RESUMO
Introduction: Artificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods. Methods: We prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions. Results: Of 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models' prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR. Conclusions: In this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.
RESUMO
The objectives of this work were to evaluate ß-lactamase-mediated ß-lactam resistance in Campylobacter coli and Campylobacter jejuni isolates obtained from broiler chickens, expression of the blaOXA-61 gene in relation to ß-lactamase production, and the possible association between blaOXA-61 gene expression and the action of inhibitors when combined with ß-lactams. All strains were tested by disk diffusion and nitrocefin methods to assess antibiotic susceptibility and ß-lactamase production, respectively. PCR and qPCR amplification were performed to evaluate qualitative and quantitative blaOXA-61 expression. Campylobacter spp. showed a high level of resistance to the most of antimicrobials tested. C. coli strains were ampicillin resistant and blaOXA-61 positive, and 59 out of 60 isolates were positive in the nitrocefin test. Twenty C. jejuni isolates were positive for blaOXA-61 and the nitrocefin test, although two isolates were ampicillin sensitive. Amoxicillin/clavulanic acid and ticarcillin/clavulanic acid do not seem to be active against C. coli, as 73.3 %, and 88.3 % of isolates were resistant to amoxicillin/clavulanic acid and ticarcillin/clavulanic acid, respectively. C. jejuni was not susceptible to amoxicillin/clavulanic acid, with 90 % of the strains showing resistance, whereas ticarcillin associated with clavulanic acid was significantly more efficient than ticarcillin alone (P < 0.01), with 90 % of the strains found to be susceptible. An association between blaOXA-61 expression and amoxicillin/clavulanic acid and ticarcillin/clavulanic acid resistance (P = 0.0001) was seen in C. coli, as well as in C. jejuni for ampicillin/sulbactam (P = 0.0001). Our results suggest that the clavulanic acid only shows an inhibitory effect on C. jejuni when combined with ticarcillin and that the inhibitors action is lower if the blaOXA-61 gene is highly expressed.