OBJECTIVE: Sleep problems and cancer-related fatigue are common symptoms in women for breast cancer, during and after treatment. Identifying key intervention targets for this symptom cluster may improve patient reported outcomes. This study aimed to explore the relationship between sleep and cancer-related fatigue to identify optimal intervention targets. METHODS: In the "Be Resilient to Breast Cancer" program, self report data were collected on sleep and cancer-related fatigue the Multidimensional Fatigue Symptom Inventory-Short Form and the Pittsburgh Sleep Quality Index. Gaussian network analysis was employed to identify central symptoms and nodes, while a Bayesian network explored their causal relationships. Computer-simulated interventions were used to identify core symptoms as targets for intervention. RESULTS: General fatigue (Str ​= ​0.95, Bet ​= ​7, Clo ​= ​0.007) was considered the node with the strongest centrality. The daytime dysfunction item on the Pittsburgh sleep quality index had the strongest bridge strength. Core symptoms were identified as targets for intervention by the computer-simulated analysis. CONCLUSIONS: Sleep quality is the strongest predictor of cancer-related fatigue from a casual networking perspective. Sleep latency and daytime dysfunction should be targeted to break the chained symptom interaction between sleep and cancer-related fatigue.