Treatments costs associated with inpatient clinical deterioration

Patient outcomes following medical emergency team review on general wards: Development of predictive models

AIM

To develop and internally validate risk prediction models for subsequent clinical deterioration, unplanned ICU admission and death among ward patients following medical emergency team (MET) review.

DESIGN

A retrospective cohort study of 1500 patients who remained on a general ward following MET review at an Australian quaternary hospital.

METHOD

Logistic regression was used to model (1) subsequent MET review within 48 h, (2) unplanned ICU admission within 48 h and (3) hospital mortality. Models included demographic, clinical and illness severity variables. Model performance was evaluated using discrimination and calibration with optimism-corrected bootstrapped estimates. Findings are reported using the TRIPOD guideline for multivariable prediction models for prognosis or diagnosis. There was no patient or public involvement in the development and conduct of this study.

RESULTS

Within 48 h of index MET review, 8.3% (n = 125) of patients had a subsequent MET review, 7.2% (n = 108) had an unplanned ICU admission and in-hospital mortality was 16% (n = 240). From clinically preselected predictors, models retained age, sex, comorbidity, resuscitation limitation, acuity-dependency profile, MET activation triggers and whether the patient was within 24 h of hospital admission, ICU discharge or surgery. Models for subsequent MET review, unplanned ICU admission, and death had adequate accuracy in development and bootstrapped validation samples.

CONCLUSION

Patients requiring MET review demonstrate complex clinical characteristics and the majority remain on the ward after review for deterioration. A risk score could be used to identify patients at risk of poor outcomes after MET review and support general ward clinical decision-making.

RELEVANCE TO CLINICAL PRACTICE

Our risk calculator estimates risk for patient outcomes following MET review using clinical data available at the bedside. Future validation and implementation could support evidence-informed team communication and patient placement decisions.

An economic evaluation of the Prioritising Responses Of Nurses To deteriorating patient Observations (PRONTO) clinical trial

BACKGROUND

Early recognition and response to clinical deterioration reduce the frequency of in-hospital cardiac arrests, mortality, and unplanned intensive care unit (ICU) admissions. This study aimed to investigate the impact of the Prioritising Responses Of Nurses To deteriorating patient Observations (PRONTO) intervention on hospital costs and patient length of stay (LOS).

METHOD

The PRONTO cluster randomised control trial was conducted to improve nurses' responses to patients with abnormal vital signs. Hospital data were collected pre-intervention (T0) at 6 months (T1) and 12 months (T2) post-intervention. The economic evaluation involved a cost-consequence analysis from the hospital's perspective. Generalised estimating equations were used to estimate the parameters for regression models of the difference in costs and LOS between study groups and time points.

RESULTS

Hospital admission data for 6065 patients (intervention group, 3102; control group, 2963) were collected from four hospitals for T0, T1 and T2. The intervention cost was 69.61 A$ per admitted patient, including the additional intervention training for nurses and associated labour costs. The results showed cost savings and a shorter LOS in the intervention group between T0 - T1 and T0 - T2 (cost differences T0 - T1: -364 (95% CI -3,782; 3049) A$ and T0 - T2: -1,710 (95% CI -5,162; 1,742) A$; and LOS differences T0 - T1: -1.10 (95% CI -2.44; 0.24) days and T0 & T2: -2.18 (95% CI -3.53; -0.82) days).

CONCLUSION

The results of the economic analysis demonstrated that the PRONTO intervention improved nurses' responses to patients with abnormal vital signs and significantly reduced hospital LOS by two days at 12 months in the intervention group compared to baseline. From the hospital's perspective, savings from reduced hospitalisations offset the costs of implementing PRONTO.

Real-Time Machine Learning Alerts to Prevent Escalation of Care: A Nonrandomized Clustered Pragmatic Clinical Trial

OBJECTIVES

Machine learning algorithms can outperform older methods in predicting clinical deterioration, but rigorous prospective data on their real-world efficacy are limited. We hypothesized that real-time machine learning generated alerts sent directly to front-line providers would reduce escalations.

DESIGN

Single-center prospective pragmatic nonrandomized clustered clinical trial.

SETTING

Academic tertiary care medical center.

PATIENTS

Adult patients admitted to four medical-surgical units. Assignment to intervention or control arms was determined by initial unit admission.

INTERVENTIONS

Real-time alerts stratified according to predicted likelihood of deterioration sent either to the primary team or directly to the rapid response team (RRT). Clinical care and interventions were at the providers' discretion. For the control units, alerts were generated but not sent, and standard RRT activation criteria were used.

MEASUREMENTS AND MAIN RESULTS

The primary outcome was the rate of escalation per 1000 patient bed days. Secondary outcomes included the frequency of orders for fluids, medications, and diagnostic tests, and combined in-hospital and 30-day mortality. Propensity score modeling with stabilized inverse probability of treatment weight (IPTW) was used to account for differences between groups. Data from 2740 patients enrolled between July 2019 and March 2020 were analyzed (1488 intervention, 1252 control). Average age was 66.3 years and 1428 participants (52%) were female. The rate of escalation was 12.3 vs. 11.3 per 1000 patient bed days (difference, 1.0; 95% CI, -2.8 to 4.7) and IPTW adjusted incidence rate ratio 1.43 (95% CI, 1.16-1.78; p < 0.001). Patients in the intervention group were more likely to receive cardiovascular medication orders (16.1% vs. 11.3%; 4.7%; 95% CI, 2.1-7.4%) and IPTW adjusted relative risk (RR) (1.74; 95% CI, 1.39-2.18; p < 0.001). Combined in-hospital and 30-day-mortality was lower in the intervention group (7% vs. 9.3%; -2.4%; 95% CI, -4.5% to -0.2%) and IPTW adjusted RR (0.76; 95% CI, 0.58-0.99; p = 0.045).

CONCLUSIONS

Real-time machine learning alerts do not reduce the rate of escalation but may reduce mortality.

Development and validation of an instrument for measuring junior nurses' recognition and response abilities to clinical deterioration (RRCD)

BACKGROUND

Nurses of all levels are expected to be competent in managing clinical deterioration. Given their limited experience and basic-level knowledge, there is a concern about junior nurses' clinical and patient management skills. However, junior nurses' abilities to recognise and respond to clinical deterioration have not been adequately explored because of the absence of a comprehensive tool.

OBJECTIVES

The aim of this study was to develop a new self-assessment scale to assess the junior nurses' recognition and response abilities to clinical deterioration and to examine its reliability and validity.

METHODS

Scale items were based on literature reviews and interviews. The preliminary scale was generated through two rounds of expert review. A panel of five experts evaluated content validity. After a pilot study, the questionnaire was distributed to 168 junior nurses via convenience sampling. Subsequent statistical analysis of results included construct validity, internal consistency, and test-retest reliability.

RESULTS

Six factors were included, and 69.310% of the total variance was explained by the 25 items comprising the scale. The Cronbach's alpha coefficient was 0.905 (95% confidence interval [CI]: 0.812-0.979) for the overall scale and 0.655-0.838 for its subscales. The Guttman split-half reliability was 0.856 (95% CI: 0.806-0.894). The test-retest reliability of the scale was 0.878 (95% CI: 0.836-0.911).

CONCLUSION

We developed a scale for measuring the abilities of junior nurses to recognise and respond to clinical deterioration and confirmed its reliability and validity. More experimental studies are needed to further evaluate this instrument.

The ACCELERATE Plus (assessment and communication excellence for safe patient outcomes) Trial Protocol: a stepped-wedge cluster randomised trial, cost-benefit analysis, and process evaluation

BACKGROUND

Nurses play an essential role in patient safety. Inadequate nursing physical assessment and communication in handover practices are associated with increased patient deterioration, falls and pressure injuries. Despite internationally implemented rapid response systems, falls and pressure injury reduction strategies, and recommendations to conduct clinical handovers at patients' bedside, adverse events persist. This trial aims to evaluate the effectiveness, implementation, and cost-benefit of an externally facilitated, nurse-led intervention delivered at the ward level for core physical assessment, structured patient-centred bedside handover and improved multidisciplinary communication. We hypothesise the trial will reduce medical emergency team calls, unplanned intensive care unit admissions, falls and pressure injuries.

METHODS

A stepped-wedge cluster randomised trial will be conducted over 52 weeks. The intervention consists of a nursing core physical assessment, structured patient-centred bedside handover and improved multidisciplinary communication and will be implemented in 24 wards across eight hospitals. The intervention will use theoretically informed implementation strategies for changing clinician behaviour, consisting of: nursing executive site engagement; a train-the-trainer model for cascading facilitation; embedded site leads; nursing unit manager leadership training; nursing and medical ward-level clinical champions; ward nurses' education workshops; intervention tailoring; and reminders. The primary outcome will be a composite measure of medical emergency team calls (rapid response calls and 'Code Blue' calls), unplanned intensive care unit admissions, in-hospital falls and hospital-acquired pressure injuries; these measures individually will also form secondary outcomes. Other secondary outcomes are: i) patient-reported experience measures of receiving safe and patient-centred care, ii) nurses' perceptions of barriers to physical assessment, readiness to change, and staff engagement, and iii) nurses' and medical officers' perceptions of safety culture and interprofessional collaboration. Primary outcome data will be collected for the trial duration, and secondary outcome surveys will be collected prior to each step and at trial conclusion. A cost-benefit analysis and post-trial process evaluation will also be undertaken.

DISCUSSION

If effective, this intervention has the potential to improve nursing care, reduce patient harm and improve patient outcomes. The evidence-based implementation strategy has been designed to be embedded within existing hospital workforces; if cost-effective, it will be readily translatable to other hospitals nationally.

TRIAL REGISTRATION

Australian New Zealand Clinical Trials Registry ID: ACTRN12622000155796. Date registered: 31/01/2022.

Development and Validation of the Medical Emergency Team-Risk Prediction Model for Clinical Deterioration in Acute Hospital Patients, at Time of an Emergency Admission

OBJECTIVES

To develop and validate a prediction model to estimate the risk of Medical Emergency Team (MET) review, within 48 hours of an emergency admission, using information routinely available at the time of hospital admission.

DESIGN

Development and validation of a multivariable risk model using prospectively collected data. Transparent Reporting of a multivariable model for Individual Prognosis Or Diagnosis recommendations were followed to develop and report the prediction model.

SETTING

A 560-bed teaching hospital, with a 22-bed ICU and 24-hour Emergency Department in Melbourne, Australia.

PATIENTS

A total of 45,170 emergency admissions of 30,064 adult patients (≥18 yr), with an inpatient length of stay greater than 24 hours, admitted under acute medical or surgical hospital services between 2015 and 2017.

MEASUREMENTS AND MAIN RESULTS

The outcome was MET review within 48 hours of emergency admission. Thirty candidate variables were selected from a routinely collected hospital dataset based on their availability to clinicians at the time of admission. The final model included nine variables: age; comorbid alcohol-related behavioral diagnosis; history of heart failure, chronic obstructive pulmonary disease (COPD), or renal disease; admitted from residential care; Charlson Comorbidity Index score 1 or 2, or 3+; at least one planned and one emergency admission in the last year; and admission diagnosis and one interaction (past history of COPD × admission diagnosis). The discrimination of the model was comparable in the training (C-statistics 0.82; 95% CI, 0.81-0.83) and the validation set (0.81; 0.80-0.83). Calibration was reasonable for training and validation sets.

CONCLUSIONS

Using only nine predictor variables available to clinicians at the time of admission, the MET-risk model can predict the risk of MET review during the first 48 hours of an emergency admission. Model utility in improving patient outcomes requires further investigation.

Artificial intelligence and clinical deterioration

PURPOSE OF REVIEW

To provide an overview of the systems being used to identify and predict clinical deterioration in hospitalised patients, with focus on the current and future role of artificial intelligence (AI).

RECENT FINDINGS

There are five leading AI driven systems in this field: the Advanced Alert Monitor (AAM), the electronic Cardiac Arrest Risk Triage (eCART) score, Hospital wide Alert Via Electronic Noticeboard, the Mayo Clinic Early Warning Score, and the Rothman Index (RI). Each uses Electronic Patient Record (EPR) data and machine learning to predict adverse events. Less mature but relevant evolutions are occurring in the fields of Natural Language Processing, Time and Motion Studies, AI Sepsis and COVID-19 algorithms.

SUMMARY

Research-based AI-driven systems to predict clinical deterioration are increasingly being developed, but few are being implemented into clinical workflows. Escobar et al. (AAM) provide the current gold standard for robust model development and implementation methodology. Multiple technologies show promise, however, the pathway to meaningfully affect patient outcomes remains challenging.

Implementation of a structured emergency nursing framework results in significant cost benefit

Background

Patients are at risk of deterioration on discharge from an emergency department (ED) to a ward, particularly in the first 72 h. The implementation of a structured emergency nursing framework (HIRAID) in regional New South Wales (NSW), Australia, resulted in a 50% reduction of clinical deterioration related to emergency nursing care. To date the cost implications of this are unknown. The aim of this study was to determine any net financial benefits arising from the implementation of the HIRAID emergency nursing framework.

Methods

This retrospective cohort study was conducted between March 2018 and February 2019 across two hospitals in regional NSW, Australia. Costs associated with the implementation of HIRAID at the study sites were calculated using an estimate of initial HIRAID implementation costs (AUD) ($492,917) and ongoing HIRAID implementation costs ($134,077). Equivalent savings per annum (i.e. in less patient deterioration) were calculated using projected estimates of ED admission and patient deterioration episodes via OLS regression with confidence intervals for incremental additional deterioration costs per episode used as the basis for scenario analysis.

Results

The HIRAID-equivalent savings per annum exceed the costs of implementation under all scenarios (Conservative, Expected and Optimistic). The estimated preliminary savings to the study sites per annum was $1,914,252 with a payback period of 75 days. Conservative projections estimated a net benefit of $1,813,760 per annum by 2022–23. The state-wide projected equivalent savings benefits of HIRAID equalled $227,585,008 per annum, by 2022–23.

Conclusions

The implementation of HIRAID reduced costs associated with resources consumed from patient deterioration episodes. The HIRAID-equivalent savings per annum to the hospital exceed the costs of implementation across a range of scenarios, and upscaling would result in significant patient and cost benefit.