RESUMEN
BACKGROUND: Existing models do poorly when it comes to quantifying the risk of Lymph node metastases (LNM). This study aimed to develop a machine learning model for LNM in patients with T1 esophageal squamous cell carcinoma (ESCC). METHODS AND RESULTS: The study is multicenter, and population based. Elastic net regression (ELR), random forest (RF), extreme gradient boosting (XGB), and a combined (ensemble) model of these was generated. The contribution to the model of each factor was calculated. The models all exhibited potent discriminating power. The Elastic net regression performed best with externally validated AUC of 0.803, whereas the NCCN guidelines identified patients with LNM with an AUC of 0.576 and logistic model with an AUC of 0. 670. The most important features were lymphatic and vascular invasion and depth of tumor invasion. CONCLUSIONS: Models created utilizing machine learning approaches had excellent performance estimating the likelihood of LNM in T1 ESCC.
RESUMEN
Precision medicine based on personalized genomics provides promising strategies to enhance the efficacy of molecular-targeted therapies. However, the clinical effectiveness of drugs has been severely limited due to genetic variations that lead to drug resistance. Predicting the impact of missense mutations on clinical drug response is an essential way to reduce the cost of clinical trials and understand genetic diseases. Here, we present Emden, a novel method integrating graph and transformer representations that predicts the effect of missense mutations on drug response through binary classification with interpretability. Emden utilized protein sequences-based features and drug structures as inputs for rapid prediction, employing competitive representation learning and demonstrating strong generalization capabilities and robustness. Our study showed promising potential for clinical drug guidance and deep insight into computer-assisted precision medicine. Emden is freely available as a web server at https://www.psymukb.net/Emden.
Asunto(s)
Genómica , Mutación Missense , Mutación , Aprendizaje , Terapia Molecular DirigidaRESUMEN
PURPOSE: Our study aimed to explore temporal trends and survival benefit of contralateral prophylactic mastectomy (CPM) in male breast cancer (MBC). METHODS: Men with stage I-III unilateral breast cancer between 1998 and 2016 were identified from the surveillance, epidemiology, and end results (SEER). We compared CPM rate over the study period using the Cochrane-Armitage test for trend. Logistic regression model was used to test for factors predicting CPM. Survival analysis was conducted in patients who underwent CPM or unilateral mastectomy (UM) with a first diagnosis of unilateral breast cancer. Kaplan-Meier curve and univariate and multivariable Cox proportional hazards regression analyses were performed to compare overall survival (OS) and breast cancer-specific survival (BCSS) between CPM and UM groups. Propensity score matching was adopted to balance baseline characteristics. RESULTS: 5118 MBC cases were included in the present study, with 4.1% (n = 209) patients underwent CPM. The proportion of men undergoing CPM increased from 1.7 in 1998 to 6.3% in 2016 (P < 0.0001). Young age, recent years of diagnosis, higher tumor grade and lower T stage were significantly associated with CPM. A cohort of 3566 patients were enrolled in survival analysis with a median follow-up of 65 months. CPM was associated with better OS (HR 0.58, 95% CI 0.37-0.89, P = 0.022) rather than BCSS (HR 0.57, 95% CI 0.29-1.11, P = 0.153) compared with UM. In propensity score-matched model, CPM was not an independent prognostic factor for OS (HR 0.83, 95% CI 0.46-1.52, P = 0.553) and BCSS (HR 0.98, 95% CI 0.39-2.47, P = 0.970). CONCLUSION: Our study revealed a dramatic increase in CPM utilization among MBC, especially in young patients. However, CPM provides no survival benefit for MBC compared with UM, indicating the decision of CPM should be fully discussed.