A logistic model for the detection of circulating tumour cells in human metastatic colorectal cancer

Abstract

The accuracy in the diagnosis of metastatic colorectal cancer (mCRC) represents one of the challenges in the clinical management of patients. The detection of circulating tumour cells (CTC) is becoming a promising alternative to current detection techniques, as it focuses on one of the players of the metastatic disease and it should provide with more specific and sensitive detection rates. Here, we describe an improved method of detection of CTC from mCRC patients by combining immune-enrichment, optimal purification of RNA from very low cell numbers, and the selection of accurate PCR probes. As a result, we obtained a logistic model that combines GAPDH and VIL1 normalized to CD45 rendering powerful results in the detection of CTC from mCRC patients (AUROC value 0.8599). We further demonstrated the utility of this model at the clinical setting, as a reliable prognosis tool to determine progression-free survival in mCRC patients. Overall, we developed a strategy that ameliorates the specificity and sensitivity in the detection of CTC, resulting in a robust and promising logistic model for the clinical management of metastatic colorectal cancer patients.

Fig 1

Heatmap representing the sensitivity and specificity of selected probes. Probes were tested into a series of twelve stage IV CRC patients. Only six of the selected twelve probes were able to detect CTC in at least 50% of patients (CD45, VIL1, TBX20, GAPDH, GPA33 and FAM132A). Those six probes were selected for further studies and evaluated in twelve control samples from healthy volunteers for specificity analysis. Strong signals were detected for GAPDH and CD45 as expected, VIL1, GPA33 and FAM132A showed a variable degree of specificity and no signal was detected in controls for TBX20. Colour scale shows higher expression for these probes in patient samples compared with controls.

Fig 2

Accuracy of GAPDH and VIL1 normalized to CD45 in CTC detection. Box plots indicate median values in the group of control compared with the group of metastatic CRC patients for CD45 (A), GAPDH (C), GAPDH normalized to CD45 (D), VIL1 (F) and VIL1 normalized to CD45 (G). Of note, while CD45 showed no differences between both groups, GAPDH and VIL1 demonstrated optimal accuracy in the detection of CTC from metastatic CRC patients when normalized to CD45 as a marker of unspecific non-CTC cells (P < 0.001). This was further demonstrated when evaluated the specificity and sensitivity of these probes with the AUROC values. As expected, CD45 demonstrated no utility to discriminate between both groups of samples (B), while GAPDH (E) and VIL1 (H) normalized to CD45 showed promising AUROC values for the detection of CTC from metastatic CRC patients.

Fig 3

Logistic model for the detection of CTC from metastatic CRC patients. (A) The combination of GAPDH and VIL1 normalized to CD45 by multivariate analysis rendered a logistic model that improved the accuracy of the individual probes as demonstrated by AUROC analysis (0.8599). The robustness of the model was further confirmed through a cross-validation strategy, demonstrating acceptable behaviour when leaving one, five or even ten samples out of the model. (B) Dot-plot representing sample distribution [patients (red dots) and controls (black dots)]. Cut-off values were established in 2 for GAPDH normalized to CD45 and −7.5 for VIL1 normalized to CD45.

Fig 4

Performance of the logistic model in the prognosis of metastatic CRC. Kaplan–Meier analysis demonstrating the accuracy of the logistic model including GAPDH and VIL1 normalized to CD45 at the clinical setting. PFS of metastatic CRC patients with CTC below the cut-off value of 4.5 for GAPDH normalized to CD45 and -2 for VIL1 normalized to CD45, was significantly better (continuous line), compared with metastatic CRC patients with CTC values above the cut-off (dashed line) (P < 0.05).