It is impossible for clinicians to stay up to date with the medical literature in all but the narrowest fields of medicine (Etheredge 2015). This contributes to wide variations in practice between clinicians and regions. Clinical decision support systems (CDSSs) have been proposed as one potential remedy to this problem.
A clinical decision support system has been defined as “an electronic system designed to aid directly in clinical decision making, in which characteristics of individual patients are used to generate patient-specific assessments or recommendations that are then presented to clinicians for consideration.” (Kawamoto, Houlihan et al. 2005). Patient facing decision support systems are also available (Walsh, Barr et al. 2014).
There are conflicting accounts regarding the success of existing systems, but a recent systematic review concluded that, across clinical settings, new generation CDSSs integrated with EHRs do not affect mortality, might moderately improve morbidity outcomes and had only a small impact on cost (Moja, Kwag et al. 2014). Other studies have had more positive findings (Schedlbauer, Prasad et al. 2009)
Participants acknowledged that existing systems have had mixed results (Etheredge 2015), but expressed optimism about the potential for future systems. As the amount of genetic, social and monitoring data relating to each patient increases, it will become more difficult for clinicians to weigh it systematically, without the help of electronic systems (Etheredge 2015, Wallace 2015).
There is increasing interest in the field. For example, The American Society for Clinical Oncology (ASCO) aim to roll out decision support tools for breast cancer this year (Etheredge 2015). If successful examples can be demonstrated, then these tools could become widespread (Etheredge 2015).
There is an appetite for machine readable guidelines that can be consumed by a Learning Healthcare System and can drive decision support systems (Friedman 2015). They could also be compared against routinely collected data retrospectively, to assess whether patients have been treated in line with best practice.
OpenClinical.net, a collaboration between University College London, Oxford University and Deontics Ltd., aims to create and maintain an open access and open source repository of medical knowledge in a machine readable format. Currently OpenClinical content makes use of the PROforma process modelling language to facilitate the creation of machine readable clinical guidelines (Fox 2015)
Novel decision support systems could be developed more rapidly if NICE and other guideline writing organisations produced machine readable guidelines alongside their human readable equivalents (Foley and Fairmichael 2015)
Such systems will be more successful if they preserve the physician’s role in forming a relationship with the patient and sharing the decision-making (Wallace 2015). “Decision directive” tools will not work, but “decision supportive” tools would be more likely to be successful and more acceptable to physicians (Participant41 2015).
“Doctors don’t go to university to be told by a computer what to do … would you use you satnav to tell you how to drive to work every day?” that is the equivalent of “if you see someone with conjunctivitis, do you need guidance to give fucithalmic? … Experience has told us that physicians do not want the paperclip popping up giving this information.” (O’Hanlon 2015)
What is needed is something with more understanding, that can help guide more complicated cases, for example patients with complex comorbidities and social problems. These are the biggest burden on resources and the source of more frequent mistakes, as physicians may not have considered all of the complexities. These should not just be solely decision support but should help structure a care plan that involves the MDT, which would lead to better clinical outcomes (O’Hanlon 2015).
Geisinger Health System have combined decision support with automation and integrated it into their EHR, so that the system uses the patient’s problem list to pre-prepare tasks and orders, in line with best practice standards, ahead of the consultation. The aim is, “making the right thing, the easy thing to do.” (Foley and Fairmichael 2015)
Ultimately, Clinical Decision Support Systems will be appropriate for changing clinician behaviour in a certain set of situations. The decision to employ such a solution should be arrived at following an analysis of the situation that is conducted within an evidence-based behaviour change framework, as discussed previously.
Making any decision relies on a combination of information and preferences. The information may be objective, but the preferences are subjective and involve values, so they should be exposed to the user (Lewis 2011). To ensure meaningful shared decision-making, the patient should be able to adjust the preferences within a clinical decision support system.
Effectiveness of Computerized Decision Support Systems Linked to Electronic Health Records: A Systematic Review and Meta-Analysis
Undetermined impact of patient decision support interventions on healthcare costs and savings: systematic review
Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success.