RESUMO
Analyzing gene expression profiles (GEP) through artificial intelligence provides meaningful insight into cancer disease. This study introduces DeepSHAP Autoencoder Filter for Genes Selection (DSAF-GS), a novel deep learning and explainable artificial intelligence-based approach for feature selection in genomics-scale data. DSAF-GS exploits the autoencoder's reconstruction capabilities without changing the original feature space, enhancing the interpretation of the results. Explainable artificial intelligence is then used to select the informative genes for chronic lymphocytic leukemia prognosis of 217 cases from a GEP database comprising roughly 20,000 genes. The model for prognosis prediction achieved an accuracy of 86.4%, a sensitivity of 85.0%, and a specificity of 87.5%. According to the proposed approach, predictions were strongly influenced by CEACAM19 and PIGP, moderately influenced by MKL1 and GNE, and poorly influenced by other genes. The 10 most influential genes were selected for further analysis. Among them, FADD, FIBP, FIBP, GNE, IGF1R, MKL1, PIGP, and SLC39A6 were identified in the Reactome pathway database as involved in signal transduction, transcription, protein metabolism, immune system, cell cycle, and apoptosis. Moreover, according to the network model of the 3D protein-protein interaction (PPI) explored using the NetworkAnalyst tool, FADD, FIBP, IGF1R, QTRT1, GNE, SLC39A6, and MKL1 appear coupled into a complex network. Finally, all 10 selected genes showed a predictive power on time to first treatment (TTFT) in univariate analyses on a basic prognostic model including IGHV mutational status, del(11q) and del(17p), NOTCH1 mutations, ß2-microglobulin, Rai stage, and B-lymphocytosis known to predict TTFT in CLL. However, only IGF1R [hazard ratio (HR) 1.41, 95% CI 1.08-1.84, P=0.013), COL28A1 (HR 0.32, 95% CI 0.10-0.97, P=0.045), and QTRT1 (HR 7.73, 95% CI 2.48-24.04, P<0.001) genes were significantly associated with TTFT in multivariable analyses when combined with the prognostic factors of the basic model, ultimately increasing the Harrell's c-index and the explained variation to 78.6% (versus 76.5% of the basic prognostic model) and 52.6% (versus 42.2% of the basic prognostic model), respectively. Also, the goodness of model fit was enhanced (χ2 = 20.1, P=0.002), indicating its improved performance above the basic prognostic model. In conclusion, DSAF-GS identified a group of significant genes for CLL prognosis, suggesting future directions for bio-molecular research.
RESUMO
Adherence to Mediterranean diet (MD) and physical activity (PA) in adolescence represent powerful indicators of healthy lifestyles in adulthood. The aim of this longitudinal study was to investigate the impact of nutrition education program (NEP) on the adherence to the MD and on the inflammatory status in healthy adolescents, categorized into three groups according to their level of PA (inactivity, moderate intensity, and vigorous intensity). As a part of the DIMENU (Dieta Mediterranea & Nuoto) study, 85 adolescents (aged 14-17 years) participated in the nutrition education sessions provided by a team of nutritionists and endocrinologists at T0. All participants underwent anthropometric measurements, bio-impedentiometric analysis (BIA), and measurements of inflammatory biomarkers such as ferritin, erythrocyte sedimentation rate (ESR), and C-reactive protein (CRP) levels. Data were collected at baseline (T0) and 6 months after NEP (T1). To assess the adherence to the MD, we used KIDMED score. In our adolescents, we found an average MD adherence, which was increased at T1 compared with T0 (T0: 6.03 ± 2.33 vs. T1: 6.96 ± 2.03, p = 0.002), with an enhanced percentage of adolescents with optimal (≥8 score) MD adherence over the study period (T0: 24.71% vs. T1: 43.52%, p = 0.001). Interestingly, in linear mixed-effects models, we found that NEP and vigorous-intensity PA levels independently influenced KIDMED score (ß = 0.868, p < 0.0001 and ß = 1.567, p = 0.009, respectively). Using ANOVA, NEP had significant effects on serum ferritin levels (p < 0.001), while either NEP or PA influenced ESR (p = 0.035 and 0.002, respectively). We also observed in linear mixed-effects models that NEP had a negative effect on ferritin and CRP (ß = -14.763, p < 0.001 and ß = -0.714, p = 0.02, respectively). Our results suggest the usefulness to promote healthy lifestyle, including either nutrition education interventions, or PA to improve MD adherence and to impact the inflammatory status in adolescence as a strategy for the prevention of chronic non-communicable diseases over the entire lifespan.
