This study, by Jung and Yun, investigates the usage of explainable artificial intelligence (XAI) in interpreting simple prediction models for the quality of life (QoL) for survivors of cancer. After 256 cancer survivors completed two surveys over the course of six months between 2013 and 2014, the data was processed using the machine learning techniques XGBoost and Shapley Additive Explanation (SHAP) which evaluated global QoL and health statuses depending on factors such as socio-demographic information, clinical characteristics, and self-management assessment scores (SAT). SHAP values were extracted from the XGBoost models, and the predictions were evaluated for accuracy. The study found that XGBoost produced the most accurate predictions for global QoL, with the strongest predicted traits being social and mental health, and the weakest prediction being physical health. Overall, it was determined that the QoL of cancer survivors was highly predictable when using basic characteristics such as socio-demographic and self-management strategies, and the XGBoost model is a useful and accurate tool for making predictions. Additionally, the most important aspect of predicting the QoL of a cancer survivor was the application of the activity copying strategy of the SAT-I.