Although hospitals and health systems do not closely track medical errors and misdiagnoses, these issues have begun to receive serious scrutiny. Evidence points to the need for immediate improvement in uniformity of care quality.
This past May, BMJ published a report estimating that medical error is the third-leading cause of death in the United States, responsible for more than 400,000 deaths per year.1 In a related finding, the National Academies of Sciences, Engineering and Medicine (NASEM) reported that diagnostic errors contribute to approximately 10 percent of U.S. patient deaths and account for up to 17 percent of hospital adverse events. In recommending solutions, NASEM observed that, "A number of studies have shown that clinical decision support systems can improve the rates of certain desirable clinician behaviors such as appropriate test ordering, disease management, and patient care."2 With this thought in mind, it's time to accelerate the application of these systems.
How CDS provides clinical insight
Today's clinical decision support (CDS) systems run on top of EMRs and issue alerts to help guide diagnosis and care processes when they detect an oncoming medical error or misdiagnosis. These tools are not meant to supersede a clinician's expertise, but rather make real-time suggestions, based on information that is not readily apparent in point-of-care examinations, for a different course of action than the clinician is currently documenting. They can do this in two ways.
First, advanced CDS systems operate on a more complete clinical picture of the patient than can be derived from observation or from an EMR's structured data. It supplements that information by extracting clinical details buried in EMR free text and non-EMR data in information systems, such as those found in labs and radiology departments. Having assembled a comprehensive view of the patient's medical history and current condition, CDS then monitors clinical documentation entries and applies rules-based analysis in comparing them to relevant clinical details. When the CDS system detects a high probability of medical error or misdiagnosis, it displays an alert in an EMR pop-up window.
Secondly, CDS systems tap into their own libraries of evidence-based best practices, which typically can be expanded to include the hospital or health system's published clinical guidelines. When the system detects a deviation from best practices or guidelines, it issues an alert, just as it does when comparing documentation with clinical details.
In all cases, alerts are logged and assembled into reports that show alert adherence. These reports give clinical leadership insight into which clinicians are ignoring alerts, so they can determine when clinicians need to improve adherence and when the system should be fine-tuned to make alerts more useful.
How CDS delivers value
If the CDS system is accurate, it will actually produce fewer alerts. It should not alert clinicians to details of which they already know or prompt for action that is simply not yet taken, as either contributes to alert fatigue. Additionally, the CDS system shouldn't issue erroneous alerts, which would further cause clinicians to ignore it altogether.
A thoroughly accurate system will know when a medical error is about to occur or a misdiagnosis is likely underway, and issue alerts that clinicians are willing to receive. Examples of the types of most helpful alerts typically encountered with CDS systems include:
• Alerting to silent deterioration. CDS can detect developing, serious conditions more quickly than unassisted observation. By continuously monitoring a patient, CDS can detect initial signs of deterioration – such as slowly rising white blood cell counts revealed in a lab test paired with the beginning of fever and hypotension – and alert to the possibility of sepsis and the immediate need for intervention.
• Improving the use of imaging. If a patient presents with dizziness, clinical guidelines may direct clinicians to order a CT scan to rule out stroke. If the patient is actually having a stroke, the best course would be to order an MRI. Yet ordering MRIs to rule out stroke in all cases would greatly increase instances of medically unnecessary imaging. CDS can align resources by suggesting MRIs only for patients with overall clinical indications of higher stroke risk, encouraging the optimal imaging order while reducing unnecessary CT scans.
• Speeding accuracy under pressure. When an ER patient presents with symptoms of pulmonary embolism (PE), clinicians will begin to quickly prepare the patient for a lung scan. As they do, the CDS system can calculate PE risk based on presentation details and recent lab results while weighing data regarding other potential conditions. If data indicate a low PE risk but a high risk of myocardial infarction (MI), the CDS system can alert clinicians to order a non-invasive blood test to rule out PE while further investigating the possibility of a heart attack.
These are just a few ways in which CDS can improve clinicians' ability to avoid medical errors and misdiagnoses, though ultimate responsibility rests with the clinician. But as a way to bolster the science portion of the blend of art and science that is the physician's unique craft, CDS promises to assist greatly in fundamental care improvements.
1 BMJ, 2016;353:i2139. Medical error – the third leading cause of death in the U.S.
2 National Academies of Sciences, Engineering, and Medicine, 2015. Improving diagnosis in health care. Washington, DC: The National Academies Press.
The views, opinions and positions expressed within these guest posts are those of the author alone and do not represent those of Becker's Hospital Review/Becker's Healthcare. The accuracy, completeness and validity of any statements made within this article are not guaranteed. We accept no liability for any errors, omissions or representations. The copyright of this content belongs to the author and any liability with regards to infringement of intellectual property rights remains with them.