Designing proper treatment plans to manage diabetes requires health
practitioners to pay heed to the individuals remaining life along with the
comorbidities affecting them. Older adults with Type 2 Diabetes Mellitus (T2DM)
are prone to experience premature death or even hypoglycaemia. The structured
dataset utilized has 68 potential mortality predictors for 275,190 diabetic
U.S. military Veterans aged 65 years or older. A new target variable is
invented by combining the two original target variables. Outliers are handled
by discretizing the continuous variables. Categorical variables have been dummy
encoded. Class balancing is achieved by random under-sampling. A benchmark
regression model is built using Multinomial Logistic Regression with LASSO.
Chi-Squared and Information Gain are the filter-based feature selection
techniques utilized. Classifiers such as Multinomial Logistic Regression,
Random Forest, Extreme Gradient Boosting (XGBoost), and One-vs-Rest classifier
are employed to build various models. Contrary to expectations, all the models
have constantly underperformed. XGBoost has given the highest accuracy of 53.03
percent with Chi-Squared feature selection. All the models have consistently
shown an acceptable performance for Class 3 (remaining life is more than 10
years), significantly low for Class 1 (remaining life is up to 5 years), and
the worst for Class 2 (remaining life is more than 5 but up to 10 years).
Features analysis has deduced that almost all input variables are associated
with multiple target classes. The high dimensionality of the input data after
dummy encoding seems to have confused the models, leading to
misclassifications. The approach taken in this study is ineffective in
producing a high-performing predictive model but lays a foundation as this
problem has never been viewed from a multiclass classification perspective.

为了管理糖尿病而设计适当的治疗计划，医务人员需关注患者剩余寿命以及影响其健康的合并症。本文研究了 65 岁及以上的美国退伍军人中 2 型糖尿病老年患者的 68 个潜在死亡预测因素的结构化数据集，通过组合两个原始目标变量构建了一个新的目标变量，采用多项式逻辑回归与 LASSO 的基准回归模型，在特征选择中采用了卡方检验和信息增益技术，并使用多种分类器构建了不同的模型，然而结果表明所有模型均未达到预期效果，主要原因是原始数据经过编码后的高维度使模型产生了混淆，导致误分类。尽管该研究未产生高性能的预测模型，但视角上的创新为这一问题从多分类的角度进行研究奠定了基础。

分析和死亡预测：用于老年 2 型糖尿病患者的多类别分类

Analysis and Mortality Prediction using Multiclass Classification for  Older Adults with Type 2 Diabetes

Background: Accurate survival time estimates aid end-of-life medical
decision-making. Objectives: Develop an interpretable survival model for
elderly residential aged care residents using advanced machine learning.
Setting: A major Australasian residential aged care provider. Participants:
Residents aged 65+ admitted for long-term care from July 2017 to August 2023.
Sample size: 11,944 residents across 40 facilities. Predictors: Factors include
age, gender, health status, co-morbidities, cognitive function, mood,
nutrition, mobility, smoking, sleep, skin integrity, and continence. Outcome:
Probability of survival post-admission, specifically calibrated for 6-month
survival estimates. Statistical Analysis: Tested CoxPH, EN, RR, Lasso, GB, XGB,
and RF models in 20 experiments with a 90/10 train/test split. Evaluated
accuracy using C-index, Harrell's C-index, dynamic AUROC, IBS, and calibrated
ROC. Chose XGB for its performance and calibrated it for 1, 3, 6, and 12-month
predictions using Platt scaling. Employed SHAP values to analyze predictor
impacts. Results: GB, XGB, and RF models showed the highest C-Index values
(0.714, 0.712, 0.712). The optimal XGB model demonstrated a 6-month survival
prediction AUROC of 0.746 (95% CI 0.744-0.749). Key mortality predictors
include age, male gender, mobility, health status, pressure ulcer risk, and
appetite. Conclusions: The study successfully applies machine learning to
create a survival model for aged care, aligning with clinical insights on
mortality risk factors and enhancing model interpretability and clinical
utility through explainable AI.

采用机器学习，为老年护理提供了生存模型，增强了模型可解释性及临床效用。