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.

Identification of Nonaggressive Pulmonary Nodules Using an Optimized Scoring System.

PURPOSE: The purpose of this study was to define the optimal scoring method for identifying benign intrapulmonary lymph nodes. MATERIALS AND METHODS: Subjects for this study were selected from the COPDGene study, a large multicenter longitudinal observational cohort study. A retrospective case-control analysis was performed using identified nodules on a subset of 377 patients who demonstrated 765 pulmonary nodules on their baseline computed tomography (CT) study. Nodule characteristics of 636 benign nodules (which resolved or showed <20% growth rate at 5 y follow-up) were compared with 51 nodules that occurred in the same lobe as a reported malignancy. Two radiologists scored each pulmonary nodule on the basis of intrapulmonary lymph node characteristics. A simple scoring strategy weighing all characteristics equally was compared with an optimized scoring strategy that weighed characteristics on the basis of their relative importance in identifying benign pulmonary nodules. RESULTS: A total of 479 of 636 benign pulmonary nodules had the majority of lymph node characteristics, whereas only 1 subpleural nodule with the majority of lymph node characteristics appeared to be malignant. Only 279 of 479 (58%) of benign pulmonary nodules with the majority of lymph node characteristics were intrafissural or subpleural. The optimized scoring strategy showed improved performance compared with the simple scoring strategy with average area under the curve of 0.80 versus 0.55. Optimized cutoff scores showed negative likelihood values for both readers of <0.2. A simulation showed a potential reduction in CT utilization of up to 36% for Fleischner criteria and up to 5% for LUNG-RADS. CONCLUSIONS: Nodules with the majority of lymph node characteristics, regardless of location, are likely benign, and weighing certain lymph node characteristics greater than others can improve overall performance. Given the potential to reduce CT utilization, lymph node characteristics should be considered when recommending appropriate follow-up.

Interhospital transfer of blunt multiply injured patients to a level 1 trauma center does not adversely affect outcome.

BACKGROUND: Stops at nontrauma centers for severely injured patients are thought to increase deaths and costs, potentially because of unnecessary imaging and indecisive/delayed care of traumatic brain injuries (TBIs). METHODS: We studied 754 consecutive blunt trauma patients with an Injury Severity Score greater than 20 with an emphasis on 212 patients who received care at other sites en route to our level 1 trauma center. RESULTS: Referred patients were older, more often women, and had more severe TBI (all P < .05). After correction for age, sex, and injury pattern, there was no difference in the type of TBI, Glasgow Coma Scale (GCS) upon arrival at the trauma center, or overall mortality between referred and directly admitted patients. GCS at the outside institution did not influence promptness of transfer. CONCLUSIONS: Interhospital transfer does not affect the outcome of blunt trauma patients. However, the unnecessarily prolonged stay of low GCS patients in hospitals lacking neurosurgical care is inappropriate.

Variability in drug formularies and implications in decision support.

Formularies are highly variable, which limits physicians ability to prescribe cost effective medications for their patients. In this study we explore the composition of 3,346 formularies in terms of outpatient prescription coverage, medication class coverage, and cost implications. Our analysis revealed that 42% of formularies are duplicative and that the unique formularies contain variability for medications that contribute little in terms of cost or overall use. These results lead us to believe the number and complexities of formularies can be dramatically reduced leading to more intuitive decision support for physicians when writing prescriptions.

Changes in gene expression during pegylated interferon and ribavirin therapy of chronic hepatitis C virus distinguish responders from nonresponders to antiviral therapy.

Treating chronic hepatitis C virus (HCV) infection using pegylated alpha interferon and ribavirin leads to sustained clearance of virus and clinical improvement in approximately 50% of patients. Response rates are lower among patients with genotype 1 than with genotypes 2 and 3 and among African-American (AA) patients compared to Caucasian (CA) patients. Using DNA microarrays, gene expression was assessed for a group of 33 African-American and 36 Caucasian American patients with chronic HCV genotype 1 infection during the first 28 days of treatment. Results were examined with respect to treatment responses and to race. Patients showed a response to treatment at the gene expression level in RNA isolated from peripheral blood mononuclear cells irrespective of degree of decrease in HCV RNA levels. However, gene expression responses were relatively blunted in patients with poor viral response (<1.5 log(10)-IU/ml decrease at 28 days) compared to those in patients with a marked (>3.5 log(10)-IU/ml decrease) or intermediate (1.5 to 3.5 log(10)-IU/ml decrease) response. The number of genes that were up- or down-regulated by pegylated interferon and ribavirin treatment was fewer in patients with a poor response than in those with an intermediate or marked viral response. However AA patients had a stronger interferon response than CA patients in general. The induced levels of known interferon-stimulated genes such as the 2'5'-oligoadenylate synthetase, MX1, IRF-7, and toll-like receptor TLR-7 genes was lower in poor-response patients than in marked- or intermediate-response patients. Thus, the relative lack of viral response to interferon therapy of hepatitis C virus infection is associated with blunted interferon cell signaling. No specific regulatory gene could be identified as responsible for this global blunting or the racial differences.