dc.contributor.author | Hunter, B | |
dc.contributor.author | Reis, S | |
dc.contributor.author | Campbell, D | |
dc.contributor.author | Matharu, S | |
dc.contributor.author | Ratnakumar, P | |
dc.contributor.author | Mercuri, L | |
dc.contributor.author | Hindocha, S | |
dc.contributor.author | Kalsi, H | |
dc.contributor.author | Mayer, E | |
dc.contributor.author | Glampson, B | |
dc.contributor.author | Robinson, EJ | |
dc.contributor.author | Al-Lazikani, B | |
dc.contributor.author | Scerri, L | |
dc.contributor.author | Bloch, S | |
dc.contributor.author | Lee, R | |
dc.coverage.spatial | Switzerland | |
dc.date.accessioned | 2022-09-02T09:59:49Z | |
dc.date.available | 2022-09-02T09:59:49Z | |
dc.date.issued | 2021-11-04 | |
dc.identifier | ARTN 748168 | |
dc.identifier.citation | Frontiers in Medicine, 2021, 8 pp. 748168 - | |
dc.identifier.issn | 2296-858X | |
dc.identifier.uri | https://repository.icr.ac.uk/handle/internal/5383 | |
dc.identifier.eissn | 2296-858X | |
dc.identifier.eissn | 2296-858X | |
dc.identifier.doi | 10.3389/fmed.2021.748168 | |
dc.description.abstract | 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. | |
dc.format | Electronic-eCollection | |
dc.format.extent | 748168 - | |
dc.language | eng | |
dc.language.iso | eng | |
dc.publisher | FRONTIERS MEDIA SA | |
dc.relation.ispartof | Frontiers in Medicine | |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
dc.subject | informatics | |
dc.subject | lung nodule | |
dc.subject | machine learning | |
dc.subject | natural language processing (NLP) | |
dc.subject | structured query language (SQL) | |
dc.title | Development of a Structured Query Language and Natural Language Processing Algorithm to Identify Lung Nodules in a Cancer Centre. | |
dc.type | Journal Article | |
dcterms.dateAccepted | 2021-10-07 | |
dc.date.updated | 2022-09-02T09:59:27Z | |
rioxxterms.version | VoR | |
rioxxterms.versionofrecord | 10.3389/fmed.2021.748168 | |
rioxxterms.licenseref.startdate | 2021-11-04 | |
rioxxterms.type | Journal Article/Review | |
pubs.author-url | https://www.ncbi.nlm.nih.gov/pubmed/34805217 | |
pubs.organisational-group | /ICR | |
pubs.organisational-group | /ICR/Primary Group | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Cancer Therapeutics | |
pubs.organisational-group | /ICR/Primary Group/ICR Divisions/Cancer Therapeutics/Computational Biology and Chemogenomics | |
pubs.organisational-group | /ICR/ImmNet | |
pubs.publication-status | Published online | |
pubs.publisher-url | http://dx.doi.org/10.3389/fmed.2021.748168 | |
pubs.volume | 8 | |
icr.researchteam | Computational Biology | |
dc.contributor.icrauthor | Al-Lazikani, Bissan | |
icr.provenance | Deposited by Mr Arek Surman on 2022-09-02. Deposit type is initial. No. of files: 1. Files: Development of a Structured Query Language and Natural Language Processing Algorithm to Identify Lung Nodules in a Cancer Ce.pdf | |