Predicting Lung Cancer Prior to Surgical Resection in Patients with Lung Nodules

Abstract

Background Existing predictive models for lung cancer focus on improving screening or referral for biopsy in general medical populations. A predictive model calibrated for use during preoperative evaluation of suspicious lung lesions is needed to reduce unnecessary operations for benign disease. A clinical prediction model (TREAT) is proposed for this purpose. Methods We developed and internally validated a clinical prediction model for lung cancer in a prospective cohort evaluated at our institution. Best statistical practices were used to construct, evaluate and validate the logistic regression model in the presence of missing covariate data using bootstrap and optimism corrected techniques. The TREAT model was externally validated in a retrospectively collected Veteran Affairs population. The discrimination and calibration of the model was estimated and compared to the Mayo Clinic model in both populations. Results The TREAT model was developed in 492 patients from Vanderbilt whose lung cancer prevalence was 72% and validated among 226 Veteran Affairs patients with a lung cancer prevalence of 93%. In the development cohort the area under the receiver operating curve (AUC) and Brier score were 0.87 (95%CI: 0.83–0.92) and 0.12 respectively compared to the AUC 0.89 (95%CI: 0.79–0.98) and Brier score 0.13 in the validation dataset. The TREAT model had significantly higher accuracy (p<0.001) and better calibration than the Mayo Clinic model (AUC=0.80, 95%CI: 75–85; Brier score=0.17). Conclusion The validated TREAT model had better diagnostic accuracy than the Mayo Clinic model in preoperative assessment of suspicious lung lesions in a population being evaluated for lung resection.

Surgical Outcomes in a Large, Clinical, Low-Dose Computed Tomographic Lung Cancer Screening Program

“…Perhaps the incorporation of more robust predictive surgical models would be beneficial. [17] have demonstrated the increased diagnostic accuracy of the thoracic research evaluation and treatment model in predicting lung cancer before surgical resection in patients with suspicious lung lesions. If validated in the screened population, models such as this may be able to standardize risk assessment and facilitate decision making.…”

Applying Risk Prediction Models to Optimize Lung Cancer Screening: Current Knowledge, Challenges, and Future Directions

“…To date, Deppen et al [74] have proposed the only model tailored to estimate risk at preoperative evaluation, although the aforementioned models developed in surgical populations might be applied in this context as well. Their model was developed and internally validated in Vanderbilt University Medical Center (VUMC) patients evaluated for a suspicious lung nodule/mass and externally validated in VA patients who underwent lung cancer surgery, outperforming the Mayo Clinic model on calibration and discrimination (AUCs, VUMC: 0.87 vs. 0.80; VA: 0.89 vs. 0.73).…”

Indeterminate Pulmonary Nodules: How to Minimize Harm

“…More objective and reproducible methods for determining likelihood of malignancy involve diagnostic prediction models, several of which have been developed and are publically available (►Table 4). [60][61][62][63][64][65] The goal of diagnostic prediction is to segregate the IPN into categories of low, high, or intermediate probability of malignancy, thus guiding subsequent management steps in the evaluation of the patient. Model performance is determined by discrimination and calibration.…”