Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?

OBJECTIVES: Post-imaging mathematical prediction models (MPMs) provide guidance for the management of solid pulmonary nodules by providing a lung cancer risk score from demographic and radiologists-indicated imaging characteristics. We hypothesized calibrating the MPM risk score threshold to a local study cohort would result in improved performance over the original recommended MPM thresholds. We compared the pre- and post-calibration performance of four MPM models and determined if improvement in MPM prediction occurs as nodules are imaged longitudinally. MATERIALS AND METHODS: A common cohort of 317 individuals with computed tomography-detected, solid nodules (80 malignant, 237 benign) were used to evaluate the MPM performance. We created a web-based application for this study that allows others to easily calibrate thresholds and analyze the performance of MPMs on their local cohort. Thirty patients with repeated imaging were tested for improved performance longitudinally. RESULTS: Using calibrated thresholds, Mayo Clinic and Brock University (BU) MPMs performed the best (AUC = 0.63, 0.61) compared to the Veteran's Affairs (0.51) and Peking University (0.55). Only BU had consensus with the original MPM threshold; the other calibrated thresholds improved MPM accuracy. No significant improvements in accuracy were found longitudinally between time points. CONCLUSIONS: Calibration to a common cohort can select the best-performing MPM for your institution. Without calibration, BU has the most stable performance in solid nodules ≥ 8 mm but has only moderate potential to refine subjects into appropriate workup. Application of MPM is recommended only at initial evaluation as no increase in accuracy was achieved over time. KEY POINTS: • Post-imaging lung cancer risk mathematical predication models (MPMs) perform poorly on local populations without calibration. • An application is provided to facilitate calibration to new study cohorts: the Mayo Clinic model, the U.S. Department of Veteran's Affairs model, the Brock University model, and the Peking University model. • No significant improvement in risk prediction occurred in nodules with repeated imaging sessions, indicating the potential value of risk prediction application is limited to the initial evaluation.

Outcomes of 4-factor Prothrombin Complex Concentrate in Patients With Liver Disease and Nonvitamin K Antagonist-Related Coagulopathy: A Retrospective Study.

The administration of 4-factor prothrombin complex concentrate (4F-PCC) has expanded beyond its Food and Drug Administration (FDA)-approved indication for the emergent reversal of vitamin K antagonists (VKAs). Therefore, this study aimed to evaluate the risks and benefits associated with the expanded use of 4F-PCC. We conducted a single-center retrospective review of 4F-PCC administrations at our university hospital. Of the 159 patients who received 4F-PCC, 76% (n = 121) and 24% (n = 38) received it for the FDA-approved indication in the vitamin K-related coagulopathy (VKA) group and for expanded use in the nonvitamin K-related coagulopathy (nVKA) group, respectively. The expanded use of 4F-PCC was associated with a less robust reduction in the international normalized ratio (INR) (INR of -0.7 ± 1.3 vs INR of -1.6 ± 1.8, P = .002), and fewer patients in the nVKA group achieved a postadministration INR of less than1.5 (11% vs 79%, P = .001) than those in the VKA group. Furthermore, the 30-day mortality rate was significantly higher in the nVKA cohort than in the VKA cohort (42% vs 20%, P = .04). Notably, based on our data, underlying differences in the patient's comorbidities, particularly advanced liver disease, may have contributed to the observed outcome variations, including mortality rate. Therefore, factors, including comorbidities and the underlying etiology of coagulopathy, should be considered when deciding on the expanded use of 4F-PCC. Further research is needed to better understand the potential risks and benefits of 4F-PCC in expanded use scenarios, and the clinical decision to use 4F-PCC outside its FDA-approved indication should be made carefully, considering this information.

Computed Tomography Features of Lung Structure Have Utility for Differentiating Malignant and Benign Pulmonary Nodules.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is a known comorbidity for lung cancer independent of smoking history. Quantitative computed tomography (qCT) imaging features related to COPD have shown promise in the assessment of lung cancer risk. We hypothesize that qCT features from the lung, lobe, and airway tree related to the location of the pulmonary nodule can be used to provide informative malignancy risk assessment. METHODS: A total of 183 qCT features were extracted from 278 individuals with a solitary pulmonary nodule of known diagnosis (71 malignant, 207 benign). These included histogram and airway characteristics of the lungs, lobe, and segmental paths. Performances of the least absolute shrinkage and selection operator (LASSO) regression analysis and an ensemble of neural networks (ENN) were compared for feature set selection and classification on a testing cohort of 49 additional individuals (15 malignant, 34 benign). RESULTS: The LASSO and ENN methods produced different feature sets for classification with LASSO selecting fewer qCT features (7) than the ENN (17). The LASSO model with the highest performing training area under the curve (AUC) (0.80) incorporated automatically extracted features and reader-measured nodule diameter with a testing AUC of 0.62. The ENN model with the highest performing AUC (0.77) also incorporated qCT and reader diameter but maintained higher testing performance AUC (0.79). CONCLUSIONS: Automatically extracted qCT imaging features of the lung can be informative of the differentiation between individuals with malignant pulmonary nodules and those with benign pulmonary nodules, without requiring nodule segmentation and analysis.

Longitudinal phenotype development in a minipig model of neurofibromatosis type 1.

Neurofibromatosis type 1 (NF1) is a rare, autosomal dominant disease with variable clinical presentations. Large animal models are useful to help dissect molecular mechanisms, determine relevant biomarkers, and develop effective therapeutics. Here, we studied a NF1 minipig model (NF1+/ex42del) for the first 12 months of life to evaluate phenotype development, track disease progression, and provide a comparison to human subjects. Through systematic evaluation, we have shown that compared to littermate controls, the NF1 model develops phenotypic characteristics of human NF1: [1] café-au-lait macules, [2] axillary/inguinal freckling, [3] shortened stature, [4] tibial bone curvature, and [5] neurofibroma. At 4 months, full body computed tomography imaging detected significantly smaller long bones in NF1+/ex42del minipigs compared to controls, indicative of shorter stature. We found quantitative evidence of tibial bowing in a subpopulation of NF1 minipigs. By 8 months, an NF1+/ex42del boar developed a large diffuse shoulder neurofibroma, visualized on magnetic resonance imaging, which subsequently grew in size and depth as the animal aged up to 20 months. The NF1+/ex42del minipig model progressively demonstrates signature attributes that parallel clinical manifestations seen in humans and provides a viable tool for future translational NF1 research.

Machine learning approach for distinguishing malignant and benign lung nodules utilizing standardized perinodular parenchymal features from CT.

PURPOSE: Computed tomography (CT) is an effective method for detecting and characterizing lung nodules in vivo. With the growing use of chest CT, the detection frequency of lung nodules is increasing. Noninvasive methods to distinguish malignant from benign nodules have the potential to decrease the clinical burden, risk, and cost involved in follow-up procedures on the large number of false-positive lesions detected. This study examined the benefit of including perinodular parenchymal features in machine learning (ML) tools for pulmonary nodule assessment. METHODS: Lung nodule cases with pathology confirmed diagnosis (74 malignant, 289 benign) were used to extract quantitative imaging characteristics from computed tomography scans of the nodule and perinodular parenchyma tissue. A ML tool development pipeline was employed using k-medoids clustering and information theory to determine efficient predictor sets for different amounts of parenchyma inclusion and build an artificial neural network classifier. The resulting ML tool was validated using an independent cohort (50 malignant, 50 benign). RESULTS: The inclusion of parenchymal imaging features improved the performance of the ML tool over exclusively nodular features (P < 0.01). The best performing ML tool included features derived from nodule diameter-based surrounding parenchyma tissue quartile bands. We demonstrate similar high-performance values on the independent validation cohort (AUC-ROC = 0.965). A comparison using the independent validation cohort with the Fleischner pulmonary nodule follow-up guidelines demonstrated a theoretical reduction in recommended follow-up imaging and procedures. CONCLUSIONS: Radiomic features extracted from the parenchyma surrounding lung nodules contain valid signals with spatial relevance for the task of lung cancer risk classification. Through standardization of feature extraction regions from the parenchyma, ML tool validation performance of 100% sensitivity and 96% specificity was achieved.