Prehospital Early Warning Scores to Predict Mortality in Patients Using Ambulances

IMPORTANCE

Early warning scores (EWSs) are designed for in-hospital use but are widely used in the prehospital field, especially in select groups of patients potentially at high risk. To be useful for paramedics in daily prehospital clinical practice, evaluations are needed of the predictive value of EWSs based on first measured vital signs on scene in large cohorts covering unselected patients using ambulance services.

OBJECTIVE

To validate EWSs' ability to predict mortality and intensive care unit (ICU) stay in an unselected cohort of adult patients who used ambulances.

DESIGN, SETTING, AND PARTICIPANTS

This prognostic study conducted a validation based on a cohort of adult patients (aged ≥18 years) who used ambulances in the North Denmark Region from July 1, 2016, to December 31, 2020. EWSs (National Early Warning Score 2 [NEWS2], modified NEWS score without temperature [mNEWS], Quick Sepsis Related Organ Failure Assessment [qSOFA], Rapid Emergency Triage and Treatment System [RETTS], and Danish Emergency Process Triage [DEPT]) were calculated using first vital signs measured by ambulance personnel. Data were analyzed from September 2022 through May 2023.

MAIN OUTCOMES AND MEASURES

The primary outcome was 30-day-mortality. Secondary outcomes were 1-day-mortality and ICU admission. Discrimination was assessed using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC).

RESULTS

There were 107 569 unique patients (52 650 females [48.9%]; median [IQR] age, 65 [45-77] years) from the entire cohort of 219 323 patients who used ambulance services, among whom 119 992 patients (54.7%) had called the Danish national emergency number. NEWS2, mNEWS, RETTS, and DEPT performed similarly concerning 30-day mortality (AUROC range, 0.67 [95% CI, 0.66-0.68] for DEPT to 0.68 [95% CI, 0.68-0.69] for mNEWS), while qSOFA had lower performance (AUROC, 0.59 [95% CI, 0.59-0.60]; P vs other scores < .001). All EWSs had low AUPRCs, ranging from 0.09 (95% CI, 0.09-0.09) for qSOFA to 0.14 (95% CI, 0.13-0.14) for mNEWS.. Concerning 1-day mortality and ICU admission NEWS2, mNEWS, RETTS, and DEPT performed similarly, with AUROCs ranging from 0.72 (95% CI, 0.71-0.73) for RETTS to 0.75 (95% CI, 0.74-0.76) for DEPT in 1-day mortality and 0.66 (95% CI, 0.65-0.67) for RETTS to 0.68 (95% CI, 0.67-0.69) for mNEWS in ICU admission, and all EWSs had low AUPRCs. These ranged from 0.02 (95% CI, 0.02-0.03) for qSOFA to 0.04 (95% CI, 0.04-0.04) for DEPT in 1-day mortality and 0.03 (95% CI, 0.03-0.03) for qSOFA to 0.05 (95% CI, 0.04-0.05) for DEPT in ICU admission.

CONCLUSIONS AND RELEVANCE

This study found that EWSs in daily clinical use in emergency medical settings performed moderately in the prehospital field among unselected patients who used ambulances when assessed based on initial measurements of vital signs. These findings suggest the need of appropriate triage and early identification of patients at low and high risk with new and better EWSs also suitable for prehospital use.

Predicting sepsis onset using a machine learned causal probabilistic network algorithm based on electronic health records data

Sepsis is a leading cause of mortality and early identification improves survival. With increasing digitalization of health care data automated sepsis prediction models hold promise to aid in prompt recognition. Most previous studies have focused on the intensive care unit (ICU) setting. Yet only a small proportion of sepsis develops in the ICU and there is an apparent clinical benefit to identify patients earlier in the disease trajectory. In this cohort of 82,852 hospital admissions and 8038 sepsis episodes classified according to the Sepsis-3 criteria, we demonstrate that a machine learned score can predict sepsis onset within 48 h using sparse routine electronic health record data outside the ICU. Our score was based on a causal probabilistic network model-SepsisFinder-which has similarities with clinical reasoning. A prediction was generated hourly on all admissions, providing a new variable was registered. Compared to the National Early Warning Score (NEWS2), which is an established method to identify sepsis, the SepsisFinder triggered earlier and had a higher area under receiver operating characteristic curve (AUROC) (0.950 vs. 0.872), as well as area under precision-recall curve (APR) (0.189 vs. 0.149). A machine learning comparator based on a gradient-boosting decision tree model had similar AUROC (0.949) and higher APR (0.239) than SepsisFinder but triggered later than both NEWS2 and SepsisFinder. The precision of SepsisFinder increased if screening was restricted to the earlier admission period and in episodes with bloodstream infection. Furthermore, the SepsisFinder signaled median 5.5 h prior to antibiotic administration. Identifying a high-risk population with this method could be used to tailor clinical interventions and improve patient care.

Machine-Learning Model for Mortality Prediction in Patients With Community-Acquired Pneumonia: Development and Validation Study

BACKGROUND

Artificial intelligence tools and techniques such as machine learning (ML) are increasingly seen as a suitable manner in which to increase the prediction capacity of currently available clinical tools, including prognostic scores. However, studies evaluating the efficacy of ML methods in enhancing the predictive capacity of existing scores for community-acquired pneumonia (CAP) are limited. We aimed to apply and validate a causal probabilistic network (CPN) model to predict mortality in patients with CAP.

RESEARCH QUESTION

Is a CPN model able to predict mortality in patients with CAP better than the commonly used severity scores?

STUDY DESIGN AND METHODS

This was a derivation-validation retrospective study conducted in two Spanish university hospitals. The ability of a CPN designed to predict mortality in sepsis (SepsisFinder [SeF]), and adapted for CAP (SeF-ML), to predict 30-day mortality was assessed and compared with other scoring systems (Pneumonia Severity Index [PSI], Sequential Organ Failure Assessment [SOFA], quick Sequential Organ Failure Assessment [qSOFA], and CURB-65 criteria [confusion, urea, respiratory rate, BP, age ≥ 65 years]). The SeF models are proprietary software. Differences between receiver operating characteristic curves were assessed by the DeLong method for correlated receiver operating characteristic curves.

RESULTS

The derivation cohort comprised 4,531 patients, and the validation cohort consisted of 1,034 patients. In the derivation cohort, the areas under the curve (AUCs) of SeF-ML, CURB-65, SOFA, PSI, and qSOFA were 0.801, 0.759, 0.671, 0.799, and 0.642, respectively, for 30-day mortality prediction. In the validation study, the AUC of SeF-ML was 0.826, concordant with the AUC (0.801) in the derivation data (P = .51). The AUC of SeF-ML was significantly higher than those of CURB-65 (0.764; P = .03) and qSOFA (0.729, P = .005). However, it did not differ significantly from those of PSI (0.830; P = .92) and SOFA (0.771; P = .14).

INTERPRETATION

SeF-ML shows potential for improving mortality prediction among patients with CAP, using structured health data. Additional external validation studies should be conducted to support generalizability.

Validation of automated sepsis surveillance based on the Sepsis-3 clinical criteria against physician record review in a general hospital population: observational study using electronic health records data

BACKGROUND

Surveillance of sepsis incidence is important for directing resources and evaluating quality-of-care interventions. The aim was to develop and validate a fully-automated Sepsis-3 based surveillance system in non-intensive care wards using electronic health record (EHR) data, and demonstrate utility by determining the burden of hospital-onset sepsis and variations between wards.

METHODS

A rule-based algorithm was developed using EHR data from a cohort of all adult patients admitted at an academic centre between July 2012 and December 2013. Time in intensive care units was censored. To validate algorithm performance, a stratified random sample of 1000 hospital admissions (674 with and 326 without suspected infection) was classified according to the Sepsis-3 clinical criteria (suspected infection defined as having any culture taken and at least two doses of antimicrobials administered, and an increase in Sequential Organ Failure Assessment (SOFA) score by >2 points) and the likelihood of infection by physician medical record review.

RESULTS

In total 82 653 hospital admissions were included. The Sepsis-3 clinical criteria determined by physician review were met in 343 of 1000 episodes. Among them, 313 (91%) had possible, probable or definite infection. Based on this reference, the algorithm achieved sensitivity 0.887 (95% CI: 0.799 to 0.964), specificity 0.985 (95% CI: 0.978 to 0.991), positive predictive value 0.881 (95% CI: 0.833 to 0.926) and negative predictive value 0.986 (95% CI: 0.973 to 0.996). When applied to the total cohort taking into account the sampling proportions of those with and without suspected infection, the algorithm identified 8599 (10.4%) sepsis episodes. The burden of hospital-onset sepsis (>48 hour after admission) and related in-hospital mortality varied between wards.

CONCLUSIONS

A fully-automated Sepsis-3 based surveillance algorithm using EHR data performed well compared with physician medical record review in non-intensive care wards, and exposed variations in hospital-onset sepsis incidence between wards.

A model of perfusion of the healthy human lung

This study presents a model that simulates the pulmonary capillary perfusion. The model describes the lungs as divided into horizontal layers and includes: capillary geometry; capillary wall elasticity; pressure at the pulmonary artery; blood viscosity; the effect of the chest wall; the change in lung height and hydrostatic effects of the lung tissue and of the blood during breathing. The model simulates pulsatile blood perfusion with an increasing blood distribution down the lungs, in agreement with previous experimental studies. Moreover the model is in agreement with experimentally measured total capillary perfusion, total capillary volume, total capillary surface area and transition time of red blood cells passing through the pulmonary capillary network. The presented model is the first to be validated against the mentioned experimental data and to model the link between airway pressure, lung volume and perfusion.

A model of ventilation of the healthy human lung

This paper presents a model of the lung mechanics which simulates the pulmonary alveolar ventilation. The model includes aspects of: the alveolar geometry; pressure due to the chest wall; pressure due to surface tension determined by surfactant activity; pressure due to lung tissue elasticity; and pressure due to the hydrostatic effects of the lung tissue and blood. The cross-sectional area of the lungs in the supine position derived from computed tomography is used to construct a horizontally layered model, which simulates heterogeneous ventilation distribution from the non-dependent to the dependent layers of the lungs. The model is in agreement with experimentally measured hysteresis of the pressure-volume curve of the lungs, static lung compliance, changes in lung depth during breathing and density distributions at total lung capacity (TLC) and residual volume (RV). In the dependent layers of the lungs, alveolar collapse may occur at RV, depending on the assumptions concerning lung tissue elasticity at very low alveolar volumes. The model simulations showed that ventilation increased with depth in the lungs, although not as pronounced as observed experimentally. The model simulates alveolar ventilation including all of the mentioned components of the respiratory system and to be validated against all the above mentioned experimental data.

Comparison between the degree of motor unit short-term synchronization and recurrence quantification analysis of the surface EMG in two human muscles

OBJECTIVE

To verify if non-linear recurrence analysis of the surface EMG is a suitable tool for assessing motor unit short-term synchronization.

METHODS

Surface and intramuscular EMG signals were recorded from the abductor digiti minimi and vastus medialis muscles of 12 and 10 healthy men, respectively, during isometric contractions. In the abductor digiti minimi, EMG signals were additionally recorded after a contraction sustained for 1min at 50% of the maximal force. In both muscles, percent of determinism (%DET) was estimated from the surface EMG and common input strength (CIS) index was computed from motor unit recordings.

RESULTS

For both muscles, CIS did not correlate with %DET (abductor digiti minimi: R(2)=0.11, P=0.12; vastus medialis: R(2)=0.04, P=0.56). Although the values of CIS for the vastus medialis were lower than those of the abductor digiti minimi (P<0.001), the %DET values did not differ between the two muscles (71.6+/-5.5% vs 66.9+/-8.7%; P=0.12).

CONCLUSION

The variable %DET extracted from the surface EMG is a poor indicator of the degree of motor unit short-term synchronization.

SIGNIFICANCE

The study provides a systematic evaluation of a technique previously proposed for the estimation of a clinically relevant characteristic of motor unit behavior.

A physiological model of the effect of hypoglycemia on plasma potassium

BACKGROUND

Adrenaline release and excess insulin during hypoglycemia stimulate the uptake of potassium from the bloodstream, causing low plasma potassium (hypokalemia). Hypokalemia has a profound effect on the heart and is associated with an increased risk of malignant cardiac arrhythmias. It is the aim of this study to develop a physiological model of potassium changes during hypoglycemia to better understand the effect of hypoglycemia on plasma potassium.

METHOD

Potassium counterregulation to hypokalemia was modeled as a linear function dependent on the absolute potassium level. An insulin-induced uptake of potassium was modeled using a negative exponential function, and an adrenaline-induced uptake of potassium was modeled as a linear function. Functional expressions for the three components were found using published data.

RESULTS

The performance of the model was evaluated by simulating plasma potassium from three published studies. Simulations were done using measured levels of adrenaline and insulin. The mean root mean squared error (RMSE) of simulating plasma potassium from the three studies was 0.09 mmol/liter, and the mean normalized RMSE was 14%. The mean difference between nadirs in simulated and measured potassium was 0.12 mmol/liter.

CONCLUSIONS

The presented model simulated plasma potassium with good accuracy in a wide range of clinical settings. The limited number of hypoglycemic episodes in the test set necessitates further tests to substantiate the ability of the model to simulate potassium during hypoglycemia. In conclusion, the model is a good first step toward better understanding of changes in plasma potassium during hypoglycemia.