Risk prediction model for brain metastasis risk among patients diagnosed with primary gastrointestinal cancers.

Clinicopathological factors associated with brain metastases development among breast cancer patients receiving neoadjuvant chemotherapy

Forecasting the risk of early death among patients suffering from lung cancer with brain metastasis after radiotherapy using interpretable machine learning: a study based on the SEER database

Background Lung cancer with brain metastasis (LCBM) significantly shortens patient survival. Accurately predicting individual prognosis remains challenging. This study aimed to identify key prognostic factors in LCBM patients after radiotherapy for the development of an interpretable machine learning (ML) model to support clinical decision-making and precision medicine. Methods Based on clinicopathological data from the U.S. Surveillance, Epidemiology, and End Results (SEER) database, patients were divided into training (70%) and validation (30%) cohorts. Thirteen variables associated with early death were screened by least absolute shrinkage and selection operator (LASSO) regression for model construction. Seven ML-based models were compared using area under the curve (AUC) values, calibration and decision curves, specificity, precision, and F1-score. SHapley Additive exPlanations (SHAP) analysis was applied to interpret the optimal model. Results The Light Gradient Boosting Machine (LightGBM) model achieved satisfactory performance in the validation set, with an AUC of 0.776, and showed good accuracy and clinical utility. SHAP analysis revealed that chemotherapy was associated with a lower risk of early death, while younger age and lower T stage were also associated with better outcomes. Conversely, bone, liver, and lung metastases were associated with a higher risk of early death. Conclusions This ML-based prediction model may help quantify the risk of early death in LCBM patients after radiotherapy, providing references for clinicians to improve prognostic evaluation and optimize treatment strategies.

RMTC-07 OBESITY AND RISK OF BRAIN METASTASES AMONG PATIENTS DIAGNOSED WITH EARLY-STAGE BREAST CANCER: A POPULATION-BASED COHORT STUDY

Abstract Background Obesity is characterized by chronic low-grade systemic inflammation and altered metabolic signaling, which may disrupt periphery-to-brain communication and compromise central nervous system interfaces. These obesity-associated inflammatory perturbations may influence tumor seeding and the phenotypic presentation of brain metastases (BrM). Methods We conducted a retrospective, population-based cohort study using linked administrative health data from ICES (Ontario, Canada). Women aged ≥18 years diagnosed with stage I–III breast cancer (2009–2021) were followed through 2023. Baseline obesity was defined using validated administrative codes. The primary outcome was incident BrM. Time-to-event analyses were performed with death as a competing risk. Cumulative incidence functions were compared using Gray’s test and Fine–Gray sub-distribution hazard models were used for survival analyses. Results Among 92,973 patients, 3,195 (3.4%) had obesity, defined using validated administrative coding. Median age was 61 years (IQR 51–71), and stage distribution was 53.5%, 33.7%, and 12.8% for stage I, II, and III disease, respectively. With a median follow-up of 6.9 years (IQR 4.1–10.3), 2,037 BrM events and 14,937 competing deaths occurred. BrM incidence rates were similar between obese and non-obese groups (2.7 vs 3.0 per 1,000 person-years; p = 0.31). Neither the cumulative incidence of BrM (Gray’s p = 0.32) nor the cumulative incidence of death (Gray’s p = 0.99) differed significantly between groups. In a subset of patients with BMI data (∼40%), a statistically significant association between increasing BMI and shorter time-to-development of BrM was observed when BMI was modeled as a continuous variable (HR 1.044 per 10-unit increase, 95% CI 1.027–1.061). Conclusions In this large population-based cohort, baseline obesity was not associated with risk of BrM. However, BMI when measured as a continuous variable, was associated with a significantly shorter time-to-development of BrM, a finding that warrants further study.

The Prevalence, Risk Factors for Bone Metastases Development and Prognosis in Gastric Cancer Patients: A Population-based Study.

OBJECTIVE The objective of the present study was to explore the prevalence, risk and prognostic factors for bone metastases (BM) developement in patients with initial gastric cancer (GC). METHODS A total of 30,817 patients with GC in the Surveillance, Epidemiology and End Results (SEER) database, diagnosed from 2010 to 2016, were used to investigate the incidence and associated risk factors for BM developments using multivariate logistic regression. Among those, 1397 and 1121 BM patients were selected to identify independent prognostic factors for BM overall survival (OS) and cancer-specific survival (CSS) using multivariate Cox regression respectively. RESULT A total of 1397 (4.53%) GC patients were diagnosed with BM at initial diagnosis. Younger age (<60 years), white race, cardia cancer, signet ring cell, higher grade, tumor size between 2.1 and 4.0 cm, the presence of regional lymph nodes (RLN) metastases, brain metastases, liver metastases, and lung metastases were positively associated with BM development. Conversely, a lower T stage was negatively associated with BM development compared to the T4 stage. The median survival time for GC patients with BM decreased dramatically to 5 months. The presence of RLN metastases was an independent predictor of worse overall survival and cancer-specific survival. Conversely, T2 stage and chemotherapy were associated with better overall survival and cancer-specific survival. Additionally, patients with cardia cancer had favorable cancer-specific survival. CONCLUSION The prognosis of gastric cancer patients with BM was dismal. Our findings of several risk factors for BM development and prognostic factors for BM patients could be useful for clinical surveillance and individualized treatment.

Analysis of prognostic factors in patients with locally advanced cervical squamous cell carcinoma and development of a nomogram prediction model

To develop and validate a predictive model integrating patient demographics and clinical data for estimating 3-, 4-, and 5-year overall survival in patients with locally advanced cervical squamous cell carcinoma (LACSC). Clinical data from 670 LACSC patients at Shanxi Cancer Hospital were collected and then randomly assigned to a training cohort and an internal validation cohort at a 6:4 ratio by stratified sampling. Independent prognostic factors were identified using LASSO regression and multivariate Cox regression analysis, with which a predictive model was constructed. Model performance was assessed using the concordance index (C-index), receiver operating characteristic (ROC) curves, and calibration curves. Clinical utility was evaluated via decision curve analysis (DCA). A robust prognostic model was developed and visualized as a nomogram comprising six variables: NEUT, MONO, CA125, SII, lymph node metastasis status, and treatment modality. Patients were stratified into high- and low-risk groups based on the median risk score in the training cohort. The high-risk group exhibited significantly poorer overall survival (OS) in both cohorts ( P  < 0.05). A clinical predictive model was established to estimate 3-, 4-, and 5-year survival rates for LACSC patients.

A predictive model of survival in early-stage medullary breast carcinoma: a population-based study.

A clinical model incorporating age (≥65 years), T stage (T3/T4), N stage (N2/N3), and chemotherapy (no) was developed to predict inferior OS in early-stage MedBC.