Relevance and Limitations of Decision Support Systems for Outpatient Cardiac Rehabilitation Volume 12 - Issue 4

Miriam Allein Zago Marcolino¹ and Rodrigo Della Méa Plentz*^1,2

• ¹Graduate Program of Rehabilitation Sciences, Porto Alegre, RS, Brazil
• ²Graduate Program of Health Sciences, Brazil

Received: December 18, 2018;   Published: January 03, 2019

*Corresponding author: Rodrigo Della Méa Plentz, Graduate Program of Health Sciences, Brazil

DOI: 10.26717/BJSTR.2019.12.002295

Abstract PDF

Decision support systems (DSS) are defined as any computational applications that improve the abilities of an individual or group of individuals to make decisions [1]. In the recent years, its use in clinical practice is gaining acknowledgment as its benefits in terms of reducing diagnostic errors [2], increasing conformity with clinical guidelines [3,4] and potentially increasing the health care quality [5-7] have been reported. Cardiac rehabilitation (CR), a multidisciplinary and comprehensive intervention to improve the physical, mental, and social capabilities of patients with cardiovascular diseases [8], can be an important field to the application of DSS. The challenging decision-making process in the outpatient CR involves the analysis about many factors, including the clinical characteristics of the patients, its values and preferences, and the indications and restrictions to the exercise training and other interventions’ prescription [9-11]. Thus, the development and use of DSS in cardiac rehabilitation may be a good alternative, helping the professionals in the daily practice and potentially increasing the health care quality in this field.

There are different types of DSS, but the most suitable for clinical DSS is the knowledge-driven, that uses artificial intelligence and statistic inference in codified knowledge to provide assistance in specialized problem solutions, suggesting or recommending actions1. The knowledge representation for knowledge-driven clinical DSS can be based on rules, clinical guidelines or probabilistic networks [12]. The clinical decision making is characterized by the presence of uncertainty and causality, making the probabilistic networks suitable for the development of DSS [13], once they are methods representative of the uncertain knowledge, allowing the manipulation of the uncertainty by based mathematical principles [14]. To identify previously developed DSS for outpatient supervised CR, we conducted a systematic search in the main health electronic databases (PubMed, Embase, Cochrane Central Register of Controlled Trials and Physiotherapy Evidence Database [PEDro]), and informatics databases (IEEExplore and Science Direct).

The search strategy was adapted for each database and included the indexed terms and their synonyms for “Clinical Decision Support Systems” and “Cardiac Rehabilitation”, combined by Boolean terms. The searches were updated until 04/12/2018, without date or language restriction, resulting in 189 registers. After duplicates removal and studies’ selection, two DSS for outpatient supervised CR were identified: the CARDSS (“Cardiac Rehabilitation Decision Support System”) [9] and the EXPERT (“Exercise Prescription in Everyday Practice and Rehabilitative Training”) [10]. CARDSS is a record system with DSS functionalities focused on the patient assessment for CR indication and to increase the guidelines adherence during the CR process, providing recommendations based on a knowledge representation of the Dutch guideline for CR [9]. CARDSS was developed for use in a computer and was distributed to CR centers in Holland that accepted to be included in a randomized controlled trial and was also for sale at the country. The randomized controlled trial included 31 Dutch CR centers, showed an improvement in the guideline’s conformity about the exercise of 3.5%, the educative interventions of 23.7% and the relaxing therapies of 41.6% with CARDSS use [7].

EXPERT was developed by a group of experts in chronic diseases from 11 European countries, with endorsing of the European Association of Preventive Cardiology. The knowledge representation for EXPERT was also based on clinical guidelines and is focused in exercise prescription in CR, including exercise intensity, frequency, duration, type, number of sessions and rehabilitation program duration and extra modalities of exercise indicated. EXPERT was also developed for use in a computer and is still in testing before the planned implantation in CR centers of the Europe [10]. It is important to notice that both systems were developed only for use in computers. One of the characteristics that were recognized to influence the success in the DSS use is the ability to provide assistance to decision-making at the place and moment of the decision6. With the availability and increased familiarity of people with mobile devices, the development of DSS for smartphones and tablets can be a way of increasing the proximity between the system and the user, with more potential of success in its use15,16.

Another important point is that both systems had the knowledge representation based on local guidelines that, although developed based in the recent evidence, need constant updating and may not represent the clinical guidelines worldwide. Also, none system was identified using probabilistic networks in the knowledge representation. Previously our research group described the development and validation of two influence diagrams (a type of probabilistic network)11 that are being used as the knowledge base for a new mobile-designed DSS for outpatient CR, however, this system is still not available. With this small review of the available options of DSS in outpatient CR rehabilitation can be seen that the current developed systems are available only in restricted geographic areas, leaving other regions, mainly the middle and lowdeveloped countries with no options of DSS in this fiel

d. Also, the systems are restricted for use in computers, which may not represent the best approach for a pretended routinely use of a DSS.

1. Power DJ, Sharda R, Burstein F (2015) Decision support systems. Wiley Encyclopedia of Management. Nova Jersey: John Wiley & Sons, pp. 1-4.
2. Main C, Moxham T, Wyatt JC, Kay J, Anderson R, et al. (2010) Computerised decision support systems in order communication for diagnostic, screening or monitoring test ordering: systematic reviews of the effects and cost-effectiveness of systems 14(48): 1-227.
3. Linder J, Schnipper J, Tsurikova R, Yu T, Volk L, et al. (2009) Documentation-based clinical decision support to improve antibiotic prescribing for acute respiratory infections in primary care: a cluster randomised controlled trial. Journal of Innovation in Health Informatics17(4): 231-240.
4. Seidling HM, Schmitt SPW, Bruckner T, Kaltschmidt J, Pruszydlo MG, et al. (2009) Patient-specific electronic decision support reduces prescription of excessive doses. BMJ Quality & Safety, qshc 19(5): e15.
5. Delaney BC, Fitzmaurice DA, Riaz A, Hobbs FDR (1999) Can computerised decision support systems deliver improved quality in primary care? BMJ: British Medical Journal 319(7220): 1281.
6. Roshanov PS, Fernandes N, Wilczynski JM, Hemens BJ, You JJ, et al. (2013) Features of effective computerised clinical decision support systems: meta-regression of 162 randomised trials. Bmj 346: 657.
7. Goud R, de Keizer NF, ter Riet G, Wyatt JC, Hasman A, et al. (2009) Effect of guideline based computerised decision support on decision making of multidisciplinary teams: cluster randomised trial in cardiac rehabilitation. Bmj 338: 1440.
8. Balady GJ, Ades PA, Bittner VA, Franklin BA, Gordon NF, et al. (2011) Referral, enrollment, and delivery of cardiac rehabilitation/secondary prevention programs at clinical centers and beyond: a presidential advisory from the American Heart Association. Circulation 124(25): 2951-2960.
9. Goud R, Hasman A, Peek N (2008) Development of a guideline-based decision support system with explanation facilities for outpatient therapy. Computer methods and programs in biomedicine 91(2): 145- 153.
10. Hansen D, Dendale P, Coninx K, Vanhees L, Piepoli MF, et al. (2017) The European Association of Preventive Cardiology Exercise Prescription in Everyday Practice and Rehabilitative Training (EXPERT) tool: A digital training and decision support system for optimized exercise prescription in cardiovascular disease. Concept, definitions and construction methodology. European journal of preventive cardiology 24(10): 1017-1031.
11. Da Silva Klahr P, Correa Coronel C, Cabral Robinson C, Fonseca JM, Dias Flores C, et al. (2015) Influence Diagram As a Support Tool for Clinical Decisions In Cardiopulmonary And Metabolic Rehabilitation. Studies in health technology and informatics 216: 290-294.
12. Kong G, Xu DL, Yang JB (2008) Clinical decision support systems: a review on knowledge representation and inference under uncertainties. International Journal of Computational Intelligence Systems 1(2): 159- 167.
13. Seixas FL, Zadrozny B, Laks J, Conci A, Saade DCM (2014) A Bayesian network decision model for supporting the diagnosis of dementia, Alzheimer ׳ s disease and mild cognitive impairment. Computers in biology and medicine 51: 140-158.
14. Pearl J (2009) Probabilistic reasoning in intelligent systems: networks of plausible inference. (2nd Edn.). Morgan Kaufmann publishers, California, USA, pp. 552.
15. Ajay VS, Jindal D, Roy A, Venugopal V, Sharma R, et al. (2016) Development of a Smartphone-Enabled Hypertension and Diabetes Mellitus Management Package to Facilitate Evidence-Based Care Delivery in Primary Healthcare Facilities in India: The mPower Heart Project. Journal of the American Heart Association 5(12): e004343.
16. Smaradottir B, Martinez S, Borycki E, Loudon G, Kushniruk A, et al.