RESUMO
Optimizing early breast cancer (BC) detection requires effective risk assessment tools. This retrospective study from Brazil showcases the efficacy of machine learning in discerning complex patterns within routine blood tests, presenting a globally accessible and cost-effective approach for risk evaluation. We analyzed complete blood count (CBC) tests from 396,848 women aged 40-70, who underwent breast imaging or biopsies within six months after their CBC test. Of these, 2861 (0.72%) were identified as cases: 1882 with BC confirmed by anatomopathological tests, and 979 with highly suspicious imaging (BI-RADS 5). The remaining 393,987 participants (99.28%), with BI-RADS 1 or 2 results, were classified as controls. The database was divided into modeling (including training and validation) and testing sets based on diagnostic certainty. The testing set comprised cases confirmed by anatomopathology and controls cancer-free for 4.5-6.5 years post-CBC. Our ridge regression model, incorporating neutrophil-lymphocyte ratio, red blood cells, and age, achieved an AUC of 0.64 (95% CI 0.64-0.65). We also demonstrate that these results are slightly better than those from a boosting machine learning model, LightGBM, plus having the benefit of being fully interpretable. Using the probabilistic output from this model, we divided the study population into four risk groups: high, moderate, average, and low risk, which obtained relative ratios of BC of 1.99, 1.32, 1.02, and 0.42, respectively. The aim of this stratification was to streamline prioritization, potentially improving the early detection of breast cancer, particularly in resource-limited environments. As a risk stratification tool, this model offers the potential for personalized breast cancer screening by prioritizing women based on their individual risk, thereby indicating a shift from a broad population strategy.
Assuntos
Neoplasias da Mama , Aprendizado de Máquina , Humanos , Neoplasias da Mama/sangue , Neoplasias da Mama/diagnóstico , Neoplasias da Mama/patologia , Feminino , Pessoa de Meia-Idade , Estudos Retrospectivos , Adulto , Idoso , Contagem de Células Sanguíneas/métodos , Medição de Risco/métodos , Detecção Precoce de Câncer/métodos , Brasil/epidemiologiaRESUMO
Atherosclerotic Cardiovascular Disease (ASCVD) represents the leading cause of death worldwide, and individual screening should be based on behavioral, metabolic, and genetic profile derived from data collected in large population-based studies. Due to the polygenic nature of ASCVD, we aimed to assess the association of genomics with ASCVD risk and its impact on the occurrence of acute myocardial infarction, stroke, or peripheral artery thrombotic-ischemic events at population level. CardioVascular Genes (CV-GENES) is a nationwide, multicenter, 1:1 case-control study of 3,734 patients in Brazil. Inclusion criterion for cases is the first occurrence of one of the ASCVD events. Individuals without known ASCVD will be eligible as controls. A core lab will perform the genetic analyses through low-pass whole genome sequencing and whole exome sequencing. In order to estimate the independent association between genetic polymorphisms and ASCVD, a polygenic risk score (PRS) will be built through a hybrid approach including effect size of each Single Nucleotide Polymorphism (SNP), number of effect alleles observed, sample ploidy, total number of SNPs included in the PRS, and number of non-missing SNPs in the sample. In addition, the presence of pathogenic or likely pathogenic variants will be screened in 8 genes (ABCG5, ABCG8, APOB, APOE, LDLR, LDLRAP1, LIPA, PCSK9) associated with atherosclerosis. Multiple logistic regression will be applied to estimate adjusted odds ratios (OR) and 95% confidence intervals (CI), and population attributable risks will be calculated. Clinical trial registration: This study is registered in clinicaltrials.gov (NCT05515653).