A systematic review of emotion recognition technology over the past decade reveals its growing importance in healthcare. The study analyzed 44 studies published between 2013 and 2023, focusing on three aspects: application scenarios, multimodal techniques, and clinical applications. The findings indicate that emotion recognition technology has facilitated remote emotion recognition and treatment in hospitals and homes. It has shifted from traditional subjective methods to objective physiological signal-based approaches, improving medical diagnosis accuracy. The evolving relationship between emotions and disease during diagnosis, intervention, and treatment is clinically significant for real-time emotion monitoring. Emotion recognition technology has been applied in various settings, including hospitals and home environments. In hospitals, it aids in diagnosing and treating emotional disorders by analyzing clinical data, facial expressions, speech, and physiological signals. In home environments, it supports continuous monitoring through IoT devices and cloud-based systems, enabling real-time data collection and analysis. The technology has shown promise in improving patient outcomes by enabling early detection of emotional changes and providing timely interventions. Emotion recognition methods include psychometric scales, speech analysis, facial expression recognition, and physiological signal analysis. These methods have been validated in various studies, demonstrating their effectiveness in identifying emotional states. Multimodal approaches, combining multiple data sources, have shown higher accuracy in emotion recognition. The integration of emotion recognition technology with intelligent devices has led to the development of application systems and models that support emotion recognition and intervention. The study also highlights the positive and negative impacts of emotion recognition technology. While it offers benefits such as improved patient outcomes, real-time monitoring, and personalized healthcare, it also raises concerns about patient privacy, data security, and the potential for overloading patients with frequent emotional assessments. The technology's implementation in healthcare faces challenges, including data access, cost, cultural differences, and ethical considerations. Future research should focus on improving the robustness of emotion recognition models, exploring multimodal data integration, and advancing automation and real-time capabilities. Additionally, addressing security, ethics, and privacy concerns is essential for the responsible development and application of emotion recognition technology in healthcare.A systematic review of emotion recognition technology over the past decade reveals its growing importance in healthcare. The study analyzed 44 studies published between 2013 and 2023, focusing on three aspects: application scenarios, multimodal techniques, and clinical applications. The findings indicate that emotion recognition technology has facilitated remote emotion recognition and treatment in hospitals and homes. It has shifted from traditional subjective methods to objective physiological signal-based approaches, improving medical diagnosis accuracy. The evolving relationship between emotions and disease during diagnosis, intervention, and treatment is clinically significant for real-time emotion monitoring. Emotion recognition technology has been applied in various settings, including hospitals and home environments. In hospitals, it aids in diagnosing and treating emotional disorders by analyzing clinical data, facial expressions, speech, and physiological signals. In home environments, it supports continuous monitoring through IoT devices and cloud-based systems, enabling real-time data collection and analysis. The technology has shown promise in improving patient outcomes by enabling early detection of emotional changes and providing timely interventions. Emotion recognition methods include psychometric scales, speech analysis, facial expression recognition, and physiological signal analysis. These methods have been validated in various studies, demonstrating their effectiveness in identifying emotional states. Multimodal approaches, combining multiple data sources, have shown higher accuracy in emotion recognition. The integration of emotion recognition technology with intelligent devices has led to the development of application systems and models that support emotion recognition and intervention. The study also highlights the positive and negative impacts of emotion recognition technology. While it offers benefits such as improved patient outcomes, real-time monitoring, and personalized healthcare, it also raises concerns about patient privacy, data security, and the potential for overloading patients with frequent emotional assessments. The technology's implementation in healthcare faces challenges, including data access, cost, cultural differences, and ethical considerations. Future research should focus on improving the robustness of emotion recognition models, exploring multimodal data integration, and advancing automation and real-time capabilities. Additionally, addressing security, ethics, and privacy concerns is essential for the responsible development and application of emotion recognition technology in healthcare.