Abstract: Predicting future heart rate (HR) not only helps in detecting abnormal heart rhythms but also provides timely support for downstream health monitoring services. Existing methods for predicting future HRs still encounter challenges, especially concerning privacy protection and data heterogeneity. To address these challenges,this paper proposes a novel HR prediction framework, PCFedH, which leverages personalized federated learningand prototypical contrastive learning to achieve stable clustering results and better predictions. PCFedH contains two core modules: the Prototypical Contrastive Learning-Based Federated Clustering Module, which characterizes data heterogeneity and enhances HR representation for better clustering, and the Two-Phase Soft Clustered Federated Learning Module, which enables personalized performance improvements for each local model based on stable clustering results. Experimental results from two real-world datasets demonstrate the superiority of our approach over state-of-the-art methods, achieving an average reduction of 3.1% in mean square error. Additionally, we conduct comprehensive experiments to empirically validate the effectiveness of the key components in our proposed method. Among these, the personalization component is identified as the most crucial aspect of our design, indicating its significant impact on the performance of our method. The code for this work is available at https://github.com/pcfedh/pcfedhgithub.com/pcfedh/pcfedh.