Establishing a colorectal cancer research database from routinely collected health data: the process and potential from a pilot study.

OBJECTIVE: Colorectal cancer is a common cause of death and morbidity. A significant amount of data are routinely collected during patient treatment, but they are not generally available for research. The National Institute for Health Research Health Informatics Collaborative in the UK is developing infrastructure to enable routinely collected data to be used for collaborative, cross-centre research. This paper presents an overview of the process for collating colorectal cancer data and explores the potential of using this data source. METHODS: Clinical data were collected from three pilot Trusts, standardised and collated. Not all data were collected in a readily extractable format for research. Natural language processing (NLP) was used to extract relevant information from pseudonymised imaging and histopathology reports. Combining data from many sources allowed reconstruction of longitudinal histories for each patient that could be presented graphically. RESULTS: Three pilot Trusts submitted data, covering 12 903 patients with a diagnosis of colorectal cancer since 2012, with NLP implemented for 4150 patients. Timelines showing individual patient longitudinal history can be grouped into common treatment patterns, visually presenting clusters and outliers for analysis. Difficulties and gaps in data sources have been identified and addressed. DISCUSSION: Algorithms for analysing routinely collected data from a wide range of sites and sources have been developed and refined to provide a rich data set that will be used to better understand the natural history, treatment variation and optimal management of colorectal cancer. CONCLUSION: The data set has great potential to facilitate research into colorectal cancer.

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

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.

Immune Checkpoint Inhibitor and Radiotherapy-Related Pneumonitis: An Informatics Approach to Determine Real-World Incidence, Severity, Management, and Resource Implications.

Pneumonitis is a well-described, potentially life-threatening adverse effect of immune checkpoint inhibitors (ICI) and thoracic radiotherapy. It can require additional investigations, treatment, and interruption of cancer therapy. It is important for clinicians to have an awareness of its incidence and severity, however real-world data are lacking and do not always correlate with findings from clinical trials. Similarly, there is a dearth of information on cost impact of symptomatic pneumonitis. Informatics approaches are increasingly being applied to healthcare data for their ability to identify specific patient cohorts efficiently, at scale. We developed a Structured Query Language (SQL)-based informatics algorithm which we applied to CT report text to identify cases of ICI and radiotherapy pneumonitis between 1/1/2015 and 31/12/2020. Further data on severity, investigations, medical management were also acquired from the electronic health record. We identified 248 cases of pneumonitis attributable to ICI and/or radiotherapy, of which 139 were symptomatic with CTCAE severity grade 2 or more. The grade ≥2 ICI pneumonitis incidence in our cohort is 5.43%, greater than the all-grade 1.3-2.7% incidence reported in the literature. Time to onset of ICI pneumonitis was also longer in our cohort (mean 4.5 months, range 4 days-21 months), compared to the median 2.7 months (range 9 days-19.2 months) described in the literature. The estimated average healthcare cost of symptomatic pneumonitis is £3932.33 per patient. In this study we use an informatics approach to present new real-world data on the incidence, severity, management, and resource burden of ICI and radiotherapy pneumonitis. To our knowledge, this is the first study to look at real-world incidence and healthcare resource utilisation at the per-patient level in a UK cancer hospital. Improved management of pneumonitis may facilitate prompt continuation of cancer therapy, and improved outcomes for this not insubstantial cohort of patients.