Developing healthcare rule-based expert systems: case study of a heart failure telemonitoring system

Background: The use of expert systems to generate automated alerts and patient instructions based on telemonitoring data could enable increased self-care and improve clinical management. However, of great importance is the development of the rule set to ensure safe and clinically relevant alerts and instructions are sent. The purpose of this work was to develop a rule-based expert system for a heart failure mobile phone-based telemonitoring system, to evaluate the expert system, and to generalize the lessons learned from the development process for use in other healthcare applications.

Methods: Semi-structured interviews were conducted with 10 heart failure clinicians to inform the development of a draft heart failure rule set for alerts and patient instructions. The draft rule set was validated and refined with 9 additional interviews with heart failure clinicians. Finally, the clinical champion of the project vetted the rule set. The concerns voiced by the clinicians during the interviews were noted, and methods to mitigate these concerns were employed. The rule set was then evaluated as part of a 6-month randomized controlled trial of a mobile phone-based heart failure telemonitoring system (n=50 for each of the telemonitoring and control groups).

Results: The developed expert system generated alerts and instructions based on the patient's weight, blood pressure, heart rate, and symptoms. During the trial, 1620 alerts were generated, which led to various clinical actions including 105 medication changes/instructions. The findings from the trial indicated the rule set was associated with improved quality of life and self-care.

Conclusions: A rule set was developed with extensive input by heart failure clinicians. The results from the trial indicated the rule set was associated with significantly increased self-care and improved the clinical management of heart failure. The developed rule set can be used as a basis for other heart failure telemonitoring systems, but should be validated and modified as necessary. In addition, the process used to develop the rule set can be generalized and applied to create robust and complete rule sets for other healthcare expert systems.