Overcoming Missing Data: Accurately Predicting Cardiovascular Risk in Type 2 Diabetes, A Systematic Review.

Abstract

Understanding is limited regarding strategies for addressing missing value when developing and validating models to predict cardiovascular disease (CVD) in type 2 diabetes mellitus (T2DM). This study aimed to investigate the presence of and approaches to missing data in these prediction models. The MEDLINE electronic database was systematically searched for English-language studies from inception to June 30, 2024. The percentages of missing values, missingness mechanisms, and missing data handling strategies in the included studies were extracted and summarized. This study included 51 articles published between 2001 and 2024, involving 19 studies that focused solely on prediction model development, and 16 and 16 studies that incorporated internal and external validation, respectively. Most articles reported missing data in the development (n = 40/51) and external validation (n = 12/16) stages. Furthermore, the missing data were addressed in 74.5% of development studies and 68.8% of validation studies. Imputation emerged as the predominant method employed for both development (27/40) and validation (7/12) purposes, followed by deletion (17/40 and 4/12, respectively). During the model development phase, the number of studies reported missing data increased from 9 out of 15 before 2016 to 31 out of 36 in 2016 and subsequent years. Although missing values have received much attention in CVD risk prediction models in patients with T2DM, most studies lack adequate reporting on the methodologies used for addressing the missing data. Enhancing the quality assurance of prediction models necessitates heightened clarity and the utilization of suitable methodologies to handle missing data effectively.