Development of a Structured Query Language and Natural Language Processing Algorithm to Identify Lung Nodules in a Cancer Centre

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.

Performance of a rule-based semi-automated method to optimize chart abstraction for surveillance imaging among patients treated for non-small cell lung cancer

“…Overall the F1 scores ranged from 0.71 to 0.89, Sensitivity ranged from 0.70–0.90, and PPV ranged from 0.64–0.89. The best performing algorithm was linear support vector machine with F1 0.89, sensitivity 0.90, and PPV 0.88 for predicting concerning lung nodules [ 24 ]. It is important to note, the machine learning technique was used after a pre-processing step using a rule-based algorithm to identify CT reports that actually had nodules.…”

“…Another study also examined CT chest imaging reports using a rule-based natural language processing algorithm to identify lung nodules and more complex machine learning algorithms to determine the presence of concerning features. However, again, the authors only examined one type of imaging modality and did not focus on post-treatment surveillance imaging [ 24 ]. Though CT chest is recommended by NCCN guidelines for post-treatment surveillance [ 16 ], in clinical practice, multiple different imaging types are utilized routinely to rule out or diagnose recurrence in these patients.…”

The Role of Artificial Intelligence in Early Cancer Diagnosis

“…The latter can be analysed using NLP approaches. An overview of NLP in oncology is provided by Yim et al [12], and example early diagnosis uses include identifying abnormal cancer screening results [31], auditing colonoscopy or cystoscopy standards [32,33] and identifying or risk-stratifying pre-malignant lesions [34][35][36][37][38]. NLP has also been used to automate patient identification for clinical trials, reducing the burden of eligibility checks [39].…”