This website is intended for healthcare professionals only.

Hospital Healthcare Europe
Hospital Healthcare Europe

Press Releases

Take a look at a selection of our recent media coverage:

Pharmacist sepsis notification system improves patient outcomes

13th September 2021

A sepsis notification system contained within electronic health records monitored by pharmacists significantly improved patient outcomes.

Sepsis is a life-threatening organ dysfunction response to infection which, according to the World Health Organization, in 2017, affected 48.9 million people and caused 11 million sepsis-related deaths. The early administration of broad-spectrum antibiotics is associated with a reduced progression to severe sepsis and septic shock and a lower mortality. These findings have prompted the development of several automated rule-based sepsis notification systems which have been combined with alerting systems. In a review of studies, it was concluded that digital sepsis alerting systems, reduce both hospital and intensive care unit stays for patients with sepsis. The incorporation of sepsis notification systems within electronic health records (EHRs), providing a real-time alert, could therefore lead to improvements in patient outcomes although recent trial concluded that this was not the case.

Whether sepsis notification systems incorporated into EHRs and monitored by an emergency department pharmacist could improve patient outcomes was the subject of a study by a team from the Division of Pulmonary and Critical Care Medicine, MetroHealth Medical Centre, Cleveland, Ohio, US.

The team incorporated a sepsis alert within with the EHR and randomised patients admitted to hospital with suspected sepsis to either standard care or augmented care (intervention group) in which the sepsis early-warning system (EWS) was visible and monitored by an emergency department pharmacist. Once the sepsis EWS score crossed over the established threshold, an alert occurred, triggering a flag that was displayed on the patient emergency department tracking tool and a message to the EHR system which was monitored by an emergency department pharmacist. Once an alert was raised, the pharmacist ordered appropriate blood tests, antibiotics and fluid boluses for the patient. The primary outcome measure was time to antibiotics from arrival and the primary clinical outcome score was a composite of days alive and out of hospital, 28 days after arrival.

A total of 598 patients were included over a 5-month period and randomised to standard care (313) or intervention. The median age of participants ranged from 62.3 (standard care) to 61.5 (intervention group) years with the proportion of females ranging from 46% to 51.2%, standard care and intervention group respectively. Among those assigned to the intervention arm, the time to antibiotic administration from emergency department arrival was 2.3 hours compared with 3 hours in the standard care group (p = 0.039). In addition, the clinical primary outcome score was also higher for the intervention, reflecting better outcomes (median 24.1 vs 22.5 days, p = 0.011). However, the length of stay between groups was not significantly different (p = 0.124) and neither was hospital mortality (p = 0.086).

In their discussion, the authors noted how their results showed only a slightly modest improvement from the intervention. The study was designed as a quality improvement initiative to compare whether visibility of the sepsis notification systems by both clinicians and pharmacists improved outcomes. They concluded that further studies are needed to determine if their approach is generalisable to other healthcare settings.

Tarabichi Y et al. Improving Timeliness of Antibiotic Administration Using a Provider and Pharmacist Facing Sepsis Early Warning System in the Emergency Department Setting: A randomised Controlled Quality Improvement Initiative. Crit Care Med 2021.

Machine learning model predictive of mortality in sepsis

26th July 2021

In patients with sepsis, the use of a machine learning algorithm identified six variables that were predictive of 7- and 30-day mortality.

Sepsis can be defined as is a life-threatening organ dysfunction caused by a dysregulated host response to infection. Furthermore, sepsis is responsible for around 11 million deaths each year, which amounts to approximately 20% of all global deaths. Thus, it is crucial that clinicians have a comprehensive understanding of all the relevant clinical factors that can help with the early identification of those patients for whom a poor outcome is likely. This is particularly important since early use of crystalloid therapy reduces mortality, as does prompt administration of antibiotics. Though several scoring systems for sepsis are available, these are based on the assessment of vital signs but which can sometimes be normal upon admission to an emergency department. While machine learning has been shown to have some level of predictive power for mortality, none of the variables currently used in these models are reflective of the symptoms at first presentation. This led a team from the Department of Medical Sciences, Orebro University, Sweden, to use machine learning in an attempt to identify the variables which were predictive of 7- and 30-day mortality in sepsis patients, based on the clinical presentation at an emergency department. They employed a retrospective design and included patients 18 years and older, admitted to hospital with suspected sepsis. The team input previously identified variables, e.g., abnormal temperature, acute altered mental status, etc into the machine learning algorithm. The sensitivity and specificity of the predictive models generated by the machine learning model, were calculated from the area under the receiver operating curve (AUC).

A total of 445 patients with sepsis and a median age of 73 years (52.6% male) were included in the retrospective analysis. Overall, 234 (49.7%) had severe sepsis and 63 patients died within 7-days of admission and 98 within 30 days. The accuracy of the 7-day predictive model was maximal after the inclusion of only six variables; fever, abnormal verbal response, low oxygen saturation, arrival by emergency services, abnormal behaviour/level of consciousness and chills. Using these variables, the AUC sensitivity was 0.84 (95 CI 0.78–0.89) and the specificity 0.67 (95% CI 0.64 –0.70). For the prediction of 30-day mortality, again, only 6 variables were significant; abnormal verbal response, fever, chills, arrival by emergency services, low oxygen saturation and breathing difficulties. This model gave a sensitivity of 0.87 (95% CI 0.81–0.93) and a specificity of 0.64 (95% CI 0.61–0.67).

In discussing their findings, the authors highlighted how their results revealed the importance of the using a clinical symptom complex that was representative of what an emergency department clinician would be likely to encounter in practice. They also suggested that the 7-day model might be of more use in practice since it would be of assistance to emergency care staff for the likely short-term outcome for patients. They concluded that given how the clinical presentation of sepsis can often be non-specific, the use of a machine learning algorithm, based on symptoms and observations, would be most helpful to staff and that future work should focus on validating the method in other cohorts.

Karlsson A et al. Predicting mortality among septic patients presenting to the emergency department– a cross sectional analysis using machine learning. BMC Emerg Med 2021