Background
Computed tomography (CT) scanning has emerged as an effective means of early detection for lung cancer. Despite marked improvement over earlier methodologies, the low level of specificity demonstrated by CT scanning has limited its clinical implementation as a screening tool. A minimally-invasive biomarker-based test that could further characterize CT-positive patients based on risk of malignancy would greatly enhance its clinical efficacy.
Methods
We performed an analysis of 81 serum proteins in 92 patients diagnosed with lung cancer and 172 CT-screened control individuals. We utilize a series of bioinformatics algorithms including Metropolis-Monte Carlo, artificial neural networks, Naïve Bayes, and additive logistic regression to identify multimarker panels capable of discriminating cases from controls with high levels of sensitivity and specificity in distinct training and independent validation sets.
Results
A three-biomarker panel comprised of MIF, prolactin, and thrombospondin identified using the Metropolis-Monte Carlo algorithm provided the best classification with a %Sensitivity/Specificity/Accuracy of 74/90/86 in the training set and 70/93/82 in the validation set. This panel was effective in the classification of control individuals demonstrating suspicious pulmonary nodules and stage I lung cancer patients.
Conclusions
The selected serum biomarker panel demonstrated a high diagnostic utility in the current study and performance characteristics which compare favorably with previous reports. Further advancements may lead to the development of a diagnostic tool useful as an adjunct to CT-scanning.
The development of accurate clinical biomarkers has been challenging in part due to the diversity between patients and diseases. One approach to account for the diversity is to use multiple markers to classify patients, based on the concept that each individual marker contributes information from its respective subclass of patients. Here we present a new strategy for developing biomarker panels that accounts for completely distinct patient subclasses. Marker State Space (MSS) defines “marker states” based on all possible patterns of high and low values among a panel of markers. Each marker state is defined as either a case state or a control state, and a sample is classified as case or control based on the state it occupies. MSS was used to define multi-marker panels that were robust in cross validation and training-set/test-set analyses and that yielded similar classification accuracy to several other classification algorithms. A three-marker panel for discriminating pancreatic cancer patients from control subjects revealed subclasses of patients based on distinct marker states. MSS provides a straightforward approach for modeling highly divergent subclasses of patients, which may be adaptable for diverse applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.