Machine Learning in Health Economics: Modeling Costs, Outcomes, and Policy Decisions

2025-11-07T22:23:14+0330

Health economics increasingly faces complex challenges in balancing rising costs, improving outcomes, and informing policy decisions under constrained resources. Traditional econometric models often struggle with nonlinearities, high-dimensional data, and heterogeneous treatment effects. Machine learning (ML) provides a promising alternative by enabling more accurate predictions of healthcare costs, health outcomes, and cost-effectiveness metrics. This paper explores how ML methods—such as random forests, gradient boosting, and neural networks—can enhance economic evaluation frameworks. Using a representative dataset of 100,000 patients over a 5-year horizon, we demonstrate that ML models reduce prediction error by up to 35% compared to generalized linear models and provide improved identification of high-cost patients. By integrating cost and outcome predictions into incremental cost-effectiveness ratio (ICER) and net monetary benefit (NMB) frameworks, ML significantly alters policy decisions, particularly under budget-constrained scenarios. Findings suggest that ML can not only improve efficiency in modeling but also shape fairer and more effective health policies.

Single Nucleotide Polymorphisms Detection of INS gene in Patients with Type 2 Diabetes Mellitus and their Association to some Clinical Features

2025-11-20T21:41:59+0330

About 90–95% of all occurrences of diabetes are type 2 diabetes mellitus (T2DM), making it the most prevalent kind of the disease. Independent of body mass index, T2DM is a major predictor of incident hypertension. The objective of this study was to detection of some single nucleotide polymorphism in INS gene and their effect in other factors. This study includes (100) patients T2DM collected from Al-Zahraa Teaching Hospital in Wasit, Iraq and individuals used as control group. The results recorded a significant increase in HbA1C levels (8.72±1.22) compared to control (4.44±0.51) also significant increase in male patients T2DM with Hypertension compared to female patients T2DM with Hypertension (19%) and (8%) receptively. According to BMI the results showed the Obese: female (12%) and male (15%), Overweight female (23%) and male (12), Normal weight: female (15%) and male (14%) depending on the Statical analysis there is non-significant between them. The results of matching the sequence showed the T2DM with Hypertension two SNPs in upstream of INS gene 12% (-106C>T), 11% (-106C>T), and two in coding region 8% (244G>T) and 8% silent mutation (353C>T). Obese T2DM two SNPs in upstream of INS gene: 7% (-106C>T) and 7% (-234A>G). Overweight T2DM SNPs in upstream 8% (-106C>T) and 8% (-234A>G). Three SNPs in Normal weight with T2DM: 13%(-106C>T) and 12%(-106C>T) in upstream of INS gene and silent mutation 8% 353C>T in coding region. In conclusion this study reported the SNPs in promoter and coding region of INS gene effecting in its function in T2DM patients and influence in displayed higher BMI value and insulin levels and confirm the link between T2DM and hypertension.

International journal of medical and applied health science

Machine Learning in Health Economics: Modeling Costs, Outcomes, and Policy Decisions

Single Nucleotide Polymorphisms Detection of INS gene in Patients with Type 2 Diabetes Mellitus and their Association to some Clinical Features