TY - JOUR
T1 - Development of a Structured Query Language and Natural Language Processing Algorithm to Identify Lung Nodules in a Cancer Centre
AU - Hunter, Benjamin
AU - Reis, Sara
AU - Campbell, Des
AU - Matharu, Sheila
AU - Ratnakumar, Prashanthi
AU - Mercuri, Luca
AU - Hindocha, Sumeet
AU - Kalsi, Hardeep
AU - Mayer, Erik
AU - Glampson, Ben
AU - Robinson, Emily J.
AU - Al-Lazikani, Bisan
AU - Scerri, Lisa
AU - Bloch, Susannah
AU - Lee, Richard
N1 - Publisher Copyright:
© Copyright © 2021 Hunter, Reis, Campbell, Matharu, Ratnakumar, Mercuri, Hindocha, Kalsi, Mayer, Glampson, Robinson, Al-Lazikani, Scerri, Bloch and Lee.
PY - 2021/11/4
Y1 - 2021/11/4
N2 - Importance: The stratification of indeterminate lung nodules is a growing problem, but the burden of lung nodules on healthcare services is not well-described. Manual service evaluation and research cohort curation can be time-consuming and potentially improved by automation. Objective: To automate lung nodule identification in a tertiary cancer centre. Methods: This retrospective cohort study used Electronic Healthcare Records to identify CT reports generated between 31st October 2011 and 24th July 2020. A structured query language/natural language processing tool was developed to classify reports according to lung nodule status. Performance was externally validated. Sentences were used to train machine-learning classifiers to predict concerning nodule features in 2,000 patients. Results: 14,586 patients with lung nodules were identified. The cancer types most commonly associated with lung nodules were lung (39%), neuro-endocrine (38%), skin (35%), colorectal (33%) and sarcoma (33%). Lung nodule patients had a greater proportion of metastatic diagnoses (45 vs. 23%, p < 0.001), a higher mean post-baseline scan number (6.56 vs. 1.93, p < 0.001), and a shorter mean scan interval (4.1 vs. 5.9 months, p < 0.001) than those without nodules. Inter-observer agreement for sentence classification was 0.94 internally and 0.98 externally. Sensitivity and specificity for nodule identification were 93 and 99% internally, and 100 and 100% at external validation, respectively. A linear-support vector machine model predicted concerning sentence features with 94% accuracy. Conclusion: We have developed and validated an accurate tool for automated lung nodule identification that is valuable for service evaluation and research data acquisition.
AB - Importance: The stratification of indeterminate lung nodules is a growing problem, but the burden of lung nodules on healthcare services is not well-described. Manual service evaluation and research cohort curation can be time-consuming and potentially improved by automation. Objective: To automate lung nodule identification in a tertiary cancer centre. Methods: This retrospective cohort study used Electronic Healthcare Records to identify CT reports generated between 31st October 2011 and 24th July 2020. A structured query language/natural language processing tool was developed to classify reports according to lung nodule status. Performance was externally validated. Sentences were used to train machine-learning classifiers to predict concerning nodule features in 2,000 patients. Results: 14,586 patients with lung nodules were identified. The cancer types most commonly associated with lung nodules were lung (39%), neuro-endocrine (38%), skin (35%), colorectal (33%) and sarcoma (33%). Lung nodule patients had a greater proportion of metastatic diagnoses (45 vs. 23%, p < 0.001), a higher mean post-baseline scan number (6.56 vs. 1.93, p < 0.001), and a shorter mean scan interval (4.1 vs. 5.9 months, p < 0.001) than those without nodules. Inter-observer agreement for sentence classification was 0.94 internally and 0.98 externally. Sensitivity and specificity for nodule identification were 93 and 99% internally, and 100 and 100% at external validation, respectively. A linear-support vector machine model predicted concerning sentence features with 94% accuracy. Conclusion: We have developed and validated an accurate tool for automated lung nodule identification that is valuable for service evaluation and research data acquisition.
KW - informatics
KW - lung nodule
KW - machine learning
KW - natural language processing (NLP)
KW - structured query language (SQL)
UR - http://www.scopus.com/inward/record.url?scp=85119412758&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119412758&partnerID=8YFLogxK
U2 - 10.3389/fmed.2021.748168
DO - 10.3389/fmed.2021.748168
M3 - Article
C2 - 34805217
AN - SCOPUS:85119412758
SN - 2296-858X
VL - 8
JO - Frontiers in Medicine
JF - Frontiers in Medicine
M1 - 748168
ER -