Two Weeks Versus One Week of Maximal Patient-Intensivist Continuity for Adult Medical Intensive Care Patients: A Two-Center Target Trial Emulation.

OBJECTIVES: To compare outcomes for 2 weeks vs. 1 week of maximal patient-intensivist continuity in the ICU. DESIGN: Retrospective cohort study. SETTING: Two U.S. urban, teaching, medical ICUs where intensivists were scheduled for 2-week service blocks: site A was in the Midwest and site B was in the Northeast. PATIENTS: Patients 18 years old or older admitted to a study ICU between March 1, 2017, and February 28, 2020. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We applied target trial emulation to compare admission during an intensivist's first week (as a proxy for 2 wk of maximal continuity) vs. admission during their second week (as a proxy for 1 wk of maximal continuity). Outcomes included hospital mortality, ICU length of stay, and, for mechanically ventilated patients, duration of ventilation. Exploratory outcomes included imaging, echocardiogram, and consultation orders. We used inverse probability weighting to adjust for baseline differences and random-effects meta-analysis to calculate overall effect estimates. Among 2571 patients, 1254 were admitted during an intensivist's first week and 1317 were admitted during a second week. At sites A and B, hospital mortality rates were 25.8% and 24.2%, median ICU length of stay were 4 and 2 days, and median mechanical ventilation durations were 3 and 3 days, respectively. There were no differences in adjusted mortality (odds ratio [OR], 1.01 [95% CI, 0.96-1.06]) or ICU length of stay (-0.25 d [-0.82 d to +0.32 d]) for 2 weeks vs. 1 week of maximal continuity. Among mechanically ventilated patients, there were no differences in adjusted mortality (OR, 1.00 [0.87-1.16]), ICU length of stay (+0.06 d [-0.78 d to +0.91 d]), or duration of mechanical ventilation (+0.37 d [-0.46 d to +1.21 d]) for 2 weeks vs. 1 week of maximal continuity. CONCLUSIONS: Two weeks of maximal patient-intensivist continuity was not associated with differences in clinical outcomes compared with 1 week in two medical ICUs.

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.

Critical Appraisal for Racial and Ethnic Equity in Clinical Prediction Models Extension: Development of a Critical Appraisal Tool Extension to Assess Racial and Ethnic Equity-Related Risk of Bias for Clinical Prediction Models.

Introduction: Despite mounting evidence that the inclusion of race and ethnicity in clinical prediction models may contribute to health disparities, existing critical appraisal tools do not directly address such equity considerations. Objective: This study developed a critical appraisal tool extension to assess algorithmic bias in clinical prediction models. Methods: A modified e-Delphi approach was utilized to develop and obtain expert consensus on a set of racial and ethnic equity-based signaling questions for appraisal of risk of bias in clinical prediction models. Through a series of virtual meetings, initial pilot application, and an online survey, individuals with expertise in clinical prediction model development, systematic review methodology, and health equity developed and refined this tool. Results: Consensus was reached for ten equity-based signaling questions, which led to the development of the Critical Appraisal for Racial and Ethnic Equity in Clinical Prediction Models (CARE-CPM) extension. This extension is intended for use along with existing critical appraisal tools for clinical prediction models. Conclusion: CARE-CPM provides a valuable risk-of-bias assessment tool extension for clinical prediction models to identify potential algorithmic bias and health equity concerns. Further research is needed to test usability, interrater reliability, and application to decision-makers.

A vignette-based evaluation of ChatGPT's ability to provide appropriate and equitable medical advice across care contexts.

ChatGPT is a large language model trained on text corpora and reinforced with human supervision. Because ChatGPT can provide human-like responses to complex questions, it could become an easily accessible source of medical advice for patients. However, its ability to answer medical questions appropriately and equitably remains unknown. We presented ChatGPT with 96 advice-seeking vignettes that varied across clinical contexts, medical histories, and social characteristics. We analyzed responses for clinical appropriateness by concordance with guidelines, recommendation type, and consideration of social factors. Ninety-three (97%) responses were appropriate and did not explicitly violate clinical guidelines. Recommendations in response to advice-seeking questions were completely absent (N = 34, 35%), general (N = 18, 18%), or specific (N = 44, 46%). 53 (55%) explicitly considered social factors like race or insurance status, which in some cases changed clinical recommendations. ChatGPT consistently provided background information in response to medical questions but did not reliably offer appropriate and personalized medical advice.

Analysis of Devices Authorized by the FDA for Clinical Decision Support in Critical Care.

This case series study examines the clinical evidence cited for US Food and Drug Administration­approved clinical decision support devices for use in the critical care setting.

Guiding Risk Adjustment Models Toward Machine Learning Methods.

This Viewpoint reviews the history of administrative risk adjustment models used in health care and provides recommendations for modernizing these models to promote their safe, transparent, equitable, and efficient use.

A Data-Driven Analysis of Ward Capacity Strain Metrics That Predict Clinical Outcomes Among Survivors of Acute Respiratory Failure.

Supply-demand mismatch of ward resources ("ward capacity strain") alters care and outcomes. Narrow strain definitions and heterogeneous populations limit strain literature. Evaluate the predictive utility of a large set of candidate strain variables for in-hospital mortality and discharge destination among acute respiratory failure (ARF) survivors. In a retrospective cohort of ARF survivors transferred from intensive care units (ICUs) to wards in five hospitals from 4/2017-12/2019, we applied 11 machine learning (ML) models to identify ward strain measures during the first 24 hours after transfer most predictive of outcomes. Measures spanned patient volume (census, admissions, discharges), staff workload (medications administered, off-ward transports, transfusions, isolation precautions, patients per respiratory therapist and nurse), and average patient acuity (Laboratory Acute Physiology Score version 2, ICU transfers) domains. The cohort included 5,052 visits in 43 wards. Median age was 65 years (IQR 56-73); 2,865 (57%) were male; and 2,865 (57%) were white. 770 (15%) patients died in the hospital or had hospice discharges, and 2,628 (61%) were discharged home and 964 (23%) to skilled nursing facilities (SNFs). Ward admissions, isolation precautions, and hospital admissions most consistently predicted in-hospital mortality across ML models. Patients per nurse most consistently predicted discharge to home and SNF, and medications administered predicted SNF discharge. In this hypothesis-generating analysis of candidate ward strain variables' prediction of outcomes among ARF survivors, several variables emerged as consistently predictive of key outcomes across ML models. These findings suggest targets for future inferential studies to elucidate mechanisms of ward strain's adverse effects.

Prediction of In-hospital Mortality Among Intensive Care Unit Patients Using Modified Daily Laboratory-based Acute Physiology Score, Version 2.

BACKGROUND: Mortality prediction for intensive care unit (ICU) patients frequently relies on single ICU admission acuity measures without accounting for subsequent clinical changes. OBJECTIVE: Evaluate novel models incorporating modified admission and daily, time-updating Laboratory-based Acute Physiology Score, version 2 (LAPS2) to predict in-hospital mortality among ICU patients. RESEARCH DESIGN: Retrospective cohort study. PATIENTS: ICU patients in 5 hospitals from October 2017 through September 2019. MEASURES: We used logistic regression, penalized logistic regression, and random forest models to predict in-hospital mortality within 30 days of ICU admission using admission LAPS2 alone in patient-level and patient-day-level models, or admission and daily LAPS2 at the patient-day level. Multivariable models included patient and admission characteristics. We performed internal-external validation using 4 hospitals for training and the fifth for validation, repeating analyses for each hospital as the validation set. We assessed performance using scaled Brier scores (SBS), c -statistics, and calibration plots. RESULTS: The cohort included 13,993 patients and 107,699 ICU days. Across validation hospitals, patient-day-level models including daily LAPS2 (SBS: 0.119-0.235; c -statistic: 0.772-0.878) consistently outperformed models with admission LAPS2 alone in patient-level (SBS: 0.109-0.175; c -statistic: 0.768-0.867) and patient-day-level (SBS: 0.064-0.153; c -statistic: 0.714-0.861) models. Across all predicted mortalities, daily models were better calibrated than models with admission LAPS2 alone. CONCLUSIONS: Patient-day-level models incorporating daily, time-updating LAPS2 to predict mortality among an ICU population performs as well or better than models incorporating modified admission LAPS2 alone. The use of daily LAPS2 may offer an improved tool for clinical prognostication and risk adjustment in research in this population.

Global, Race-Neutral Reference Equations and Pulmonary Function Test Interpretation.

Importance: Race and ethnicity are routinely used to inform pulmonary function test (PFT) interpretation. However, there is no biological justification for such use, and it may reinforce health disparities. Objective: To compare the PFT interpretations produced with race-neutral and race-specific equations. Design, Setting, and Participants: In this cross-sectional study, race-neutral reference equations recently developed by the Global Lung Function Initiative (GLI) were used to interpret PFTs performed at an academic medical center between January 2010 and December 2020. The interpretations produced with these race-neutral reference equations were compared with those produced using the race and ethnicity-specific reference equations produced by GLI in 2012. The analysis was conducted from April to October 2022. Main Outcomes and Measures: The primary outcomes were differences in the percentage of obstructive, restrictive, mixed, and nonspecific lung function impairments identified using the 2 sets of reference equations. Secondary outcomes were differences in severity of these impairments. Results: PFTs were interpreted from 2722 Black (686 men [25.4%]; mean [SD] age, 51.8 [13.9] years) and 5709 White (2654 men [46.5%]; mean [SD] age, 56.4 [14.3] years) individuals. Among Black individuals, replacing the race-specific reference equations with the race-neutral reference equations was associated with an increase in the prevalence of restriction from 26.8% (95% CI, 25.2%-28.5%) to 37.5% (95% CI, 35.7%-39.3%) and of a nonspecific pattern of impairment from 3.2% (95% CI, 2.5%- 3.8%) to 6.5% (95% CI, 5.6%-7.4%) and no significant change in the prevalence of obstruction (19.9% [95% CI, 18.4%-21.4%] vs 19.5% [95% CI, 18.0%-21.0%]). Among White individuals, replacing the race-specific reference equations with the race-neutral reference equations was associated with a decrease in the prevalence of restriction from 22.6% (95% CI, 21.5%-23.6%) to 18.0% (95% CI, 17.0%-19.0%), a decrease in the prevalence of a nonspecific pattern of impairment from 8.7% (95% CI, 7.9%-9.4%) to 4.0% (95% CI, 3.5%-4.5%), and no significant change in the percentage with obstruction from 23.9% (95% CI, 22.8%-25.1%) to 25.1% (95% CI, 23.9%- 26.2%). The race-neutral reference equations were associated with an increase in severity in 22.8% (95% CI, 21.2%-24.4%) of Black individuals and a decrease in severity in 19.3% (95% CI, 18.2%-20.3%) of White individuals vs the race-specific reference equations. Conclusions and Relevance: In this cross-sectional study, the use of race-neutral reference equations to interpret PFTs resulted in a significant increase in the number of Black individuals with respiratory impairments along with a significant increase in the severity of the identified impairments. More work is needed to quantify the effect these reference equations would have on diagnosis, referral, and treatment patterns.

Association of Time of Day with Delays in Antimicrobial Initiation among Ward Patients with Hospital-Onset Sepsis.

Rationale: Although the mainstay of sepsis treatment is timely initiation of broad-spectrum antimicrobials, treatment delays are common, especially among patients who develop hospital-onset sepsis. The time of day has been associated with suboptimal clinical care in several contexts, but its association with treatment initiation among patients with hospital-onset sepsis is unknown. Objectives: Assess the association of time of day with antimicrobial initiation among ward patients with hospital-onset sepsis. Methods: This retrospective cohort study included ward patients who developed hospital-onset sepsis while admitted to five acute care hospitals in a single health system from July 2017 through December 2019. Hospital-onset sepsis was defined by the Centers for Disease Control and Prevention Adult Sepsis Event criteria. We estimated the association between the hour of day and antimicrobial initiation among patients with hospital-onset sepsis using a discrete-time time-to-event model, accounting for time elapsed from sepsis onset. In a secondary analysis, we fit a quantile regression model to estimate the association between the hour of day of sepsis onset and time to antimicrobial initiation. Results: Among 1,672 patients with hospital-onset sepsis, the probability of antimicrobial initiation at any given hour varied nearly fivefold throughout the day, ranging from 3.0% (95% confidence interval [CI], 1.8-4.1%) at 7 a.m. to 13.9% (95% CI, 11.3-16.5%) at 6 p.m., with nadirs at 7 a.m. and 7 p.m. and progressive decline throughout the night shift (13.4% [95% CI, 10.7-16.0%] at 9 p.m. to 3.2% [95% CI, 2.0-4.0] at 6 a.m.). The standardized predicted median time to antimicrobial initiation was 3.2 hours (interquartile range [IQR], 2.5-3.8 h) for sepsis onset during the day shift (7 a.m.-7 p.m.) and 12.9 hours (IQR, 10.9-14.9 h) during the night shift (7 p.m.-7 a.m.). Conclusions: The probability of antimicrobial initiation among patients with new hospital-onset sepsis declined at shift changes and overnight. Time to antimicrobial initiation for patients with sepsis onset overnight was four times longer than for patients with onset during the day. These findings indicate that time of day is associated with important care processes for ward patients with hospital-onset sepsis. Future work should validate these findings in other settings and elucidate underlying mechanisms to inform quality-enhancing interventions.

Development of a Machine Learning Model to Identify Colorectal Cancer Stage in Medicare Claims.

PURPOSE: Staging information is essential for colorectal cancer research. Medicare claims are an important source of population-level data but currently lack oncologic stage. We aimed to develop a claims-based model to identify stage at diagnosis in patients with colorectal cancer. METHODS: We included patients age 66 years or older with colorectal cancer in the SEER-Medicare registry. Using patients diagnosed from 2014 to 2016, we developed models (multinomial logistic regression, elastic net regression, and random forest) to classify patients into stage I-II, III, or IV on the basis of demographics, diagnoses, and treatment utilization identified in Medicare claims. Models developed in a training cohort (2014-2016) were applied to a testing cohort (2017), and performance was evaluated using cancer stage listed in the SEER registry as the reference standard. RESULTS: The cohort of patients with 30,543 colorectal cancer included 14,935 (48.9%) patients with stage I-II, 9,203 (30.1%) with stage III, and 6,405 (21%) with stage IV disease. A claims-based model using elastic net regression had a scaled Brier score (SBS) of 0.45 (95% CI, 0.43 to 0.46). Performance was strongest for classifying stage IV (SBS, 0.62; 95% CI, 0.59 to 0.64; sensitivity, 93%; 95% CI, 91 to 94) followed by stage I-II (SBS, 0.45; 95% CI, 0.44 to 0.47; sensitivity, 86%; 95% CI, 85 to 76) and stage III (SBS, 0.32; 95% CI, 0.30 to 0.33; sensitivity, 62%; 95% CI, 61 to 64). CONCLUSION: Machine learning models effectively classified colorectal cancer stage using Medicare claims. These models extend the ability of claims-based research to risk-adjust and stratify by stage.

Physiologic dead space is independently associated with mortality and discharge of mechanically ventilated patients with COVID-19 ARDS: a retrospective study.

Physiologic dead space is a well-established independent predictor of death in patients with acute respiratory distress syndrome (ARDS). Here, we explore the association between a surrogate measure of dead space (DS) and early outcomes of mechanically ventilated patients admitted to Intensive Care Unit (ICU) because of COVID-19-associated ARDS. Retrospective cohort study on data derived from Italian ICUs during the first year of the COVID-19 epidemic. A competing risk Cox proportional hazard model was applied to test for the association of DS with two competing outcomes (death or discharge from the ICU) while adjusting for confounders. The final population consisted of 401 patients from seven ICUs. A significant association of DS with both death (HR 1.204; CI 1.019-1.423; p = 0.029) and discharge (HR 0.434; CI 0.414-0.456; p [Formula: see text]) was noticed even when correcting for confounding factors (age, sex, chronic obstructive pulmonary disease, diabetes, PaO[Formula: see text]/FiO[Formula: see text], tidal volume, positive end-expiratory pressure, and systolic blood pressure). These results confirm the important association between DS and death or ICU discharge in mechanically ventilated patients with COVID-19-associated ARDS. Further work is needed to identify the optimal role of DS monitoring in this setting and to understand the physiological mechanisms underlying these associations.

Natural Language Processing of Learners' Evaluations of Attendings to Identify Professionalism Lapses.

Unprofessional faculty behaviors negatively impact the well-being of trainees yet are infrequently reported through established reporting systems. Manual review of narrative faculty evaluations provides an additional avenue for identifying unprofessional behavior but is time- and resource-intensive, and therefore of limited value for identifying and remediating faculty with professionalism concerns. Natural language processing (NLP) techniques may provide a mechanism for streamlining manual review processes to identify faculty professionalism lapses. In this retrospective cohort study of 15,432 narrative evaluations of medical faculty by medical trainees, we identified professionalism lapses using automated analysis of the text of faculty evaluations. We used multiple NLP approaches to develop and validate several classification models, which were evaluated primarily based on the positive predictive value (PPV) and secondarily by their calibration. A NLP-model using sentiment analysis (quantifying subjectivity of the text) in combination with key words (using the ensemble technique) had the best performance overall with a PPV of 49% (CI 38%-59%). These findings highlight how NLP can be used to screen narrative evaluations of faculty to identify unprofessional faculty behaviors. Incorporation of NLP into faculty review workflows enables a more focused manual review of comments, providing a supplemental mechanism to identify faculty professionalism lapses.

Prediction of in-hospital mortality among intensive care unit patients using modified daily Laboratory-based Acute Physiology Scores, version 2 (LAPS2).

Background: Mortality prediction for intensive care unit (ICU) patients frequently relies on single acuity measures based on ICU admission physiology without accounting for subsequent clinical changes. Objectives: Evaluate novel models incorporating modified admission and daily, time-updating Laboratory-based Acute Physiology Scores, version 2 (LAPS2) to predict in-hospital mortality among ICU patients. Research design: Retrospective cohort study. Subjects: All ICU patients in five hospitals from October 2017 through September 2019. Measures: We used logistic regression, penalized logistic regression, and random forest models to predict in-hospital mortality within 30 days of ICU admission using admission LAPS2 alone in patient-level and patient-day-level models, or admission and daily LAPS2 at the patient-day level. Multivariable models included patient and admission characteristics. We performed internal-external validation using four hospitals for training and the fifth for validation, repeating analyses for each hospital as the validation set. We assessed performance using scaled Brier scores (SBS), c-statistics, and calibration plots. Results: The cohort included 13,993 patients and 120,101 ICU days. The patient-level model including the modified admission LAPS2 without daily LAPS2 had an SBS of 0.175 (95% CI 0.148-0.201) and c-statistic of 0.824 (95% CI 0.808-0.840). Patient-day-level models including daily LAPS2 consistently outperformed models with modified admission LAPS2 alone. Among patients with <50% predicted mortality, daily models were better calibrated than models with modified admission LAPS2 alone. Conclusions: Models incorporating daily, time-updating LAPS2 to predict mortality among an ICU population perform as well or better than models incorporating modified admission LAPS2 alone.

A Quantitative Study of Decision Thresholds for Initiation of Antibiotics in Suspected Sepsis.

BACKGROUND: Clinicians' decision thresholds for initiating antibiotics in patients with suspected sepsis have not been quantified. We aimed to define an average threshold of infection likelihood at which clinicians initiate antibiotics when treating a patient with suspected infection and to evaluate the influence of severity of illness and clinician-related factors on the threshold. DESIGN: This was a prospective survey of 153 clinicians responding to 8 clinical vignettes constructed from real-world data from 3 health care systems in the United States. We treated each hour in the vignette as a decision to treat or not treat with antibiotics and assigned an infection probability to each hour using a previously developed infection prediction model. We then estimated decision thresholds using regression models based on the timing of antibiotic initiation. We compared thresholds across categories of severity of illness and clinician-related factors. RESULTS: Overall, the treatment threshold occurred at a 69% probability of infection, but the threshold varied significantly across severity of illness categories-when patients had high severity of illness, the treatment threshold occurred at a 55% probability of infection; when patients had intermediate severity, the threshold for antibiotic initiation occurred at an infection probability of 69%, and the threshold was 84% when patients had low severity of illness (P < 0.001 for group differences). Thresholds differed significantly across specialty, highest among infectious disease and lowest among emergency medicine clinicians and across years of experience, decreasing with increasing years of experience. CONCLUSIONS: The threshold infection probability above which physicians choose to initiate antibiotics in suspected sepsis depends on illness severity as well as clinician factors. IMPLICATIONS: Incorporating these context-dependent thresholds into discriminating and well-calibrated models will inform the development of future sepsis clinical decision support systems. Clinician-related differences in treatment thresholds suggests potential unwarranted variation and opportunities for performance improvement. HIGHLIGHTS: Decision making about antibiotic initiation in suspected sepsis occurs under uncertainty, and little is known about clinicians' thresholds for treatment.In this prospective study, 153 clinicians from 3 health care systems reviewed 8 real-world clinical vignettes representing patients with sepsis and indicated the time that they would initiate antibiotics.Using a model-based approach, we estimated decision thresholds and found that thresholds differed significantly across illness severity categories and by clinician specialty and years of experience.

Association of Time to Rapid Response Team Activation With Patient Outcomes Using a Range of Physiologic Deterioration Thresholds.

Clinical deterioration of hospitalized patients is common and can lead to critical illness and death. Rapid response teams (RRTs) assess and treat high-risk patients with signs of clinical deterioration to prevent further worsening and subsequent adverse outcomes. Whether activation of the RRT early in the course of clinical deterioration impacts outcomes, however, remains unclear. We sought to characterize the relationship between increasing time to RRT activation after physiologic deterioration and short-term patient outcomes. DESIGN: Retrospective multicenter cohort study. SETTING: Three academic hospitals in Pennsylvania. PATIENTS: We included the RRT activation of a hospitalization for non-ICU inpatients greater than or equal to 18 years old. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The primary exposure was time to RRT activation after physiologic deterioration. We selected four Cardiac Arrest Risk Triage (CART) score thresholds a priori from which to measure time to RRT activation (CART score ≥ 12, ≥ 16, ≥ 20, and ≥ 24). The primary outcome was 7-day mortality-death or discharge to hospice care within 7 days of RRT activation. For each CART threshold, we modeled the association of time to RRT activation duration with 7-day mortality using multivariable fractional polynomial regression. Increased time from clinical decompensation to RRT activation was associated with higher risk of 7-day mortality. This relationship was nonlinear, with odds of mortality increasing rapidly as time to RRT activation increased from 0 to 4 hours and then plateauing. This pattern was observed across several thresholds of physiologic derangement. CONCLUSIONS: Increasing time to RRT activation was associated in a nonlinear fashion with increased 7-day mortality. This relationship appeared most marked when using a CART score greater than 20 threshold from which to measure time to RRT activation. We suggest that these empirical findings could be used to inform RRT delay definitions in further studies to determine the clinical impact of interventions focused on timely RRT activation.

Desired Characteristics of a Clinical Decision Support System for Early Sepsis Recognition: Interview Study Among Hospital-Based Clinicians.

BACKGROUND: Sepsis is a major burden for health care systems in the United States, with over 750,000 cases annually and a total cost of approximately US $20 billion. The hallmark of sepsis treatment is early and appropriate initiation of antibiotic therapy. Although sepsis clinical decision support (CDS) systems can provide clinicians with early predictions of suspected sepsis or imminent clinical decline, such systems have not reliably demonstrated improvements in clinical outcomes or care processes. Growing evidence suggests that the challenges of integrating sepsis CDS systems into clinical workflows, gaining the trust of clinicians, and making sepsis CDS systems clinically relevant at the bedside are all obstacles to successful deployment. However, there are significant knowledge gaps regarding the achievement of these implementation and deployment goals. OBJECTIVE: We aimed to identify perceptions of predictive information in sepsis CDS systems based on clinicians' past experiences, explore clinicians' perceptions of a hypothetical sepsis CDS system, and identify the characteristics of a CDS system that would be helpful in promoting timely recognition and management of suspected sepsis in a multidisciplinary, team-based clinical setting. METHODS: We conducted semistructured interviews with practicing bedside nurses, advanced practice providers, and physicians at a large academic medical center between September 2020 and March 2021. We used modified human factor methods (contextual interview and cognitive walkthrough performed over video calls because of the COVID-19 pandemic) and conducted a thematic analysis using an abductive approach for coding to identify important patterns and concepts in the interview transcripts. RESULTS: We interviewed 6 bedside nurses and 9 clinicians responsible for ordering antibiotics (advanced practice providers or physicians) who had a median of 4 (IQR 4-6.5) years of experience working in an inpatient setting. We then synthesized critical content from the thematic analysis of the data into four domains: clinician perceptions of prediction models and alerts; previous experiences of clinician encounters with predictive information and risk scores; desired characteristics of a CDS system build, including predictions, supporting information, and delivery methods for a potential alert; and the clinical relevance and potential utility of a CDS system. These 4 domains were strongly linked to clinicians' perceptions of the likelihood of adoption and the impact on clinical workflows when diagnosing and managing patients with suspected sepsis. Ultimately, clinicians desired a trusted and actionable CDS system to improve sepsis care. CONCLUSIONS: Building a trusted and actionable sepsis CDS alert is paramount to achieving acceptability and use among clinicians. These findings can inform the development, implementation, and deployment strategies for CDS systems that support the early detection and treatment of sepsis. This study also highlights several key opportunities when eliciting clinician input before the development and deployment of prediction models.