The integration of the Internet of Things (IoT) and machine learning (ML) has enabled the development of smart home healthcare systems that enhance the quality of life for individuals, particularly the elderly and those with chronic conditions. These systems leverage IoT devices to monitor daily activities and ML algorithms to recognize patterns, detect anomalies, and provide personalized healthcare solutions. This review focusing on IoT-based smart home healthcare systems with ML-based activity recognition. The findings highlight advancements in real-time monitoring, predictive analytics, and decision support, emphasizing their potential to improve patient outcomes, reduce healthcare costs, and enable independent living. Challenges such as data privacy, interoperability, and computational efficiency are also discussed, along with future research directions.