Missing data is poorly handled and reported in prediction model studies using machine learning: a literature review

•Prediction model studies that adopt machine learning (ML) methods rarely report the presence and handling of missing data.•Although many types of machine learning methods offer built-in capabilities for handling missing values, these strategies are rarely used. Instead, most ML-based prediction model studies resort to complete case analysis or mean imputation.•Missing data are often poorly handled and reported, even when adopting advanced machine learning methods for which advanced imputation procedures are available.•The handling and reporting of missing data in prediction model studies should be improved. A general recommendation to avoid bias is to use multiple imputation. It is also possible to consider machine learning methods with built-in capabilities for handling missing data (e.g., decision trees with surrogate splits, use of pattern submodels, or incorporation of autoencoders).•Authors should take note of and appreciate the existing reporting guidelines (notably, TRIPOD and STROBE) when publishing ML-based prediction model studies. These guidelines offer a minimal set of reporting items that help to improve the interpretation and reproducibility of research findings. Missing data is a common problem during the development, evaluation, and implementation of prediction models. Although machine learning (ML) methods are often said to be capable of circumventing missing data, it is unclear how these methods are used in medical research. We aim to find out if and how well prediction model studies using machine learning report on their handling of missing data. We systematically searched the literature on published papers between 2018 and 2019 about primary studies developing and/or validating clinical prediction models using any supervised ML methodology across medical fields. From the retrieved studies information about the amount and nature (e.g. missing completely at random, potential reasons for missingness) of missing data and the way they were handled were extracted. We identified 152 machine learning-based clinical prediction model studies. A substantial amount of these 152 papers did not report anything on missing data (n = 56/152). A majority (n = 96/152) reported details on the handling of missing data (e.g., methods used), though many of these (n = 46/96) did not report the amount of the missingness in the data. In these 96 papers the authors only sometimes reported possible reasons for missingness (n = 7/96) and information about missing