From Neutral to Promotors: Improving Patient Satisfaction through Artificial Intelligence-enabled Voice Feedback and Real-time Escalation
Priyanka Maan, Saryu JadonAbstract
Introduction:
Patient satisfaction has become a crucial measure of the quality of health care, impacting not just clinical results but also hospital reputation and long-term viability. Conventional techniques for gathering patient input, such as manual interviews and postdischarge surveys, sometimes fall short of offering timely and useful insights. Healthcare professionals are less able to handle issues during a patient’s stay as a result of these delayed systems, which leads to lost chances for successful service recovery. As artificial intelligence (AI) becomes more widely used in health care, feedback systems are becoming more responsive and dynamic. Real-time patient experience collection and analysis are made possible by AI-enabled voice feedback systems that are backed by natural language processing. The aim of this study is to evaluate the effectiveness of AI-enabled real-time feedback and escalation mechanisms in improving patient satisfaction within healthcare settings.
Objective:
The study focuses on assessing the impact of real-time escalation on patient satisfaction, classifying patients into promoters, passives, and detractors, identifying key factors causing dissatisfaction, and examining how AI-driven feedback systems help convert neutral patients into promoters while reducing negative experiences.
Methodology:
The study uses a descriptive and analytical design based on secondary data from 248 patient feedback responses. It combines quantitative analysis with qualitative insights, classifying patients into promoters, passives, and detractors using the Net Promoter Score framework. Statistical tools such as percentage analysis and frequency distribution, along with thematic evaluation of feedback, were used to identify patterns and key issues. Factors such as facilities, waiting time, staff behavior, cleanliness, food, and billing were analyzed in relation to patient satisfaction.
Results:
The study shows a significant improvement in patient satisfaction after implementing AI-enabled real-time feedback and escalation. The average sentiment score increased from 3.27 to 3.88, with over 60% of patients showing improvement. Many patients shifted from detractor to passive or promoter categories, and overall complaints decreased.
Conclusion:
While major improvements were seen in areas such as food services and medical administration, some issues persisted in housekeeping and billing, confirming the effectiveness of the system in enhancing patient experience.