Comparing ensemble learning algorithms and severity of illness scoring systems in cardiac intensive care units: a retrospective study.

BACKGROUND: Beatriz Nistal-Nuño designed a machine learning system type of ensemble learning for patients undergoing cardiac surgery and intensive care unit cardiology patients, based on sequences of cardiovascular physiological measurements and other intensive care unit physiological measurements in addition to static features, which generates a score for prediction of mortality of cardiac intensive care unit patients. BACKGROUND: ■ Gradient Boosting Machine and Random Forest models were built for prediction of mortality at cardiac intensive care units. BACKGROUND: ■ A total of 9,761 intensive care unit stays of patients admitted under a Cardiac Surgery and Cardiac Medical services were studied. BACKGROUND: ■ The AUROC and AUPRC values were significantly superior to seven conventional systems compared. BACKGROUND: ■ The machine learning models' calibration curves were substantially closer to the ideal line. OBJECTIVE: Logistic Regression has been used traditionally for the development of most predictor tools of intensive care unit mortality. The purpose of this study is to combine shared risk factors between patients undergoing cardiac surgery and intensive care unit cardiology patients to develop a risk score for prediction of mortality in cardiac intensive care unit patients, using machine learning. METHODS: Gradient Boosting Machine and Distributed Random Forest models were developed based on 9,761 intensive care unit-stays from the MIMIC-III database. Sequential and static features were collected. The primary endpoint was intensive care unit mortality prediction. Discrimination, calibration, and accuracy statistics were evaluated. The predictive performance of traditional scoring systems was compared. RESULTS: Machine learning models' AUROC and AUPRC were significantly superior to all conventional systems for the primary endpoint (p<0.05), with AUROC of 0.9413 for Gradient Boosting Machine and 0.9311 for Distributed Random Forest. Sensitivity was 0.6421 for Gradient Boosting Machine, 0.6 for Distributed Random Forest, and <0.3 for all conventional systems except for serial SOFA (0.6316). Precision was 0.574 for Gradient Boosting Machine, 0.566 for Distributed Random Forest, and <0.5 for all conventional systems. Diagnostic odds ratio was 58.8144 for Gradient Boosting Machine, 51.2926 for Distributed Random Forest and <34 for all conventional systems. Brier score was 0.025 for Gradient Boosting Machine and 0.028 for Distributed Random Forest, being worse for the traditional systems. Calibration curves of Gradient Boosting Machine and Distributed Random Forest were substantially closer to the ideal line. CONCLUSION: The machine learning models showed superiority over the traditional scoring systems compared, with Gradient Boosting Machine having the best performance. Discrimination and calibration were excellent for Gradient Boosting Machine, followed by Distributed Random Forest. The machine learning methods exhibited better capacity for most accuracy statistics.

Assessing the Nursing Workload in the Cardiothoracic Intensive Care Unit: Comparative Study.

AIMS: This study aimed to assess nursing workload in Cardiac Intensive Care Unit (CICU) after three cardiothoracic surgery procedures during first four postoperative days using Nursing Activities Score (NAS) and Nine Equivalents of Nursing Manpower Use Score (NEMS) systems, to compare their performance for that purpose and to investigate association between nursing workload and type of surgery. DESIGN: A comparative study. METHODS: The research environment includes CICU of the University Hospital for Cardiovascular Diseases in Serbia. A total of 808 patients who underwent coronary, valvular, or combined surgery, resulting in 2282 filled NAS and NEMS pairs chart. Statistical analysis was performed using SPSS-19. The correlation between NAS and NEMS was tested by Spearman's correlation coefficient. Differences were considered statistically significant at p < 0.05. RESULTS: The lowest median of cumulative NAS 176 (175-257) and NEMS 76 (64-91) had coronary surgery patients, the highest NAS 224.5 (178-334.5) and NEMS 83 (69-121) had those with combined surgery; this difference was statistically significant (p < 0.001). The median of both scores decreased after surgery, with the following values from the first to the fourth postoperative day: NAS from 104 (102-105) to 81 (74-85) and NEMS from 46 (42-46) to 30 (30-37). The difference in mean values of both scores between the first and the fourth postoperative day was statistically significant (p < 0.001). NAS and NEMS were in a positive, strong correlation (r = 0.913; p < 0.005). CONCLUSION: Both scores can be used to measure nursing workload, identify the required number of nurses in CICU, and support task allocation. NAS may have an advantage because it better describes extensive postoperative monitoring and care needed for cardiac surgery patients. Nursing workload is associated with type of surgery, with the highest workload measured in patients who underwent combined surgery procedure and on the first postoperative day.

The World Society for Pediatric and Congenital Heart Surgery: 2024 Update of the World Database for Pediatric and Congenital Heart Surgery.

BACKGROUND: The World Database for Pediatric and Congenital Heart Surgery (WDPCHS), sponsored by the World Society for Pediatric and Congenital Heart Surgery (WSPCHS), provides complex congenital heart surgery outcomes analyses for member programs. This report represents the seven-year descriptive analysis of outcomes from active members of the WDPCHS. METHODS: Individual institutions submit data based on the specific procedure via a password protected platform. The data are collected, stored, and analyzed at Kirklin Solutions Inc., based in Birmingham, Alabama. This report presents a descriptive analysis of these procedures submitted from January 1, 2017, to December 31, 2023. RESULTS: A total of 50,174 procedures were submitted with an overall mortality of 4.6%. The majority of submissions were from Asian countries. The majority of cases submitted from these countries were of STAT mortality category I and II. Repair of a ventricular septal defect (with a mortality of 0.8%) and correction of tetralogy of Fallot (2.0% mortality) were the most common procedures submitted to the database. CONCLUSIONS: The WSPCHS accomplished one of its missions in 2017 when the WDPCHS began accepting data from pediatric and congenital heart surgery programs across the globe. In doing so, it became one of the first organizations to create a platform for the exchange of knowledge and experience, regardless of the socioeconomic status of the particular program or country.

Inequalities in access to and outcomes of cardiac surgery in England: retrospective analysis of Hospital Episode Statistics (2010-2019).

BACKGROUND: We aimed to characterise the variation in access to and outcomes of cardiac surgery for people in England. METHODS: We included people >18 years of age with hospital admission for ischaemic heart disease (IHD) and heart valve disease (HVD) between 2010 and 2019. Within these populations, we identified people who had coronary artery bypass graft (CABG) and/or valve surgery, respectively. We fitted logistic regression models to examine the effects of age, sex, ethnicity and socioeconomic deprivation on having access to surgery and in-hospital mortality, 1-year mortality and hospital readmission. RESULTS: We included 292 140 people, of whom 28% were women, 11% were from an ethnic minority and 17% were from the most deprived areas. Across all types of surgery, one in five people are readmitted to hospital within 1 year, rising to almost one in four for valve surgery. Women, black people and people living in the most deprived areas were less likely to have access to surgery (CABG: 59%, 32% and 35% less likely; valve: 31%, 33% and 39% less likely, respectively) and more likely to die within 1 year of surgery (CABG: 24%, 85% and 18% more likely, respectively; valve: 19% (women) and 10% (people from most deprived areas) more likely). CONCLUSIONS: Female sex, black ethnicity and economic deprivation are independently associated with limited access to cardiac surgery and higher post-surgery mortality. Actions are required to address these inequalities.

County-level food insecurity is associated with outcomes following cardiac surgery.

BACKGROUND: As there is limited literature evaluating food insecurity status (FI) and surgical outcomes, we sought to assess the association between county-level FI and outcomes following cardiac surgery. METHODS: In a retrospective cohort, patients who underwent coronary artery bypass grafting between 2016 and 2020 were identified utilizing the Medicare Standard Analytic Files. Using County-level FI, patients were stratified into low, moderate, and high cohorts. The primary outcome was textbook outcomes, a measure of "optimal" post-operative outcomes. Adjusted multiple logistic regression and Cox regression models were utilized to evaluate outcomes and survival. RESULTS: Among 267,914 patients, patients residing in high FI regions were less likely to achieve textbook outcomes (OR: 0.94, 95 â€‹% CI: 0.90-0.99). When evaluating individual post-operative outcomes of interest, patients residing in high FI regions also had a greater odd of 90-day mortality (OR: 1.24, 95 â€‹% CI: 1.12-1.36) and extended LOS (OR: 1.07, 95 â€‹% CI: 1.01-1.14) (all p â€‹< â€‹0.0001). Moreover, this population was also at greater risk of 5-year mortality (HR: 1.11, 95 â€‹% CI: 1.06-1.17) compared with their counterparts from low food insecurity regions. Racial disparities persisted in high FI counties as Black patients had a greater risk of 5-year mortality (HR: 1.27, 95 â€‹% CI: 1.17-1.38, p â€‹< â€‹0.0001) compared with White patients within the same FI level. CONCLUSIONS: County-level FI was associated with worse outcomes following cardiac surgery.

Gender gap in cardiothoracic surgery randomized controlled trial and post-hoc analysis of randomized controlled trial authorship from 2014 to 2020.

OBJECTIVES: To estimate gender disparities among first and last authorships in cardiothoracic randomized controlled trials (RCTs) and association of gender with publications in high-impact journals. METHODS: PubMed/MEDLINE database was searched from 1 January 2014 to 31 December 2020 using R statistical software via the 'easyPubMed' package to retrieve pertinent data. The 'gender' package was utilized to determine gender using the United States Social Security Administration Baby Name Data. The percentage of female first and last authors were computed along with determining the uniqueness of the names. The association of gender and publication in high-impact peer-reviewed journals was delineated. Jonckheere's trend was computed. RESULTS: The database search retrieved a total of 4820 RCTs, of which gender was encoded for the first author in 3247 (67%) RCTs, among which 911 (28%) studies had women as first authors, with a similar trend across 7 years (P = 0.23). Gender was encoded for the last author of 3204 (66%) RCTs, of which 622 (19%) studies had women as last authors, with a similar trend across 7 years (P = 0.45). A total of 627 studies were published in high-impact-factor journals, among which 79 (16%) studies had female first authors and 67 (13%) studies had female last authors. CONCLUSIONS: There is an obvious gender disparity of first and last authors in cardiothoracic surgery-related RCTs, with a similar trend across 7 years. However, the post-hoc analysis did demonstrate a positive trend with an increase in the number of female first authors, demonstrating progress.

Predictors of premature termination of cardiac surgery trials: insights from the Clinicaltrial.gov database.

OBJECTIVES: Clinical trials that are terminated prematurely may generate incomplete and potentially biased data and the reasons for premature trials termination are poorly understood. Our objective was to describe the incidence of premature trial termination and identify factors associated with it. METHODS: We performed a systematic search on ClinicalTrials.gov to identify all cardiac surgery trials from 1991 to 2023. Trials that were terminated prematurely were identified. Factors independently associated with premature termination were identified using multivariable logistic regression analysis. RESULTS: A total of 746 clinical trials were included; of them 577 were completed and 169 (22.6%) were terminated prematurely. Most of the trials originated from North America [294 (39.4%)], Europe [264 (35.4%)] or Asia [141 (18.9%)]. Fourteen of the trials terminated prematurely (8.3%) were phase 1, 75 (44.4%) phase 2, 49 (29.0%) phase 3 and 31 (18.3%) phase 4. Fifty (29.6%) trials were terminated because of slow recruitment, 20 (11.8%) because of sponsor decision and 12 (7.1%) because of lack of funding. Left ventricular assist device trials [odds ratio (OR) 3.65, 95% confidence interval (CI) (1.65-8.00) P = 0.001], valve surgery trials [OR 4.30, 95% CI (2.33-8.00) P < 0.001], aortic surgery trials [OR 2.86 95% CI (1.22-6.43) P = 0.012], phase 2 [OR 3.02, 95% CI (1.31-7.93) P = 0.015] and phase 4 trials [OR 3.62, 95% CI (1.43-10.23) P = 0.010] were at higher risk of premature termination while trials performed in Asia [OR 0.18, 95% CI (0.07-0.39) P ≤ 0.001] and Europe [OR 0.49, 95% CI (0.30-0.80) P = 0.004] were less likely to be terminated prematurely. CONCLUSIONS: Slow recruitment is the most common reason for premature termination of cardiac surgery trials. Trials on left ventricular assist device, valve surgery, aortic surgery, phase 2 trials and phase 4 trials are more likely to be terminated, while trials conducted in Asia and Europe are less likely to be terminated prematurely.

Automated Versus Semi-Automated Lab Value Extraction for the VA Cardiac Surgical Quality Improvement Program.

INTRODUCTION: The Veterans Affairs Surgical Quality Improvement Program (VASQIP) trains surgical quality nurses (SQNs) at each Veterans Affairs (VA) hospital to extract or verify 187 variables from the medical record for all cardiac surgical cases. For ten preoperative laboratory values, VASQIP has a semiautomated (SA) system in which local lab values are automatically extracted, verified by SQNs, and lab values recorded at other VA facilities are manually extracted. The objective of this study was to develop and validate a method to automate the extraction of these ten preoperative laboratory values and compare results with the current SA method. MATERIALS AND METHODS: We developed methods to extract ten preoperative laboratory values and measurement dates from the VA Corporate Data Warehouse using Logical Observation Identifiers Names and Codes. Automated (A) versus SA information extraction was compared in terms of agreement, conformance to data definitions, proximity to surgery, and missingness. RESULTS: For surgeries with both A and SA lab values, the intraclass correlation coefficients for the ten variables ranged from 0.90 to 0.98. For several variables, the A method resulted in much lower rates of missing data (e.g., 2.4% versus 22.5% missing data for high-density lipoprotein) and eliminated out-of-date-range entries. CONCLUSIONS: Although SQN-extracted data are widely considered the gold standard within National Surgical Quality Improvement Programs, there may be advantages to fully automating extraction of lab values, including high congruence with SA SQN-extracted or verified values and lower rates of missingness and out-of-date-range data.

Effect of Preoperative Recombinant Human Erythropoietin on the Need for Blood Transfusion and Surgical Outcomes in Adult Patients Undergoing Cardiac Surgery: A Systematic Review and Meta-Analysis with Trial Sequential Analysis.

This study aimed to examine the value of preoperative recombinant human erythropoietin (rhEPO) administration to adults undergoing elective cardiac surgery. Databases were searched for randomized controlled trials (RCTs) comparing rhEPO plus standard treatment versus standard treatment only. Primary outcomes were the need for and volume of homologous blood transfusion (HBT). Secondary outcomes were the lengths of intensive care unit (ICU) and hospital stay and the incidence of major adverse events. There was very low certainty that rhEPO is associated with a reduction in the need for HBT, with a number needed to treat of 5.6 (95% confidence interval [CI], 3.9-12.5), and low certainty that it is associated with a moderate reduction in HBT volume (Hedges g = -0.55; 95% CI, -0.79 to -0.32). Meta-regression revealed that studies with a higher proportion of females or older patients demonstrated less benefit of rhEPO in terms of reduced consumption of HBT. Trial sequential analysis showed that rhEPO was superior to standard treatment only for reducing the need for and volume of HBT. Regarding secondary outcomes, there was moderate certainty that rhEPO is associated with a limited reduction in the length of ICU (Hedges g = -0.10; 95% CI, -0.19 to -0.01) and hospital stay (Hedges g = -0.13; 95% CI = -0.25 to -0.02), and low certainty for increased risk of myocardial infarction, with a number needed to harm of 36.1 (95% CI, 17.9-127.4). More well-designed, adequately powered RCTs are needed to draw conclusions regarding the value of rhEPO.

Cardiac surgery during wartime in Israel.

BACKGROUND: The war that began on October 7th, 2023, has impacted all major tertiary medical centers in Israel. In the largest cardiac surgery department in Israel there has been a surprising increase in the number of open-heart procedures, despite having approximately 50% of surgeons recruited to military service. The purpose of this study is to characterize this increase in the number of operations performed during wartime and assess whether the national crisis has affected patient outcomes. METHODS: The study was based on a prospectively collected registry of 275 patients who underwent cardiac surgery or extracorporeal membrane oxygenation (ECMO) during the first two months of war, October 7th 2023 - December 7th 2023, as well as patients that underwent cardiac surgery during the same period of time in 2022 (October 7th, 2022 - December 7th, 2022). RESULTS: 120 patients (43.6%) were operated on in 2022, and 155 (56.4%) during wartime in 2023. This signifies a 33.0% increase in open-heart procedures (109 in 2022 vs. 145 in 2023, p-value 0.26). There were no significant differences in the baseline characteristics of patients when comparing the 2022 patients to those in 2023. No significant differences between the two groups were found with regards to intraoperative characteristics or the type of surgery. However, compared to 2022, there was a 233% increase in the number of transplantations in the 2023 cohort (p-value 0.24). Patient outcomes during wartime were similar to those of 2022, including postoperative complications, length of stay, and mortality. CONCLUSIONS: Patients who underwent cardiac surgery during wartime presented with comparable outcomes when compared to those of last year despite the increase in cardiac surgery workload. There was an increase in the number of transplants this year, attributed to the unfortunate increase in organ donors.

Sex-related differences in patients with infective endocarditis requiring cardiac surgery: insights from the CAMPAIGN Study Group.

OBJECTIVES: Sex-related differences play a role in cardiovascular disease-related outcomes. There is, however, a knowledge gap regarding sex-specific differences in patients with infective endocarditis (IE)-requiring surgical treatment. This study aims to analyse sex-related differences in the clinical presentation, treatment and clinical outcomes of patients with IE-requiring surgical treatment from the multicentric Germany-wide CAMPAIGN registry. METHODS: Patients with IE who underwent cardiac surgery between 1994 and 2018 at six German centres were retrospectively analysed. Outcomes were compared based on patients' sex. Primary outcomes were 30-day mortality and mid-term survival. RESULTS: A total of 4917 patients were included in the analysis (1364 female [27.7%] and 3553 male [72.3%]). Female patients presented with more comorbidities and higher surgical risk (EuroScore II 12.0% vs 10.0%, P < 0.001). The early postoperative course of female patients was characterized by longer ventilation times (20.0 h vs 16.0 h; P = 0.004), longer intensive care unit stay (4.0 days vs 3.0 days; P < 0.001), and more frequent new-onset dialysis (265 [20.3%] vs 549 [16.3%]; P = 0.001). The 30-day mortality was 13.8% and 15.5% in female and male patients, respectively (P = 0.06). The estimated mid-term survival was significantly higher amongst male patients (56.1% vs 45.4%; Log-rank P < 0.001). Female sex was an independent predictor of mid-term mortality (HR 1.2 [95% CI 1.0-1.4], P = 0.01). CONCLUSIONS: Male patients more frequently undergo cardiac surgery for IE. However, female patients have a higher surgical risk profile and subsequently an increased early postoperative morbidity, but with similar 30-day mortality compared with male patients. The estimated mid-term survival is lower amongst female patients.

The Ross Operation Over 55 Years Later: Comparing Surgical Techniques and Outcomes.

The Ross procedure is often considered the best option for a small group of patients. Some critics argue that harvesting the pulmonary artery again can cause problems, such as exposing the native pulmonary autograft to systemic pressures and requiring further intervention. However, the pulmonary autograft is a living tissue that can adjust to growing conditions and undergo remodelling. The pathophysiology of living tissue, harvesting techniques, indications for use of pulmonary autograft in aortic valve disease, contraindications, and variations of pulmonary autograft as an aortic conduit are discussed in this seminar. Following recent updates from high-volume centres, the indications, contraindications, techniques, and variations of pulmonary autograft as an aortic conduit and, in the absence of substantial well-designed randomised controlled trials, areas where the Ross procedure needs to be reaffirmed as part of the surgical armamentarium are also discussed. Furthermore, increasing evidence suggests that the Ross procedure produces better long-term results than traditional aortic valve replacement in young and middle-aged adults. To enable cardiologists and surgeons to make appropriate decisions for their patients with aortic valve disease, the author provides a complete review of the most recent published studies on the Ross procedure.

Transfusion strategy trials excluding patients transfused outside the trial study period are more likely to report a trend favoring restrictive strategies: a meta-analysis.

OBJECTIVES: Some large, randomized trials investigating red cell transfusion strategies have significant numbers of transfusions administered outside the trial study period. We sought to investigate the potential impact of this methodological issue. STUDY DESIGN AND SETTING: Meta-analysis of randomized controlled trials (RCTs) comparing liberal vs restrictive transfusion strategies in cardiac surgery and acute myocardial infarction patients. The outcome of interest was 30-day or in-hospital mortality. RESULTS: In cardiac surgery, the pooled risk ratio for mortality was 0.83 (95% confidence interval [CI] 0.62-1.12, P = .22) times lower in the restrictive group when compared to the liberal group in trials applying a transfusion strategy throughout the patient's entire perioperative period, and 1.33 (95% CI 0.84-2.11, P = .22) times higher in the restrictive group in trials not applying transfusion strategies throughout the entire perioperative period. When combined, the risk ratio for mortality was 0.98 (95% CI 0.73-1.32, P = .89). In patients with acute myocardial infarction, the risk ratio for mortality was 0.72 (95% CI 0.40-1.28, P = .26) times lower in the restrictive group when compared to the liberal group in 1 trial excluding patients administered the intervention prerandomization and 1.19 (95% CI 0.96-1.47, P = .11) times higher in the restrictive group in 1 trial including patients receiving the intervention prerandomization. When combined the risk ratio for mortality was 1.00 (0.62-1.59, P = .99). CONCLUSION: Though not statistically significant, there was a consistent difference in trends between RCTs administering significant numbers of transfusion outside the trial study period compared to those that did not. The implications of our results may extend to RCTs in other settings that ignore if and how frequently an investigated therapy is administered outside the trial window.

Distribution and Characteristics of Congenital Cardiac Surgery Centers within Bangladesh.

Congenital heart disease is a leading cause of non-communicable childhood death. This is especially true in nations with limited resources where shortages of skilled workforce, healthcare facilities, and essential equipment limit the ability to provide care. This retrospective study was designed to determine the volume and distribution of surgical care being provided to patients with congenital heart disease in Bangladesh, as well as to characterize the facilities providing such care. Pre-existing survey data of hospitals performing congenital heart surgery in the year 2022 in Bangladesh was obtained. Additional information was gathered on these facilities, including hospital location and type. The distribution of care by geographic location, type of facility, and volume of cases was reported. Overall, a total of 2333 surgeries were performed in 2022 at 28 facilities. The majority of hospitals were performing <50 cases per year, while a small number (5) provided greater than 50.0% of all surgeries. In addition, while the majority of hospitals were private in nature, the majority of surgeries occurred at not-for-profit hospitals. There was a large geographic skew of surgeries and hospitals being located within the city of Dhaka (79.0% of centers and 94.0% of surgeries). The data suggests that, though there has been great progress in increasing the number of surgeries performed in Bangladesh, the vast majority of patients still do not have access to care. In addition, nearly all care is being provided in Dhaka, which presents challenges for patients who come from across the nation seeking care. Finally, there is a great need for further research to fully understand the challenges faced and find workable solutions.

Factors Associated With Lack of Long-Term Follow-Up Data After Global Cardiac Surgery Missions.

Background: Humanitarian medical missions attempt to lessen the burden of limited access to cardiac surgery in low- and middle-income countries. While organizations express difficulties obtaining follow-up information, there is currently little evidence to support the various assumptions for lack of data. This study examines the factors influencing long-term patient follow-ups on repeated short-term cardiac surgery missions across nine countries. Methods: A retrospective analysis of CardioStart International's database (RedCap) was conducted to investigate demographic, socioeconomic, and surgical factors associated with follow-ups. Results: A total of 550 pediatric (50%) and adult (50%) cardiac surgery patients displayed a follow-up rate of 14.7%, with no significant difference between populations (P = 1). Mean follow-up time was 1.5 years postoperative. Countries were highly variable, with Dominican Republic and Vietnam showing follow-up rates of 30.4% and 43.2%, respectively, while Brazil, Nepal, and Tanzania had no follow-ups (P < 0.0001). The 11 surrogate factors for socioeconomic status, including home amenities and technology access, were predominantly insignificant, with the exception of phone access showing an unexpectedly decreased follow-up rate (11.6%, P = 0.006). Surgical intervention was a significant factor (P = 0.009). No adult cardiac surgery trends were noted; however, congenital cases demonstrated increased follow-ups in patients with higher Risk Adjusted Congenital Heart Surgery scores, with ventricular septal defects (32.5%) exceeding atrial septal defects (7.3%). Conclusions: Follow-ups correlate with mission factors, including location and types of intervention, more so than previously assumed socioeconomic and technological factors. Thus, certain missions may require more allocation of resources and adapted organizational policies to overcome site-specific barriers to follow-up.

Reduce intraoperative albumin utilisation in cardiac surgical patients: a quality improvement initiative.

BACKGROUND: Albumin continues to be used routinely by cardiac anaesthesiologists perioperatively despite lack of evidence for improved outcomes. The Multicenter Perioperative Outcomes Group (MPOG) data ranked our institution as one of the highest intraoperative albumin users during cardiac surgery. Therefore, we designed a quality improvement project (QIP) to introduce a bundle of interventions to reduce intraoperative albumin use in cardiac surgical patients. METHODS: Our institutional MPOG data were used to analyse the FLUID-01-C measure that provides the number of adult cardiac surgery cases where albumin was administered intraoperatively by anaesthesiologists from 1 July 2019 to 30 June 2022. The QIP involved introduction of the following interventions: (1) education about appropriate albumin use and indications (January 2021), (2) email communications reinforced with OR teaching (March 2021), (3) removal of albumin from the standard pharmacy intraoperative medication trays (April 2021), (4) grand rounds presentation discussing the QIP and highlighting the interventions (May 2021) and (5) quarterly provider feedback (starting July 2021). Multivariable segmented regression models were used to assess the changes from preintervention to postintervention time period in albumin utilisation, and its total monthly cost. RESULTS: Among the 5767 cardiac surgery cases that met inclusion criteria over the 3-year study period, 16% of patients received albumin intraoperatively. The total number of cases that passed the metric (albumin administration was avoided), gradually increased as our interventions went into effect. Intraoperative albumin utilisation (beta=-101.1, 95% CI -145 to -56.7) and total monthly cost of albumin (beta=-7678, 95% CI -10712 to -4640) demonstrated significant decrease after starting the interventions. CONCLUSIONS: At a single academic cardiac surgery programme, implementation of a bundle of simple and low-cost interventions as part of a coordinated QIP were effective in significantly decreasing intraoperative use of albumin, which translated into considerable costs savings.