Origins of Racial and Ethnic Bias in Pulmonary Technologies.

Understanding how biases originate in medical technologies and developing safeguards to identify, mitigate, and remove their harms are essential to ensuring equal performance in all individuals. Drawing upon examples from pulmonary medicine, this article describes how bias can be introduced in the physical aspects of the technology design, via unrepresentative data, or by conflation of biological with social determinants of health. It then can be perpetuated by inadequate evaluation and regulatory standards. Research demonstrates that pulse oximeters perform differently depending on patient race and ethnicity. Pulmonary function testing and algorithms used to predict healthcare needs are two additional examples of medical technologies with racial and ethnic biases that may perpetuate health disparities.

Shift-Level Team Familiarity Is Associated with Improved Outcomes in Mechanically Ventilated Adults.

RATIONALE: Organizing intensive care unit (ICU) interprofessional teams is a high priority due to workforce needs, but the role of interprofessional familiarity remains unexplored. OBJECTIVE: Determine if mechanically ventilated patients cared for by teams with greater familiarity have improved outcomes, such as lower mortality, shorter duration of mechanical ventilation (MV), and greater spontaneous breathing trial (SBT) implementation. METHODS: We used electronic health records data of 5 ICUs in an academic medical center to map interprofessional teams and their ICU networks, measuring team familiarity as network coreness and mean team value. We used patient-level regression models to link team familiarity with patient outcomes, accounting for patient/unit factors. We also performed a split-sample analysis by using 2018 team familiarity data to predict 2019 outcomes. MEASUREMENTS: Team familiarity was measured as the average number of patients shared by each clinician with all other clinicians in the ICU (i.e., coreness) and the average number of patients shared by any two members of the team (i.e., mean team value). MAIN RESULTS: Among 4,485 encounters, unadjusted mortality was 12.9%, average duration of MV was 2.32 days and SBT implementation was 89%; average team coreness was 467.2 (SD = 96.15) and average mean team value was 87.02 (SD=42.42). A standard-deviation increase in team coreness was significantly associated with a 4.5% greater probability of SBT implementation, 23% shorter MV duration, and 3.8% lower probability of dying; mean team value was significantly associated with lower mortality. Split-sample results were attenuated but congruent in direction and interpretation. CONCLUSIONS: Interprofessional familiarity was associated with improved outcomes; assignment models that prioritize familiarity might be a novel solution.

The Lung Microbiome Predicts Mortality and Response to Azithromycin in Lung Transplant Recipients with Chronic Rejection.

Rationale: Chronic lung allograft dysfunction (CLAD) is the leading cause of death after lung transplant, and azithromycin has variable efficacy in CLAD. The lung microbiome is a risk factor for developing CLAD, but the relationship between lung dysbiosis, pulmonary inflammation, and allograft dysfunction remains poorly understood. Whether lung microbiota predict outcomes or modify treatment response after CLAD is unknown. Objectives: To determine whether lung microbiota predict post-CLAD outcomes and clinical response to azithromycin. Methods: Retrospective cohort study using acellular BAL fluid prospectively collected from recipients of lung transplant within 90 days of CLAD onset. Lung microbiota were characterized using 16S rRNA gene sequencing and droplet digital PCR. In two additional cohorts, causal relationships of dysbiosis and inflammation were evaluated by comparing lung microbiota with CLAD-associated cytokines and measuring ex vivo P. aeruginosa growth in sterilized BAL fluid. Measurements and Main Results: Patients with higher bacterial burden had shorter post-CLAD survival, independent of CLAD phenotype, azithromycin treatment, and relevant covariates. Azithromycin treatment improved survival in patients with high bacterial burden but had negligible impact on patients with low or moderate burden. Lung bacterial burden was positively associated with CLAD-associated cytokines, and ex vivo growth of P. aeruginosa was augmented in BAL fluid from transplant recipients with CLAD. Conclusions: In recipients of lung transplants with chronic rejection, increased lung bacterial burden is an independent risk factor for mortality and predicts clinical response to azithromycin. Lung bacterial dysbiosis is associated with alveolar inflammation and may be promoted by underlying lung allograft dysfunction.

Higher versus lower oxygenation targets in adult ICU patients: A rapid practice guideline.

The aim of this Intensive Care Medicine Rapid Practice Guideline (ICM-RPG) was to provide evidence-based clinical guidance about the use of higher versus lower oxygenation targets for adult patients in the intensive care unit (ICU). The guideline panel comprised 27 international panelists, including content experts, ICU clinicians, methodologists, and patient representatives. We adhered to the methodology for trustworthy clinical practice guidelines, including the use of the Grading of Recommendations Assessment, Development, and Evaluation approach to assess the certainty of evidence, and used the Evidence-to-Decision framework to generate recommendations. A recently published updated systematic review and meta-analysis constituted the evidence base. Through teleconferences and web-based discussions, the panel provided input on the balance and magnitude of the desirable and undesirable effects, the certainty of evidence, patients' values and preferences, costs and resources, equity, feasibility, acceptability, and research priorities. The updated systematic review and meta-analysis included data from 17 randomized clinical trials with 10,248 participants. There was little to no difference between the use of higher versus lower oxygenation targets for all outcomes with available data, including all-cause mortality, serious adverse events, stroke, functional outcomes, cognition, and health-related quality of life (very low certainty of evidence). The panel felt that values and preferences, costs and resources, and equity favored the use of lower oxygenation targets. The ICM-RPG panel issued one conditional recommendation against the use of higher oxygenation targets: "We suggest against the routine use of higher oxygenation targets in adult ICU patients (conditional recommendation, very low certainty of evidence). Remark: an oxygenation target of SpO2 88%-92% or PaO2 8 kPa/60 mmHg is relevant and safe for most adult ICU patients."

The Gut Microbiome Modulates Body Temperature Both in Sepsis and Health.

Rationale: Among patients with sepsis, variation in temperature trajectories predicts clinical outcomes. In healthy individuals, normal body temperature is variable and has decreased consistently since the 1860s. The biologic underpinnings of this temperature variation in disease and health are unknown. Objectives: To establish and interrogate the role of the gut microbiome in calibrating body temperature. Methods: We performed a series of translational analyses and experiments to determine whether and how variation in gut microbiota explains variation in body temperature in sepsis and in health. We studied patient temperature trajectories using electronic medical record data. We characterized gut microbiota in hospitalized patients using 16S ribosomal RNA gene sequencing. We modeled sepsis using intraperitoneal LPS in mice and modulated the microbiome using antibiotics, germ-free, and gnotobiotic animals. Measurements and Main Results: Consistent with prior work, we identified four temperature trajectories in patients hospitalized with sepsis that predicted clinical outcomes. In a separate cohort of 116 hospitalized patients, we found that the composition of patients' gut microbiota at admission predicted their temperature trajectories. Compared with conventional mice, germ-free mice had reduced temperature loss during experimental sepsis. Among conventional mice, heterogeneity of temperature response in sepsis was strongly explained by variation in gut microbiota. Healthy germ-free and antibiotic-treated mice both had lower basal body temperatures compared with control animals. The Lachnospiraceae family was consistently associated with temperature trajectories in hospitalized patients, experimental sepsis, and antibiotic-treated mice. Conclusions: The gut microbiome is a key modulator of body temperature variation in both health and critical illness and is thus a major, understudied target for modulating physiologic heterogeneity in sepsis.

In critically ill patients, anti-anaerobic antibiotics increase risk of adverse clinical outcomes.

BACKGROUND: Critically ill patients routinely receive antibiotics with activity against anaerobic gut bacteria. However, in other disease states and animal models, gut anaerobes are protective against pneumonia, organ failure and mortality. We therefore designed a translational series of analyses and experiments to determine the effects of anti-anaerobic antibiotics on the risk of adverse clinical outcomes among critically ill patients. METHODS: We conducted a retrospective single-centre cohort study of 3032 critically ill patients, comparing patients who did and did not receive early anti-anaerobic antibiotics. We compared intensive care unit outcomes (ventilator-associated pneumonia (VAP)-free survival, infection-free survival and overall survival) in all patients and changes in gut microbiota in a subcohort of 116 patients. In murine models, we studied the effects of anaerobe depletion in infectious (Klebsiella pneumoniae and Staphylococcus aureus pneumonia) and noninfectious (hyperoxia) injury models. RESULTS: Early administration of anti-anaerobic antibiotics was associated with decreased VAP-free survival (hazard ratio (HR) 1.24, 95% CI 1.06-1.45), infection-free survival (HR 1.22, 95% CI 1.09-1.38) and overall survival (HR 1.14, 95% CI 1.02-1.28). Patients who received anti-anaerobic antibiotics had decreased initial gut bacterial density (p=0.00038), increased microbiome expansion during hospitalisation (p=0.011) and domination by Enterobacteriaceae spp. (p=0.045). Enterobacteriaceae were also enriched among respiratory pathogens in anti-anaerobic-treated patients (p<2.2×10-16). In murine models, treatment with anti-anaerobic antibiotics increased susceptibility to Enterobacteriaceae pneumonia (p<0.05) and increased the lethality of hyperoxia (p=0.0002). CONCLUSIONS: In critically ill patients, early treatment with anti-anaerobic antibiotics is associated with increased mortality. Mechanisms may include enrichment of the gut with respiratory pathogens, but increased mortality is incompletely explained by infections alone. Given consistent clinical and experimental evidence of harm, the widespread use of anti-anaerobic antibiotics should be reconsidered.

External Validation and Comparison of a General Ward Deterioration Index Between Diversely Different Health Systems.

OBJECTIVES: Implementing a predictive analytic model in a new clinical environment is fraught with challenges. Dataset shifts such as differences in clinical practice, new data acquisition devices, or changes in the electronic health record (EHR) implementation mean that the input data seen by a model can differ significantly from the data it was trained on. Validating models at multiple institutions is therefore critical. Here, using retrospective data, we demonstrate how Predicting Intensive Care Transfers and other UnfoReseen Events (PICTURE), a deterioration index developed at a single academic medical center, generalizes to a second institution with significantly different patient population. DESIGN: PICTURE is a deterioration index designed for the general ward, which uses structured EHR data such as laboratory values and vital signs. SETTING: The general wards of two large hospitals, one an academic medical center and the other a community hospital. SUBJECTS: The model has previously been trained and validated on a cohort of 165,018 general ward encounters from a large academic medical center. Here, we apply this model to 11,083 encounters from a separate community hospital. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The hospitals were found to have significant differences in missingness rates (> 5% difference in 9/52 features), deterioration rate (4.5% vs 2.5%), and racial makeup (20% non-White vs 49% non-White). Despite these differences, PICTURE's performance was consistent (area under the receiver operating characteristic curve [AUROC], 0.870; 95% CI, 0.861-0.878), area under the precision-recall curve (AUPRC, 0.298; 95% CI, 0.275-0.320) at the first hospital; AUROC 0.875 (0.851-0.902), AUPRC 0.339 (0.281-0.398) at the second. AUPRC was standardized to a 2.5% event rate. PICTURE also outperformed both the Epic Deterioration Index and the National Early Warning Score at both institutions. CONCLUSIONS: Important differences were observed between the two institutions, including data availability and demographic makeup. PICTURE was able to identify general ward patients at risk of deterioration at both hospitals with consistent performance (AUROC and AUPRC) and compared favorably to existing metrics.

Association between choice of reversal agent for neuromuscular block and postoperative pulmonary complications in patients at increased risk undergoing non-emergency surgery: STIL-STRONGER, a multicentre matched cohort study.

BACKGROUND: Postoperative pulmonary complications are a source of morbidity after major surgery. In patients at increased risk of postoperative pulmonary complications we sought to assess the association between neuromuscular blocking agent reversal agent and development of postoperative pulmonary complications. METHODS: We conducted a retrospective matched cohort study, a secondary analysis of data collected in the prior STRONGER study. Data were obtained from the Multicenter Perioperative Outcomes Group. Included patients were aged 18 yr and older undergoing non-emergency surgery under general anaesthesia with tracheal intubation with neuromuscular block and reversal, who were predicted to be at elevated risk of postoperative pulmonary complications. This risk was defined as American Society of Anesthesiologists Physical Status 3 or 4 in patients undergoing either intrathoracic or intra-abdominal surgery who were either aged >80 yr or underwent a procedure lasting >2 h. Cohorts were defined by reversal with neostigmine or sugammadex. The primary composite outcome was the occurrence of pneumonia or respiratory failure. RESULTS: After matching by institution, sex, age (within 5 yr), body mass index, anatomic region of surgery, comorbidities, and neuromuscular blocking agent, 3817 matched pairs remained. The primary postoperative pulmonary complications outcome occurred in 224 neostigmine cases vs 100 sugammadex cases (5.9% vs 2.6%, odds ratio 0.41, P<0.01). After adjustment for unbalanced covariates, the adjusted odds ratio for the association between sugammadex use and the primary outcome was 0.39 (P<0.0001). CONCLUSIONS: In a cohort of patients at increased risk for pulmonary complications compared with neostigmine, use of sugammadex was independently associated with reduced risk of subsequent development of pneumonia or respiratory failure.

Prediction of episode of hemodynamic instability using an electrocardiogram based analytic: a retrospective cohort study.

BACKGROUND: Predicting the onset of hemodynamic instability before it occurs remains a sought-after goal in acute and critical care medicine. Technologies that allow for this may assist clinicians in preventing episodes of hemodynamic instability (EHI). We tested a novel noninvasive technology, the Analytic for Hemodynamic Instability-Predictive Indicator (AHI-PI), which analyzes a single lead of electrocardiogram (ECG) and extracts heart rate variability and morphologic waveform features to predict an EHI prior to its occurrence. METHODS: Retrospective cohort study at a quaternary care academic health system using data from hospitalized adult patients between August 2019 and April 2020 undergoing continuous ECG monitoring with intermittent noninvasive blood pressure (NIBP) or with continuous intraarterial pressure (IAP) monitoring. RESULTS: AHI-PI's low and high-risk indications were compared with the presence of EHI in the future as indicated by vital signs (heart rate > 100 beats/min with a systolic blood pressure < 90 mmHg or a mean arterial blood pressure of < 70 mmHg). 4,633 patients were analyzed (3,961 undergoing NIBP monitoring, 672 with continuous IAP monitoring). 692 patients had an EHI (380 undergoing NIBP, 312 undergoing IAP). For IAP patients, the sensitivity and specificity of AHI-PI to predict EHI was 89.7% and 78.3% with a positive and negative predictive value of 33.7% and 98.4% respectively. For NIBP patients, AHI-PI had a sensitivity and specificity of 86.3% and 80.5% with a positive and negative predictive value of 11.7% and 99.5% respectively. Both groups performed with an AUC of 0.87. AHI-PI predicted EHI in both groups with a median lead time of 1.1 h (average lead time of 3.7 h for IAP group, 2.9 h for NIBP group). CONCLUSIONS: AHI-PI predicted EHIs with high sensitivity and specificity and within clinically significant time windows that may allow for intervention. Performance was similar in patients undergoing NIBP and IAP monitoring.

Measuring the Impact of AI in the Diagnosis of Hospitalized Patients: A Randomized Clinical Vignette Survey Study.

Importance: Artificial intelligence (AI) could support clinicians when diagnosing hospitalized patients; however, systematic bias in AI models could worsen clinician diagnostic accuracy. Recent regulatory guidance has called for AI models to include explanations to mitigate errors made by models, but the effectiveness of this strategy has not been established. Objectives: To evaluate the impact of systematically biased AI on clinician diagnostic accuracy and to determine if image-based AI model explanations can mitigate model errors. Design, Setting, and Participants: Randomized clinical vignette survey study administered between April 2022 and January 2023 across 13 US states involving hospitalist physicians, nurse practitioners, and physician assistants. Interventions: Clinicians were shown 9 clinical vignettes of patients hospitalized with acute respiratory failure, including their presenting symptoms, physical examination, laboratory results, and chest radiographs. Clinicians were then asked to determine the likelihood of pneumonia, heart failure, or chronic obstructive pulmonary disease as the underlying cause(s) of each patient's acute respiratory failure. To establish baseline diagnostic accuracy, clinicians were shown 2 vignettes without AI model input. Clinicians were then randomized to see 6 vignettes with AI model input with or without AI model explanations. Among these 6 vignettes, 3 vignettes included standard-model predictions, and 3 vignettes included systematically biased model predictions. Main Outcomes and Measures: Clinician diagnostic accuracy for pneumonia, heart failure, and chronic obstructive pulmonary disease. Results: Median participant age was 34 years (IQR, 31-39) and 241 (57.7%) were female. Four hundred fifty-seven clinicians were randomized and completed at least 1 vignette, with 231 randomized to AI model predictions without explanations, and 226 randomized to AI model predictions with explanations. Clinicians' baseline diagnostic accuracy was 73.0% (95% CI, 68.3% to 77.8%) for the 3 diagnoses. When shown a standard AI model without explanations, clinician accuracy increased over baseline by 2.9 percentage points (95% CI, 0.5 to 5.2) and by 4.4 percentage points (95% CI, 2.0 to 6.9) when clinicians were also shown AI model explanations. Systematically biased AI model predictions decreased clinician accuracy by 11.3 percentage points (95% CI, 7.2 to 15.5) compared with baseline and providing biased AI model predictions with explanations decreased clinician accuracy by 9.1 percentage points (95% CI, 4.9 to 13.2) compared with baseline, representing a nonsignificant improvement of 2.3 percentage points (95% CI, -2.7 to 7.2) compared with the systematically biased AI model. Conclusions and Relevance: Although standard AI models improve diagnostic accuracy, systematically biased AI models reduced diagnostic accuracy, and commonly used image-based AI model explanations did not mitigate this harmful effect. Trial Registration: ClinicalTrials.gov Identifier: NCT06098950.

Asthma and coronavirus disease 2019-related outcomes in hospitalized patients: A single-center experience.

BACKGROUND: Several chronic conditions have been associated with a higher risk of severe coronavirus disease 2019 (COVID-19), including asthma. However, there are conflicting conclusions regarding risk of severe disease in this population. OBJECTIVE: To understand the impact of asthma on COVID-19 outcomes in a cohort of hospitalized patients and whether there is any association between asthma severity and worse outcomes. METHODS: We identified hospitalized patients with COVID-19 with confirmatory polymerase chain reaction testing with (n = 183) and without asthma (n = 1319) using International Classification of Diseases, Tenth Revision, codes between March 1 and December 30, 2020. We determined asthma maintenance medications, pulmonary function tests, highest historical absolute eosinophil count, and immunoglobulin E. Primary outcomes included death, mechanical ventilation, intensive care unit (ICU) admission, and ICU and hospital length of stay. Analysis was adjusted for demographics, comorbidities, smoking status, and timing of illness in the pandemic. RESULTS: In unadjusted analyses, we found no difference in our primary outcomes between patients with asthma and patients without asthma. However, in adjusted analyses, patients with asthma were more likely to have mechanical ventilation (odds ratio, 1.58; 95% confidence interval [CI], 1.02-2.44; P = .04), ICU admission (odds ratio, 1.58; 95% CI, 1.09-2.29; P = .02), longer hospital length of stay (risk ratio, 1.30; 95% CI, 1.09-1.55; P < .003), and higher mortality (hazard ratio, 1.53; 95% CI, 1.01-2.33; P = .04) compared with the non-asthma cohort. Inhaled corticosteroid use and eosinophilic phenotype were not associated with considerabledifferences. Interestingly, patients with moderate asthma had worse outcomes whereas patients with severe asthma did not. CONCLUSION: Asthma was associated with severe COVID-19 after controlling for other factors.

Lung Microbiota Predict Clinical Outcomes in Critically Ill Patients.

Rationale: Recent studies have revealed that, in critically ill patients, lung microbiota are altered and correlate with alveolar inflammation. The clinical significance of altered lung bacteria in critical illness is unknown.Objectives: To determine if clinical outcomes of critically ill patients are predicted by features of the lung microbiome at the time of admission.Methods: We performed a prospective, observational cohort study in an ICU at a university hospital. Lung microbiota were quantified and characterized using droplet digital PCR and bacterial 16S ribosomal RNA gene quantification and sequencing. Primary predictors were the bacterial burden, community diversity, and community composition of lung microbiota. The primary outcome was ventilator-free days, determined at 28 days after admission.Measurements and Main Results: Lungs of 91 critically ill patients were sampled using miniature BAL within 24 hours of ICU admission. Patients with increased lung bacterial burden had fewer ventilator-free days (hazard ratio, 0.43; 95% confidence interval, 0.21-0.88), which remained significant when the analysis was controlled for pneumonia and severity of illness. The community composition of lung bacteria predicted ventilator-free days (P = 0.003), driven by the presence of gut-associated bacteria (e.g., species of the Lachnospiraceae and Enterobacteriaceae families). Detection of gut-associated bacteria was also associated with the presence of acute respiratory distress syndrome.Conclusions: Key features of the lung microbiome (bacterial burden and enrichment with gut-associated bacteria) predict outcomes in critically ill patients. The lung microbiome is an understudied source of clinical variation in critical illness and represents a novel therapeutic target for the prevention and treatment of acute respiratory failure.

Causes and characteristics of death in patients with acute hypoxemic respiratory failure and acute respiratory distress syndrome: a retrospective cohort study.

BACKGROUND: Acute hypoxemic respiratory failure (AHRF) and acute respiratory distress syndrome (ARDS) are associated with high in-hospital mortality. However, in cohorts of ARDS patients from the 1990s, patients more commonly died from sepsis or multi-organ failure rather than refractory hypoxemia. Given increased attention to lung-protective ventilation and sepsis treatment in the past 25 years, we hypothesized that causes of death may be different among contemporary cohorts. These differences may provide clinicians with insight into targets for future therapeutic interventions. METHODS: We identified adult patients hospitalized at a single tertiary care center (2016-2017) with AHRF, defined as PaO2/FiO2 ≤ 300 while receiving invasive mechanical ventilation for > 12 h, who died during hospitalization. ARDS was adjudicated by multiple physicians using the Berlin definition. Separate abstractors blinded to ARDS status collected data on organ dysfunction and withdrawal of life support using a standardized tool. The primary cause of death was defined as the organ system that most directly contributed to death or withdrawal of life support. RESULTS: We identified 385 decedents with AHRF, of whom 127 (33%) had ARDS. The most common primary causes of death were sepsis (26%), pulmonary dysfunction (22%), and neurologic dysfunction (19%). Multi-organ failure was present in 70% at time of death, most commonly due to sepsis (50% of all patients), and 70% were on significant respiratory support at the time of death. Only 2% of patients had insupportable oxygenation or ventilation. Eighty-five percent died following withdrawal of life support. Patients with ARDS more often had pulmonary dysfunction as the primary cause of death (28% vs 19%; p = 0.04) and were also more likely to die while requiring significant respiratory support (82% vs 64%; p <  0.01). CONCLUSIONS: In this contemporary cohort of patients with AHRF, the most common primary causes of death were sepsis and pulmonary dysfunction, but few patients had insupportable oxygenation or ventilation. The vast majority of deaths occurred after withdrawal of life support. ARDS patients were more likely to have pulmonary dysfunction as the primary cause of death and die while requiring significant respiratory support compared to patients without ARDS.

Early Detection of Heart Failure With Reduced Ejection Fraction Using Perioperative Data Among Noncardiac Surgical Patients: A Machine-Learning Approach.

BACKGROUND: Heart failure with reduced ejection fraction (HFrEF) is a condition imposing significant health care burden. Given its syndromic nature and often insidious onset, the diagnosis may not be made until clinical manifestations prompt further evaluation. Detecting HFrEF in precursor stages could allow for early initiation of treatments to modify disease progression. Granular data collected during the perioperative period may represent an underutilized method for improving the diagnosis of HFrEF. We hypothesized that patients ultimately diagnosed with HFrEF following surgery can be identified via machine-learning approaches using pre- and intraoperative data. METHODS: Perioperative data were reviewed from adult patients undergoing general anesthesia for major surgical procedures at an academic quaternary care center between 2010 and 2016. Patients with known HFrEF, heart failure with preserved ejection fraction, preoperative critical illness, or undergoing cardiac, cardiology, or electrophysiologic procedures were excluded. Patients were classified as healthy controls or undiagnosed HFrEF. Undiagnosed HFrEF was defined as lacking a HFrEF diagnosis preoperatively but establishing a diagnosis within 730 days postoperatively. Undiagnosed HFrEF patients were adjudicated by expert clinician review, excluding cases for which HFrEF was secondary to a perioperative triggering event, or any event not associated with HFrEF natural disease progression. Machine-learning models, including L1 regularized logistic regression, random forest, and extreme gradient boosting were developed to detect undiagnosed HFrEF, using perioperative data including 628 preoperative and 1195 intraoperative features. Training/validation and test datasets were used with parameter tuning. Test set model performance was evaluated using area under the receiver operating characteristic curve (AUROC), positive predictive value, and other standard metrics. RESULTS: Among 67,697 cases analyzed, 279 (0.41%) patients had undiagnosed HFrEF. The AUROC for the logistic regression model was 0.869 (95% confidence interval, 0.829-0.911), 0.872 (0.836-0.909) for the random forest model, and 0.873 (0.833-0.913) for the extreme gradient boosting model. The corresponding positive predictive values were 1.69% (1.06%-2.32%), 1.42% (0.85%-1.98%), and 1.78% (1.15%-2.40%), respectively. CONCLUSIONS: Machine-learning models leveraging perioperative data can detect undiagnosed HFrEF with good performance. However, the low prevalence of the disease results in a low positive predictive value, and for clinically meaningful sensitivity thresholds to be actionable, confirmatory testing with high specificity (eg, echocardiography or cardiac biomarkers) would be required following model detection. Future studies are necessary to externally validate algorithm performance at additional centers and explore the feasibility of embedding algorithms into the perioperative electronic health record for clinician use in real time.

Robust segmentation of lung in chest x-ray: applications in analysis of acute respiratory distress syndrome.

BACKGROUND: This study outlines an image processing algorithm for accurate and consistent lung segmentation in chest radiographs of critically ill adults and children typically obscured by medical equipment. In particular, this work focuses on applications in analysis of acute respiratory distress syndrome - a critical illness with a mortality rate of 40% that affects 200,000 patients in the United States and 3 million globally each year. METHODS: Chest radiographs were obtained from critically ill adults (n = 100), adults diagnosed with acute respiratory distress syndrome (ARDS) (n = 25), and children (n = 100) hospitalized at Michigan Medicine. Physicians annotated the lung field of each radiograph to establish the ground truth. A Total Variation-based Active Contour (TVAC) lung segmentation algorithm was developed and compared to multiple state-of-the-art methods including a deep learning model (U-Net), a random walker algorithm, and an active spline model, using the Sørensen-Dice coefficient to measure segmentation accuracy. RESULTS: The TVAC algorithm accurately segmented lung fields in all patients in the study. For the adult cohort, an averaged Dice coefficient of 0.86 ±0.04 (min: 0.76) was reported for TVAC, 0.89 ±0.12 (min: 0.01) for U-Net, 0.74 ±0.19 (min: 0.15) for the random walker algorithm, and 0.64 ±0.17 (min: 0.20) for the active spline model. For the pediatric cohort, a Dice coefficient of 0.85 ±0.04 (min: 0.75) was reported for TVAC, 0.87 ±0.09 (min: 0.56) for U-Net, 0.67 ±0.18 (min: 0.18) for the random walker algorithm, and 0.61 ±0.18 (min: 0.18) for the active spline model. CONCLUSION: The proposed algorithm demonstrates the most consistent performance of all segmentation methods tested. These results suggest that TVAC can accurately identify lung fields in chest radiographs in critically ill adults and children.

Evaluating Delivery of Low Tidal Volume Ventilation in Six ICUs Using Electronic Health Record Data.

OBJECTIVES: Mechanical ventilation with low tidal volumes is recommended for all patients with acute respiratory distress syndrome and may be beneficial to other intubated patients, yet consistent implementation remains difficult to obtain. Using detailed electronic health record data, we examined patterns of tidal volume administration, the effect on clinical outcomes, and alternate metrics for evaluating low tidal volume compliance in clinical practice. DESIGN: Observational cohort study. SETTING: Six ICUs in a single hospital system. PATIENTS: Adult patients who received invasive mechanical ventilation more than 12 hours. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Tidal volumes were analyzed across 1,905 hospitalizations. Although mean tidal volume was 6.8 mL/kg predicted body weight, 40% of patients were exposed to tidal volumes greater than 8 mL/kg predicted body weight, with 11% for more than 24 hours. At a patient level, exposure to 24 total hours of tidal volumes greater than 8 mL/kg predicted body weight was associated with increased mortality (odds ratio, 1.82; 95% CI, 1.20-2.78), whereas mean tidal volume exposure was not (odds ratio, 0.87/1 mL/kg increase; 95% CI, 0.74-1.02). Initial tidal volume settings strongly predicted exposure to volumes greater than 8 mL/kg for 24 hours; the adjusted rate was 21.5% when initial volumes were greater than 8 mL/kg predicted body weight and 7.1% when initial volumes were less than 8 mL/kg predicted body weight. Across ICUs, correlation of mean tidal volume with alternative measures of low tidal volume delivery ranged from 0.38 to 0.66. CONCLUSIONS: Despite low mean tidal volume in the cohort, a significant percentage of patients were exposed to a prolonged duration of high tidal volumes which was correlated with higher mortality. Detailed ventilator records in the electronic health record provide a unique window for evaluating low tidal volume delivery and targets for improvement.

Rapid breath analysis for acute respiratory distress syndrome diagnostics using a portable two-dimensional gas chromatography device.

Acute respiratory distress syndrome (ARDS) is the most severe form of acute lung injury, responsible for high mortality and long-term morbidity. As a dynamic syndrome with multiple etiologies, its timely diagnosis is difficult as is tracking the course of the syndrome. Therefore, there is a significant need for early, rapid detection and diagnosis as well as clinical trajectory monitoring of ARDS. Here, we report our work on using human breath to differentiate ARDS and non-ARDS causes of respiratory failure. A fully automated portable 2-dimensional gas chromatography device with high peak capacity (> 200 at the resolution of 1), high sensitivity (sub-ppb), and rapid analysis capability (~ 30 min) was designed and made in-house for on-site analysis of patients' breath. A total of 85 breath samples from 48 ARDS patients and controls were collected. Ninety-seven elution peaks were separated and detected in 13 min. An algorithm based on machine learning, principal component analysis (PCA), and linear discriminant analysis (LDA) was developed. As compared to the adjudications done by physicians based on the Berlin criteria, our device and algorithm achieved an overall accuracy of 87.1% with 94.1% positive predictive value and 82.4% negative predictive value. The high overall accuracy and high positive predicative value suggest that the breath analysis method can accurately diagnose ARDS. The ability to continuously and non-invasively monitor exhaled breath for early diagnosis, disease trajectory tracking, and outcome prediction monitoring of ARDS may have a significant impact on changing practice and improving patient outcomes. Graphical abstract.