Intensive care unit design and mortality in trauma patients

Development and validation of an artificial intelligence mobile application for predicting 30-day mortality in critically ill patients with orthopaedic trauma

BACKGROUND

Given the intricate and grave nature of trauma-related injuries in ICU settings, it is imperative to develop and deploy reliable predictive tools that can aid in the early identification of high-risk patients who are at risk of early death. The objective of this study is to create and validate an artificial intelligence (AI) model that can accurately predict early mortality among critical fracture patients.

METHODS

A total of 2662 critically ill patients with orthopaedic trauma were included from the MIMIC III database. Early mortality was defined as death within 30 days in this study. The patients were randomly divided into a model training cohort and a model validation cohort. Various algorithms, including logistic regression (LR), extreme gradient boosting machine (eXGBM), decision tree (DT), support vector machine (SVM), random forest (RF), and neural network (NN), were employed. Evaluation metrics, including discrimination and calibration, were used to develop a comprehensive scoring system ranging from 0 to 60, with higher scores indicating better prediction performance. Furthermore, external validation was carried out using 131 patients. The optimal model was deployed as an internet-based AI tool.

RESULTS

Among all models, the eXGBM demonstrated the highest area under the curve (AUC) value (0.974, 95%CI: 0.959-0.983), followed by the RF model (0.951, 95%CI: 0.935-0.967) and the NN model (0.922, 95%CI: 0.905-0.941). Additionally, the eXGBM model outperformed other models in terms of accuracy (0.915), precision (0.906), recall (0.926), F1 score (0.916), Brier score (0.062), log loss (0.210), and discrimination slope (0.767). Based on the scoring system, the eXGBM model achieved the highest score (53), followed by RF (42) and NN (39). The LR, DT, and SVM models obtained scores of 28, 18, and 32, respectively. Decision curve analysis further confirmed the superior clinical net benefits of the eXGBM model. External validation of the model achieved an AUC value of 0.913 (95%CI: 0.878-0.948). Consequently, the model was deployed on the Internet at https://30-daymortalityincriticallyillpatients-fnfsynbpbp6rgineaspuim.streamlit.app/, allowing users to input patient features and obtain predicted risks of early mortality among critical fracture patients. Furthermore, the AI model successfully stratified patients into low or high risk of early mortality based on a predefined threshold and provided recommendations for appropriate therapeutic interventions.

CONCLUSION

This study successfully develops and validates an AI model, with the eXGBM algorithm demonstrating the highest predictive performance for early mortality in critical fracture patients. By deploying the model as a web-based AI application, healthcare professionals can easily access the tool, enabling them to predict 30-day mortality and aiding in the identification and management of high-risk patients among those critically ill with orthopedic trauma.

Development and validation of a nomogram for predicting in-hospital mortality in patients with nonhip femoral fractures

BACKGROUND

The incidence of nonhip femoral fractures is gradually increasing, but few studies have explored the risk factors for in-hospital death in patients with nonhip femoral fractures in the ICU or developed mortality prediction models. Therefore, we chose to study this specific patient group, hoping to help clinicians improve the prognosis of patients.

METHODS

This is a retrospective study based on the data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Least absolute shrinkage and selection operator (LASSO) regression was used to screen risk factors. The receiver operating characteristic (ROC) curve was drawn, and the areas under the curve (AUC), net reclassification index (NRI) and integrated discrimination improvement (IDI) were calculated to evaluate the discrimination of the model. The consistency between the actual probability and the predicted probability was assessed by the calibration curve and Hosmer-Lemeshow goodness of fit test (HL test). Decision curve analysis (DCA) was performed, and the nomogram was compared with the scoring system commonly used in clinical practice to evaluate the clinical net benefit.

RESULTS

The LASSO regression analysis showed that heart rate, temperature, red blood cell distribution width, blood urea nitrogen, Glasgow Coma Scale (GCS), Simplified Acute Physiology Score II (SAPSII), Charlson comorbidity index and cerebrovascular disease were independent risk factors for in-hospital death in patients with nonhip femoral fractures. The AUC, IDI and NRI of our model in the training set and validation set were better than those of the GCS and SAPSII scoring systems. The calibration curve and HL test results showed that our model prediction results were in good agreement with the actual results (P = 0.833 for the HL test of the training set and P = 0.767 for the HL test of the validation set). DCA showed that our model had a better clinical net benefit than the GCS and SAPSII scoring systems.

CONCLUSION

In this study, the independent risk factors for in-hospital death in patients with nonhip femoral fractures were determined, and a prediction model was constructed. The results of this study may help to improve the clinical prognosis of patients with nonhip femoral fractures.

Intensive Care Unit Built Environments: A Comprehensive Literature Review (2005-2020)

BACKGROUND

The intensive care environment in hospitals has been the subject of significant empirical and qualitative research in the 2005-2020 period. Particular attention has been devoted to the role of infection control, family engagement, staff performance, and the built environment ramifications of the recent COVID-19 global pandemic. A comprehensive review of this literature is reported summarizing recent advancements in this rapidly expanding body of knowledge.

PURPOSE AND AIM

This comprehensive review conceptually structures the recent medical intensive care literature to provide conceptual clarity and identify current priorities and future evidence-based research and design priorities.

METHOD AND RESULT

Each source reviewed was classified as one of the five types-opinion pieces/essays, cross-sectional empirical investigations, nonrandomized comparative investigations, randomized studies, and policy review essays-and into nine content categories: nature engagement and outdoor views; family accommodations; intensive care unit (ICU), neonatal ICU, and pediatric ICU spatial configuration and amenity; noise considerations; artificial and natural lighting; patient safety and infection control; portable critical care field hospitals and disaster mitigation facilities including COVID-19; ecological sustainability; and recent planning and design trends and prognostications.

CONCLUSIONS

Among the findings embodied in the 135 literature sources reviewed, single-bed ICU rooms have increasingly become the norm; family engagement in the ICU experience has increased; acknowledgment of the therapeutic role of staff amenities; exposure to nature, view, and natural daylight has increased; the importance of ecological sustainability; and pandemic concerns have increased significantly in the wake of the coronavirus pandemic. Discussion of the results of this comprehensive review includes topics noticeably overlooked or underinvestigated in the 2005-2020 period and priorities for future research.

Mapping the impact of ICU design on patients, families and the ICU team: A scoping review

PURPOSE

Scoping review to map outcomes and describe effects of intensive care unit (ICU) design features on patients, family, and healthcare professionals (HCPs).

MATERIALS AND METHODS

Iteratively developed search strategy executed across seven databases. We included studies (January 2007 to May 2020) exploring ICU design features using any study design. We grouped studies into 12 design features and categorized outcomes into four domains.

RESULTS

Of 18,577 citations screened, 44 studies met inclusion criteria. Newly built or renovated ICUs/ICU rooms were evaluated in 27 (61%) studies; 17 (39%) evaluated existing designs/features. Most commonly evaluated design features were lighting (24, 55%), single vs multi-occupancy rooms/pods (17, 39%), and family-centered design (13, 30%). We identified 63 distinct outcomes in four domains; HCP-related (20, 45%); patient-related (20, 45%); family-related (11, 25%); and environment-related (7, 16%). Eleven (25%) studies measured patient/family-reported outcomes. In studies evaluating single occupancy rooms, three reported increased family satisfaction, two reported decreased delirium burden, while six reported negative consequences on HCP wellbeing and working.

CONCLUSION

Studies evaluating ICU design measure disparate outcomes. Few studies included patient/ family-reported outcomes; fewer measured objective environment characteristics. Single room layouts may benefit patients and family but contribute to adverse HCP-related outcomes.

Impact of Inpatient Unit Design Features on Overall Patient Experience and Perceived Room-Level Call Button Response

This study explores the relationship between inpatient unit design and patient experience and how spatial features and visibility impact patients' perception of staff responsiveness. The first part of this study is a retrospective pre-post and cross-sectional study evaluating the impacts of unit design on patient experience at the unit level. This study compares patient experiences based on Press Ganey and HCAHPS surveys in two orthopedic units (existing unit in Atrium building and new unit in Tower) with differing design features at Rush University Medical Center. The chi-square test results show that when moving from the old orthopedic unit to the new unit, almost all patient survey items related to patient experience showed statistically significant improvements. The second part of this study is a room level on the new unit. The ANOVA and Pearson correlation tests revealed that the visibility measure of metric step depth had significant impacts on patients' perception of staff's "promptness in responding to call button" and "help with toileting". This study confirms that inpatient unit design plays a direct role in improvement for patient experience and should be considered as an important area of focus for future development.

Telemedicine Implementation in COVID-19 ICU: Balancing Physical and Virtual Forms of Visibility

Objective:

This case study examines the implementation of inpatient telemedicine in COVID-19 intensive care units (ICUs) and explores the impact of shifting forms of visibility on the management of the unit, staff collaboration, and patient care.

Background:

The COVID-19 crisis drove healthcare institutions to rapidly develop new models of care based on integrating digital technologies for remote care with transformations in the hospital-built environment. The Sheba Medical Center in Israel created COVID-19 ICUs in an underground structure with an open-ward layout and telemedicine control rooms to remotely supervise, communicate, and support the operations in the contaminated zones. One unit had a physical visual connection between the control room and the contaminated zone through a window, while the other had only a virtual connection with digital technologies.

Methods:

The findings are based on semistructured interviews with Sheba medical staff, telemedicine companies, and the architectural design team and observations at the COVID-19 units during March–August 2020.

Results:

The case study illustrates the implications of virtual and physical visibility on the management of the unit, staff collaboration, and patient care. It demonstrates the correlations between patterns of visibility and the users’ sense of control, orientation in space, teamwork, safety, quality of care, and well-being.

Conclusions:

The case study demonstrates the limitations of current telemedicine technologies that were not designed for inpatient care to account for the spatial perception of the unit and the dynamic use of the space. It presents the potential of a hybrid model that balances virtual and physical forms of visibility and suggests directions for future research and development of inpatient telemedicine.

MPPED2 Polymorphism Is Associated With Altered Systemic Inflammation and Adverse Trauma Outcomes

Trauma is a leading cause of morbidity and mortality. It is unclear why some trauma victims follow a complicated clinical course and die, while others, with apparently similar injury characteristics, do not. Interpatient genomic differences, in the form of single nucleotide polymorphisms (SNPs), have been associated previously with adverse outcomes after trauma. Recently, we identified seven novel SNPs associated with mortality following trauma. The aim of the present study was to determine if one or more of these SNPs was also associated with worse clinical outcomes and altered inflammatory trajectories in trauma survivors. Accordingly, of 413 trauma survivors, DNA samples, full blood samples, and clinical data were collected at multiple time points in the first 24 h and then daily over 7 days following hospital admission. Subsequently, single-SNP groups were created and outcomes, such as hospital length of stay (LOS), ICU LOS, and requirement for mechanical ventilation, were compared. Across a broad range of Injury Severity Scores (ISS), patients carrying the rs2065418 TT SNP in the metallophosphoesterase domain-containing 2 (MPPED2) gene exhibited higher Marshall MODScores vs. the control group of rs2065418 TG/GG patients. In patients with high-severity trauma (ISS ≥ 25, n = 94), those carrying the rs2065418 TT SNP in MPPED2 exhibited higher Marshall MODScores, longer hospital LOS (21.8 ± 2 days), a greater requirement for mechanical ventilation (9.2 ± 1.4 days on ventilator, DOV), and higher creatinine plasma levels over 7 days vs. the control group of rs2065418 TG/GG high-severity trauma patients (LOS: 15.9 ± 1.2 days, p = 0.03; DOV: 5.7 ± 1 days, p = 0.04; plasma creatinine; p < 0.0001 MODScore: p = 0.0003). Furthermore, rs2065418 TT patients with ISS ≥ 25 had significantly different plasma levels of nine circulating inflammatory mediators and elevated dynamic network complexity. These studies suggest that the rs2065418 TT genotype in the MPPED2 gene is associated with altered systemic inflammation, increased organ dysfunction, and greater hospital resource utilization. A screening for this specific SNP at admission might stratify severely injured patients regarding their lung and kidney function and clinical complications.

Association Between Room Location and Adverse Outcomes in Hospitalized Patients

OBJECTIVE

To investigate whether a patient's proximity to the nurse's station or ward entrance at time of admission was associated with increased risk of adverse outcomes.

METHOD

We conducted a retrospective cohort study of consecutive adult inpatients to 13 medical-surgical wards at an academic hospital from 2009 to 2013. Proximity of admission room to the nurse's station and to the ward entrance was measured using Euclidean distances. Outcomes of interest include development of critical illness (defined as cardiac arrests or transfer to an intensive care unit), inhospital mortality, and increase in length of stay (LOS).

RESULTS

Of the 83,635 admissions, 4,129 developed critical illness and 1,316 died. The median LOS was 3 days. After adjusting for admission severity of illness, ward, shift, and year, we found no relationship between proximity at admission to nurse's station our outcomes. However, patients admitted to end of the ward had higher risk of developing critical illness (odds ratio [ OR] = 1.15, 95% confidence interval [CI] = [1.08, 1.23]), mortality ( OR = 1.16, 95% CI [1.03, 1.33]), and a higher LOS (13-hr increase, 95% CI [10, 15] hours) compared to patients admitted closer to the ward entrance. Similar results were observed in sensitivity analyses adjusting for isolation room patients and considering patients without room transfers in the first 48 hr.

CONCLUSIONS

Our study suggests that being away from the nurse's station did not increase the risk of these adverse events in ward patients, but being farther from the ward entrance was associated with increase in risk of adverse outcomes. Patient safety can be improved by recognizing this additional risk factor.

Providers' Reports of Environmental Conditions and Resources at Births in the United States

Environmental conditions and resources that may influence provider's behaviors have been investigated in birth environments focusing on location rather than conditions and available resources. Using a descriptive, cross sectional design, we surveyed a random sample of certified nurse-midwives (CNMs), obstetricians, family practice physicians, and certified professional midwives (CPMs) to describe conditions, resources, and workforce present during U.S. births. In all, 1,243 midwives and physicians reported most environmental resources were present at almost 100% of births they attended. Conditions varied: room noise acceptability restriction of phone calls/texts from any source and lighting kept to a minimum. Trainees were present at most births regardless of setting and provider type. The impact of room noise, phone calls/texting, and lighting on outcomes should be determined. The roles and impact of personnel, including trainees, should be described. The extent to which clusters of resources are associated with outcomes might provide new directions for interventions that improve care.

Safety and Security Concerns of Nurses Working in the Intensive Care Unit: A Qualitative Study

Intensive care units (ICUs) exist to serve as a safe place for critically ill patients to receive care from skilled practitioners. In this qualitative study, ICU nurses shared their perspectives on elements that promote safety and security on their units. After obtaining institutional review board approval, participants participated in telephone interviews with a nurse researcher who has experience as a bedside ICU nurse. Five categories and 14 themes were identified and then confirmed using member checking. Results indicate that participants prefer to provide care in ICUs with no more than 12 to 14 beds and provide the following: visibility of patients and coworkers; more than 1 way to exit; and can be locked in case of emergency or threat. Nearly all respondents mentioned adequate staffing as the most important attribute of a safe, secure care environment for patients and families. More research is needed to identify design features that make the most impact on providing a safe, secure ICU environment.