Introduction: There is a need for earlier bladder cancer screening to reduce lifetime costs and improve patient outcomes. Urinary protein biomarkers have shown some promise, but reported sensitivities appear compromised by low and/or variable biomarker concentrations. In this study, we investigated the potential of using extracellular vesicles (EV) circulating in the blood to detect stage I and II bladder cancer. Using an alternating current electrokinetic (ACE) platform to purify EVs from plasma, we show how a multi-marker EV protein-based methodology can be used to discriminate bladder cancer cases from controls in stage I and II cases.
Methods: Plasma samples were obtained from a biorepository. We used an ACE microelectrode array to isolate plasma EVs of stage I and II bladder cancer cases (N=58) or controls (N=387). EV proteins were quantified using multiplex protein immunoassays for 54 cancer-related proteins. EV protein expression patterns were analyzed using a boosted decision tree-based binary classification algorithm. To identify biomarker subsets that optimized sensitivity of the model, the permutation importance at sensitivity >99% was calculated for each feature. To evaluate biomarker and algorithm performance, a round of 10 repetitions of 5-fold cross validation was done using both the optimized hyper-parameters and the features selected via the permutation importance.
Results: We found that relative concentrations of a set of protein biomarkers carried by circulating plasma EVs was sufficient to discriminate bladder cancer cases from controls, with enough sensitivity to detect stage I and II cancers. The EV protein-based classifier had an overall area under curve (AUC) of 0.964 (95% CI: 0.947 – 0.981) with a sensitivity of 56.9% (95% CI: 44.1% – 68.8%) at 99.2% specificity (95% CI: 97.8% - 99.7%). At a lower 95.6% specificity (95% CI: 93.1% - 97.2%) the sensitivity was 72.4% (95% CI: 59.8% - 82.3%).
Conclusions: Testing of EV-associated plasma proteins may enable early-stage I and II bladder cancer detection where treatment is simpler and does not require bladder resection. The classifier’s performance in this pilot, case-control study showed encouraging results for the initial 54 biomarkers studied. Since we have observed much higher specificities for other early-stage cancer types, the performance for bladder cancer will likely be improved by inclusion of additional biomarker proteins. Future efforts will include examining additional cancer types and evaluating classifier performance using samples from donors with related benign conditions with the aim of a pan-cancer early detection assay.