Prediction model of ocular metastasis from primary liver cancer: Machine learning-based development and interpretation study.

BACKGROUND: Ocular metastasis (OM) is a rare metastatic site of primary liver cancer (PLC). The purpose of this study was to establish a clinical predictive model of OM in PLC patients based on machine learning (ML). METHODS: We retrospectively collected the clinical data of 1540 PLC patients and divided it into a training set and an internal test set in a 7:3 proportion. PLC patients were divided into OM and non-ocular metastasis (NOM) groups, and univariate logistic regression analysis was performed between the two groups. The variables with univariate logistic analysis p < 0.05 were selected for the ML model. We constructed six ML models, which were internally verified by 10-fold cross-validation. The prediction performance of each ML model was evaluated by receiver operating characteristic curves (ROCs). We also constructed a web calculator based on the optimal performance ML model to personalize the risk probability for OM. RESULTS: Six variables were selected for the ML model. The extreme gradient boost (XGB) ML model achieved the optimal differential diagnosis ability, with an area under the curve (AUC) = 0.993, accuracy = 0.992, sensitivity = 0.998, and specificity = 0.984. Based on these results, an online web calculator was constructed by using the XGB ML model to help clinicians diagnose and treat the risk probability of OM in PLC patients. Finally, the Shapley additive explanations (SHAP) library was used to obtain the six most important risk factors for OM in PLC patients: CA125, ALP, AFP, TG, CA199, and CEA. CONCLUSION: We used the XGB model to establish a risk prediction model of OM in PLC patients. The predictive model can help identify PLC patients with a high risk of OM, provide early and personalized diagnosis and treatment, reduce the poor prognosis of OM patients, and improve the quality of life of PLC patients.

Primary Treatment for Clinically Early Cervical Cancer with Lymph Node Metastasis: Radical Surgery or Radiation?

OBJECTIVE: To compare survival outcomes between primary radical surgery and primary radiation in early cervical cancer. METHODS: Patient information was extracted from the Surveillance, Epidemiology, and Results database. Patients diagnosed with early cervical cancer of stage T1a, T1b, and T2a (American Joint Committee on Cancer, 7th edition) from 1998 to 2015 were included in this study after propensity score matching. Overall survival (OS) was analyzed using the Kaplan-Meier method. RESULTS: Among the 4964 patients included in the study, 1080 patients were identified as having positive lymph nodes (N1), and 3884 patients were identified as having negative lymph nodes (N0). Patients with primary surgery had significantly longer 5-year OS than those with primary radiotherapy in both the N1 group (P<0.001) and N0 group (P<0.001). In the subgroup analysis, similar results were found in patients with positive lymph nodes of stage T1a (100.0% vs. 61.1%), T1b (84.1% vs. 64.3%), and T2a (74.4% vs. 63.8%). In patients with T1b1 and T2a1, primary surgery resulted in longer OS than primary radiation, but not in patients with T1b2 and T2a2. In multivariate analysis, the primary treatment was identified as an independent prognostic factor in both N1 and N0 patients (HRN1=2.522, 95% CI=1.919-3.054, PN1<0.001; HRN0=1.895, 95% CI=1.689-2.126, PN0<0.001). CONCLUSION: In early cervical cancer stage T1a, T1b1, and T2a1, primary surgery may result in longer OS than primary radiation for patients with and without lymph node metastasis.