Automated Electronic Health Record-Based Tool for Identification of Patients With Metastatic Disease to Facilitate Clinical Trial Patient Ascertainment.

PURPOSE: To facilitate identification of clinical trial participation candidates, we developed a machine learning tool that automates the determination of a patient's metastatic status, on the basis of unstructured electronic health record (EHR) data. METHODS: This tool scans EHR documents, extracting text snippet features surrounding key words (such as metastatic, progression, and local). A regularized logistic regression model was trained and used to classify patients across five metastatic categories: highly likely and likely positive, highly likely and likely negative, and unknown. Using a real-world oncology database of patients with solid tumors with manually abstracted information as reference, we calculated sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). We validated the performance in a real-world data set, evaluating accuracy gains upon additional user review of tool's outputs after integration into clinic workflows. RESULTS: In the training data set (N = 66,532), the model sensitivity and specificity (% [95% CI]) were 82.4 [81.9 to 83.0] and 95.5 [95.3 to 96.7], respectively; the PPV was 89.3 [88.8 to 90.0], and the NPV was 94.0 [93.8 to 94.2]. In the validation sample (n = 200 from five distinct care sites), after user review of model outputs, values increased to 97.1 [85.1 to 99.9] for sensitivity, 98.2 [94.8 to 99.6] for specificity, 91.9 [78.1 to 98.3] for PPV, and 99.4 [96.6 to 100.0] for NPV. The model assigned 163 of 200 patients to the highly likely categories. The error prevalence was 4% before and 2% after user review. CONCLUSION: This tool infers metastatic status from unstructured EHR data with high accuracy and high confidence in more than 75% of cases, without requiring additional manual review. By enabling efficient characterization of metastatic status, this tool could mitigate a key barrier for patient ascertainment and clinical trial participation in community clinics.

Patient-Defined Treatment Success: Perspectives of Patients With Advanced-Stage Lung Cancer.

PURPOSE: In the United States, lung cancer accounts for 14% of cancer diagnoses and 28% of cancer deaths annually. Because no cure exists for advanced lung cancer, the primary treatment goal is to prolong survival. OBJECTIVES: The study aim was to determine whether individual preferences, characteristics, and treatment experiences affect the meaning of treatment success. MATERIALS AND METHODS: A quantitative study using an observational, longitudinal cohort of patients with advanced stage non-small-cell lung cancer was conducted. Data sources included medical records and patient interviews. Data were analyzed using χ2, Fisher's exact, and McNemar's tests, as well as logistic regressions. RESULTS: At the first interview of 235 individuals, 12% considered survival alone as their definition of treatment success; others defined treatment success as survival plus other aspects, such as quality of life and reaching an important personal goal. As they moved through chemotherapy, 47% of the patients changed their definition of treatment success. Bivariate analysis showed that patients with lower incomes tended to be more likely to change their definition of treatment success compared with their counterparts with higher income (P = .0245). CONCLUSION: By taking chemotherapy, patients expect to increase their odds of survival and want to maintain the quality of life and functionality. A patient's definition of treatment success is often changing as treatment continues, making it appropriate to ensure patient-provider communication throughout their clinical care. The study results are limited to patients with advanced non-small-cell lung cancer and drawn from a predominantly white patient population, mainly from the US Midwest.

Bortezomib in combination with celecoxib in patients with advanced solid tumors: a phase I trial.

BACKGROUND: COX-2 inhibitors, such as celecoxib, and ubiquitin-proteasome pathway inhibitors, such as bortezomib, can down-regulate NF-kappaB, a transcription factor implicated in tumor growth. The objective of this study was to determine the maximum tolerated dose and dose-limiting toxicities of bortezomib in combination with celecoxib in patients with advanced solid tumors. METHODS: Patients received escalating doses of bortezomib either on a weekly schedule (days 1, 8, 15, 22, and 29 repeated every 42 days) or on a twice-weekly administration schedule (days 1, 4, 8, and 11 repeated every 21 days), in combination with escalating doses of celecoxib twice daily throughout the study period from 200 mg to 400 mg twice daily. RESULTS: No dose-limiting toxicity was observed during the study period. Two patients had stable disease lasting for four and five months each, and sixteen patients developed progressive disease. CONCLUSION: The combination of bortezomib and celecoxib was well tolerated, without dose limiting toxicities observed throughout the dosing ranges tested, and will be studied further at the highest dose levels investigated. TRIAL REGISTRATION NUMBER: NCT00290680.