It was revealed that separation of LCP with early LC (n=215) from invasive LCP (n=555) significantly depended on: Hb, leucocytes (abs, total), thrombocytes (abs, tot), erythrocytes (abs, tot), segmented neutrophils (%, abs, total), stick neutrophils (%, abs, total), lymphocytes (%), monocytes (abs, tot), ESS, coagulation time, fibrinogen, cell ratio factors (CRF) (ratio between cancer cells- CC and blood cells subpopulations), tumor size, age, tumor growth, T1-4, G1-3, PT N0---N12 (P=0.046-0.000). Neural networks computing, genetic algorithm selection and bootstrap simulation revealed relationships of PT early—invasive cancer and CRF: healthy cells/CC (rank=1), erythrocytes/CC (2), stick neutrophils/CC (3), thrombocytes/CC (4), eosinophils/CC (5), segmented neutrophils/CC (6), lymphocytes/CC (7), monocytes/CC (8), leucocytes/CC (9). Correct classification PT early—invasive cancer was 100% by neural networks computing (area under ROC curve=1.0; error=0.0).
CONCLUSION: Blood cell circuit significantly influenced the phase transition early—invasive lung cancer.