Chronic critical illness: unintended consequence of intensive care medicine

Early Warning Models Using Machine Learning to Predict Sepsis-Associated Chronic Critical Illness: A Study Based on the Medical Information Mart for Intensive Care Database

Background Patients with chronic critical illness (CCI) experience poor prognoses and incur high medical costs. However, there is currently limited clinical awareness of sepsis-associated CCI, resulting in insufficient vigilance. Therefore, it is necessary to build a machine learning model that can predict whether sepsis patients will develop CCI. Methods Clinical data on 19,077 sepsis patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were analyzed. Predictive factors were identified using the Student's t-test, Mann-Whitney U test, or χ 2 test. Six machine learning classification models, namely, the logistic regression, support vector machine, decision tree, random forest, extreme gradient enhancement, and artificial neural network, were established. The optimal model was selected on the basis of its performance. Calibration curves were used to evaluate the accuracy of model classification, while the external validation dataset was used to evaluate the performance of the model. Results Thirty-seven characteristics, such as elevated alanine aminotransferase, rapid heart rate, and high Logistic Organ Dysfunction System scores, were identified as risk factors for developing CCI. The area under the receiver operating characteristic curve (AUROC) values for all models were above 0.73 on the internal test set. Among them, the extreme gradient enhancement model exhibited superior performance (F1 score = 0.91, AUROC = 0.91, Brier score = 0.052). It also exhibited stable prediction performance on the external validation set (AUROC = 0.72). Conclusion A machine learning model was established to predict whether sepsis patients will develop CCI. It can provide useful predictive information for clinical decision-making.

Subphenotyping heterogeneous patients with chronic critical illness to guide individualised fluid balance treatment using machine learning: a retrospective cohort study

BACKGROUND

The great heterogeneity of patients with chronic critical illness (CCI) leads to difficulty for intensive care unit (ICU) management. Identifying subphenotypes could assist in individualized care, which has not yet been explored. In this study, we aim to identify the subphenotypes of patients with CCI and reveal the heterogeneous treatment effect of fluid balance for them.

METHODS

In this retrospective study, we defined CCI as an ICU length of stay over 14 days and coexists with persistent organ dysfunction (cardiovascular Sequential Organ Failure Assessment (SOFA) score ≥1 or score in any other organ system ≥2) at Day 14. Data from five electronic healthcare record datasets covering geographically distinct populations (the US, Europe, and China) were studied. These five datasets include (1) subset of Derivation (MIMIC-IV v1.0, US) cohort (2008-2019); (2) subset Derivation (MIMIC-III v1.4 'CareVue', US) cohort (2001-2008); (3) Validation I (eICU-CRD, US) cohort (2014-2015); (4) Validation II (AmsterdamUMCdb/AUMC, Euro) cohort (2003-2016); (5) Validation III (Jinling, CN) cohort (2017-2021). Patients who meet the criteria of CCI in their first ICU admission period were included in this study. Patients with age over 89 or under 18 years old were excluded. Three unsupervised clustering algorithms were employed independently for phenotypes derivation and validation. Extreme Gradient Boosting (XGBoost) was used for phenotype classifier construction. A parametric G-formula model was applied to estimate the cumulative risk under different daily fluid management strategies in different subphenotypes of ICU mortality.

FINDINGS

We identified four subphenotypes as Phenotype A, B, C, and D in a total of 8145 patients from three countries. Phenotype A is the mildest and youngest subgroup; Phenotype B is the most common group, of whom patients showed the oldest age, significant acid-base abnormality, and low white blood cell count; Patients with Phenotype C have hypernatremia, hyperchloremia, and hypercatabolic status; and in Phenotype D, patients accompany with the most severe multiple organ failure. An easy-to-use classifier showed good effectiveness. Phenotype characteristics showed robustness across all cohorts. The beneficial fluid balance threshold intervals of subphenotypes were different.

INTERPRETATION

We identified four novel phenotypes that revealed the different patterns and significant heterogeneous treatment effects of fluid therapy within patients with CCI. A prospective study is needed to validate our findings, which could inform clinical practice and guide future research on individualized care.

FUNDING

This study was funded by 333 High Level Talents Training Project of Jiangsu Province (BRA2019011), General Program of Medical Research from the Jiangsu Commission of Health (M2020052), and Key Research and Development Program of Jiangsu Province (BE2022823).

Explainable Machine Learning to Predict Successful Weaning Among Patients Requiring Prolonged Mechanical Ventilation: A Retrospective Cohort Study in Central Taiwan

Objective: The number of patients requiring prolonged mechanical ventilation (PMV) is increasing worldwide, but the weaning outcome prediction model in these patients is still lacking. We hence aimed to develop an explainable machine learning (ML) model to predict successful weaning in patients requiring PMV using a real-world dataset. Methods: This retrospective study used the electronic medical records of patients admitted to a 12-bed respiratory care center in central Taiwan between 2013 and 2018. We used three ML models, namely, extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR), to establish the prediction model. We further illustrated the feature importance categorized by clinical domains and provided visualized interpretation by using SHapley Additive exPlanations (SHAP) as well as local interpretable model-agnostic explanations (LIME). Results: The dataset contained data of 963 patients requiring PMV, and 56.0% (539/963) of them were successfully weaned from mechanical ventilation. The XGBoost model (area under the curve [AUC]: 0.908; 95% confidence interval [CI] 0.864-0.943) and RF model (AUC: 0.888; 95% CI 0.844-0.934) outperformed the LR model (AUC: 0.762; 95% CI 0.687-0.830) in predicting successful weaning in patients requiring PMV. To give the physician an intuitive understanding of the model, we stratified the feature importance by clinical domains. The cumulative feature importance in the ventilation domain, fluid domain, physiology domain, and laboratory data domain was 0.310, 0.201, 0.265, and 0.182, respectively. We further used the SHAP plot and partial dependence plot to illustrate associations between features and the weaning outcome at the feature level. Moreover, we used LIME plots to illustrate the prediction model at the individual level. Additionally, we addressed the weekly performance of the three ML models and found that the accuracy of XGBoost/RF was ~0.7 between weeks 4 and week 7 and slightly declined to 0.6 on weeks 8 and 9. Conclusion: We used an ML approach, mainly XGBoost, SHAP plot, and LIME plot to establish an explainable weaning prediction ML model in patients requiring PMV. We believe these approaches should largely mitigate the concern of the black-box issue of artificial intelligence, and future studies are warranted for the landing of the proposed model.

Effective Care Practices in Patients Receiving Prolonged Mechanical Ventilation. An Ethnographic Study

Rationale: Patients receiving prolonged mechanical ventilation experience low survival rates and incur high healthcare costs. However, little is known about how to optimally organize and manage their care.Objectives: To identify a set of effective care practices for patients receiving prolonged mechanical ventilation.Methods: We performed a focused ethnographic evaluation at eight long-term acute care hospitals in the United States ranking in either the lowest or highest quartile of risk-adjusted mortality in at least four of the five years between 2007 and 2011.Measurements and Main Results: We conducted 329 hours of direct observation, 196 interviews, and 39 episodes of job shadowing. Data were analyzed using thematic content analysis and a positive-negative deviance approach. We found that high- and low-performing hospitals differed substantially in their approach to care. High-performing hospitals actively promoted interdisciplinary communication and coordination using a range of organizational practices, including factors related to leadership (e.g., leaders who communicate a culture of quality improvement), staffing (e.g., lower nurse-to-patient ratios and ready availability of psychologists and spiritual care providers), care protocols (e.g., specific yet flexible respiratory therapy-driven weaning protocols), team meetings (e.g., interdisciplinary meetings that include direct care providers), and the physical plant (e.g., large workstations that allow groups to interact). These practices were believed to facilitate care that is simultaneously goal directed and responsive to individual patient needs, leading to more successful liberation from mechanical ventilation and improved survival.Conclusions: High-performing long-term acute care hospitals employ several organizational practices that may be helpful in improving care for patients receiving prolonged mechanical ventilation.

Hospital-level variation in the development of persistent critical illness

PURPOSE

Patients with persistent critical illness may account for up to half of all intensive care unit (ICU) bed-days. It is unknown if there is hospital variation in the development of persistent critical illness and if hospital performance affects the incidence of persistent critical illness.

METHODS

This is a retrospective analysis of Veterans admitted to the Veterans Administration (VA) ICUs from 2015 to 2017. Hospital performance was defined by the risk- and reliability-adjusted 30-day mortality. Persistent critical illness was defined as an ICU length of stay of at least 11 days. We used 2-level multilevel logistic regression models to assess variation in risk- and reliability-adjusted probabilities in the development of persistent critical illness.

RESULTS

In the analysis of 100 hospitals which encompassed 153,512 hospitalizations, 4.9% (N = 7640/153,512) developed persistent critical illness. There was variation in the development of persistent critical illness despite controlling for patient characteristics (intraclass correlation: 0.067, 95% CI 0.049-0.091). Hospitals with higher risk- and reliability-adjusted 30-day mortality had higher probabilities of developing persistent critical illness (predicted probability: 0.057, 95% CI 0.051-0.063, p < 0.01) compared to those with lower risk- and reliability-adjusted 30-day mortality (predicted probability: 0.046, 95% CI 0.041-0.051, p < 0.01). The median odds ratio was 1.4 (95% CI 1.33-1.49) implying that, for two patients with the same physiology on admission at two different VA hospitals, the patient admitted to the hospital with higher adjusted mortality would have 40% greater odds of developing persistent critical illness.

CONCLUSION

Hospitals with higher risk- and reliability-adjusted 30-day mortality have a higher probability of developing persistent critical illness. Understanding the drivers of this variation may identify modifiable factors contributing to the development of persistent critical illness.

Timing of Onset, Burden, and Postdischarge Mortality of Persistent Critical Illness in Scotland, 2005-2014: A Retrospective, Population-Based, Observational Study

We aimed to understand the prevalence, timing of onset, resource use, and long-term outcomes of patients who developed persistent critical illness in a national dataset.

Design

Retrospective cohort. Using a physiologic risk adjustment model from ICU admission, we examined the relative ability of acute (related to reason for ICU presentation) and antecedent (demographics, comorbidities) characteristics to discriminate hospital mortality models. Persistent critical illness was defined as the point during an ICU stay when, at the population-level, patients' acute diagnoses and physiologic disturbance are no longer more accurate at discriminating who survives than are baseline demographics and comorbidity. We examined the change across ICU stay in the relative discrimination of those characteristics, and short-term (in-hospital and 30 d after admission) and medium-term (90 d after admission) survival. Finally, we analyzed the changes in the population definition of persistent critical illness over time.

Setting

Patients admitted as level 3 to Scottish ICUs between 2005 and 2014.

Patients

Seventy-two-thousand two-hundred fifty-three adult level 3 ICU admissions in 23 ICUs across Scotland.

Interventions

None.

Measurements and Main Results

The onset of persistent critical illness, occurs at an average of 5.0 days (95% CI, 3.9-6.4 d) across this dataset. The crossing point increased across the decade, by an average of 0.36 days (95% CI, 0.22-0.50 d) per year. In this dataset, 24,425 (33.8%) remained in the ICU long enough to meet this greater than 5-day definition of persistent critical illness. The care of such patients involved 72.3% ICU days used by any level 3 patient; 46.5% of all Scottish ICU bed-days were after day 5. Although rates of 30 days after admission survival rose dramatically during the decade under study, these rates were similar for those with shorter or longer ICU stays, as were the rates of 90-day survival among those who survived at least 30 days.

Conclusions

Persistent critical illness occurred in one in three ICU patients in Scotland. These minority of patients accounted for disproportionate hospital resources but did not have worse 30- or 90-day postadmission survival.

Mental health and quality of life outcomes in family members of patients with chronic critical illness admitted to the intensive care units of two Brazilian hospitals serving the extremes of the socioeconomic spectrum

Chronic critical illness (CCI) is a relevant clinical, social and financial health issue. The aim of this study was to compare the mental outcomes (symptoms of anxiety and depression) and quality of life outcomes of the family members of patients with CCI from different socioeconomic backgrounds who were admitted to one of the intensive care units (ICUs) in two Brazilian hospitals, one private and one public. It is a prospective study involving a public hospital that serves a low-income population and a tertiary private hospital that serves a high-income population. Family members of patients with CCI answered the Hospital Anxiety and Depression Scale (HADS) and The World Health Organization Quality of Life–WHOQOL-bref questionnaires. They responded to the European Quality of life Five Dimension three Level (EuroQol-5D-3L) and the Activities of Daily Living (ADL) questionnaires on behalf of the patients at three time points: during the ICU stay, 30 and 90 days after the patient was discharged. We used logistic regression models to evaluate the main predictors of a binary outcome regarding symptoms of anxiety and depression. We enrolled 186 patients with CCI. Many patients from public hospitals who were independent became dependent for their ADLs at 90 days (41.7% versus 14.3%, p = 0.03). At 30 days, family members from public hospital had worse impact on all domains of WHOQOL-bref compared with families from private hospital. At 90-days, the difference persists in the physical domain, worse for families from public hospital (p = 0.006). The symptoms of depression at 30-days (p = 0.008) and at 90-days (p = 0.013) were worse in the public hospital. CCIs affected quality of life and the emotional condition of family members, especially in families with fewer resources when the patients became more dependent. Family members with higher education were more likely to experience depression, while depression was associated with cohabiting with the patient in low-income families.

The biology of natural killer cells during sepsis

Natural killer (NK) cells are large granular lymphocytes largely recognized for their importance in tumour surveillance and the host response to viral infections. However, as the major innate lymphocyte population, NK cells also coordinate early responses to bacterial infections by amplifying the antimicrobial functions of myeloid cells, especially macrophages, by production of interferon-γ (IFN-γ). Alternatively, excessive NK cell activation and IFN-γ production can amplify the systemic inflammatory response during sepsis resulting in increased physiological dysfunction and organ injury. Our understanding of NK cell biology during bacterial infections and sepsis is mostly derived from studies performed in mice. Human studies have demonstrated a correlation between altered NK cell functions and outcomes during sepsis. However, mechanistic understanding of NK cell function during human sepsis is limited. In this review, we will review the current understanding of NK cell biology during sepsis and discuss the challenges associated with modulating NK cell function during sepsis for therapeutic benefit.