Complete Blood Count as a Tool for Screening Cancer, Indices, Scores and Predictive Models

Le résumé fourni par la source

Cancer-related systemic inflammation is a hallmark of cancer. Investigation of complete blood count may provide sufficient objective laboratory data to measure the intensity of cancer-associated inflammation. Routinely used hematological and biochemical laboratory parameters have the potential to evaluate the immune–inflammatory response to developing malignancy, such as hemoglobin; red blood cell distribution width; populations of leukocytes (neutrophils, lymphocytes, monocytes); platelet count; and serum concentrations of albumin, fibrinogen, and C-reactive protein. The imbalance of the immune system during cancer development can be expressed by the ratio(s) between different laboratory parameters, for example, neutrophil-to-lymphocyte ratio, monocyte-to-lymphocyte ratio, C-reactive protein-to-albumin ratio, or hemoglobin-to-red blood cell distribution width ratio. We explore inflammation-based scores or ratios to detect early stages of cancer, progression of malignancy, and prediction of prognosis in patients with solid cancer. We have analyzed the effectiveness of different ratios and scores toward the creation of predictive models using modern statistical methods (LCA, LASSO) and artificial intelligence (ML and deep learning). Advances in inflammation-based models may be a useful diagnostic and prognostic tool in primary care, general medicine, and secondary care, including oncology and surgery.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.