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

https://doi.org/10.1016/j.ijmedinf.2012.03.001Get rights and content

Abstract

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.

Highlights

► A practical process for development of rule sets for healthcare expert systems. ► A feasible and effective rule set for heart failure telemonitoring systems. ► Identification of clinician and patient concerns on telemonitoring expert systems.

Introduction

The increasing prevalence of chronic diseases, such as heart failure, as the population ages is expected to result in a severe shortage in healthcare resources including nurses, physicians, and hospital beds [1], [2], [3]. Telemonitoring is a promising tool that can potentially alleviate some of the burden on the healthcare system by empowering patients to care for themselves and enabling more efficient clinical care, such as through automated alerts at the earliest sign of deteriorating patient health.

Currently, computerized clinical decision support systems exist for heart failure diagnosis and treatment plans. The rule sets for these systems can be based on clinical practice guidelines [4], [5], [6]. Although methods to transform clinical practice guidelines for use in decision support have been developed [7], [8], no guidelines presently exist that are comprehensive enough for direct use in the relatively new area of automated heart failure patient decision support and alerting systems (e.g., to create patient instructions for each possible combination of symptoms, blood pressure, and weight readings). Furthermore, even if such guidelines did exist, clinical input during the development of computerized clinical practice guidelines would be important to bridge the “gap between the guideline text and clinical practice” [9]. That is, rule sets need to take into consideration each healthcare institution's own workflow and policies, as well as the individuality of the patients. The clinical input could be implemented through various user-centered design processes, such as participatory design, usability testing, or contextual design [10], [11], [12].

An expert system is a “knowledge-intensive program that solves a problem by capturing the expertise of a human in limited domains of knowledge and experience” [13]. Expert systems have been used in a variety of fields, including medicine, space, and business [14], [15], [16], [17], [18]. For rule-based expert systems, the knowledge from experts is translated by a knowledge engineer into a set of rules [19].

The purpose of this work was to develop a rule-based expert system for a heart failure mobile phone-based telemonitoring system. The expert system would be used to automatically generate appropriate alerts for clinicians and patients, as well as to generate suitable patient instructions. This expert system would be fundamentally different from existing clinical decision support tools available to healthcare providers for diagnosis and management because it would function independently of the clinician with automated alerts being sent directly to the patient and to the clinician. This article describes the process used to create the heart failure rule set, the resultant rule set, and the lessons learned. To determine the efficacy of the rule set, it was incorporated into a heart failure telemonitoring system that was evaluated in a randomized controlled trial. The effects of the rule set on the trial results are also summarized below. Details of the trial results have been published elsewhere [20], [21].

Section snippets

Methods

The University Health Network (UHN) Research Ethics Board approved both the development process of the heart failure telemonitoring system, including the rule set, and the randomized controlled trial. All individuals participating in this research provided informed consent.

Features of the rule set

Each interviewed heart failure clinician agreed the parameters listed in Table 1 should be monitored at the patient's home. Patients were asked to take their weight, blood pressure, and symptoms daily, and ECG readings weekly. Although there was some debate on the necessity for all patients to take their blood pressure daily, it was decided all patients should be asked to take their blood pressure daily to help them establish a routine and to simplify the rule set. Clinicians were be able to

Discussion

Heart failure clinicians participated extensively in the development of a rule set that generated patient alerts/instructions and alerts sent to an on-call clinician. The rule set was implemented in a heart failure telemonitoring expert system and evaluated with a randomized controlled trial. A large number of clinical actions resulted from the alerts generated by the rule set, particularly with respect to optimization of medication (N = 105 over the 6-month trial). The trial indicated improved

Conclusions

A rule set for automated alerts and patient instructions for heart failure telemonitoring was developed with extensive input from heart failure clinicians. The rule set was evaluated through a randomized controlled trial. The trial findings indicate the rule set was associated with improved clinical management, self-care, and quality of life. Although the resultant heart failure rule set should not be applied verbatim to other clinical settings without validation, the development process and

Authors’ contributions

The corresponding author was the primary researcher involved in the development of the expert system and its evaluation, including the participant recruitment, maintenance of the telemonitoring system, data gathering, and data analysis. She also was the main author of the manuscript. The other authors provided advice and expertise throughout the research and creation of the manuscript. In addition, Dr. Heather Ross was the clinical champion of the project and responded to the clinical alerts

Conflicts of interest

The researcher who developed the expert system also was the study coordinator for the randomized controlled trial.

Summary points

What was already known on the topic

  • Processes to create rule sets for healthcare expert systems have not been extensively studied.

  • To our knowledge, there has not been a published rule set for expert systems for heart failure telemonitoring.

  • Currently poor understanding of the concerns of patients and clinicians on using expert systems for telemonitoring and how to

Acknowledgments

The authors would like to thank the heart failure clinicians from the UHN Heart Function Clinic for their time and expertise during the rule set development process. We would also like to thank the software developers for their work in implementing the rule set. Funding for this work was in part provided by the Toronto General Hospital Foundation and a Natural Sciences and Engineering Research Council of Canada Strategic Research Network Grant (Healthcare Support through Information Technology

References (32)

  • J.O. Prochaska et al.

    Stage-based expert systems to guide a population of primary care patients to quit smoking, eat healthier, prevent skin cancer, and receive regular mammograms

    Prev. Med.

    (2005 August)
  • R.J. Rosseter

    Nursing Shortage Fact Sheet

    (2011)
  • P. Sullivan

    Concerns about size of MD workforce, Medicine's Future Dominate CMA Annual Meeting

    CMAJ

    (1999 September)
  • G. George et al.

    Effect of population ageing on emergency department speed and efficiency: a historical perspective from a district general hospital in the UK

    Emerg. Med. J.

    (2006 May)
  • K. Swedberg et al.

    Guidelines for the diagnosis and treatment of chronic heart failure: executive summary (update 2005): The Task Force for the Diagnosis and Treatment of Chronic Heart Failure of the European Society of Cardiology

    Eur. Heart J.

    (2005 June)
  • S.A. Hunt et al.

    2009 focused update incorporated into the ACC/AHA 2005 Guidelines for the Diagnosis and Management of Heart Failure in Adults: a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines: developed in collaboration with the International Society for Heart and Lung Transplantation

    Circulation

    (2009 April)
  • Cited by (76)

    • Expert systems: Definitions, advantages and issues in medical field applications

      2021, Expert Systems with Applications
      Citation Excerpt :

      By making remote patient monitoring possible, the clinicians can intervene early if there is evidence of clinical deterioration. Therefore, the purpose of the work conducted by Seto et al. (2012) is to develop a rule-based ES for a heart failure mobile phone-based telemonitoring system. First they create a rule set based on expert interviews.

    • Do-Care: A dynamic ontology reasoning based healthcare monitoring system

      2021, Future Generation Computer Systems
      Citation Excerpt :

      Rule-based and case-based reasoning are the earliest healthcare reasoning techniques. In [33], a rule-based expert system was proposed for a heart failure telemonitoring system based on the patient’s weight, blood pressure, heart rate, and symptoms. Valijo et al. [34] proposed a case-based reasoning system called InNoCPR for nosocomial infection24 detection and classification.

    • Machine learning in healthcare: Review, opportunities and challenges

      2021, Machine Learning and the Internet of Medical Things in Healthcare
    • Knowledge-based systems in medical applications

      2020, Computational Intelligence and Its Applications in Healthcare
    View all citing articles on Scopus

    Trial Registration: ClinicalTrials.gov NCT00778986.

    View full text