School of Management and Business, Universidad del Rosario, Bogotá, Colombia.
Facultad de Medicina, Departamento de Nutrición Humana, Universidad Nacional de Colombia, Hospital de la Misericordia, Universidad Del Rosario, Bogotá, Colombia.
PLoS One. 2024 Jun 4;19(6):e0301860. doi: 10.1371/journal.pone.0301860. eCollection 2024.
To assess the effectiveness of different machine learning models in estimating the pharmaceutical and non-pharmaceutical expenditures associated with Diabetes Mellitus type II diagnosis, based on the clinical risk index determined by the analysis of comorbidities.
In this cross-sectional study, we have used data from 11,028 anonymized records of patients admitted to a high-complexity hospital in Bogota, Colombia between 2017-2019 with a primary diagnosis of Diabetes. These cases were classified according to Charlson's comorbidity index in several risk categories. The main variables analyzed in this study are hospitalization costs (which include pharmaceutical and non-pharmaceutical expenditures), age, gender, length of stay, medicines and services consumed, and comorbidities assessed by the Charlson's index. The model's dependent variable is expenditure (composed of pharmaceutical and non-pharmaceutical expenditures). Based on these variables, different machine learning models (Multivariate linear regression, Lasso model, and Neural Networks) were used to estimate the pharmaceutical and non-pharmaceutical expenditures associated with the clinical risk classification. To evaluate the performance of these models, different metrics were used: Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2).
The results indicate that the Neural Networks model performed better in terms of accuracy in predicting pharmaceutical and non-pharmaceutical expenditures considering the clinical risk based on Charlson's comorbidity index. A deeper understanding and experimentation with Neural Networks can improve these preliminary results, therefore we can also conclude that the main variables used and those that were proposed can be used as predictors for the medical expenditures of patients with diabetes type-II.
With the increase of technology elements and tools, it is possible to build models that allow decision-makers in hospitals to improve the resource planning process given the accuracy obtained with the different models tested.
评估基于合并症分析得出的临床风险指数，使用不同机器学习模型估算与 2 型糖尿病诊断相关的药物和非药物支出的效果。
在这项横断面研究中，我们使用了哥伦比亚波哥大一家高复杂度医院在 2017-2019 年间收治的 11028 名匿名 2 型糖尿病患者的记录数据。这些病例根据 Charlson 合并症指数分为不同风险类别。本研究分析的主要变量包括住院费用（包括药物和非药物支出）、年龄、性别、住院时间、使用的药物和服务以及 Charlson 指数评估的合并症。模型的因变量是支出（包括药物和非药物支出）。基于这些变量，使用不同的机器学习模型（多元线性回归、套索模型和神经网络）来估算与临床风险分类相关的药物和非药物支出。为了评估这些模型的性能，使用了不同的指标：平均绝对百分比误差（MAPE）、均方误差（MSE）、均方根误差（RMSE）、平均绝对误差（MAE）和决定系数（R2）。
结果表明，考虑到基于 Charlson 合并症指数的临床风险，神经网络模型在预测药物和非药物支出的准确性方面表现更好。更深入地理解和试验神经网络可以改进这些初步结果，因此我们还可以得出结论，所使用的主要变量和提出的变量可以用作预测 2 型糖尿病患者医疗支出的指标。
随着技术元素和工具的增加，构建模型成为可能，这些模型可以让医院的决策者在不同测试模型获得的准确性的基础上，改进资源规划过程。
