Clinical decision support systems (CDSS) are vital to the modern healthcare system. They improve quality of care and lower costs by integrating information and preventing physicians from experiencing information overload. Here, we will introduce the modalities of CDSS and what makes them effective.
Passive Notation: Passive Notation is a flag or marker that is automatically incorporated into a patient's electronic health record. Since it is automatic, no additional work is needed. This modality also doesn’t interrupt workflow. However, this makes it ineffective during emergencies when actions need to be triggered and staff need to be notified.
Dashboard/Website Based: This feature allows staff to see the latest information about the patient and the information is always accessible. The information is also often displayed in a graphical or summary table format, making trends easy to notice. Further, this modality can also include suggestion of actions to be taken. Drawbacks to this modality include the need to constantly check for updates, staff monitoring, and the need to for staff to send alerts.
Pager or Text: This feature allows alerts to be sent to patient staff about patient status. This modality is automatic, it can include suggestions of decisions, and can contain detailed information. In emergency situations it can also trigger a response. This system, however, has the potential to interrupt workflow and can lead to alert fatigue. With this approach, it important to make sure the alerts are being sent out to the correct staff.
Bedside Alert: This is a bedside audio alarm alone and it may graphically display patient information. If there is a graphical display, there may be recommendations for action and a clear display of trends and medical history. Since it is a bedside audio alarm, it requires staff to walk to the bedside to disable the alert, and thus increases the chance that patients are evaluated but at a cost of interrupting workflow.
What makes Clinical Decision Support Tools effective?
Meta-analysis studies of clinical decision tools have found that certain features should be included in CDSS to make them effective. In one study conducted in 2005, it was found that CDDS should, “(a) provide decision support, (b) deliver decision support at the time and location of decision making, (c) provide actionable recommendations, and (d) use a computer to generate the decision support.” All these features allow for easy use of CDDS. For example, by using a computer to generate decision support, physicians don’t have to go through the tedious process of recording information into charts.
In a study published in 2012, nine features were found to be correlated with the success of CDSS:
- Automatic provision of decision support as part of clinician workflow
- Provision of recommendations rather than just assessments
- Provision of decision support at the time and location of decision making
- Computer based decision support
- Require practitioners to provide reasons when over-riding advice
- Provide advice concurrently to patients and practitioners
- No need for additional clinician data entry
- Justification of decision support via research evidence
- Local user involvement in development or customization
CDSS are powerful tools that, when used right, can have a positive impact on the healthcare system.