The Experience of Physical Recovery and Physical Rehabilitation Following Hospital Discharge for Intensive Care Survivors-A Qualitative Systematic Review

BACKGROUND

Over 120,000 people in the UK survive critical illness each year, with over 60% of these experiencing mobility issues and reduced health-related quality of life after discharge home. This qualitative systematic review aimed to explore critical care survivors' perceptions, opinions, and experiences of physical recovery and physical rehabilitation following hospital discharge.

METHODS

This review followed the Joanna Briggs Institute (JBI) methodology with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and was conducted between January 2020 and June 2022. The search was conducted using the following databases: Embase, CINAHL, Medline Ovid, Cochrane, and the Joanna Briggs Institute, and sources of grey literature were searched for eligible studies. Qualitative studies focused on physical rehabilitation or recovery, involving adult survivors of critical illness who had been discharged from hospital.

RESULTS

A total of 7 of 548 identified studies published in 2007-2019 were eligible for inclusion. The findings indicate that qualitative evidence around the experiences of physical recovery and rehabilitation interventions following discharge home after critical illness is limited. Three synthesised findings were identified: 'Positivity, motivation and hope'; 'Recovery is hard and patients need support'; and 'Patients experience challenges in momentum of physical recovery'.

CONCLUSIONS

Survivors struggle to access healthcare professionals and services following discharge home, which influences the momentum of physical recovery. Supervised exercise programmes had a positive impact on the perception of recovery and motivation. However, 'simple' structured exercise provision will not address the range of challenges experienced by ICU survivors. Whilst some factors influencing physical recovery are similar to other groups, there are unique issues experienced by those returning home after critical illness. Further research is needed to identify the support or interventions survivors feel would meet their needs and assist their physical recovery. This study was prospectively registered with Prospero on 3/2/2020 with registration number CRD42020165290.

Comparing machine learning algorithms to predict COVID‑19 mortality using a dataset including chest computed tomography severity score data

Since the beginning of the COVID-19 pandemic, new and non-invasive digital technologies such as artificial intelligence (AI) had been introduced for mortality prediction of COVID-19 patients. The prognostic performances of the machine learning (ML)-based models for predicting clinical outcomes of COVID-19 patients had been mainly evaluated using demographics, risk factors, clinical manifestations, and laboratory results. There is a lack of information about the prognostic role of imaging manifestations in combination with demographics, clinical manifestations, and laboratory predictors. The purpose of the present study is to develop an efficient ML prognostic model based on a more comprehensive dataset including chest CT severity score (CT-SS). Fifty-five primary features in six main classes were retrospectively reviewed for 6854 suspected cases. The independence test of Chi-square was used to determine the most important features in the mortality prediction of COVID-19 patients. The most relevant predictors were used to train and test ML algorithms. The predictive models were developed using eight ML algorithms including the J48 decision tree (J48), support vector machine (SVM), multi-layer perceptron (MLP), k-nearest neighbourhood (k-NN), Naïve Bayes (NB), logistic regression (LR), random forest (RF), and eXtreme gradient boosting (XGBoost). The performances of the predictive models were evaluated using accuracy, precision, sensitivity, specificity, and area under the ROC curve (AUC) metrics. After applying the exclusion criteria, a total of 815 positive RT-PCR patients were the final sample size, where 54.85% of the patients were male and the mean age of the study population was 57.22 ± 16.76 years. The RF algorithm with an accuracy of 97.2%, the sensitivity of 100%, a precision of 94.8%, specificity of 94.5%, F1-score of 97.3%, and AUC of 99.9% had the best performance. Other ML algorithms with AUC ranging from 81.2 to 93.9% had also good prediction performances in predicting COVID-19 mortality. Results showed that timely and accurate risk stratification of COVID-19 patients could be performed using ML-based predictive models fed by routine data. The proposed algorithm with the more comprehensive dataset including CT-SS could efficiently predict the mortality of COVID-19 patients. This could lead to promptly targeting high-risk patients on admission, the optimal use of hospital resources, and an increased probability of survival of patients.

Prognostic significance of chest CT severity score in mortality prediction of COVID-19 patients, a machine learning study

Background

The high mortality rate of COVID-19 makes it necessary to seek early identification of high-risk patients with poor prognoses. Although the association between CT-SS and mortality of COVID-19 patients was reported, its prognosis significance in combination with other prognostic parameters was not evaluated yet.

Methods

This retrospective single-center study reviewed a total of 6854 suspected patients referred to Imam Khomeini hospital, Ilam city, west of Iran, from February 9, 2020 to December 20, 2020. The prognostic performances of k-Nearest Neighbors (kNN), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and J48 decision tree algorithms were evaluated based on the most important and relevant predictors. The metrics derived from the confusion matrix were used to determine the performance of the ML models.

Results

After applying exclusion criteria, 815 hospitalized cases were entered into the study. Of these, 447(54.85%) were male and the mean (± SD) age of participants was 57.22(± 16.76) years. The results showed that the performances of the ML algorithms were improved when they are fed by the dataset with CT-SS data. The kNN model with an accuracy of 94.1%, sensitivity of 100. 0%, precision of 89.5%, specificity of 88.3%, and AUC around 97.2% had the best performance among the other three ML techniques.

Conclusions

The integration of CT-SS data with demographics, risk factors, clinical manifestations, and laboratory parameters improved the prognostic performances of the ML algorithms. An ML model with a comprehensive collection of predictors could identify high-risk patients more efficiently and lead to the optimal use of hospital resources.

Optimizing Recovery Following Critical Illness: A Systematic Review of Home-Based Interventions

Around 5 million Americans are treated in an intensive care unit (ICU) annually. Upon discharge, it is not uncommon for ICU survivors to experience psychological, physical, or cognitive symptoms related to their ICU stay. Home-based interventions have been touted as a potential treatment modality for post-ICU sequelae. However, limited evidence exists regarding the effectiveness of home-based interventions for patients in the post-ICU recovery period. As such, the purpose of this review was to aggregate and summarize the findings of studies focused on post-ICU rehabilitation, following critical illness, delivered in the home setting. A literature search was performed in MEDLINE, CINAHL, EMBASE, APA PsycINFO, and Google Scholar. Studies were included if they: used a RCT or quasi-experimental study design; included participants aged ≥18 years discharged home from an ICU; examined the effectiveness of a home-based, post-ICU intervention; were published in English after the year 2010; and were peer-reviewed. Nine studies met inclusion criteria. Sample sizes ranged from 21 to 386, with most participants receiving mechanical ventilation. Target outcomes included: physical function, psychological well-being, cognitive function, quality of life, and healthcare utilization. Interventions included face-to-face, web-based, telephone, or self-directed activities. Findings of included studies were mixed or inconclusive. Limitations of this review include: inclusion of only adult ICU survivors, exclusion of Post-Intensive Care Syndrome as a search term, and search restricted to pre-pandemic studies. Findings suggest a need for more rigorous research to develop and test home-based interventions.

Using decision tree algorithms for estimating ICU admission of COVID-19 patients

Introduction

Materials and methods

Results

Conclusions

Proposed subtypes of post-COVID-19 syndrome (or long-COVID) and their respective potential therapies

The effects of coronavirus disease 2019 (COVID-19), a highly transmissible infectious respiratory disease that has initiated an ongoing pandemic since early 2020, do not always end in the acute phase. Depending on the study referred, about 10%-30% (or more) of COVID-19 survivors may develop long-COVID or post-COVID-19 syndrome (PCS), characterised by persistent symptoms (most commonly fatigue, dyspnoea, and cognitive impairments) lasting for 3 months or more after acute COVID-19. While the pathophysiological mechanisms of PCS have been extensively described elsewhere, the subtypes of PCS have not. Owing to its highly multifaceted nature, this review proposes and characterises six subtypes of PCS based on the existing literature. The subtypes are non-severe COVID-19 multi-organ sequelae (NSC-MOS), pulmonary fibrosis sequelae (PFS), myalgic encephalomyelitis or chronic fatigue syndrome (ME/CFS), postural orthostatic tachycardia syndrome (POTS), post-intensive care syndrome (PICS) and medical or clinical sequelae (MCS). Original studies supporting each of these subtypes are documented in this review, as well as their respective symptoms and potential interventions. Ultimately, the subtyping proposed herein aims to provide better clarity on the current understanding of PCS.

Management of COVID-19 ICU-survivors in primary care: - a narrative review

Many survivors of critical illness suffer from long-lasting physical, cognitive, and mental health sequelae. The number of affected patients is expected to markedly increase due to the COVID-19 pandemic. Many ICU survivors receive long-term care from a primary care physician. Hence, awareness and appropriate management of these sequelae is crucial. An interdisciplinary authorship team participated in a narrative literature review to identify key issues in managing COVID-19 ICU-survivors in primary care. The aim of this perspective paper is to synthesize important literature to understand and manage sequelae of critical illness due to COVID-19 in the primary care setting.