Performance of intensive care unit severity scoring systems across different ethnicities in the USA: a retrospective observational study

Association between lactate/albumin ratio and 28-day all-cause mortality in critically ill patients with acute myocardial infarction

Acute myocardial infarction (AMI) is a leading cause of morbidity and mortality worldwide. Early identification of high-risk patients is crucial for timely interventions and improved outcomes. The lactate/albumin ratio (LAR) has been suggest as a significant correlate for assessing the risk of mortality in critically ill patients. This study aimed to utilize the American eICU Collaborative Research Database to explore the association between baseline LAR and all-cause mortality within 28 days in ICU of critically ill patients diagnosed with AMI. We conducted a retrospective cohort study of 989 AMI patients from the eICU Collaborative Research Database. Patients were included based on ICD-9 code 410 and the universal definition of AMI. LAR was calculated as the ratio of baseline lactate to albumin levels within the first 24 h of ICU admission. The outcome was all-cause mortality within 28 days after ICU admission. Multivariable logistic regression models were used to evaluate the independent association between LAR and the risk of death, adjusting for potential confounders including demographics, comorbidities, vital signs, and laboratory parameters. Subgroup analyses and nonlinear modeling were performed to further explore the relationship. Of the 989 AMI patients, 171 (17.3%) died within 28 days after ICU admission. Patients who died had significantly higher LAR compared to survivors (1.66 vs. 0.96, p < 0.001). Multivariable analysis showed that each unit increase in LAR was associated with a 2.15-fold higher risk of all-cause mortality within 28 days after ICU admission (95% CI: 1.64-2.83, p < 0.001). Subgroup analyses confirmed the consistent association across different patient characteristics. Nonlinear modeling revealed a threshold effect, where LAR above 2.15 was no longer significantly associated with mortality. Kaplan-Meier survival analysis demonstrated lower survival probabilities for patients with higher LAR(1.0526-5.8235). The findings suggest that a higher LAR was associated with an increased risk of 28-day all-cause mortality for critically ill patients with AMI after ICU admission.

In-Hospital Triage

The intensive care unit (ICU) is a finite and expensive resource with demand not infrequently exceeding capacity. Understanding ICU capacity strain is essential to gain situational awareness. Increased capacity strain can influence ICU triage decisions, which rely heavily on clinical judgment. Having an admission and triage protocol with which clinicians are very familiar can mitigate difficult, inappropriate admissions. This article reviews these concepts and methods of in-hospital triage.

SOFA score performs worse than age for predicting mortality in patients with COVID-19

The use of the Sequential Organ Failure Assessment (SOFA) score, originally developed to describe disease morbidity, is commonly used to predict in-hospital mortality. During the COVID-19 pandemic, many protocols for crisis standards of care used the SOFA score to select patients to be deprioritized due to a low likelihood of survival. A prior study found that age outperformed the SOFA score for mortality prediction in patients with COVID-19, but was limited to a small cohort of intensive care unit (ICU) patients and did not address whether their findings were unique to patients with COVID-19. Moreover, it is not known how well these measures perform across races. In this retrospective study, we compare the performance of age and SOFA score in predicting in-hospital mortality across two cohorts: a cohort of 2,648 consecutive adult patients diagnosed with COVID-19 who were admitted to a large academic health system in the northeastern United States over a 4-month period in 2020 and a cohort of 75,601 patients admitted to one of 335 ICUs in the eICU database between 2014 and 2015. We used age and the maximum SOFA score as predictor variables in separate univariate logistic regression models for in-hospital mortality and calculated area under the receiver operator characteristic curves (AU-ROCs) and area under precision-recall curves (AU-PRCs) for each predictor in both cohorts. Among the COVID-19 cohort, age (AU-ROC 0.795, 95% CI 0.762, 0.828) had a significantly better discrimination than SOFA score (AU-ROC 0.679, 95% CI 0.638, 0.721) for mortality prediction. Conversely, age (AU-ROC 0.628 95% CI 0.608, 0.628) underperformed compared to SOFA score (AU-ROC 0.735, 95% CI 0.726, 0.745) in non-COVID-19 ICU patients in the eICU database. There was no difference between Black and White COVID-19 patients in performance of either age or SOFA Score. Our findings bring into question the utility of SOFA score-based resource allocation in COVID-19 crisis standards of care.

Development and validation of a nomogram for predicting 28-day mortality in patients with ischemic stroke

BACKGROUND/AIM

We aimed to construct a validated nomogram model for predicting short-term (28-day) ischemic stroke mortality among critically ill populations.

MATERIALS AND METHODS

We collected raw data from the Medical Information Mart for Intensive Care IV database, a comprehensive repository renowned for its depth and breadth in critical care information. Subsequently, a rigorous analytical framework was employed, incorporating a 10-fold cross-validation procedure to ensure robustness and reliability. Leveraging advanced statistical methodologies, specifically the least absolute shrinkage and selection operator regression, variables pertinent to 28-day mortality in ischemic stroke were meticulously screened. Next, binary logistic regression was utilized to establish nomogram, then applied concordance index to evaluate discrimination of the prediction models. Predictive performance of the nomogram was assessed by integrated discrimination improvement (IDI) and net reclassification index (NRI). Additionally, we generated calibration curves to assess calibrating ability. Finally, we evaluated the nomogram's net clinical benefit using decision curve analysis (DCA), in comparison with scoring systems clinically applied under common conditions.

RESULTS

A total of 2089 individuals were identified and assigned into training (n = 1443) or validation (n = 646) cohorts. Various identified risk factors, including age, ethnicity, marital status, underlying metastatic solid tumor, Charlson comorbidity index, heart rate, Glasgow coma scale, glucose concentrations, white blood cells, sodium concentrations, potassium concentrations, mechanical ventilation, use of heparin and mannitol, were associated with short-term (28-day) mortality in ischemic stroke individuals. A concordance index of 0.834 was obtained in the training dataset, indicating that our nomogram had good discriminating ability. Results of IDI and NRI in both cohorts proved that our nomogram had positive improvement of predictive performance, compared to other scoring systems. The actual and predicted incidence of mortality showed favorable concordance on calibration curves (P > 0.05). DCA curves revealed that, compared with scoring systems clinically used under common conditions, the constructed nomogram yielded a greater net clinical benefit.

CONCLUSIONS

Utilizing a comprehensive array of fourteen readily accessible variables, a prognostic nomogram was meticulously formulated and rigorously validated to provide precise prognostication of short-term mortality within the ischemic stroke cohort.

The Impact of Health Care Algorithms on Racial and Ethnic Disparities : A Systematic Review

BACKGROUND

There is increasing concern for the potential impact of health care algorithms on racial and ethnic disparities.

PURPOSE

To examine the evidence on how health care algorithms and associated mitigation strategies affect racial and ethnic disparities.

DATA SOURCES

Several databases were searched for relevant studies published from 1 January 2011 to 30 September 2023.

STUDY SELECTION

Using predefined criteria and dual review, studies were screened and selected to determine: 1) the effect of algorithms on racial and ethnic disparities in health and health care outcomes and 2) the effect of strategies or approaches to mitigate racial and ethnic bias in the development, validation, dissemination, and implementation of algorithms.

DATA EXTRACTION

Outcomes of interest (that is, access to health care, quality of care, and health outcomes) were extracted with risk-of-bias assessment using the ROBINS-I (Risk Of Bias In Non-randomised Studies - of Interventions) tool and adapted CARE-CPM (Critical Appraisal for Racial and Ethnic Equity in Clinical Prediction Models) equity extension.

DATA SYNTHESIS

Sixty-three studies (51 modeling, 4 retrospective, 2 prospective, 5 prepost studies, and 1 randomized controlled trial) were included. Heterogenous evidence on algorithms was found to: a) reduce disparities (for example, the revised kidney allocation system), b) perpetuate or exacerbate disparities (for example, severity-of-illness scores applied to critical care resource allocation), and/or c) have no statistically significant effect on select outcomes (for example, the HEART Pathway [history, electrocardiogram, age, risk factors, and troponin]). To mitigate disparities, 7 strategies were identified: removing an input variable, replacing a variable, adding race, adding a non-race-based variable, changing the racial and ethnic composition of the population used in model development, creating separate thresholds for subpopulations, and modifying algorithmic analytic techniques.

LIMITATION

Results are mostly based on modeling studies and may be highly context-specific.

CONCLUSION

Algorithms can mitigate, perpetuate, and exacerbate racial and ethnic disparities, regardless of the explicit use of race and ethnicity, but evidence is heterogeneous. Intentionality and implementation of the algorithm can impact the effect on disparities, and there may be tradeoffs in outcomes.

PRIMARY FUNDING SOURCE

Agency for Healthcare Quality and Research.

The Glycemic Ratio Is Strongly and Independently Associated With Mortality in the Critically Ill

BACKGROUND

Interventional studies investigating blood glucose (BG) management in intensive care units (ICU) have been inconclusive. New insights are needed. We assessed the ability of a new metric, the Glycemic Ratio (GR), to determine the relationship of ICU glucose control relative to preadmission glycemia and mortality.

METHODS

Retrospective cohort investigation (n = 4790) in an adult medical-surgical ICU included patients with minimum four BGs, hemoglobin (Hgb), and hemoglobin A1c (HbA1c). The GR is the quotient of mean ICU BGs (mBG) and estimated preadmission BG, derived from HbA1c.

RESULTS

Mortality displayed a J-shaped curve with GR (nadir GR 0.9), independent of background glycemia, consistent for HbA1c <6.5% vs >6.5%, and Hgb >10 g/dL vs <10 g/dL and medical versus surgical. An optimal range of GR 0.80 to 0.99 was associated with decreased mortality compared with GR above and below this range. The mBG displayed a linear relationship with mortality at lower HbA1c but diminished for HbA1c >6.5%, and dependent on preadmission glycemia. In adjusted analysis, GR remained associated with mortality (odds ratio = 2.61, 95% confidence interval = 1.48-4.62, P = .0012), but mBG did not (1.004, 1.000-1.009, .059). A single value on admission was not independently associated with mortality.

CONCLUSIONS

The GR provided new insight into malglycemia that was not apparent using mBG, or an admission value. Mortality was associated with acute change from preadmission glycemia (GR). Further assessment of the impact of GR deviations from the nadir in mortality at GR 0.80 to 0.99, as both relative hypo- and hyperglycemia, and as duration of exposure and intensity, may further define the multifaceted nature of malglycemia.

Clinical data mining: challenges, opportunities, and recommendations for translational applications

Clinical data mining of predictive models offers significant advantages for re-evaluating and leveraging large amounts of complex clinical real-world data and experimental comparison data for tasks such as risk stratification, diagnosis, classification, and survival prediction. However, its translational application is still limited. One challenge is that the proposed clinical requirements and data mining are not synchronized. Additionally, the exotic predictions of data mining are difficult to apply directly in local medical institutions. Hence, it is necessary to incisively review the translational application of clinical data mining, providing an analytical workflow for developing and validating prediction models to ensure the scientific validity of analytic workflows in response to clinical questions. This review systematically revisits the purpose, process, and principles of clinical data mining and discusses the key causes contributing to the detachment from practice and the misuse of model verification in developing predictive models for research. Based on this, we propose a niche-targeting framework of four principles: Clinical Contextual, Subgroup-Oriented, Confounder- and False Positive-Controlled (CSCF), to provide guidance for clinical data mining prior to the model's development in clinical settings. Eventually, it is hoped that this review can help guide future research and develop personalized predictive models to achieve the goal of discovering subgroups with varied remedial benefits or risks and ensuring that precision medicine can deliver its full potential.

Defining the Time-limited Trial for Patients with Critical Illness: An Official American Thoracic Society Workshop Report

In critical care, the specific, structured approach to patient care known as a "time-limited trial" has been promoted in the literature to help patients, surrogate decision makers, and clinicians navigate consequential decisions about life-sustaining therapy in the face of uncertainty. Despite promotion of the time-limited trial approach, a lack of consensus about its definition and essential elements prevents optimal clinical use and rigorous evaluation of its impact. The objectives of this American Thoracic Society Workshop Committee were to establish a consensus definition of a time-limited trial in critical care, identify the essential elements for conducting a time-limited trial, and prioritize directions for future work. We achieved these objectives through a structured search of the literature, a modified Delphi process with 100 interdisciplinary and interprofessional stakeholders, and iterative committee discussions. We conclude that a time-limited trial for patients with critical illness is a collaborative plan among clinicians and a patient and/or their surrogate decision makers to use life-sustaining therapy for a defined duration, after which the patient's response to therapy informs the decision to continue care directed toward recovery, transition to care focused exclusively on comfort, or extend the trial's duration. The plan's 16 essential elements follow four sequential phases: consider, plan, support, and reassess. We acknowledge considerable gaps in evidence about the impact of time-limited trials and highlight a concern that if inadequately implemented, time-limited trials may perpetuate unintended harm. Future work is needed to better implement this defined, specific approach to care in practice through a person-centered equity lens and to evaluate its impact on patients, surrogates, and clinicians.

Association between Patient Race and Ethnicity and Use of Invasive Ventilation in the United States

Rationale: Outcomes for people with respiratory failure in the United States vary by patient race and ethnicity. Invasive ventilation is an important treatment initiated based on expert opinion. It is unknown whether the use of invasive ventilation varies by patient race and ethnicity. Objectives: To measure 1) the association between patient race and ethnicity and the use of invasive ventilation; and 2) the change in 28-day mortality mediated by any association. Methods: We performed a multicenter cohort study of nonintubated adults receiving oxygen within 24 hours of intensive care admission using the Medical Information Mart for Intensive Care IV (MIMIC-IV, 2008-2019) and Phillips eICU (eICU, 2014-2015) databases from the United States. We modeled the association between patient race and ethnicity (Asian, Black, Hispanic, White) and invasive ventilation rate using a Bayesian multistate model that adjusted for baseline and time-varying covariates, calculated hazard ratios (HRs), and estimated 28-day hospital mortality changes mediated by differential invasive ventilation use. We reported posterior means and 95% credible intervals (CrIs). Results: We studied 38,258 patients, 52% (20,032) from MIMIC-IV and 48% (18,226) from eICU: 2% Asian (892), 11% Black (4,289), 5% Hispanic (1,964), and 81% White (31,113). Invasive ventilation occurred in 9.2% (3,511), and 7.5% (2,869) died. The adjusted rate of invasive ventilation was lower in Asian (HR, 0.82; CrI, 0.70-0.95), Black (HR, 0.78; CrI, 0.71-0.86), and Hispanic (HR, 0.70; CrI, 0.61-0.79) patients compared with White patients. For the average patient, lower rates of invasive ventilation did not mediate differences in 28-day mortality. For a patient on high-flow nasal cannula with inspired oxygen fraction of 1.0, the odds ratios for mortality if invasive ventilation rates were equal to the rate for White patients were 0.97 (CrI, 0.91-1.03) for Asian patients, 0.96 (CrI, 0.91-1.03) for Black patients, and 0.94 (CrI, 0.89-1.01) for Hispanic patients. Conclusions: Asian, Black, and Hispanic patients had lower rates of invasive ventilation than White patients. These decreases did not mediate harm for the average patient, but we could not rule out harm for patients with more severe hypoxemia.

Predicting Depression Risk in Patients With Cancer Using Multimodal Data: Algorithm Development Study

BACKGROUND

Patients with cancer starting systemic treatment programs, such as chemotherapy, often develop depression. A prediction model may assist physicians and health care workers in the early identification of these vulnerable patients.

OBJECTIVE

This study aimed to develop a prediction model for depression risk within the first month of cancer treatment.

METHODS

We included 16,159 patients diagnosed with cancer starting chemo- or radiotherapy treatment between 2008 and 2021. Machine learning models (eg, least absolute shrinkage and selection operator [LASSO] logistic regression) and natural language processing models (Bidirectional Encoder Representations from Transformers [BERT]) were used to develop multimodal prediction models using both electronic health record data and unstructured text (patient emails and clinician notes). Model performance was assessed in an independent test set (n=5387, 33%) using area under the receiver operating characteristic curve (AUROC), calibration curves, and decision curve analysis to assess initial clinical impact use.

RESULTS

Among 16,159 patients, 437 (2.7%) received a depression diagnosis within the first month of treatment. The LASSO logistic regression models based on the structured data (AUROC 0.74, 95% CI 0.71-0.78) and structured data with email classification scores (AUROC 0.74, 95% CI 0.71-0.78) had the best discriminative performance. The BERT models based on clinician notes and structured data with email classification scores had AUROCs around 0.71. The logistic regression model based on email classification scores alone performed poorly (AUROC 0.54, 95% CI 0.52-0.56), and the model based solely on clinician notes had the worst performance (AUROC 0.50, 95% CI 0.49-0.52). Calibration was good for the logistic regression models, whereas the BERT models produced overly extreme risk estimates even after recalibration. There was a small range of decision thresholds for which the best-performing model showed promising clinical effectiveness use. The risks were underestimated for female and Black patients.

CONCLUSIONS

The results demonstrated the potential and limitations of machine learning and multimodal models for predicting depression risk in patients with cancer. Future research is needed to further validate these models, refine the outcome label and predictors related to mental health, and address biases across subgroups.

Prediction of incident atrial fibrillation in hypertrophic cardiomyopathy

BACKGROUND AND AIM

Atrial fibrillation (AF) is the most common sustained arrhythmia in hypertrophic cardiomyopathy (HCM) with significant effects on outcome. We aim to compare the left atrial (LA) diameter measurement with HCM-AF Score in predicting atrial fibrillation (AF) development in HCM.

METHODS

From the regional cohort of the Campania Region, Italy, 519 HCM patients (38% women, age45 ± 17 years) without history of AF, were enrolled in the study. The primary clinical endpoint was the development of AF, defined as at least 1 episode documented by ECG.

RESULTS

During the follow-up (mean 8 ± 6, IQ range 2.5-11.2 years), 99 patients (19%) developed AF. Patients who developed AF were more symptomatic, had higher prevalence of ICD implantation, had larger LA diameter, greater left ventricular (LV) maximal wall thickness and LV outflow tract obstruction (p < 0.01). Both LA diameter and HCM-AF score were higher in patients who developed AF versus those who did not (LA diameter 49 ± 7 versus 43 ± 6 mm; HCM-AF score 22 ± 4 versus 19 ± 4; p < 0.0001); however, ROC curve analysis demonstrated that LA diameter had a significant greater area under the curve than HCM-AF Score (p < 0.0001). At 5 years follow-up, a LA diameter > 46 mm, showed a similar accuracy in predicting AF development of HCM-AF score ≥ 22, which identifies patients at high risk to develop AF.

CONCLUSION

Our analysis shows that LA diameter, a worldwide and simple echocardiographic measure, is capable alone to predict AF development in HCM patients.

Association of body temperature and mortality in critically ill patients: an observational study using two large databases

BACKGROUND

Body temperature (BT) is routinely measured and can be controlled in critical care settings. BT can impact patient outcome, but the relationship between BT and mortality has not been well-established.

METHODS

A retrospective cohort study was conducted based on the MIMIC-IV (N = 43,537) and eICU (N = 75,184) datasets. The primary outcome and exposure variables were hospital mortality and first 48-h median BT, respectively. Generalized additive models were used to model the associations between exposures and outcomes, while adjusting for patient age, sex, APS-III, SOFA, and Charlson comorbidity scores, temperature gap, as well as ventilation, vasopressor, steroids, and dialysis usage. We conducted subgroup analysis according to ICU setting, diagnoses, and demographics.

RESULTS

Optimal BT was 37 °C for the general ICU and subgroup populations. A 10% increase in the proportion of time that BT was within the 36-38 °C range was associated with reduced hospital mortality risk in both MIMIC-IV (OR 0.91; 95% CI 0.90-0.93) and eICU (OR 0.86; 95% CI 0.85-0.87). On the other hand, a 10% increase in the proportion of time when BT < 36 °C was associated with increased mortality risk in both MIMIC-IV (OR 1.08; 95% CI 1.06-1.10) and eICU (OR 1.18; 95% CI 1.16-1.19). Similarly, a 10% increase in the proportion of time when BT > 38 °C was associated with increased mortality risk in both MIMIC-IV (OR 1.09; 95% CI 1.07-1.12) and eICU (OR 1.09; 95% CI 1.08-1.11). All patient subgroups tested consistently showed an optimal temperature within the 36-38 °C range.

CONCLUSIONS

A BT of 37 °C is associated with the lowest mortality risk among ICU patients. Further studies to explore the causal relationship between the optimal BT and mortality should be conducted and may help with establishing guidelines for active BT management in critical care settings.

Interpretable machine learning models for predicting 90-day death in patients in the intensive care unit with epilepsy

PURPOSE

This study aims to develop a machine learning-based model for predicting mortality risk in patients with epilepsy admitted to the intensive care unit (ICU), providing clinicians with an accurate prognostic tool to guide individualized treatment.

METHODS

We collected clinical data from clinical databases (MIMIC IV and eICU-CRD) of epilepsy patients 24 h after ICU admission. The clinical characteristics of ICU patients with epilepsy were carefully feature selected and processed. MIMIC IV as the training set and eICU-CRD database as the test set. Six models were developed and validated, and the best LightGBM model was selected by performance comparison and analysed for interpretability.

RESULTS

The final cohort comprised 429 patients for training and 1217 for testing. The training set exhibited a 90-day mortality rate of 9.32 %, and the test set had an in-hospital 90-day mortality rate of 4.10 %. Utilizing the LightGBM model, we achieved an AUC of 0.956 in the training set. External validation demonstrated promising results with accuracy of 0.898, precision of 0.975, AUC of 0.781, F1 score of 0.945, highlighting the model's potential for guiding clinical decision-making. Significant factors influencing model performance included the severity of illness, as measured by the OASIS score, and clinical parameters like heart rate and body temperature.

CONCLUSION

This study introduces a machine learning-based approach to predict mortality risk in ICU epilepsy patients, offering a valuable tool for clinicians to identify high-risk individuals and devise personalized treatment strategies, thus improving patient prognosis and treatment outcomes.

Evaluating Prognostic Bias of Critical Illness Severity Scores Based on Age, Sex, and Primary Language in the United States: A Retrospective Multicenter Study

OBJECTIVES

Although illness severity scoring systems are widely used to support clinical decision-making and assess ICU performance, their potential bias across different age, sex, and primary language groups has not been well-studied.

DESIGN SETTING AND PATIENTS

We aimed to identify potential bias of Sequential Organ Failure Assessment (SOFA) and Acute Physiology and Chronic Health Evaluation (APACHE) IVa scores via large ICU databases.

SETTING/PATIENTS

This multicenter, retrospective study was conducted using data from the Medical Information Mart for Intensive Care (MIMIC) and eICU Collaborative Research Database. SOFA and APACHE IVa scores were obtained from ICU admission. Hospital mortality was the primary outcome. Discrimination (area under receiver operating characteristic [AUROC] curve) and calibration (standardized mortality ratio [SMR]) were assessed for all subgroups.

INTERVENTIONS

Not applicable.

MEASUREMENTS AND MAIN RESULTS

A total of 196,310 patient encounters were studied. Discrimination for both scores was worse in older patients compared with younger patients and female patients rather than male patients. In MIMIC, discrimination of SOFA in non-English primary language speakers patients was worse than that of English speakers (AUROC 0.726 vs. 0.783, p < 0.0001). Evaluating calibration via SMR showed statistically significant underestimations of mortality when compared with overall cohort in the oldest patients for both SOFA and APACHE IVa, female patients (1.09) for SOFA, and non-English primary language patients (1.38) for SOFA in MIMIC.

CONCLUSIONS

Differences in discrimination and calibration of two scores across varying age, sex, and primary language groups suggest illness severity scores are prone to bias in mortality predictions. Caution must be taken when using them for quality benchmarking and decision-making among diverse real-world populations.

Efficient adversarial debiasing with concept activation vector - Medical image case-studies

BACKGROUND

A major hurdle for the real time deployment of the AI models is ensuring trustworthiness of these models for the unseen population. More often than not, these complex models are black boxes in which promising results are generated. However, when scrutinized, these models begin to reveal implicit biases during the decision making, particularly for the minority subgroups.

METHOD

We develop an efficient adversarial de-biasing approach with partial learning by incorporating the existing concept activation vectors (CAV) methodology, to reduce racial disparities while preserving the performance of the targeted task. CAV is originally a model interpretability technique which we adopted to identify convolution layers responsible for learning race and only fine-tune up to that layer instead of fine-tuning the complete network, limiting the drop in performance RESULTS:: The methodology has been evaluated on two independent medical image case-studies - chest X-ray and mammograms, and we also performed external validation on a different racial population. On the external datasets for the chest X-ray use-case, debiased models (averaged AUC 0.87 ) outperformed the baseline convolution models (averaged AUC 0.57 ) as well as the models trained with the popular fine-tuning strategy (averaged AUC 0.81). Moreover, the mammogram models is debiased using a single dataset (white, black and Asian) and improved the performance on an external datasets (averaged AUC 0.8 to 0.86 ) with completely different population (primarily Hispanic patients).

CONCLUSION

In this study, we demonstrated that the adversarial models trained only with internal data performed equally or often outperformed the standard fine-tuning strategy with data from an external setting. The adversarial training approach described can be applied regardless of predictor's model architecture, as long as the convolution model is trained using a gradient-based method. We release the training code with academic open-source license - https://github.com/ramon349/JBI2023_TCAV_debiasing.

Race and ethnicity in the COVID-19 Critical Care Consortium: demographics, treatments, and outcomes, an international observational registry study

BACKGROUND

Improving access to healthcare for ethnic minorities is a public health priority in many countries, yet little is known about how to incorporate information on race, ethnicity, and related social determinants of health into large international studies. Most studies of differences in treatments and outcomes of COVID-19 associated with race and ethnicity are from single cities or countries.

METHODS

We present the breadth of race and ethnicity reported for patients in the COVID-19 Critical Care Consortium, an international observational cohort study from 380 sites across 32 countries. Patients from the United States, Australia, and South Africa were the focus of an analysis of treatments and in-hospital mortality stratified by race and ethnicity. Inclusion criteria were admission to intensive care for acute COVID-19 between January 14th, 2020, and February 15, 2022. Measurements included demographics, comorbidities, disease severity scores, treatments for organ failure, and in-hospital mortality.

RESULTS

Seven thousand three hundred ninety-four adults met the inclusion criteria. There was a wide variety of race and ethnicity designations. In the US, American Indian or Alaska Natives frequently received dialysis and mechanical ventilation and had the highest mortality. In Australia, organ failure scores were highest for Aboriginal/First Nations persons. The South Africa cohort ethnicities were predominantly Black African (50%) and Coloured* (28%). All patients in the South Africa cohort required mechanical ventilation. Mortality was highest for South Africa (68%), lowest for Australia (15%), and 30% in the US.

CONCLUSIONS

Disease severity was higher for Indigenous ethnicity groups in the US and Australia than for other ethnicities. Race and ethnicity groups with longstanding healthcare disparities were found to have high acuity from COVID-19 and high mortality. Because there is no global system of race and ethnicity classification, researchers designing case report forms for international studies should consider including related information, such as socioeconomic status or migration background. *Note: "Coloured" is an official, contemporary government census category of South Africa and is a term of self-identification of race and ethnicity of many citizens of South Africa.

Cell-free DNA as diagnostic and prognostic biomarkers for adult sepsis: a systematic review and meta-analysis

Although cell-free DNA (cfDNA) is an emerging sepsis biomarker, the use of cfDNA, especially as diagnostic and prognostic indicators, has surprisingly not been systemically analyzed. Data of adult patients with sepsis that conducted cfDNA measurement within 24 h of the admission was collected from PubMed, ScienceDirect, Scopus, and Cochrane Library until October 2022. The Quality in Prognosis Studies (QUIPS) and Quality Assessment in Diagnostic Studies-2 (QUADAS-2) tools were used to reduce the risk of biased assessment. The mean difference (MD) of cfDNA concentration and the standardized mean difference (SMD) between populations was calculated using Review Manager (RevMan) version 5.4.1 package software. Pooled analysis from 18 included studies demonstrated increased serum cfDNA levels in sepsis when compared with healthy control (SMD = 1.02; 95% confidence interval (CI) 0.46-1.57) or non-sepsis patients in the intensive care unit (ICU) (SMD = 1.03; 95% CI 0.65-1.40), respectively. Meanwhile, a slight decrease in the statistical value was observed when compared with non-sepsis ICU patients with SIRS (SMD = 0.74; 95% 0.41-1.06). The lower cfDNA levels were also observed in sepsis survivors compared to the non-survivors (SMD at 1.43; 95%CI 0.69-2.17) with the pooled area under the receiver operating characteristic curve (AUC) of 0.76 (95% CI 0.64-0.87) for the mortality prediction. Levels of cfDNA showed a pooled sensitivity of 0.81 (95% CI 0.75-0.86) and specificity of 0.72 (95% CI 0.65-0.78) with pooled diagnostic odd ratio (DOR) at 25.03 (95% CI 5.48-114.43) for the identification of sepsis in critically ill conditions. The cfDNA levels were significantly higher in patients with sepsis and being a helpful indicator for the critically ill conditions of sepsis. Nevertheless, results of the test must be interpreted carefully with the context of all clinical situations.

The association between blood pressure at admission and in-hospital mortality in patients with subarachnoid hemorrhage

PURPOSE

The objective of this study was to examine the association between mean arterial pressure (MAP) at admission and in-hospital mortality among patients diagnosed with subarachnoid hemorrhage (SAH).

METHODS

In this cohort study, 1420 SAH patients were categorized into four groups based on quartiles of MAP: <82 mmHg group, 82-93 mmHg group, 93-103 mmHg group, and >103 mmHg group. Furthermore, the X-tile program was used to divide all patients into four groups: < 81.7 mmHg group, 81.7-92.3 mmHg group, 92.3-103.7 mmHg group, and > 103.7 mmHg group. The association between MAP and in-hospital mortality of SAH patients was evaluated using univariate and multivariable Cox proportional hazards models. A restricted cubic spline (RCS) was plotted to explore the association between MAP at admission and in-hospital mortality in patients with SAH.

RESULTS

The median follow-up duration was 7.87 days, during which, 1219 (85.85%) patients survived. After adjusting for confounding factors, MAP <82 mmHg (hazard ratio (HR)=1.67, 95% confidence interval (CI): 1.08-2.57) or MAP >103 mmHg (HR=2.13, 95% CI: 1.38-3.29) was associated with increased risk of in-hospital mortality of SAH patients. Subgroup analysis depicted that MAP <82 mmHg or MAP >103 mmHg was associated with increased risk of in-hospital mortality in male patients or those aged ≥ 65 years. MAP >103 mmHg was linked with elevated risk of in-hospital mortality in patients aged <65 years; individuals with normal and underweight, overweight, and obesity; or people with hypertension.

CONCLUSION

The findings may offer a preliminary estimate of the optimum range for SAH patients for future randomized trials.

Illness severity assessment of older adults in critical illness using machine learning (ELDER-ICU): an international multicentre study with subgroup bias evaluation

BACKGROUND

Comorbidity, frailty, and decreased cognitive function lead to a higher risk of death in elderly patients (more than 65 years of age) during acute medical events. Early and accurate illness severity assessment can support appropriate decision making for clinicians caring for these patients. We aimed to develop ELDER-ICU, a machine learning model to assess the illness severity of older adults admitted to the intensive care unit (ICU) with cohort-specific calibration and evaluation for potential model bias.

METHODS

In this retrospective, international multicentre study, the ELDER-ICU model was developed using data from 14 US hospitals, and validated in 171 hospitals from the USA and Netherlands. Data were extracted from the Medical Information Mart for Intensive Care database, electronic ICU Collaborative Research Database, and Amsterdam University Medical Centers Database. We used six categories of data as predictors, including demographics and comorbidities, physical frailty, laboratory tests, vital signs, treatments, and urine output. Patient data from the first day of ICU stay were used to predict in-hospital mortality. We used the eXtreme Gradient Boosting algorithm (XGBoost) to develop models and the SHapley Additive exPlanations method to explain model prediction. The trained model was calibrated before internal, external, and temporal validation. The final XGBoost model was compared against three other machine learning algorithms and five clinical scores. We performed subgroup analysis based on age, sex, and race. We assessed the discrimination and calibration of models using the area under receiver operating characteristic (AUROC) and standardised mortality ratio (SMR) with 95% CIs.

FINDINGS

Using the development dataset (n=50 366) and predictive model building process, the XGBoost algorithm performed the best in all types of validations compared with other machine learning algorithms and clinical scores (internal validation with 5037 patients from 14 US hospitals, AUROC=0·866 [95% CI 0·851-0·880]; external validation in the US population with 20 541 patients from 169 hospitals, AUROC=0·838 [0·829-0·847]; external validation in European population with 2411 patients from one hospital, AUROC=0·833 [0·812-0·853]; temporal validation with 4311 patients from one hospital, AUROC=0·884 [0·869-0·897]). In the external validation set (US population), the median AUROCs of bias evaluations covering eight subgroups were above 0·81, and the overall SMR was 0·99 (0·96-1·03). The top ten risk predictors were the minimum Glasgow Coma Scale score, total urine output, average respiratory rate, mechanical ventilation use, best state of activity, Charlson Comorbidity Index score, geriatric nutritional risk index, code status, age, and maximum blood urea nitrogen. A simplified model containing only the top 20 features (ELDER-ICU-20) had similar predictive performance to the full model.

INTERPRETATION

The ELDER-ICU model reliably predicts the risk of in-hospital mortality using routinely collected clinical features. The predictions could inform clinicians about patients who are at elevated risk of deterioration. Prospective validation of this model in clinical practice and a process for continuous performance monitoring and model recalibration are needed.

FUNDING

National Institutes of Health, National Natural Science Foundation of China, National Special Health Science Program, Health Science and Technology Plan of Zhejiang Province, Fundamental Research Funds for the Central Universities, Drug Clinical Evaluate Research of Chinese Pharmaceutical Association, and National Key R&D Program of China.

Critical Bias in Critical Care Devices

Critical care data contain information about the most physiologically fragile patients in the hospital, who require a significant level of monitoring. However, medical devices used for patient monitoring suffer from measurement biases that have been largely underreported. This article explores sources of bias in commonly used clinical devices, including pulse oximeters, thermometers, and sphygmomanometers. Further, it provides a framework for mitigating these biases and key principles to achieve more equitable health care delivery.

AI pitfalls and what not to do: mitigating bias in AI

Various forms of artificial intelligence (AI) applications are being deployed and used in many healthcare systems. As the use of these applications increases, we are learning the failures of these models and how they can perpetuate bias. With these new lessons, we need to prioritize bias evaluation and mitigation for radiology applications; all the while not ignoring the impact of changes in the larger enterprise AI deployment which may have downstream impact on performance of AI models. In this paper, we provide an updated review of known pitfalls causing AI bias and discuss strategies for mitigating these biases within the context of AI deployment in the larger healthcare enterprise. We describe these pitfalls by framing them in the larger AI lifecycle from problem definition, data set selection and curation, model training and deployment emphasizing that bias exists across a spectrum and is a sequela of a combination of both human and machine factors.

Development and verification of a nomogram for predicting short-term mortality in elderly ischemic stroke populations

Stroke is a major healthcare problem worldwide, particularly in the elderly population. Despite limited research on the development of prediction models for mortality in elderly individuals with ischemic stroke, our study aimed to address this knowledge gap. By leveraging data from the Medical Information Mart for Intensive Care IV database, we collected comprehensive raw data pertaining to elderly patients diagnosed with ischemic stroke. Through meticulous screening of clinical variables associated with 28-day mortality, we successfully established a robust nomogram. To assess the performance and clinical utility of our nomogram, various statistical analyses were conducted, including the concordance index, integrated discrimination improvement (IDI), net reclassification index (NRI), calibration curves and decision curve analysis (DCA). Our study comprised a total of 1259 individuals, who were further divided into training (n = 894) and validation (n = 365) cohorts. By identifying several common clinical features, we developed a nomogram that exhibited a concordance index of 0.809 in the training dataset. Notably, our findings demonstrated positive improvements in predictive performance through the IDI and NRI analyses in both cohorts. Furthermore, calibration curves indicated favorable agreement between the predicted and actual incidence of mortality (P > 0.05). DCA curves highlighted the substantial net clinical benefit of our nomogram compared to existing scoring systems used in routine clinical practice. In conclusion, our study successfully constructed and validated a prognostic nomogram, which enables accurate short-term mortality prediction in elderly individuals with ischemic stroke.

Linking Sepsis with chronic arterial hypertension, diabetes mellitus, and socioeconomic factors in the United States: A scoping review

RATIONALE

Sepsis is a syndrome of life-threatening organ dysfunction caused by a dysregulated host immune response to infection. Social risk factors including location and poverty are associated with sepsis-related disparities. Understanding the social and biological phenotypes linked with the incidence of sepsis is warranted to identify the most at-risk populations. We aim to examine how factors in disadvantage influence health disparities related to sepsis.

METHODS

A scoping review was performed for English-language articles published in the United States from 1990 to 2022 on PubMed, Web of Science, and Scopus. Of the 2064 articles found, 139 met eligibility criteria and were included for review.

RESULTS

There is consistency across the literature of disproportionately higher rates of sepsis incidence, mortality, readmissions, and associated complications, in neighborhoods with socioeconomic disadvantage and significant poverty. Chronic arterial hypertension and diabetes mellitus also occur more frequently in the same geographic distribution as sepsis, suggesting a potential shared pathophysiology.

CONCLUSIONS

The distribution of chronic arterial hypertension, diabetes mellitus, social risk factors associated with socioeconomic disadvantage, and sepsis incidence, are clustered in specific geographical areas and linked by endothelial dysfunction. Such population factors can be utilized to create equitable interventions aimed at mitigating sepsis incidence and sepsis-related disparities.

Circulating extracellular vesicles are associated with the clinical outcomes of sepsis

Introduction

Sepsis is associated with endothelial cell (EC) dysfunction, increased vascular permeability and organ injury, which may lead to mortality, acute respiratory distress syndrome (ARDS) and acute renal failure (ARF). There are no reliable biomarkers to predict these sepsis complications at present. Recent evidence suggests that circulating extracellular vesicles (EVs) and their content caspase-1 and miR-126 may play a critical role in modulating vascular injury in sepsis; however, the association between circulating EVs and sepsis outcomes remains largely unknown.

Methods

We obtained plasma samples from septic patients (n=96) within 24 hours of hospital admission and from healthy controls (n=45). Total, monocyte- or EC-derived EVs were isolated from the plasma samples. Transendothelial electrical resistance (TEER) was used as an indicator of EC dysfunction. Caspase-1 activity in EVs was detected and their association with sepsis outcomes including mortality, ARDS and ARF was analyzed. In another set of experiments, total EVs were isolated from plasma samples of 12 septic patients and 12 non-septic critical illness controls on days 1, and 3 after hospital admission. RNAs were isolated from these EVs and Next-generation sequencing was performed. The association between miR-126 levels and sepsis outcomes such as mortality, ARDS and ARF was analyzed.

Results

Septic patients with circulating EVs that induced EC injury (lower transendothelial electrical resistance) were more likely to experience ARDS (p<0.05). Higher caspase-1 activity in total EVs, monocyte- or EC-derived EVs was significantly associated with the development of ARDS (p<0.05). MiR-126-3p levels in EC EVs were significantly decreased in ARDS patients compared with healthy controls (p<0.05). Moreover, a decline in miR-126-5p levels from day 1 to day 3 was associated with increased mortality, ARDS and ARF; while decline in miR-126-3p levels from day 1 to day 3 was associated with ARDS development.

Conclusions

Enhanced caspase-1 activity and declining miR-126 levels in circulating EVs are associated with sepsis-related organ failure and mortality. Extracellular vesicular contents may serve as novel prognostic biomarkers and/or targets for future therapeutic approaches in sepsis.

Prediction of long-term mortality in patients with ischemic stroke based on clinical characteristics on the first day of ICU admission: An easy-to-use nomogram

Background

This study aimed to establish and validate an easy-to-use nomogram for predicting long-term mortality among ischemic stroke patients.

Methods

All raw data were obtained from the Medical Information Mart for Intensive Care IV database. Clinical features associated with long-term mortality (1-year mortality) among ischemic stroke patients were identified using least absolute shrinkage and selection operator regression. Then, binary logistic regression was used to construct a nomogram, the discrimination of which was evaluated by the concordance index (C-index), integrated discrimination improvement (IDI), and net reclassification index (NRI). Finally, a calibration curve and decision curve analysis (DCA) were employed to study calibration and net clinical benefit, compared to the Glasgow Coma Scale (GCS) and the commonly used disease severity scoring system.

Results

Patients who were identified with ischemic stroke were randomly assigned into developing (n = 1,443) and verification (n = 646) cohorts. The following factors were associated with 1-year mortality among ischemic stroke patients, including age on ICU admission, marital status, underlying dementia, underlying malignant cancer, underlying metastatic solid tumor, heart rate, respiratory rate, oxygen saturation, white blood cells, anion gap, mannitol injection, invasive mechanical ventilation, and GCS. The construction of the nomogram was based on the abovementioned features. The C-index of the nomogram in the developing and verification cohorts was 0.820 and 0.816, respectively. Compared with GCS and the commonly used disease severity scoring system, the IDI and NRI of the constructed nomogram had a statistically positive improvement in predicting long-term mortality in both developing and verification cohorts (all with p < 0.001). The actual mortality was consistent with the predicted mortality in the developing (p = 0.862) and verification (p = 0.568) cohorts. Our nomogram exhibited greater net clinical benefit than GCS and the commonly used disease severity scoring system.

Conclusion

This proposed nomogram has good performance in predicting long-term mortality among ischemic stroke patients.

Picture a data scientist: a call to action for increasing diversity, equity, and inclusion in the age of AI

The lack of diversity, equity, and inclusion continues to hamper the artificial intelligence (AI) field and is especially problematic for healthcare applications. In this article, we expand on the need for diversity, equity, and inclusion, specifically focusing on the composition of AI teams. We call to action leaders at all levels to make team inclusivity and diversity the centerpieces of AI development, not the afterthought. These recommendations take into consideration mitigation at several levels, including outreach programs at the local level, diversity statements at the academic level, and regulatory steps at the federal level.

Machine Learning Models to Predict In-Hospital Mortality among Inpatients with COVID-19: Underestimation and Overestimation Bias Analysis in Subgroup Populations

Prediction of the death among COVID-19 patients can help healthcare providers manage the patients better. We aimed to develop machine learning models to predict in-hospital death among these patients. We developed different models using different feature sets and datasets developed using the data balancing method. We used demographic and clinical data from a multicenter COVID-19 registry. We extracted 10,657 records for confirmed patients with PCR or CT scans, who were hospitalized at least for 24 hours at the end of March 2021. The death rate was 16.06%. Generally, models with 60 and 40 features performed better. Among the 240 models, the C5 models with 60 and 40 features performed well. The C5 model with 60 features outperformed the rest based on all evaluation metrics; however, in external validation, C5 with 32 features performed better. This model had high accuracy (91.18%), F-score (0.916), Area under the Curve (0.96), sensitivity (94.2%), and specificity (88%). The model suggested in this study uses simple and available data and can be applied to predict death among COVID-19 patients. Furthermore, we concluded that machine learning models may perform differently in different subpopulations in terms of gender and age groups.

AI recognition of patient race in medical imaging: a modelling study

BACKGROUND

Previous studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. We aimed to conduct a comprehensive evaluation of the ability of AI to recognise a patient's racial identity from medical images.

METHODS

Using private (Emory CXR, Emory Chest CT, Emory Cervical Spine, and Emory Mammogram) and public (MIMIC-CXR, CheXpert, National Lung Cancer Screening Trial, RSNA Pulmonary Embolism CT, and Digital Hand Atlas) datasets, we evaluated, first, performance quantification of deep learning models in detecting race from medical images, including the ability of these models to generalise to external environments and across multiple imaging modalities. Second, we assessed possible confounding of anatomic and phenotypic population features by assessing the ability of these hypothesised confounders to detect race in isolation using regression models, and by re-evaluating the deep learning models by testing them on datasets stratified by these hypothesised confounding variables. Last, by exploring the effect of image corruptions on model performance, we investigated the underlying mechanism by which AI models can recognise race.

FINDINGS

In our study, we show that standard AI deep learning models can be trained to predict race from medical images with high performance across multiple imaging modalities, which was sustained under external validation conditions (x-ray imaging [area under the receiver operating characteristics curve (AUC) range 0·91-0·99], CT chest imaging [0·87-0·96], and mammography [0·81]). We also showed that this detection is not due to proxies or imaging-related surrogate covariates for race (eg, performance of possible confounders: body-mass index [AUC 0·55], disease distribution [0·61], and breast density [0·61]). Finally, we provide evidence to show that the ability of AI deep learning models persisted over all anatomical regions and frequency spectrums of the images, suggesting the efforts to control this behaviour when it is undesirable will be challenging and demand further study.

INTERPRETATION

The results from our study emphasise that the ability of AI deep learning models to predict self-reported race is itself not the issue of importance. However, our finding that AI can accurately predict self-reported race, even from corrupted, cropped, and noised medical images, often when clinical experts cannot, creates an enormous risk for all model deployments in medical imaging.

FUNDING

National Institute of Biomedical Imaging and Bioengineering, MIDRC grant of National Institutes of Health, US National Science Foundation, National Library of Medicine of the National Institutes of Health, and Taiwan Ministry of Science and Technology.

Origin of Sepsis Associated with the Short-Term Mortality of Patients: A Retrospective Study Using the eICU Collaborative Research Database

OBJECTIVE

The aim of this study was to compare the clinical characteristics and short-term mortality of patients with abdominal and pulmonary sepsis.

DESIGN

Retrospective cohort study.

SETTING

Adult intensive care units (ICUs) at tertiary hospitals.

PARTICIPANTS

Adult ICU patients from 2014 to 2015 in the eICU Collaborative Research Database.

INTERVENTIONS

In univariate analysis, we compared the differences in the characteristics of patients in each group. Logistic regression models were used to evaluate the relationships between primary site of sepsis and short-term prognosis.

PRIMARY AND SECONDARY OUTCOME MEASURES

Hospital and ICU survival.

RESULTS

The final dataset included 7023 pulmonary and 2360 abdominal sepsis patients, who accounted for 74.84% and 25.16%, respectively. We compared the results of the baseline characteristics, vital signs and laboratory indicators between the two groups. In the logistic regression models, we found that the hospital and ICU mortality of patients with abdominal sepsis was higher than that with pulmonary sepsis (p < 0.05, OR = 1.15, p < 0.05, OR = 1.19, respectively), although these results were no longer significantly after adjustment for confounders, but in the subgroups with SOFA score ≧ 8, the adjusted hospital mortality rate of patients with abdominal sepsis was 1.30 times higher than that of patients with pulmonary sepsis (p < 0.005, OR = 1.30, 95% CI 1.09-1.55), while there was no significant difference in the subgroups that SOFA score < 8.

CONCLUSION

In the patients with SOFA score ≧ 8, the adjusted hospital mortality of patients with abdominal sepsis was higher than patients with pulmonary sepsis.

Predictive Value of Sequential Organ Failure Assessment Score across Patients with and without COVID-19 Infection

Rationale

Sequential organ failure assessment (SOFA) scores are commonly used in crisis standards of care policies to assist in resource allocation. The relative predictive value of SOFA by coronavirus disease (COVID-19) infection status and among racial and ethnic subgroups within patients infected with COVID-19 is unknown.

Objectives

To evaluate the accuracy and calibration of SOFA in predicting hospital mortality by COVID-19 infection status and across racial and ethnic subgroups.

Methods

We performed a retrospective cohort study of adult admissions to the University of Miami Hospital and Clinics inpatient wards (July 1, 2020–April 1, 2021). We primarily considered maximum SOFA within 48 hours of hospitalization. We assessed accuracy using the area under the receiver operating characteristic curve (AUROC) and created calibration belts. Considered subgroups were defined by COVID-19 infection status (by severe acute respiratory syndrome coronavirus 2 polymerase chain reaction testing) and prevalent racial and ethnic minorities. Comparisons across subgroups were made with DeLong testing for discriminative accuracy and visualization of calibration belts.

Results

Our primary cohort consisted of 20,045 hospitalizations, of which 1,894 (9.5%) were COVID-19 positive. SOFA was similarly accurate for COVID-19–positive (AUROC, 0.835) and COVID-19–negative (AUROC, 0.810; P = 0.15) admissions but was slightly better calibrated in patients who were positive for COVID-19. For those with critical illness, maximum SOFA score accuracy at critical illness onset also did not differ by COVID-19 status (AUROC, COVID-19 positive vs. negative: intensive care unit admissions, 0.751 vs. 0.775; P = 0.46; mechanically ventilated, 0.713 vs. 0.792, P = 0.13), and calibration was again better for patients positive for COVID-19. Among patients with COVID-19, SOFA accuracy was similar between the non-Hispanic White population (AUROC, 0.894) and racial and ethnic minorities (Hispanic White population: AUROC, 0.824 [P vs. non-Hispanic White = 0.05]; non-Hispanic Black population: AUROC, 0.800 [P = 0.12]; Hispanic Black population: AUROC, 0.948 [P = 0.31]). This similar accuracy was also found for those without COVID-19 (non-Hispanic White population: AUROC, 0.829; Hispanic White population: AUROC, 0.811 [P = 0.37]; Hispanic Black population: AUROC, 0.828 [P = 0.97]; non-Hispanic Black population: AUROC, 0.867 [P = 0.46]). SOFA was well calibrated for all racial and ethnic groups with COVID-19 but estimated mortality more variably and performed less well across races and ethnicities without COVID-19.

Conclusions

SOFA accuracy does not differ by COVID-19 status and is similar among racial and ethnic groups both with and without COVID-19. Calibration is better for COVID-19–infected patients and, among those without COVID-19, varies by race and ethnicity.

Comparison of prognosis predictive value of 4 disease severity scoring systems in patients with acute respiratory failure in intensive care unit: A STROBE report

Various disease severity scoring systems were currently used in critically ill patients with acute respiratory failure, while their performances were not well investigated.The study aimed to investigate the difference in prognosis predictive value of 4 different disease severity scoring systems in patients with acute respiratory failure.With a retrospective cohort study design, adult patients admitted to intensive care unit (ICU) with acute respiratory failure were screened and relevant data were extracted from an open-access American intensive care database to calculate the following disease severity scores on ICU admission: acute physiology score (APS) III, Sequential Organ Failure Assessment score (SOFA), quick SOFA (qSOFA), and Oxford Acute Severity of Illness Score (OASIS). Hospital mortality was chosen as the primary outcome. Multivariable logistic regression analyses were performed to analyze the association of each scoring system with the outcome. Receiver operating characteristic curve analyses were conducted to evaluate the prognosis predictive performance of each scoring system.A total of 4828 patients with acute respiratory failure were enrolled with a hospital mortality rate of 16.78%. APS III (odds ratio [OR] 1.03, 95% confidence interval [CI] 1.02-1.03), SOFA (OR 1.15, 95% CI 1.12-1.18), qSOFA (OR 1.26, 95% CI 1.11-1.42), and OASIS (OR 1.06, 95% CI 1.05-1.08) were all significantly associated with hospital mortality after adjustment for age and comorbidities. Receiver operating characteristic analyses showed that APS III had the highest area under the curve (AUC) (0.703, 95% CI 0.683-0.722), and SOFA and OASIS shared similar predictive performance (area under the curve 0.653 [95% CI 0.631-0.675] and 0.664 [95% CI 0.644-0.685], respectively), while qSOFA had the worst predictive performance for predicting hospital mortality (0.553, 95% CI 0.535-0.572).These results suggested the prognosis predictive value varied among the 4 different disease severity scores for patients admitted to ICU with acute respiratory failure.

Harnessing of real world data and real world evidence using digital tools: utility and potential models in rheumatology practice

The diversity of diseases in rheumatology and variability in disease prevalence necessitates greater data parity in disease presentation, treatment responses including adverse events to drugs and various co-morbidities. Randomized Controlled Trials (RCTs) are the gold standard for drug development and performance evaluation. However, when the drug is applied outside the controlled environment the outcomes may differ in patient population. In this context, the need to understand the macro and micro changes involved in disease evolution and progression becomes important and so is the need for harvesting and harnessing the Real-World Data (RWD) from various resources to use them in generating Real World Evidence (RWE). Digital tools with potential relevance to rheumatology can be potentially leveraged to obtain greater patient insights, greater information on disease progression and disease micro processes and even in the early diagnosis of diseases. Since the patients spend only a minuscule proportion of their time in hospital or in a clinic, using the modern digital tools to generate realistic, bias proof RWD in non-invasive patient friendly manner becomes critical. In this review we have appraised different digital mediums and mechanisms for collecting RWD and proposed digital care models for generating RWE in rheumatology.

Contraindications to the Initiation of Veno-Venous ECMO for Severe Acute Respiratory Failure in Adults: A Systematic Review and Practical Approach Based on the Current Literature

(1) Background: Extracorporeal membrane oxygenation (ECMO) is increasingly used for acute respiratory failure with few absolute but many relative contraindications. The provider in charge often has a difficult time weighing indications and contraindications to anticipate if the patient will benefit from this treatment, a decision that often decides life and death for the patient. To assist in this process in coming to a good evidence-based decision, we reviewed the available literature. (2) Methods: We performed a systematic review through a literature search of the MEDLINE database of former and current absolute and relative contraindications to the initiation of ECMO treatment. (3) Results: The following relative and absolute contraindications were identified in the literature: absolute-refusal of the use of extracorporeal techniques by the patient, advanced stage of cancer, fatal intracerebral hemorrhage/cerebral herniation/intractable intracranial hypertension, irreversible destruction of the lung parenchyma without the possibility of transplantation, and contraindications to lung transplantation; relative-advanced age, immunosuppressed patients/pharmacological immunosuppression, injurious ventilator settings > 7 days, right-heart failure, hematologic malignancies, especially bone marrow transplantation and graft-versus-host disease, SAPS II score ≥ 60 points, SOFA score > 12 points, PRESERVE score ≥ 5 points, RESP score ≤ -2 points, PRESET score ≥ 6 points, and "do not attempt resuscitation" order (DN(A)R status). (4) Conclusions: We provide a simple-to-follow algorithm that incorporates absolute and relative contraindications to the initiation of ECMO treatment. This algorithm attempts to weigh pros and cons regarding the benefit for an individual patient and hopefully assists caregivers to make better, informed decisions.