Background Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis. Methods Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate “Safety-Net” and “Early Diagnosis” decision-support tools. Results In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82–0.87), 0.78 (95% CI: 0.70–0.85) and 0.78 (95% CI: 0.59–0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65–81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers. Conclusions SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.

ABSTRACT In response to the first COVID-19 surge in 2020, secondary care outpatient services were rapidly reconfigured to provide specialist review for disease sequelae. At our institution, comprising hospitals across three sites in London, we initially implemented a COVID-19 follow-up pathway that was in line with expert opinion at the time but more intensive than initial clinical guidelines suggested. We retrospectively evaluated the resource requirements for this service, which supported 526 patients from April 2020 to October 2020. At the 6-week review, 193/403 (47.9%) patients reported persistent breathlessness, 46/336 (13.7%) desaturated on exercise testing, 167/403 (41.4%) were discharged from COVID-19-related secondary care services and 190/403 (47.1%) needed 12-week follow-up. At the 12-week review, 113/309 (36.6%) patients reported persistent breathlessness, 30/266 (11.3%) desaturated on exercise testing and 150/309 (48.5%) were discharged from COVID-19-related secondary care services. Referrals were generated to multiple medical specialties, particularly respiratory subspecialties. Our analysis allowed us to justify rationalising and streamlining provisions for subsequent COVID-19 waves while reassured that opportunities for early intervention were not being missed.

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.

Background The symptoms, radiography, biochemistry and healthcare utilisation of patients with COVID-19 following discharge from hospital have not been well described. Methods Retrospective analysis of 401 adult patients attending a clinic following an index hospital admission or emergency department attendance with COVID-19. Regression models were used to assess the association between characteristics and persistent abnormal chest radiographs or breathlessness. Results 75.1% of patients were symptomatic at a median of 53 days post discharge and 72 days after symptom onset and chest radiographs were abnormal in 47.4%. Symptoms and radiographic abnormalities were similar in PCR-positive and PCR-negative patients. Severity of COVID-19 was significantly associated with persistent radiographic abnormalities and breathlessness. 18.5% of patients had unscheduled healthcare visits in the 30 days post discharge. Conclusions Patients with COVID-19 experience persistent symptoms and abnormal blood biomarkers with a gradual resolution of radiological abnormalities over time. These findings can inform patients and clinicians about expected recovery times and plan services for follow-up of patients with COVID-19.