Increasing efficiency of SVMp+ for handling missing values in healthcare prediction

Missing data presents a challenge for machine learning applications specifically when utilizing electronic health records to develop clinical decision support systems. The lack of these values is due in part to the complex nature of clinical data in which the content is personalized to each patient. Several methods have been developed to handle this issue, such as imputation or complete case analysis, but their limitations restrict the solidity of findings. However, recent studies have explored how using some features as fully available privileged information can increase model performance including in SVM. Building on this insight, we propose a computationally efficient kernel SVM-based framework (l2-SVMp+) that leverages partially available privileged information to guide model construction. Our experiments validated the superiority of l2-SVMp+ over common approaches for handling missingness and previous implementations of SVMp+ in both digit recognition, disease classification and patient readmission prediction tasks. The performance improves as the percentage of available privileged information increases. Our results showcase the capability of l2-SVMp+ to handle incomplete but important features in real-world medical applications, surpassing traditional SVMs that lack privileged information. Additionally, l2-SVMp+ achieves comparable or superior model performance compared to imputed privileged features.Author summary: Clinical problems often suffer from missing value issues, which require careful consideration. There are various approaches developed to tackle this problem, including imputation methods, but these methods have limitations. In this study, we introduced an efficient algorithm called l2- SVMp+ to address missing values in important features using a partially available privileged information framework. Our approach offers a novel perspective for handling missing values by regarding them as privileged information to guide the training process. Our results indicate that (1) our proposed method outperforms the standard SVM, SVMp+; and (2) Our approach achieves comparable or superior performance to two commonly used imputation methods. This non-parametric approach offers a new direction for handling missing values and may potentially avoid imputation-related bias and overfitting in the model. With further testing and validation, our approach may lead to more accurate diagnoses and better treatment outcomes for patients.