The rapid growth of the Internet of Health Things (IoHT) has increased the vulnerability of healthcare systems to various cyberattacks, jeopardizing the security and privacy of critical medical data. In this paper, we propose an Explainable-Random Forest (XRF) model, an ensemble-based decision tree approach, designed to detect and classify cyberattacks targeting IoHT ecosystems. The model integrates explainable AI (XAI) techniques, offering not only high accuracy but also the ability to interpret and justify the model’s predictions, ensuring transparency in decision-making. Our approach achieves an overall classification accuracy of more than 95%, with 100% accuracy in detecting ARP Spoofing and Smurf Attack, demonstrating its high reliability in detecting malicious activities. By providing explainable results, the proposed model enhances cybersecurity in smart healthcare systems, ensuring early detection of cyberthreats, reducing risks from malicious actors, and improving the overall security and continuity of services. This paper underscores the critical role of AI-driven solutions in advancing cybersecurity for smart cities, offering an in-depth analysis of the proposed method’s performance and its potential to safeguard smart healthcare system through proactive and transparent attack detection.