Development of an explainable clinical decision support system for the prediction of patient quality of life in amyotrophic lateral sclerosis
Anna Markella Antoniadi, Miriam Galvin, Mark Heverin, Orla Hardiman, Catherine Mooney
Abstract
Amyotrophic Lateral Sclerosis (ALS) is a rare neurodegenerative and currently incurable disease. It causes a rapid decline in motor functions and has a fatal trajectory. The aim of the treatment is mostly to alleviate symptoms and improve the patient's quality of life (QoL). The goal of this study is to develop a Clinical Decision Support System (CDSS) in order to alert clinicians when a patient is at risk of experiencing a low QoL, so that they are better supported. The source of the data was the Irish ALS Registry and interviews with the 90 patients and their primary informal caregiver at three time-points. In this dataset, there were two different scores to measure a person's overall QoL, based on the McGill QoL (MQoL) Questionnaire and we worked towards the prediction of both. The method we used for the development of the predictive models was Extreme Gradient Boosting (XGBoost), which was compared to a logistic regression baseline model. We used the SHAP (SHapley Additive exPlanations) values as a technique to provide local and global explanations to the outputs as well as to select the most important features. The total calculated MQoL score was predicted accurately by three features, with a F1-score on the test set equal to 0.81, a recall score of 0.78, and a precision score of 0.84, while, the addition of two features produced similar outcomes (0.79, 0.70 and 0.90 respectively). The three most important features were the age at disease onset, ALSFRS score for orthopnoea and the caregiver's status pre-caregiving.