Junjie Huang

Machine Learning–Predictive Models for Survival in Uterine Cancer Patients With Type 2 Diabetes: A Territory‐Wide Cohort Study

ABSTRACT Aim This study aimed to develop predictive models and establish a risk scoring system to identify risk factors associated with survival in uterine cancer patients with type 2 diabetes (T2D) and estimate their survival probabilities. Methods Data were collected from the Hong Kong Hospital Authority Data Collaboration Laboratory (HADCL) from 2000 to 2020. Cox proportional hazards regression, survival tree, LASSO Cox regression, boosting, and random survival forest (RSF) were utilized to develop predictive models for survival. Key risk factors were identified through Shapley Additive Explanations analysis, whereas the AutoScore‐Survival package facilitated the development of a risk scoring system. Results This cohort study included 2047 uterine cancer patients with T2D. The average survival time was 100.82 (standard deviation: 72.75) months. The RSF model demonstrated the strongest predictive performance, achieving a time‐dependent area under the curve (AUC) of 0.823 and a C ‐index of 0.90. A risk scoring system was created based on several criteria: age at cancer diagnosis, duration of T2D, creatinine levels, serum potassium level, low‐density lipoprotein cholesterol level (LDL‐C) level, body mass index (BMI), and triglycerides level. This scoring system classified 31.4% of patients as high‐risk, resulting in a 5‐year survival probability of 43.5%, about 1.7 times lower than that of the low‐risk group. Conclusion This study leveraged machine learning to identify key survival predictors and develop a clinically interpretable risk scoring system for uterine cancer patients with T2D. Key predictors, including age at cancer diagnosis, duration of T2D, creatinine levels, serum potassium levels, LDL‐C levels, BMI, and triglycerides levels, effectively stratified survival risk. These findings demonstrate the potential of data‐driven models to enhance individualized prediction and inform targeted clinical management.

Incidence distributions, risk factors and trends of vaginal cancer: A global population‐based study

AbstractObjectiveThis study aimed to investigate the incidence, risk factors and trends for vaginal cancer.DesignRetrospective observational design.SettingData were collected from multiple sources, including the Global Cancer Observatory, Cancer Incidence in Five Continents Plus, Global Burden of Disease, World Bank and the United Nations.PopulationIndividuals diagnosed with vaginal cancer.MethodsThe study collected data on vaginal cancer from the specified sources. The age‐standardised rate (ASR) of vaginal cancer was calculated for different regions and age groups. Multivariable and univariable linear regression analyses were performed to examine the associations between risk factors and the incidence of vaginal cancer. Trend analysis was conducted using joinpoint regression analysis, and the average annual percentage change (AAPC) was calculated to quantify the temporal trend.Main Outcome MeasuresThe main outcome measures of the study were the incidence of vaginal cancer, risk factors associated with the disease and the trend of its incidence over time.ResultsThere were 17 908 newly reported cases of vaginal cancer (ASR = 0.36, 95% CI 0.30–0.44) in 2020, with the highest ASRs reported in South–Central Asia and Southern Africa. Risk factors associated with a higher incidence of vaginal cancer included a higher prevalence of unsafe sex and human immunodeficiency virus (HIV) infection. The temporal trend showed an overall rising incidence globally, with Iceland (AAPC = 29.56, 95% CI 12.12–49.71), Chile (AAPC = 22.83, 95% CI 13.20–33.27), Bahrain (AAPC = 22.05, 95% CI 10.83–34.40) and the UK (AAPC = 1.40, 95% CI 0.41–2.39) demonstrating the most significant rising trends.ConclusionsThe significant regional disparities and risk factors associated with vaginal cancer underscore the necessity for targeted interventions and education, particularly in regions with a lower human development index (HDI) and a higher prevalence of human papillomavirus (HPV) infection. The increasing incidence trend emphasises the need for enhanced HPV vaccination rates to prevent the development of vaginal cancer.

Global incidence, risk factors and trends of vulvar cancer: A country‐based analysis of cancer registries

AbstractVulvar cancer is an uncommon malignancy. Vulvar cancer alarmed the public health problem in terms of the cost of diagnostic and medical treatments and psychical health of females. Our study aims to provide a thorough analysis of the global disease burden, related risk factors and temporal incidence trends of vulvar cancer in population subgroups. Data from Global Cancer Observatory and the Cancer Incidence in Five Continents Plus were used for the vulvar cancer incidence. Age‐standardized rates (ASR) were used to depict the incidence of vulvar cancer. The 10‐year trend of incidence was assessed using joinpoint regression with average annual percentage change and 95% confidence intervals in various age groups, while its correlations with risk factors were investigated using linear regression. Higher ASR were found in Western Europe (2.4), Northern America (1.9), Northern Europe (1.9), Australia and New Zealand (1.8) and Eastern Africa (1.4). The associated risk factors of higher vulvar cancer incidence were gross domestic product per capita, Human Development Index, higher prevalence of smoking, alcohol drinking, unsafe sex and human immunodeficiency virus infection. The overall trend of vulvar cancer incidence was increasing. An increasing trend was found in older females while a mixed trend was observed in younger females. The disease burden of vulvar cancer follows a bimodal pattern according to its two histologic pathways, affecting women in both developed and developing regions. Smoking cessation, sex education and human papillomavirus vaccination programs should be promoted among the general population. Subsequent studies can be done to explore the reasons behind the increasing trend of vulvar cancer.