Defining clinical surveillance, Clinical decision support (CDS)

Defining Clinical Surveillance

Guest Blog by Gregg Malkary

Clinical decision support (CDS) and clinical surveillance are often used by clinicians as an interchangeable, catch-all category of human- and technology-based capabilities that allow for the observation of patients for the purposes of ensuring safety and optimal outcomes.1

However, next-generation technological capabilities—advanced analytics, utilization of real-time physiological data, smart alarms and the ability to route that information to remote clinicians—suggests that these terms are distinct, while sharing overlapping attributes.

The Office of the National Coordinator defines CDS as tools that provide “clinicians, staff, patients or other individuals with knowledge and person-specific information, intelligently filtered or presented at appropriate times, to enhance health and health care.”2

Most traditional CDS tools are integrated into the electronic health record (EHR) to “streamline workflows” and deploy effective protocols for clinical guidelines, diagnostic support and “decision-making pathways, although many organizations are still facing significant challenges when it comes to creating intuitive, user-friendly, and effective protocols for alarms, alerts, and decision-making pathways.”3

The realm of clinical surveillance may be seen as a more advanced species of CDS, one that is utilized for specific conditions, such as sepsis or opioid-induced respiratory depression.4

Distinctions with a Difference

In my reporting on trends in clinical surveillance, I highlight four key distinctions between traditional CDS and clinical surveillance.5

  1. Primary purpose. CDS is intended to improve care quality, avoid adverse events such as errors of commission or omission and allow care team members to be more efficient. Clinical surveillance is expected to detect deteriorating patient conditions and/or to provide the ability to determine compliance with protocols.
  2. Clinical workflow. CDS is often linked directly to clinical workflow to facilitate decision-making or action. As such, CDS is often task-oriented and designed to catch a clinician’s attention while performing various processes or tasks. Clinical surveillance continuously runs in background, is not typically linked to a specific workflow and does not impede clinicians’ work.
  3. Data and process orientation. CDS is almost exclusively EHR-centric, but can be generated by standalone CDS systems. Clinical surveillance is systems- and medical device-centric. Data capture and processing occur outside the EHR. However, pertinent data can populate records. Clinical surveillance relies on real-time patient data to ensure timely and accurate detection of deteriorating conditions before emergency escalation is required.
  4. Common issues. With CDS, clinicians often experience alert fatigue resulting from too many spurious—usually technical—notifications. With clinical surveillance, smart alarms communicate contextual patient-safety information and help to minimize non-emergent alerts. Additionally, smart alarm strategies allow for not just the analysis of the alarm signals themselves, but also of the high-fidelity physiological data associated with them, including time trends, cross-parameter correlation, in-depth alarm sensitivity and statistical and predictive analysis.

CDS and Clinical Surveillance Together

It’s critical to call out the fact that the real-time capabilities of clinical surveillance further separates it from more traditional CDS.

When data are not captured and reviewed in real-time, the potential exists for time gaps which can result in the failure to detect significant events that would not normally be visible with variable data collection frequencies.6

Additionally, EHRs store data on patients that are relatively static—history, observations and treatment—rather than moment-to-moment changes, such as heart rate or respiration events. These changes can be quite clinically-significant, but frequently fall outside of the observation window of EHR-captured data.

While EHRs are not repositories for real-time, continuous data, these systems can form the foundation of how most hospitals are approaching clinical surveillance—and make for a natural starting point. Hospitals are fully vested and thinking about how to get more from the EHR.

There is value to augmenting surveillance strategies by adding real-time data captured from patient-connected devices. In my reporting, I note that “hospitals recognize the importance of real-time capabilities to enhance patient safety and improve care quality. Real-time clinical surveillance and analytics solutions can collect and aggregate retrospective data from the EHR, including patient demographics and lab values and correlate it with real-time streaming data, including temperature, heart rate, oxygenation levels, and blood pressure.”7

EHR + Continuous Surveillance = Better Quality of Care

Additionally, analytics based on multiple sources of data also can help offset the problem of alarm fatigue by filtering out false or artifact signals that typically invade the high-fidelity data at the core of continuous surveillance.

Those real-time capabilities can enhance patient safety and improve care quality. This aligns directly with the key performance indicators of the organization, especially as it relates to the Triple Aim of improving patient care, improving population health and reducing healthcare costs.

Moreover, safely surveilling high-risk populations across the enterprise and decreasing utilization of more expensive beds could provide significant cost savings for the institution and a more accurate and timely channel for clinical decision support regarding imminent, tractable problems.8

The Exploration Continues

Through extensive market research, Spyglass believes that CDS is related to clinical surveillance, but clinical surveillance has distinct characteristics. Our latest report as aforementioned also elaborates on the differences of clinical surveillance vs. patient monitoring and also basic vs. advanced clinical surveillance. If this is of interest to you see below.


  1. Malkary G. Healthcare without bounds: trends in clinical surveillance and analytics. Spyglass Consulting Group. March 2018.
  2. Health Clinical decision support. Office of the National Coordinator. Available at:
  3. Bresnick J. Understanding the basic of clinical decision support systems. Health IT Analytics. Available at:
  4. Raths D. What will the next-generation clinical surveillance solution look like? Healthcare Informatics. April 4, 2018. Available at:
  5. Malkary G. Healthcare without bounds: trends in clinical surveillance and analytics. Spyglass Consulting Group. March 2018.
  6. Bernoulli. Continuous clinical surveillance: a business and clinical case for creating the foundation for real-time healthcare. 2018. Available at
  7. Malkary G. Healthcare without bounds: trends in clinical surveillance and analytics. Spyglass Consulting Group. March 2018.
  8. Moss TJ, Clark MT, Calland JF, Enfield KB, Voss JD, Lake DE, Moorman JR. Cardiorespiratory dynamics measured from continuous ECG monitoring improves detection of deterioration in acute care patients: A retrospective cohort study. PLOSOne. August 3, 2017.

About the Author:
Gregg Malkary is the Founder and Managing Director of the Spyglass Consulting Group

Gregg Malkary,
Managing Director
Spyglass Consulting Group

About Spyglass Consulting Group

Spyglass Consulting Group is a leading market intelligence and strategy firm focused exclusively on the healthcare industry.  Based in Menlo Park, CA, the firm provides thought leadership, market coverage, and insights for the most transformative sectors of healthcare IT including point of care computing/communications, patient engagement, healthcare analytics and remote patient monitoring.  Spyglass clients include more than 200 leading technology companies, management consulting firms, healthcare provider organizations, and the investment community.

Gregg Malkary is the Founder and Managing Director of the Spyglass Consulting Group. This blog post was based in part on his report Healthcare without Bounds: Trends in Clinical Surveillance and Analytics, which can be ordered here.