RESUMO
Background: The B-type rafkinase (BRAF) V600E gene mutation plays an important role in the pathogenesis, diagnosis, and prognosis of thyroid carcinoma. This study was conducted to investigate the rate of the BRAF V600E mutation, the relationships between the BRAF V600E gene mutation and some immunohistochemical markers, and recurrence rate in patients with differentiated thyroid cancer. Method: The study was conducted by a descriptive and longitudinal follow-up method on 102 thyroid carcinoma patients at 103 Military Hospital, Hanoi, Vietnam. All patients were identified with the BRAF V600E gene mutation by real-time polymerase chain reaction. Results: The rate of BRAF V600E gene mutation in patients with thyroid cancer was 60.8%. Patients with BRAF V600E gene mutation had a significantly higher rate of positive cyclooxygenase 2 (COX-2) and Ki67 markers than those without the mutation (COX-2: odds ratio [OR] = 2.93; 95% confidence interval [CI] = 1.27-6.74, P = .011; Ki67: OR = 3.41; 95% CI = 1.31-8.88, P = .01). A statistically significant relationship was identified between the rate of BRAF V600E mutation and the rate of positive Hector Battifora mesothelial 1 (HBME-1) (B = -1.040; P = .037) and COX-2 (B = -1.123; P = .023) markers. The recurrence rate in patients with BRAF V600E gene mutation was significantly higher than that in those without the mutation (P = .007). The mean of the recurrence time of patients with BRAF V600E mutation was significantly lower than that in those without the mutation (P = .011). Conclusions: A high prevalence of BRAF V600E gene mutation was found in thyroid carcinoma patients. The rates of positive HBME-1, COX-2, and Ki67 markers were significantly correlated to BRAF V600E gene mutation. Patients with BRAF V600E gene mutation showed a significantly higher relapse rate and earlier relapse time than those without the mutation.
RESUMO
Introduction: Artificial Intelligence (AI) and machine learning (ML) are used extensively in HICs to detect and control antibiotic resistance (AMR) in laboratories and clinical institutions. ML is designed to predict outcome variables using an algorithm to enable "machines" to learn the "rules" from the data. ML is increasingly being applied in intensive care units to identify AMR and to assist empiric antibiotic therapy. This study aimed to evaluate the performance of ML models for predicting AMR bacteria and resistance to antibiotics in two Vietnamese hospitals. Patients and Methods: A cross-sectional study combined with retrospective was conducted from 1st January 2020 to 30th June 2022. Five models were developed to predict antibiotic resistance of bacterial infections of ICU patients. Two datasets were prepared to predict AMR bacteria and antibiotics with ML models. The performance of the prediction models was evaluated by various indicators (sensitivity, specificity, precision, accuracy, F1-score, PRC, AuROC, and NormMCC) to determine the optimal time point for data selection. Python version 3.8 was used for statistical analyses. Results: The accuracy, F1-score, AuROC, and normMMC of LightGBM, XGBoost, and Random Forest models were higher than those of other models in both datasets. In both datasets 1 and 2, accuracy, F1-score, AuROC and normMCC of the XGBoost model were the highest among five models (from 0.890 to 1.000). Only Random Forest models had specificity scores higher than 0.850. High scores of sensitivity, accuracy, precision, F1-score, and normMCC indicated that the models were making accurate predictions for datasets 1 and 2. Conclusion: XGBoost, LightGBM, and Random Forest were the best-performed machine learning models to predict antibiotic resistance of bacterial infections of ICUs patients using the patients' EMRs.
