What factors predict length of stay in the intensive care unit? Systematic review and meta-analysis

What factors predict length of stay in the intensive care unit? Systematic review and meta-analysis 
J Crit Care. 2020;60:183-194. doi:10.1016/j.jcrc.2020.08.003

• A systematic review and metaanalysis for six factors from 28 papers and concluded that patients with mechanical ventilation, hypomagnesemia, delirium, and malnutrition tend to have longer ICU stay, and that age and gender were not significant factors. This work suggested a list of risk factors that should be considered in prediction models for ICU LoS, as follows: severity scores, mechanical ventilation, hypomagnesemia, delirium, malnutrition, infection, trauma, red blood cells, and PaO2:FiO2. 

Abstract

Outcomes from intensive care in patients with COVID‐19: a systematic review and meta‐analysis of observational studies

Outcomes from intensive care in patients with COVID‐19: a systematic review and meta‐analysis of observational studies
Anaesthesia 30 June 2020 https://doi.org/10.1111/anae.15201

• A literature search identified 4 articles which reported ICU outcome data for patients admitted to ICU with a COVID-19 diagnosis (n=10,150). The largest patient group was in the Intensive Care National Audit and Research Centre (ICNARC) study from the UK. 
• In patients with completed ICU admissions with COVID-19 infection, combined ICU mortality was 41.6% (95%CI 34.0-49.7%, I2 = 93.2%). Subgroup analysis by continent showed that mortality is broadly consistent across the globe. The in-ICU mortality from COVID-19 is higher than usually seen in ICU admissions with other viral pneumonias. The mortality from completed episodes of ICU differs considerably from the crude mortality rates in some early reports.

Summary

COVID-19 ICU Preparation Simulation

COVID-19 ICU Preparation Simulation
SIMUL8 5 June 2020

• A covid-19 ICU preparation simulation tool from SIMUL8, designed to help hospitals evaluate the bed, ventilator and staffing levels needed to cope with covid-19 patients is now available to download. 

Early prediction of ICU readmissions using classification algorithms

Early prediction of ICU readmissions using classification algorithms
Computers in Biology and Medicine; Mar 2020; v118, March 2020, 103636 https://doi.org/10.1016/j.compbiomed.2020.103636

• Existing work on predicting ICU readmissions relies on information available at the time of discharge, however, in order to be more useful and to prevent complications, predictions need to be made earlier. This work investigates the hypothesis that the basal characteristics and information collected at the time of the patient's admission can enable accurate predictions of ICU readmission.

Abstract:

Intensive care medicine in smaller hospitals: here to stay

Intensive care medicine in smaller hospitals: here to stay
Future Healthcare Journal February 2020 DOI: https://doi.org/10.7861/fhj.2019-0068

• This article outlines the background and work of the Faculty of Intensive Care Medicine Smaller and Specialist Units Advisory Group to support and sustain intensive care medicine in smaller hospitals and looks at critical care in the context of remote and rural healthcare.

Developing an intervention around referral and admissions to intensive care

Developing an intervention around referral and admissions to intensive care: a mixed-methods study. Health Serv Deliv Res 2019;7(39) November 2019

• This study highlighted the complexity of professional and patient communication in decision-making around referral and admissions to intensive care, with a decision support intervention showing some improved communication with patients.

Analysis and prediction of unplanned intensive care unit readmission

Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory
PLoS ONE 14(7): e0218942. 8 July 2019

• Research using machine learning methods on comprehensive, longitudinal clinical data from the MIMIC-III to predict the ICU readmission of patients within 30 days of their discharge.
• Machine learning techniques such as Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) were used to incorporate the multivariate features of EHRs and capture sudden fluctuations in chart event features. These machine learning models identify ICU readmissions at a higher sensitivity rate and an improved Area Under the Curve compared with traditional methods.

Man vs. machine: Comparison of a machine learning algorithm to clinician intuition for predicting ICU readmission

Man vs. machine: Comparison of a machine learning algorithm to clinician intuition for predicting intensive care unit readmission [Midwest Clinical & Translational Research Meeting Conference Abstract A09]
Journal of Investigative Medicine; Jun 2019; vol. 67 (no. 5); p. 929

• A prospective study of 937 ICU discharges (University of Chicago, IL, USA) found that a machine learning model was more accurate than clinician intuition for predicting ICU readmission, suggesting that a machine learning model using real-time patient data could provide clinicians with additional information to guide decision-making regarding the timing of ICU discharge.

Abstract 

Intensive Care Unit Telemedicine

Intensive Care Unit Telemedicine
Critical Care Clinics v35(3), July 2019

• A special issue dedicated to telemedicne in the ICU including:
• Intensive Care Unit Telemedicine in the Era of Big Data, Artificial Intelligence, and Computer Clinical Decision Support Systems p483-495

[Contact your local NHS Library for a copy of this journal]

Telemedicine in the ICU: clinical outcomes, economic aspects, and trainee education.

Telemedicine in the ICU: clinical outcomes, economic aspects, and trainee education
Curr Opin Anaesthesiol. 28 January 2019

• The value of tele-ICU to improve patient outcomes, optimize ICU bed utilization, increase financial performance and enhance educational opportunities for the next generation of providers has become more evident and differentiated in the last 2 years.

Abstract

Evaluating Tele-ICU Implementation Based on Observed and Predicted ICU Mortality

Evaluating Tele-ICU Implementation Based on Observed and Predicted ICU Mortality: A Systematic Review and Meta-Analysis
Crit Care Med. 24 January 2019

• After evaluating 13 included studies, tele-ICU implementation was associated with an overall reduction in ICU mortality.

Abstract

National Maternity and Perinatal Audit – Intensive Care Report

National Maternity and Perinatal Audit – Intensive Care Report
HQIP 10 January 2019

• The purpose of this report is to describe the feasibility of linking the NMPA’s maternity data to intensive care data and to evaluate the suitability of rates of maternal admission to intensive care as an indicator of care quality. It also describes the demographics of women admitted to intensive care and the reasons for admission.
• This report shows that the linkage of maternity data to intensive care data offers the potential to understand the demographic factors underlying admission to intensive care, and the timing of intensive care admission relative to birth. However, as NHS organisations differ in their configuration of care for women who are critically ill during pregnancy, birth or the postnatal period, criteria for admission to intensive care varies so admissions to intensive care do not reliably indicate severe maternal morbidity. In different hospitals women with the same clinical condition may be cared for in different settings.

Postoperative Medical Complications and Intermediate Care Unit/ICU Admission in Joint Replacement Surgery:

Postoperative Medical Complications and Intermediate Care Unit/Intensive Care Unit Admission in Joint Replacement Surgery: A Prospective Risk Model.
J Arthroplasty. 2019 Jan 5. pii: S0883-5403(18)31236-1. doi: 10.1016/j.arth.2018.12.034.

• The introduced risk-estimation model offers a specialised preoperative resource-stratification method for  measuring the individual probability for intermediate care unit or ICU admission in knee joint replacement surgery. It condenses the most influential, individual risk factors to avoid clinical test redundancy and improve resource efficiency and presurgical care planning.

Abstract

Impact of Prolonged ICU Stay in Cardiac Surgical Patients: A Systematic Review

Survival, Quality of Life, and Functional Status Following Prolonged ICU Stay in Cardiac Surgical Patients: A Systematic Review.
Crit Care Med. 47(1):e52-e63 January 2019

• A systematic review of the outcomes of cardiac surgical patients requiring prolonged intensive care with respect to survival, residential status, functional recovery, and quality of life in both hospital and long-term follow-up.
• The review found consistent evidence that patients with increases in ICU length of stay beyond 48 hours have significantly increasing risk of hospital and long-term mortality.

Cancer in Children, Teens and Young Adults - high risk patients

Medical & Surgical Review Programme: Cancer in Children, Teens and Young Adults Report
HQIP 13 December 2018

• Cancer outcomes in children and young people have improved dramatically over the last few decades with over 80% of those diagnosed now being cured of their disease. This report deliberately focuses on a sample of patients who were a high-risk group who died or who had an unexpected admission to intensive care. 
• One of the recommendations is that the audit and quality improvement methods, with action plans, are essential for on-going improvement but require access to data eg prescribing, which are not always available.

Early Discharge From Intensive Care After Cardiac Surgery

Early Discharge From Intensive Care After Cardiac Surgery is Feasible With an Adequate Fast Track, Stepdown Unit: Waikato Experience.
Heart, Lung and Circulation DOI: https://doi.org/10.1016/j.hlc.2018.11.002, 13 November 2018

• Experience of an Australian day zero discharge enhanced recovery unit from the Cardiothoracic intensive care department.
• Survival analysis demonstrated that the patients who were discharged early from ICU had significantly better follow-up survival compared to those who were discharged after 24 hours (p < 0.05).

Abstract

Follow‐up services for improving long‐term outcomes in ICU survivors

Follow‐up services for improving long‐term outcomes in intensive care unit (ICU) survivors
Cochrane Systematic Reviews 2 November 2018

• An assessment of the evidence around the effectiveness of follow‐up services for ICU survivors found insufficient evidence to determine whether existing ICU follow‐up services are effective in identifying and addressing the unmet health needs of ICU survivors.

Determinants of ICUTelemedicine Effectiveness: An Ethnographic Study.

Determinants of Intensive Care Unit Telemedicine Effectiveness: An Ethnographic Study.
Am J Respir Crit Care Med. 2018 Oct 23. doi: 10.1164/rccm.201802-0259OC. [Epub ahead of print]

• A focused ethnographic evaluation of 10 ICU telemedicine programs using site visits, interviews, and focus groups in both facilities providing remote care and the target ICUs.
• Data analysis revealed three domains that influence ICU telemedicine effectiveness: leadership, perceived value and organizational characteristics.
• Location: Pennsylvania, United States

Intensive care: balancing risk and benefit to facilitate informed decisions

Intensive care: balancing risk and benefit to facilitate informed decisions
BMJ 2018;363:k4135, 19 October 2018 doi: https://doi.org/10.1136/bmj.k4135

• Intensive care can be associated with substantial physical and psychosocial burdens for patients and may have adverse psychological consequences for families. Potential harms of intensive care are commonly overlooked in times of crisis when timely decisions need to be made about escalation of care. Frail, elderly patients have poorer outcomes after a stay in an intensive care unit (ICU) and are rarely consulted about their wishes for life sustaining treatments. 
• The decision to admit a patient to the ICU should include assessment of whether the likely benefits outweigh the risks. Where possible, patients and their families should be involved in the decision making process. Earlier information about intensive care practices and outcomes may help patients make informed choices about their future care.

Advanced critical care practitioners

Advanced critical care practitioners at Newcastle upon Tyne Hospitals NHS FT
NHS Employers 8 October 2018

• This case study looks at how Newcastle upon Tyne Hospitals NHS Foundation Trust introduced advanced critical care practitioners (ACCPs) into multidisciplinary teams across its critical care units.