Development and validation of a race-agnostic computable phenotype for kidney health in adult hospitalized patients.

Standard race adjustments for estimating glomerular filtration rate (GFR) and reference creatinine can yield a lower acute kidney injury (AKI) and chronic kidney disease (CKD) prevalence among African American patients than non-race adjusted estimates. We developed two race-agnostic computable phenotypes that assess kidney health among 139,152 subjects admitted to the University of Florida Health between 1/2012-8/2019 by removing the race modifier from the estimated GFR and estimated creatinine formula used by the race-adjusted algorithm (race-agnostic algorithm 1) and by utilizing 2021 CKD-EPI refit without race formula (race-agnostic algorithm 2) for calculations of the estimated GFR and estimated creatinine. We compared results using these algorithms to the race-adjusted algorithm in African American patients. Using clinical adjudication, we validated race-agnostic computable phenotypes developed for preadmission CKD and AKI presence on 300 cases. Race adjustment reclassified 2,113 (8%) to no CKD and 7,901 (29%) to a less severe CKD stage compared to race-agnostic algorithm 1 and reclassified 1,208 (5%) to no CKD and 4,606 (18%) to a less severe CKD stage compared to race-agnostic algorithm 2. Of 12,451 AKI encounters based on race-agnostic algorithm 1, race adjustment reclassified 591 to No AKI and 305 to a less severe AKI stage. Of 12,251 AKI encounters based on race-agnostic algorithm 2, race adjustment reclassified 382 to No AKI and 196 (1.6%) to a less severe AKI stage. The phenotyping algorithm based on refit without race formula performed well in identifying patients with CKD and AKI with a sensitivity of 100% (95% confidence interval [CI] 97%-100%) and 99% (95% CI 97%-100%) and a specificity of 88% (95% CI 82%-93%) and 98% (95% CI 93%-100%), respectively. Race-agnostic algorithms identified substantial proportions of additional patients with CKD and AKI compared to race-adjusted algorithm in African American patients. The phenotyping algorithm is promising in identifying patients with kidney disease and improving clinical decision-making.

Economic Evaluation of Extended-Release Buprenorphine for Persons With Opioid Use Disorder.

Importance: In 2017, the US Food and Drug Administration (FDA) approved a monthly injectable form of buprenorphine, extended-release buprenorphine; published data show that extended-release buprenorphine is effective compared with no treatment, but its current cost is higher and current retention is lower than that of transmucosal buprenorphine. Preliminary research suggests that extended-release buprenorphine may be an important addition to treatment options, but the cost-effectiveness of extended-release buprenorphine compared with transmucosal buprenorphine remains unclear. Objective: To evaluate the cost-effectiveness of extended-release buprenorphine compared with transmucosal buprenorphine. Design, Setting, and Participants: This economic evaluation used a state transition model starting in 2019 to simulate the lifetime of a closed cohort of individuals with OUD presenting for evaluation for opioid agonist treatment with buprenorphine. The data sources used to estimate model parameters included cohort studies, clinical trials, and administrative data. The model relied on pharmaceutical costs from the Federal Supply Schedule and health care utilization costs from published studies. Data were analyzed from September 2021 to January 2023. Interventions: No treatment, treatment with transmucosal buprenorphine, or treatment with extended-release buprenorphine. Main Outcomes and Measures: Mean lifetime costs per person, discounted quality-adjusted life-years (QALYs), and incremental cost-effectiveness ratios (ICERs). Results: The simulated cohort included 100 000 patients with OUD receiving (61% male; mean [SD] age, 38 [11] years) or not receiving medication treatment (58% male, mean [SD] age, 48 [18] years). Compared with no medication treatment, treatment with transmucosal buprenorphine yielded an ICER of $19 740 per QALY. Compared with treatment with transmucosal buprenorphine, treatment with extended-release buprenorphine yielded lower effectiveness by 0.03 QALYs per person at higher cost, suggesting that treatment with extended-release buprenorphine was dominated and not preferred. In probabilistic sensitivity analyses, treatment with transmucosal buprenorphine was the preferred strategy 60% of the time. Treatment with extended-release buprenorphine was cost-effective compared with treatment with transmucosal buprenorphine at a $100 000 per QALY willingness-to-pay threshold only after substantial changes in key parameters. Conclusions and Relevance: In this economic evaluation of extended-release buprenorphine compared with transmucosal buprenorphine for the treatment of OUD, extended-release buprenorphine was not associated with efficient allocation of limited resources when transmucosal buprenorphine was available. Future initiatives should aim to improve retention rates or decrease costs associated with extended-release buprenorphine.

Estimated Costs and Outcomes Associated With Use and Nonuse of Medications for Opioid Use Disorder During Incarceration and at Release in Massachusetts.

Importance: Most prisons and jails in the US discontinue medications for opioid use disorder (MOUD) upon incarceration and do not initiate MOUD prior to release. Objective: To model the association of MOUD access during incarceration and at release with population-level overdose mortality and OUD-related treatment costs in Massachusetts. Design, Setting, and Participants: This economic evaluation used simulation modeling and cost-effectiveness with costs and quality-adjusted life-years (QALYs) discounted at 3% to compare MOUD treatment strategies in a corrections cohort and an open cohort representing individuals with OUD in Massachusetts. Data were analyzed between July 1, 2021, and September 30, 2022. Exposures: Three strategies were compared: (1) no MOUD provided during incarceration or at release, (2) extended-release (XR) naltrexone offered only at release from incarceration, and (3) all 3 MOUDs (naltrexone, buprenorphine, and methadone) offered at intake. Main Outcomes and Measures: Treatment starts and retention, fatal overdoses, life-years and QALYs, costs, and incremental cost-effectiveness ratios (ICERs). Results: Among 30 000 simulated incarcerated individuals with OUD, offering no MOUD was associated with 40 927 (95% uncertainty interval [UI], 39 001-42 082) MOUD treatment starts over a 5-year period and 1259 (95% UI, 1130-1323) overdose deaths after 5 years. Over 5 years, offering XR-naltrexone at release led to 10 466 (95% UI, 8515-12 201) additional treatment starts, 40 (95% UI, 16-50) fewer overdose deaths, and 0.08 (95% UI, 0.05-0.11) QALYs gained per person, at an incremental cost of $2723 (95% UI, $141-$5244) per person. In comparison, offering all 3 MOUDs at intake led to 11 923 (95% UI, 10 861-12 911) additional treatment starts, compared with offering no MOUD, 83 (95% UI, 72-91) fewer overdose deaths, and 0.12 (95% UI, 0.10-0.17) QALYs per person gained, at an incremental cost of $852 (95% UI, $14-$1703) per person. Thus, XR-naltrexone only was a dominated strategy (both less effective and more costly) and the ICER of all 3 MOUDs compared with no MOUD was $7252 (95% UI, $140-$10 018) per QALY. Among everyone with OUD in Massachusetts, XR-naltrexone only averted 95 overdose deaths over 5 years (95% UI, 85-169)-a 0.9% decrease in state-level overdose mortality-while the all-MOUD strategy averted 192 overdose deaths (95% UI, 156-200)-a 1.8% decrease. Conclusions and Relevance: The findings of this simulation-modeling economic study suggest that offering any MOUD to incarcerated individuals with OUD would prevent overdose deaths and that offering all 3 MOUDs would prevent more deaths and save money compared with an XR-naltrexone-only strategy.

A Method to Explore Variations of Ventilator-Associated Event Surveillance Definitions in Large Critical Care Databases in the United States.

The Centers for Disease Control has well-established surveillance programs to monitor preventable conditions in patients supported by mechanical ventilation (MV). The aim of the study was to develop a data-driven methodology to examine variations in the first tier of the ventilator-associated event surveillance definition, described as a ventilator-associated condition (VAC). Further, an interactive tool was designed to illustrate the effect of changes to the VAC surveillance definition, by applying different ventilator settings, time-intervals, demographics, and selected clinical criteria. DESIGN: Retrospective, multicenter, cross-sectional analysis. SETTING: Three hundred forty critical care units across 209 hospitals, comprising 261,910 patients in both the electronic Intensive Care Unit Clinical Research Database and Medical Information Mart for Intensive Care III databases. PATIENTS: A total of 14,517 patients undergoing MV for 4 or more days. MEASUREMENTS AND MAIN RESULTS: We designed a statistical analysis framework, complemented by a custom interactive data visualization tool to depict how changes to the VAC surveillance definition alter its prognostic performance, comparing patients with and without VAC. This methodology and tool enable comparison of three clinical outcomes (hospital mortality, hospital length-of-stay, and ICU length-of-stay) and provide the option to stratify patients by six criteria in two categories: patient population (dataset and ICU type) and clinical features (minimum Fio2, minimum positive end-expiratory pressure, early/late VAC, and worst first-day respiratory Sequential Organ Failure Assessment score). Patient population outcomes were depicted by heatmaps with mortality odds ratios. In parallel, outcomes from ventilation setting variations and clinical features were depicted with Kaplan-Meier survival curves. CONCLUSIONS: We developed a method to examine VAC using information extracted from large electronic health record databases. Building upon this framework, we developed an interactive tool to visualize and quantify the implications of variations in the VAC surveillance definition in different populations, across time and critical care settings. Data for patients with and without VAC was used to illustrate the effect of the application of this method and visualization tool.

Early Biomarker Signatures in Surgical Sepsis.

INTRODUCTION: Sepsis has complex, time-sensitive pathophysiology and important phenotypic subgroups. The objective of this study was to use machine learning analyses of blood and urine biomarker profiles to elucidate the pathophysiologic signatures of subgroups of surgical sepsis patients. METHODS: This prospective cohort study included 243 surgical sepsis patients admitted to a quaternary care center between January 2015 and June 2017. We applied hierarchical clustering to clinical variables and 42 blood and urine biomarkers to identify phenotypic subgroups in a development cohort. Clinical characteristics and short-term and long-term outcomes were compared between clusters. A naïve Bayes classifier predicted cluster labels in a validation cohort. RESULTS: The development cohort contained one cluster characterized by early organ dysfunction (cluster I, n = 18) and one cluster characterized by recovery (cluster II, n = 139). Cluster I was associated with higher Acute Physiologic Assessment and Chronic Health Evaluation II (30 versus 16, P < 0.001) and SOFA scores (13 versus 5, P < 0.001), greater prevalence of chronic cardiovascular and renal disease (P < 0.001) and septic shock (78% versus 17%, P < 0.001). Cluster I had higher mortality within 14 d of sepsis onset (11% versus 1.5%, P = 0.001) and within 1 y (44% versus 20%, P = 0.032), and higher incidence of chronic critical illness (61% versus 30%, P = 0.001). The Bayes classifier achieved 95% accuracy and identified two clusters that were similar to development cohort clusters. CONCLUSIONS: Machine learning analyses of clinical and biomarker variables identified an early organ dysfunction sepsis phenotype characterized by inflammation, renal dysfunction, endotheliopathy, and immunosuppression, as well as poor short-term and long-term clinical outcomes.

Analysis of Discrepancies Between Pulse Oximetry and Arterial Oxygen Saturation Measurements by Race and Ethnicity and Association With Organ Dysfunction and Mortality.

Importance: Discrepancies in oxygen saturation measured by pulse oximetry (Spo2), when compared with arterial oxygen saturation (Sao2) measured by arterial blood gas (ABG), may differentially affect patients according to race and ethnicity. However, the association of these disparities with health outcomes is unknown. Objective: To examine racial and ethnic discrepancies between Sao2 and Spo2 measures and their associations with clinical outcomes. Design, Setting, and Participants: This multicenter, retrospective, cross-sectional study included 3 publicly available electronic health record (EHR) databases (ie, the Electronic Intensive Care Unit-Clinical Research Database and Medical Information Mart for Intensive Care III and IV) as well as Emory Healthcare (2014-2021) and Grady Memorial (2014-2020) databases, spanning 215 hospitals and 382 ICUs. From 141 600 hospital encounters with recorded ABG measurements, 87 971 participants with first ABG measurements and an Spo2 of at least 88% within 5 minutes before the ABG test were included. Exposures: Patients with hidden hypoxemia (ie, Spo2 ≥88% but Sao2 <88%). Main Outcomes and Measures: Outcomes, stratified by race and ethnicity, were Sao2 for each Spo2, hidden hypoxemia prevalence, initial demographic characteristics (age, sex), clinical outcomes (in-hospital mortality, length of stay), organ dysfunction by scores (Sequential Organ Failure Assessment [SOFA]), and laboratory values (lactate and creatinine levels) before and 24 hours after the ABG measurement. Results: The first Spo2-Sao2 pairs from 87 971 patient encounters (27 713 [42.9%] women; mean [SE] age, 62.2 [17.0] years; 1919 [2.3%] Asian patients; 26 032 [29.6%] Black patients; 2397 [2.7%] Hispanic patients, and 57 632 [65.5%] White patients) were analyzed, with 4859 (5.5%) having hidden hypoxemia. Hidden hypoxemia was observed in all subgroups with varying incidence (Black: 1785 [6.8%]; Hispanic: 160 [6.0%]; Asian: 92 [4.8%]; White: 2822 [4.9%]) and was associated with greater organ dysfunction 24 hours after the ABG measurement, as evidenced by higher mean (SE) SOFA scores (7.2 [0.1] vs 6.29 [0.02]) and higher in-hospital mortality (eg, among Black patients: 369 [21.1%] vs 3557 [15.0%]; P < .001). Furthermore, patients with hidden hypoxemia had higher mean (SE) lactate levels before (3.15 [0.09] mg/dL vs 2.66 [0.02] mg/dL) and 24 hours after (2.83 [0.14] mg/dL vs 2.27 [0.02] mg/dL) the ABG test, with less lactate clearance (-0.54 [0.12] mg/dL vs -0.79 [0.03] mg/dL). Conclusions and Relevance: In this study, there was greater variability in oxygen saturation levels for a given Spo2 level in patients who self-identified as Black, followed by Hispanic, Asian, and White. Patients with and without hidden hypoxemia were demographically and clinically similar at baseline ABG measurement by SOFA scores, but those with hidden hypoxemia subsequently experienced higher organ dysfunction scores and higher in-hospital mortality.

Projected Estimates of Opioid Mortality After Community-Level Interventions.

Importance: The United States is experiencing a crisis of opioid overdose. In response, the US Department of Health and Human Services has defined a goal to reduce overdose mortality by 40% by 2022. Objective: To identify specific combinations of 3 interventions (initiating more people to medications for opioid use disorder [MOUD], increasing 6-month retention with MOUD, and increasing naloxone distribution) associated with at least a 40% reduction in opioid overdose in simulated populations. Design, Setting, and Participants: This decision analytical model used a dynamic population-level state-transition model to project outcomes over a 2-year horizon. Each intervention scenario was compared with the counterfactual of no intervention in simulated urban and rural communities in Massachusetts. Simulation modeling was used to determine the associations of community-level interventions with opioid overdose rates. The 3 examined interventions were initiation of more people to MOUD, increasing individuals' retention with MOUD, and increasing distribution of naloxone. Data were analyzed from July to November 2020. Main Outcomes and Measures: Reduction in overdose mortality, medication treatment capacity needs, and naloxone needs. Results: No single intervention was associated with a 40% reduction in overdose mortality in the simulated communities. Reaching this goal required use of MOUD and naloxone. Achieving a 40% reduction required that 10% to 15% of the estimated OUD population not already receiving MOUD initiate MOUD every month, with 45% to 60%% retention for at least 6 months, and increased naloxone distribution. In all feasible settings and scenarios, attaining a 40% reduction in overdose mortality required that in every month, at least 10% of the population with OUD who were not currently receiving treatment initiate an MOUD. Conclusions and Relevance: In this modeling study, only communities with increased capacity for treating with MOUD and increased MOUD retention experienced a 40% decrease in overdose mortality. These findings could provide a framework for developing community-level interventions to reduce opioid overdose death.

Improved predictive models for acute kidney injury with IDEA: Intraoperative Data Embedded Analytics.

BACKGROUND: Acute kidney injury (AKI) is a common complication after surgery that is associated with increased morbidity and mortality. The majority of existing perioperative AKI risk prediction models are limited in their generalizability and do not fully utilize intraoperative physiological time-series data. Thus, there is a need for intelligent, accurate, and robust systems to leverage new information as it becomes available to predict the risk of developing postoperative AKI. METHODS: A retrospective single-center cohort of 2,911 adults who underwent surgery at the University of Florida Health between 2000 and 2010 was utilized for this study. Machine learning and statistical analysis techniques were used to develop perioperative models to predict the risk of developing AKI during the first three days after surgery, first seven days after surgery, and overall (after surgery during the index hospitalization). The improvement in risk prediction was examined by incorporating intraoperative physiological time-series variables. Our proposed model enriched a preoperative model that produced a probabilistic AKI risk score by integrating intraoperative statistical features through a machine learning stacking approach inside a random forest classifier. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, and Net Reclassification Improvement (NRI). RESULTS: The predictive performance of the proposed model is better than the preoperative data only model. The proposed model had an AUC of 0.86 (accuracy of 0.78) for the seven-day AKI outcome, while the preoperative model had an AUC of 0.84 (accuracy of 0.76). Furthermore, by integrating intraoperative features, the algorithm was able to reclassify 40% of the false negative patients from the preoperative model. The NRI for each outcome was AKI at three days (8%), seven days (7%), and overall (4%). CONCLUSIONS: Postoperative AKI prediction was improved with high sensitivity and specificity through a machine learning approach that dynamically incorporated intraoperative data.