- A pair of clinical informaticist consultants found clinical decision support (CDS) systems to have a positive impact on identifying instances of sepsis and reducing sepsis mortality at an Alabama hospital.
According to the research published in the Journal of the American Medical Informatics Association, the combination of a computerized surveillance algorithm and CDS tools amounted to 53 percent fewer deaths per 1000 cases (i.e., 40 deaths) as compared to the control group with 90 deaths per 1000 cases. When identifying sepsis identification more widely using IDC-9 codes, the former figure dropped to a still significant 41 percent lower mortality.
"We believe that the highly accurate alerts (sensitive and specific) in the system designed for this study minimized alert fatigue, allowing optimal clinician utilization of the system, and, when combined with the timely detection of sepsis allowed by the system, resulted in the positive outcome of significantly reduced sepsis mortality in the study population," concluded Sharad Manaktala and Stephen Claypool of Wolters Kluwer Health.
The real-time electronic surveillance of sepsis went live in two units of Huntsville Hopsital back in 2014. As the authors described, the system includes four different types of alert notifications for clinical staff.
The first provided information prompts for certain conditions (e.g., isolated tachycardia, isolated hypothermia). The second comprised diagnostic alerts for new positive sepsis screening results or indications of worsening sepsis for previously screen patients. The third category of alerts offered advice on evidence-based care sepsis care. Lastly, the four set of alerts reminded staff to acknowledge and comply with recommended treatment plans.
As part of the sepsis surveillance system, nurses were responsible for alerting physicians about patients with sepsis diagnoses.
The algorithms used as part of the surveillance had their roots based in work by both the Office of the National Coordinator for Health Information Technology (ONC) and Health Information Management Systems Society (HIMSS) for CDS implementation, which required adjustments to EMR data, namely clinical documentation.
Improvement accuracy in identifying cases of sepsis was another benefit of the computerized approach at Huntsville.
"The electronic system had excellent accuracy for detecting sepsis or severe sepsis, with sensitivity of 95% for sepsis cases and 82% specificity, compared to the gold standard of physician chart review," wrote Manaktala & Claypool.
The authors credited the sophistication of the CDS system at the Alabaman hospital with demonstrating clear improvements over previous attempts at the same end.
"The sepsis screening algorithms used in the current study were based on standard IHI guidelines," they claimed. "However, these algorithms also contained additional specifications to adjust for comorbid medical conditions and medications. We believe that the complexity of the system’s algorithms are responsible for its high sensitivity and high specificity and are key contributors to the impressive outcomes reported in our results."
Likewise, the system avoided the pitfalls of alert fatigue previously associated with electronic surveillance systems.
"Previous electronic surveillance systems have either had issues with high alert fatigue, when they have been successful in detecting sepsis (high sensitivity with low specificity), or have had modest alert fatigue, but missed a significant number of sepsis cases (high specificity, low sensitivity)," Manaktala & Claypool continued. "Likely as a result of this, previously published electronic surveillance systems have not been shown to have a significant impact on mortality."
Underpinning the improvements at Huntsville were the use of four metrics:
Sepsis mortality was reduced in the study group, based on four assessments: (1) measuring sepsis prevalence and mortality using ICD-9 codes for sepsis; (2) calculating sepsis mortality over a period of time; (3) calculating sepsis prevalence and mortality using Angus implementation criteria; and (4) measuring sepsis mortality after adjusting for patient-level parameters.
According to the authors, the timeliness of clinical responses to sepsis diagnoses was the deciding factor in preventing sepsis mortality.