner for data mining purposes. This is also true for radiology reports, which still consist mostly of free text. Accurate and complete reports are very important for clinical decision support, for instance, in oncological staging. As such, NLP can be a tool to structure the content of the radiology report, thereby increasing the report’s value. Objective This study describes the implementation and validation of an N-stage classifier for pulmonary oncology. It is based on free-text radiological chest computed tomography reports according to the tumor, node, and metastasis (TNM) classification, which has been added to the already existing T-stage classifier to create a combined TN-stage classifier. Methods SpaCy, PyContextNLP, and regular expressions were used for proper information extraction, after additional rules were set to accurately extract N-stage. Results The overall TN-stage classifier accuracy scores were 0.84 and 0.85, respectively, for the training (N=95) and validation (N=97) sets. This is comparable to the outcomes of the T-stage classifier (0.87-0.92). Conclusions This study shows that NLP has potential in classifying pulmonary oncology from free-text radiological reports according to the TNM classification system as both the T- and N-stages can be extracted with high accuracy.

ChatGPT for automating lung cancer staging: feasibility study on open radiology report dataset

“…Following previous researches [4][5][6], we calculated the accuracy score, or the proportion of correct answers, for the T, N, and M categories.…”

“…Table 4 summarizes previously suggested methods for automating lung cancer staging from radiology reports. Rule-based methods achieved an accuracy score of around 0.9 for the T and N categories [4][5][6],…”

“…To alleviate workloads, several natural language processing (NLP) techniques have been proposed to automate staging from unstructured radiology reports. While their potential has been demonstrated in existing studies, they often depended on meticulously organized rules and vocabularies [4][5][6] or large training datasets [7][8][9].…”

Natural Language Processing Algorithm Used for Staging Pulmonary Oncology from Free-Text Radiological Reports: “Including PET-CT and Validation Towards Clinical Use”

“…Also, in nuclear medicine, several studies have been published on NLP and oncologic imaging, such as finding bone metastasis in free-text bone scintigraphy reports [ 10 ]. Efforts to explore the potential of NLP in this field are illustrated by research published on finding pulmonary nodules and its characteristics in radiological reports [ 11 ] and finding a Lung-RADS classification out of structured reports used in pulmonary CT screening [ 12 ], as well as identifying staging characteristics about lung carcinoma in free-text radiology reports [ 13 – 15 ]. NLP is able to extract the TN stage of pulmonary oncology from the free-text radiological report of diagnostic staging CT scans by analyzing the text for this specific information and was shown by a rule-based TN-CT algorithm [ 13 – 15 ].…”

“…Efforts to explore the potential of NLP in this field are illustrated by research published on finding pulmonary nodules and its characteristics in radiological reports [ 11 ] and finding a Lung-RADS classification out of structured reports used in pulmonary CT screening [ 12 ], as well as identifying staging characteristics about lung carcinoma in free-text radiology reports [ 13 – 15 ]. NLP is able to extract the TN stage of pulmonary oncology from the free-text radiological report of diagnostic staging CT scans by analyzing the text for this specific information and was shown by a rule-based TN-CT algorithm [ 13 – 15 ]. This research showed that it is possible to automatically extract T and N stage from free-text radiological reports with accuracy scores of 0.84–0.85.…”