RESUMEN
BACKGROUND: Fresh frozen plasma (FFP) transfusion is used to manage coagulopathy and bleeding in cardiac surgery patients despite uncertainty about its safety and effectiveness. METHODS: We performed a propensity score matched analysis of the Australian and New Zealand Society of Cardiac and Thoracic Surgeons National Cardiac Surgery Database including patients from 39 centres from 2005 to 2018. We investigated the association of perioperative FFP transfusion with mortality and other clinical outcomes. RESULTS: Of 119,138 eligible patients, we successfully matched 13,131 FFP recipients with 13,131 controls. FFP transfusion was associated with 30-day mortality (odds ratio (OR), 1.41; 99% CI, 1.17-1.71; p < .0001), but not with long-term mortality (hazard ratio (HR), 0.92; 99% CI, 0.85-1.00; p = .007, Holm-Bonferroni α = 0.0004). FFP was also associated with return to theatre for bleeding (OR, 1.97; 99% CI, 1.66-2.34; p < .0001), prolonged intubation (OR, 1.15; 99% CI, 1.05-1.26; p < .0001) and increased chest tube drainage (Mean difference (MD) in mL, 131; 99% CI, 120-141; p < .0001). It was also associated with reduced postoperative creatinine levels (MD in g/L, -6.33; 99% CI, -10.28 to -2.38; p < .0001). CONCLUSION: In a multicentre, propensity score matched analysis, perioperative FFP transfusion was associated with increased 30-day mortality and had variable associations with secondary clinical outcomes.
Asunto(s)
Procedimientos Quirúrgicos Cardíacos , Plasma , Humanos , Femenino , Masculino , Anciano , Persona de Mediana Edad , Atención Perioperativa/métodos , Puntaje de Propensión , Transfusión Sanguínea/estadística & datos numéricos , Transfusión Sanguínea/métodos , Resultado del Tratamiento , Australia , Transfusión de Componentes Sanguíneos/estadística & datos numéricos , Nueva Zelanda , Complicaciones Posoperatorias/epidemiologíaRESUMEN
OBJECTIVES: To assess whether there are sex-based differences in the administration of opioid analgesic drugs among inpatients after cardiac surgery. DESIGN: A retrospective cohort study. SETTING: At a tertiary academic referral center. PARTICIPANTS: Adult patients who underwent cardiac surgery from 2014 to 2019. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The primary outcome was the cumulative oral morphine equivalent dose (OMED) for the postoperative admission. Secondary outcomes were the daily difference in OMED and the administration of nonopioid analgesics. The authors developed multivariate regression models controlling for known confounders, including weight and length of stay. A total of 3,822 patients (1,032 women and 2,790 men) were included. The mean cumulative OMED was 139 mg for women and 180 mg for men, and this difference remained significant after adjustment for confounders (adjusted mean difference [aMD], -33.21 mg; 95% CI, -47.05 to -19.36 mg; p < 0.001). The cumulative OMED was significantly lower in female patients on postoperative days 1 to 5, with the greatest disparity observed on day 5 (aMD, -89.83 mg; 95% CI, -155.9 to -23.80 mg; p = 0.009). By contrast, women were more likely to receive a gabapentinoid (odds ratio, 1.91; 95% CI, 1.42-2.58; p < 0.001). The authors found no association between patient sex and the administration of other nonopioid analgesics or specific types of opioid analgesics. The authors found no association between patient sex and pain scores recorded within the first 48 hours after extubation, or the number of opioids administered in close proximity to pain assessments. CONCLUSIONS: Female sex was associated with significantly lower amounts of opioids administered after cardiac surgery.
Asunto(s)
Analgésicos no Narcóticos , Procedimientos Quirúrgicos Cardíacos , Adulto , Humanos , Femenino , Masculino , Analgésicos Opioides , Estudios Retrospectivos , Caracteres Sexuales , Dolor Postoperatorio/diagnóstico , Dolor Postoperatorio/tratamiento farmacológico , Dolor Postoperatorio/etiología , Morfina , Procedimientos Quirúrgicos Cardíacos/efectos adversosRESUMEN
BACKGROUND: Platelet transfusion is common in cardiac surgery, but some studies have suggested an association with harm. Accordingly, we investigated the association of perioperative platelet transfusion with morbidity and mortality. METHODS: We conducted a retrospective analysis of prospectively collected data from the Australian Society of Cardiac and Thoracic Surgeons National Cardiac Surgery Database. We included consecutive adults from 2005 to 2018 across 40 centers. We used inverse probability of treatment weighting via entropy balancing to investigate the association of perioperative platelet transfusion with our 2 primary outcomes, operative mortality (composite of both 30-day and in-hospital mortality) and 90-day mortality, as well as multiple other clinically relevant secondary outcomes. RESULTS: Among 119,132 eligible patients, 25,373 received perioperative platelets and 93,759 were considered controls. After entropy balancing, platelet transfusion was associated with reduced operative mortality (odds ratio [OR], 0.63; 99% confidence interval [CI], 0.47-0.84; P < .0001) and 90-day mortality (OR, 0.66; 99% CI, 0.51-0.85; P < .0001). Moreover, it was associated with reduced odds of deep sternal wound infection (OR, 0.57; 99% CI, 0.36-0.89; P = .0012), acute kidney injury (OR, 0.84; 99% CI, 0.71-0.99; P = .0055), and postoperative renal replacement therapy (OR, 0.71; 99% CI, 0.54-0.93; P = .0013). These positive associations were observed despite an association with increased odds of return to theatre for bleeding (OR, 1.55; 99% CI, 1.16-2.09; P < .0001), pneumonia (OR, 1.26; 99% CI, 1.11-1.44; P < .0001), intubation for longer than 24 hours postoperatively (OR, 1.13; 99% CI, 1.03-1.24; P = .0012), inotrope use for >4 hours postoperatively (OR, 1.14; 99% CI, 1.11-1.17; P < .0001), readmission to hospital within 30 days of surgery (OR, 1.22; 99% CI, 1.11-1.34; P < .0001), as well as increased drain tube output (adjusted mean difference, 89.2 mL; 99% CI, 77.0 mL-101.4 mL; P < .0001). CONCLUSIONS: In cardiac surgery patients, perioperative platelet transfusion was associated with reduced operative and 90-day mortality. Until randomized controlled trials either confirm or refute these findings, platelet transfusion should not be deliberately avoided when considering odds of death.
Asunto(s)
Procedimientos Quirúrgicos Cardíacos , Transfusión de Plaquetas , Adulto , Humanos , Transfusión de Plaquetas/efectos adversos , Estudios Retrospectivos , Entropía , Australia , Procedimientos Quirúrgicos Cardíacos/efectos adversosRESUMEN
INTRODUCTION: Fresh frozen plasma (FFP) transfusion in the intensive care unit (ICU) is commonly used to treat coagulopathy and bleeding in cardiac surgery, despite suggestion that it may increase the risk of morbidity and mortality through mechanisms such as fluid overload and infection. METHODS: We retrospectively studied consecutive adults undergoing cardiac surgery from the Medical Information Mart for Intensive Care III and IV databases. We applied propensity score matching to investigate the independent association of within-ICU FFP transfusion with mortality and other key clinical outcomes. RESULTS: Of our 12,043 adults who met inclusion criteria, 1585 (13.2%) received perioperative FFP with a median of 2.48 units per recipient (interquartile range [IQR]: 2.04, 4.33) at a median time of 1.83 h (IQR: 0.75, 3.75) after ICU admission. After propensity matching of 952 FFP recipients to 952 controls, we found no significant association between FFP use and hospital mortality (odds ratio (OR): 1.58; 99% confidence interval (CI): 0.57, 3.71), suspected infection (OR: 0.72; 99% CI: 0.49, 1.08), or acute kidney injury (OR: 1.23; 99% CI: 0.91, 1.67). However, FFP was associated with increased days in hospital (adjusted mean difference (AMD): 1.28; 99% CI: 0.27, 2.41; p = .0050), days in intensive care (AMD: 1.28; 99% CI: 0.27, 2.28; p = .0011), and chest tube output in millilitres up to 8 h after transfusion (AMD: 92.98; 99% CI: 52.22, 133.74; p < .0001). CONCLUSIONS: After propensity matching, FFP transfusion was not associated with increased hospital mortality, but was associated with increased length of stay and no decrease in bleeding in the early post-transfusion period.
RESUMEN
Machine learning (ML) is increasingly applied to predict adverse postoperative outcomes in cardiac surgery. Commonly used ML models fail to translate to clinical practice due to absent model explainability, limited uncertainty quantification, and no flexibility to missing data. We aimed to develop and benchmark a novel ML approach, the uncertainty-aware attention network (UAN), to overcome these common limitations. Two Bayesian uncertainty quantification methods were tested, generalized variational inference (GVI) or a posterior network (PN). The UAN models were compared with an ensemble of XGBoost models and a Bayesian logistic regression model (LR) with imputation. The derivation datasets consisted of 153,932 surgery events from the Australian and New Zealand Society of Cardiac and Thoracic Surgeons (ANZSCTS) Cardiac Surgery Database. An external validation consisted of 7343 surgery events which were extracted from the Medical Information Mart for Intensive Care (MIMIC) III critical care dataset. The highest performing model on the external validation dataset was a UAN-GVI with an area under the receiver operating characteristic curve (AUC) of 0.78 (0.01). Model performance improved on high confidence samples with an AUC of 0.81 (0.01). Confidence calibration for aleatoric uncertainty was excellent for all models. Calibration for epistemic uncertainty was more variable, with an ensemble of XGBoost models performing the best with an AUC of 0.84 (0.08). Epistemic uncertainty was improved using the PN approach, compared to GVI. UAN is able to use an interpretable and flexible deep learning approach to provide estimates of model uncertainty alongside state-of-the-art predictions. The model has been made freely available as an easy-to-use web application demonstrating that by designing uncertainty-aware models with innately explainable predictions deep learning may become more suitable for routine clinical use.
Asunto(s)
Procedimientos Quirúrgicos Cardíacos , Lepidópteros , Animales , Teorema de Bayes , Incertidumbre , Australia , Aprendizaje Automático , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND: The 'weekend effect' is the term given to the observed discrepancy regarding patient care and outcomes on weekends compared to weekdays. This study aimed to determine whether the weekend effect exists within Aotearoa New Zealand (AoNZ) for patients undergoing emergency laparotomy (EL), given recent advances in management of EL patients. METHODS: A cohort study was conducted across five hospitals, comparing the outcomes of weekend and weekday acute EL. A propensity-score matched analysis was used to remove potential confounding patient characteristics. RESULTS: Of the 487 patients included, 132 received EL over the weekend. There was no statistically significant difference between patients undergoing EL over the weekend compared to weekdays. Mortality rates were comparable between the weekday and weekend cohorts (P = 0.464). CONCLUSIONS: These results suggest that modern perioperative care practice in New Zealand obviates the 'weekend' effect.
Asunto(s)
Laparotomía , Admisión del Paciente , Humanos , Puntaje de Propensión , Estudios de Cohortes , Mortalidad Hospitalaria , Factores de Tiempo , Estudios RetrospectivosRESUMEN
Objectives: Machine learning (ML) classification tools are known to accurately predict many cardiac surgical outcomes. A novel approach, ML-based survival analysis, remains unstudied for predicting mortality after cardiac surgery. We aimed to benchmark performance, as measured by the concordance index (C-index), of tree-based survival models against Cox proportional hazards (CPH) modeling and explore risk factors using the best-performing model. Methods: 144,536 patients with 147,301 surgery events from the Australian and New Zealand Society of Cardiac and Thoracic Surgeons (ANZSCTS) national database were used to train and validate models. Univariate analysis was performed using Student's T-test for continuous variables, Chi-squared test for categorical variables, and stratified Kaplan-Meier estimation of the survival function. Three ML models were tested, a decision tree (DT), random forest (RF), and gradient boosting machine (GBM). Hyperparameter tuning was performed using a Bayesian search strategy. Performance was assessed using 2-fold cross-validation repeated 5 times. Results: The highest performing model was the GBM with a C-index of 0.803 (0.002), followed by RF with 0.791 (0.003), DT with 0.729 (0.014), and finally CPH with 0.596 (0.042). The 5 most predictive features were age, type of procedure, length of hospital stay, drain output in the first 4â h (ml), and inotrope use greater than 4â h postoperatively. Conclusion: Tree-based learning for survival analysis is a non-parametric and performant alternative to CPH modeling. GBMs offer interpretable modeling of non-linear relationships, promising to expose the most relevant risk factors and uncover new questions to guide future research.
RESUMEN
BACKGROUND: Cryoprecipitate is often transfused in patients undergoing cardiac surgery. However, its safety and effectiveness remain uncertain. METHODS: This study was a propensity score-matched analysis of data from the Australian and New Zealand Society of Cardiac and Thoracic Surgeons National Cardiac Surgery Database. The study included adults undergoing cardiac surgery between 2005 and 2018 across 38 sites. The association between perioperative cryoprecipitate transfusion and clinical outcomes was estimated, with a primary outcome of operative mortality. RESULTS: Of 119,132 eligible patients, 11,239 (9.43%) patients received cryoprecipitate. The median cumulative dose was 8 U (interquartile range, 5-10 U). After propensity score matching, we matched 9055 cryoprecipitate recipients to 9055 control subjects. Postoperative cryoprecipitate transfusion was associated with reduced operative mortality (odds ratio [OR], 0.82; 99% CI, 0.69-0.97; P = .002) and long-term mortality (hazard ratio, 0.92; 99% CI, 0.87-0.97; P = .0042). It was also associated with a reduction in acute kidney injury (OR, 0.85; 99% CI, 0.73-0.98; P = .0037) and all-cause infection (OR, 0.77; 99% CI, 0.67-0.88; P < .0001). These findings were observed despite increased rates of return to the operating room (OR, 1.36; 99% CI, 1.22-1.51; P < .0001) and cumulative 4-hour postoperative chest tube output (adjusted mean difference in mL, 97.69; 99% CI, 81.65;113.74; P < .0001). CONCLUSIONS: In a large, multicenter cohort study and after propensity score matching, perioperative transfusion of cryoprecipitate was associated with reduced operative and long-term mortality.
Asunto(s)
Procedimientos Quirúrgicos Cardíacos , Hemostáticos , Adulto , Humanos , Estudios de Cohortes , Australia , Transfusión Sanguínea , Estudios RetrospectivosRESUMEN
RED CELL DISTRIBUTION WIDTH (RDW) is a routinely available biomarker of likely erythropoietic dysfunction, which may be associated with adverse outcomes after cardiac surgery. This systematic review and meta-analysis aimed to clarify the prognostic value of RDW in patients undergoing cardiac surgery. The authors searched MEDLINE, Embase, and the Cochrane Library from inception to May 10, 2022 for studies investigating the association between elevated RDW (as defined by the authors of included studies) and adverse outcomes after cardiac surgery. Herein, the authors extracted maximally adjusted hazard ratios (HRs) and odds ratios (ORs) with associated CIs, and pooled them using random-effects inverse- variance modeling. The authors explored interstudy heterogeneity using metaregression. The authors included 26 studies involving 48,092 patients who had undergone cardiac surgery. Elevated preoperative RDW was associated with long-term mortality (pooled HR 1.63, 95% CI 1.05-2.52), short-term mortality (pooled OR 2.16, 95% CI 1.21-3.87), acute kidney injury (AKI; pooled OR 1.30, 95% CI 1.19-1.41) and postoperative atrial fibrillation (POAF; pooled OR 1.44, 95% CI 1.05-1.96). Some studies suggested a significant association between preoperative RDW elevation and neurologic complications; however, their number was insufficient for meta-analysis. The postoperative RDW levels were less consistently reported and could not be meta-analyzed. In conclusion, the authors found that elevated preoperative RDW was associated with increased short- and long-term mortality, POAF, and AKI after cardiac surgery. Further research is needed to investigate its role in the risk stratification of patients undergoing cardiac surgery.
Asunto(s)
Lesión Renal Aguda , Procedimientos Quirúrgicos Cardíacos , Humanos , Índices de Eritrocitos , Pronóstico , Procedimientos Quirúrgicos Cardíacos/efectos adversos , Biomarcadores , Lesión Renal Aguda/etiologíaRESUMEN
OBJECTIVES: To investigate the independent association of platelet transfusion with hospital mortality and key relevant clinical outcomes in cardiac surgery. DESIGN: A single-center, propensity score-matched, retrospective, cohort study. SETTING: At an American tertiary teaching hospital data from the Medical Information Mart for Intensive Care III and IV databases from 2001 to 2019. PARTICIPANTS: Consecutive adults undergoing coronary artery bypass graft and/or cardiac valvular surgery. INTERVENTIONS: Platelet transfusion during perioperative intensive care unit (ICU) admission. MEASUREMENTS AND MAIN RESULTS: Overall, 12,043 adults met the study inclusion criteria. Of these, 1,621 (13.5%) received apheresis-leukoreduced platelets, with a median of 1.19 units per recipient (IQR: 0.93-1.19) at a median of 1.78 hours (IQR: 0.75-4.25) after ICU admission. The platelet count was measured in 1,176 patients (72.5%) before transfusion, with a median count of 120 × 109/L (IQR: 89.0-157.0), and only 53 (3.3%) had platelet counts below 50 × 109/L. After propensity matching of 1,046 platelet recipients with 1,046 controls, perioperative platelet transfusion carried no association with in-hospital mortality (odds ratio [OR]: 1.28; 99% CI: 0.49-3.35; p = 0.4980). However, it was associated with a pattern of decreased odds of suspected infection (eg, respiratory infection, urinary tract infection, septicaemia, or other; OR: 0.70; 99% CI: 0.50-0.97; p = 0.0050), days in the hospital (adjusted mean difference [AMD]: 0.86; 99% CI: -0.27 to 1.98; p = 0.048), or days in intensive care (AMD 0.83; 99% CI: -0.15 to 1.82; p = 0.0290). CONCLUSIONS: Platelet transfusion was not associated with hospital mortality, but it was associated with decreased odds of suspected infection and with shorter ICU and hospital stays.
Asunto(s)
Procedimientos Quirúrgicos Cardíacos , Transfusión de Plaquetas , Adulto , Humanos , Estudios de Cohortes , Estudios Retrospectivos , Transfusión SanguíneaRESUMEN
OBJECTIVES: The association of cryoprecipitate transfusion with patient outcomes after cardiac surgery is unclear. We aimed to investigate the predictors of, and outcomes associated with, postoperative cryoprecipitate transfusion in cardiac surgery patients. METHODS: We used the Medical Information Mart for Intensive Care III and IV databases. We included adults undergoing cardiac surgery, and propensity score matched cryoprecipitate-treated patients to controls. Using the matched cohort, we investigated the association of cryoprecipitate use with clinical outcomes. The primary outcome was in-hospital mortality. Secondary outcomes were infection, acute kidney injury, intensive care unit length of stay, hospital length of stay, and chest tube output at 2-hour intervals. RESULTS: Of 12,043 eligible patients, 283 (2.35%) patients received cryoprecipitate. The median dose was 5.83 units (IQR 4.17-7.24) given at a median first transfusion time of 1.75 hours (IQR 0.73-4.46) after intensive care unit admission. After propensity scoring, we matched 195 cryoprecipitate recipients to 743 controls. Postoperative cryoprecipitate transfusion was not significantly associated with in-hospital mortality (odds ratio [OR] 1.10; 99% confidence interval [CI] 0.43-2.84; p=0.791), infection (OR 0.77; 99% CI 0.45-1.34; p=0.220), acute kidney injury (OR 1.03; 99% CI 0.65-1.62; p=0.876) or cumulative chest tube output (adjusted mean difference 8 hrs post transfusion, 11 mL; 99% CI -104 to 125; p=0.804). CONCLUSIONS: Although cryoprecipitate was typically given to sicker patients with more bleeding, its administration was not associated with worse outcomes. Large, multicentred studies are warranted to further elucidate cryoprecipitate's safety profile and patterns of use in cardiac surgery.
Asunto(s)
Transfusión Sanguínea , Procedimientos Quirúrgicos Cardíacos , Adulto , Humanos , Procedimientos Quirúrgicos Cardíacos/efectos adversos , Hemorragia/etiología , Estudios RetrospectivosRESUMEN
BACKGROUND: Transcatheter aortic valve implantation (TAVI) is emerging as a therapeutic gold standard in the management of aortic stenosis. However, post-procedural complications of this procedure are being increasingly recognised. We therefore performed this systematic review and meta-analysis on the prognostic value of elevated troponin prior to TAVI to predict risk of post-procedural complications. METHODS: We searched Medline (Ovid), Embase (Ovid), and the Cochrane Library from inception until May 2022, and included studies on the association between elevated pre-procedural troponin with 30-day mortality, long-term mortality, and post-procedural myocardial injury (PPMI). We generated summary odds ratios (OR) and hazards ratios (HR) using random-effects meta-analysis and performed subgroup analyses to evaluate differences in troponin threshold selection. Inter-study heterogeneity was tested using the I2 test. RESULTS: We included 10 studies involving 4200 patients. Serum troponin elevation prior to TAVI was significantly associated with long-term mortality [HR = 2.09 (95% CI 1.30-3.36)], but not with 30-day mortality [OR 1.76 (95% CI 0.96-3.22)]. Subgroup analysis showed a trend towards increased effect size and statistical significance for 30-day mortality as troponin elevation was more narrowly defined. Two studies reported on PPMI and found no statistically significant mean difference between groups. CONCLUSIONS: Raised serum troponin is associated with increased long-term mortality following TAVI. Further clarification on the optimal troponin threshold for risk identification is required. High-quality studies that utilise ROC analysis for threshold selection are warranted.
Asunto(s)
Estenosis de la Válvula Aórtica , Reemplazo de la Válvula Aórtica Transcatéter , Humanos , Reemplazo de la Válvula Aórtica Transcatéter/efectos adversos , Reemplazo de la Válvula Aórtica Transcatéter/métodos , Troponina , Resultado del Tratamiento , Factores de Riesgo , Estenosis de la Válvula Aórtica/diagnóstico , Estenosis de la Válvula Aórtica/cirugía , Válvula Aórtica/cirugíaRESUMEN
BACKGROUND: Patients undergoing cardiac surgery are at significant risk of developing postoperative acute kidney injury (AKI). Neutrophil-lymphocyte ratio (NLR) is a widely available inflammatory biomarker which may be of prognostic value in this setting. METHODS: We conducted a systematic review and meta-analysis of studies reporting associations between perioperative NLR with postoperative AKI. We searched Medline, Embase and the Cochrane Library, without language restriction, from inception to May 2022 for relevant studies. We meta-analysed the reported odds ratios (ORs) with 95% confidence intervals (CIs) for both elevated preoperative and postoperative NLR with risk of postoperative AKI and need for renal replacement therapy (RRT). We conducted a meta-regression to explore inter-study statistical heterogeneity. RESULTS: Twelve studies involving 10,724 participants undergoing cardiac surgery were included, with eight studies being deemed at high risk of bias using PROBAST modelling. We found statistically significant associations between elevated preoperative NLR and postoperative AKI (OR 1.45, 95% CI 1.18-1.77), as well as postoperative need for RRT (OR 2.37, 95% CI 1.50-3.72). Postoperative NLR measurements were not of prognostic significance. CONCLUSIONS: Elevated preoperative NLR is a reliable inflammatory biomarker for predicting AKI following cardiac surgery.
Asunto(s)
Lesión Renal Aguda , Procedimientos Quirúrgicos Cardíacos , Humanos , Pronóstico , Neutrófilos , Linfocitos , Procedimientos Quirúrgicos Cardíacos/efectos adversos , Biomarcadores , Lesión Renal Aguda/diagnóstico , Lesión Renal Aguda/etiologíaRESUMEN
OBJECTIVE(S): To use machine learning (ML) to predict short-term requirements for invasive ventilation in patients with COVID-19 admitted to Australian intensive care units (ICUs). DESIGN: A machine learning study within a national ICU COVID-19 registry in Australia. PARTICIPANTS: Adult patients who were spontaneously breathing and admitted to participating ICUs with laboratory-confirmed COVID-19 from 20 February 2020 to 7 March 2021. Patients intubated on day one of their ICU admission were excluded. MAIN OUTCOME MEASURES: Six machine learning models predicted the requirement for invasive ventilation by day three of ICU admission from variables recorded on the first calendar day of ICU admission; (1) random forest classifier (RF), (2) decision tree classifier (DT), (3) logistic regression (LR), (4) K neighbours classifier (KNN), (5) support vector machine (SVM), and (6) gradient boosted machine (GBM). Cross-validation was used to assess the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of machine learning models. RESULTS: 300 ICU admissions collected from 53 ICUs across Australia were included. The median [IQR] age of patients was 59 [50-69] years, 109 (36%) were female and 60 (20%) required invasive ventilation on day two or three. Random forest and Gradient boosted machine were the best performing algorithms, achieving mean (SD) AUCs of 0.69 (0.06) and 0.68 (0.07), and mean sensitivities of 77 (19%) and 81 (17%), respectively. CONCLUSION: Machine learning can be used to predict subsequent ventilation in patients with COVID-19 who were spontaneously breathing and admitted to Australian ICUs.
Asunto(s)
COVID-19 , Ventilación no Invasiva , Adulto , Humanos , Persona de Mediana Edad , Anciano , COVID-19/epidemiología , COVID-19/terapia , Enfermedad Crítica/terapia , Australia/epidemiología , Aprendizaje AutomáticoRESUMEN
BACKGROUND: Machine learning (ML) models are promising tools for predicting adverse postoperative outcomes in cardiac surgery, yet have not translated to routine clinical use. We conducted a systematic review and meta-analysis to assess the predictive performance of ML approaches. METHODS: We conducted an electronic search to find studies assessing ML and traditional statistical models to predict postoperative outcomes. Our primary outcome was the concordance (C-) index of discriminative performance. Using a Bayesian meta-analytic approach we pooled the C-indices with the 95% credible interval (CrI) across multiple outcomes comparing ML methods to logistic regression (LR) and clinical scoring tools. Additionally, we performed critical difference and sensitivity analysis. RESULTS: We identified 2792 references from the search of which 51 met inclusion criteria. Two postoperative outcomes were amenable for meta-analysis: 30-day mortality and in-hospital mortality. For 30-day mortality, the pooled C-index and 95% CrI were 0.82 (0.79-0.85), 0.80 (0.77-0.84), 0.78 (0.74-0.82) for ML models, LR, and scoring tools respectively. For in-hospital mortality, the pooled C-index was 0.81 (0.78-0.84) and 0.79 (0.73-0.84) for ML models and LR, respectively. There were no statistically significant results indicating ML superiority over LR. CONCLUSION: In cardiac surgery patients, for the prediction of mortality, current ML methods do not have greater discriminative power over LR as measured by the C-index.
Asunto(s)
Procedimientos Quirúrgicos Cardíacos , Aprendizaje Automático , Teorema de Bayes , Procedimientos Quirúrgicos Cardíacos/efectos adversos , Mortalidad Hospitalaria , Humanos , Modelos LogísticosRESUMEN
Cardiac troponin is well known as a highly specific marker of cardiomyocyte damage, and has significant diagnostic accuracy in many cardiac conditions. However, the value of elevated recipient troponin in diagnosing adverse outcomes in heart transplant recipients is uncertain. We searched MEDLINE (Ovid), Embase (Ovid), and the Cochrane Library from inception until December 2020. We generated summary sensitivity, specificity, and Bayesian areas under the curve (BAUC) using bivariate Bayesian modelling, and standardised mean differences (SMDs) to quantify the diagnostic relationship of recipient troponin and adverse outcomes following cardiac transplant. We included 27 studies with 1,684 cardiac transplant recipients. Patients with acute rejection had a statistically significant late elevation in standardised troponin measurements taken at least 1 month postoperatively (SMD 0.98, 95% CI 0.33-1.64). However, pooled diagnostic accuracy was poor (sensitivity 0.414, 95% CrI 0.174-0.696; specificity 0.785, 95% CrI 0.567-0.912; BAUC 0.607, 95% CrI 0.469-0.723). In summary, late troponin elevation in heart transplant recipients is associated with acute cellular rejection in adults, but its stand-alone diagnostic accuracy is poor. Further research is needed to assess its performance in predictive modelling of adverse outcomes following cardiac transplant. Systematic Review Registration: identifier CRD42021227861.
Asunto(s)
Rechazo de Injerto , Trasplante de Corazón , Adulto , Teorema de Bayes , Biomarcadores , Rechazo de Injerto/diagnóstico , Trasplante de Corazón/efectos adversos , Humanos , TroponinaRESUMEN
BACKGROUND: Hyperbilirubinemia following cardiac surgery is a common phenomenon and is of emerging interest in prognostic factor research. This systematic review and meta-analysis evaluated the association between post-operative hyperbilirubinemia (PH) and mortality and morbidity in cardiac surgery patients. METHODS: Ovid Medline and Ovid Embase were searched from inception to July 2020 for studies evaluating the prognostic significance of PH following cardiac surgery. Maximally adjusted odds ratios (OR) with associated confidence intervals were obtained from each study and pooled using random effects inverse variance modelling to assess in-hospital mortality. Standardised mean differences were pooled to assess Intensive Care Unit (ICU) and hospital length of stay (LOS). Qualitative analysis was performed to assess ventilation requirements and long-term mortality. Meta-regression was used to assess inter- and intra-study heterogeneity. RESULTS: 3251 studies satisfied the selection criteria, from which 12 studies incorporating 3876 participants were included. PH significantly predicted in-hospital mortality with a pooled OR of 7.29 (95% CI 3.53, 15.09). Multiple pre-defined covariates contributed to the prognostic significance of PH, however only aortic cross-clamp time (p < 0.0001) and number of transfusions (p = 0.0001) were significant effect modifiers. PH significantly predicted both ICU LOS (Mean difference 1.32 [95% CI 0.04-2.6]) and hospital LOS (Mean difference 1.79 [95% CI 0.36-3.21]). Qualitative analysis suggested PH is associated with increased post-operative ventilation requirements and reduced long-term survival rates. CONCLUSIONS: Hyperbilirubinemia is a cost-effective, widely available prognostic marker of adverse outcomes following cardiac surgery, albeit with residual sources of heterogeneity.
Asunto(s)
Procedimientos Quirúrgicos Cardíacos , Procedimientos Quirúrgicos Cardíacos/efectos adversos , Mortalidad Hospitalaria , Humanos , Hiperbilirrubinemia/etiología , Tiempo de Internación , PronósticoRESUMEN
OBJECTIVES: Cardiac troponin is a highly specific biomarker of myocardial injury that is of prognostic significance in a range of cardiovascular diseases. However, the prognostic value of elevated troponin in cardiac transplant recipients is uncertain. We aimed to evaluate the prognostic value of elevated cardiac troponin in predicting adverse recipient outcomes following heart transplant. MATERIALS AND METHODS: We searched MEDLINE (Ovid), Embase (Ovid), and the Cochrane Library from inception until December 2020 and included studies reporting associations between elevated recipient troponin and outcomes after cardiac transplant. We generated summary odds ratios for associations with short- and long-term adverse events and used descriptive analyses where meta-analyses were inappropriate. RESULTS: We included 15 studies involving 1830 patients undergoing cardiac transplant. The risk of primary graft failure was greater in recipients with elevated troponin than in those without (odds ratio = 3.09; 95% CI, 1.08-8.87). Considerable interstudy heterogeneity (I2 statistic 98%) was partially explained by variations in study design, troponin subtype, and overall risk of bias. Descriptive analyses suggested associations between elevated recipient troponin and long-term adverse cardiac events, coronary artery disease, and mortality. CONCLUSIONS: Elevated cardiac troponin in cardiac transplant recipients may be prognostic for primary graft failure, adverse cardiac events, coronary artery disease, and mortality. Further high-quality, prospective, and multicenter research is needed to demonstrate the clinical applicability of these findings.
Asunto(s)
Enfermedad de la Arteria Coronaria , Trasplante de Corazón , Adulto , Trasplante de Corazón/efectos adversos , Humanos , Estudios Multicéntricos como Asunto , Pronóstico , Estudios Prospectivos , Resultado del Tratamiento , TroponinaRESUMEN
BACKGROUND: Cardiac troponin is a highly specific and widely available marker of myocardial injury, and elevations in cardiac transplant donors may influence donor selection. We aimed to investigate whether elevated donor troponin has a role as a prognostic biomarker in cardiac transplantation. METHODS: In a systematic review and meta-analysis, we searched MEDLINE, Embase, and the Cochrane Library, without language restriction, from inception to December 2020. We included studies reporting the association of elevated donor troponin with recipient outcome after cardiac transplant. We generated summary odds ratios and hazard ratios for the association of elevated donor troponin with short- and long-term adverse outcomes. Methodological quality was monitored using the Quality In Prognosis Studies tool, and interstudy heterogeneity was assessed using a series of sensitivity and subgroup analyses. RESULTS: We included 17 studies involving 15 443 patients undergoing cardiac transplantation. Elevated donor troponin was associated with increased odds of graft rejection at 1 y (odds ratio, 2.54; 95% confidence interval, 1.22-5.28). No significant prognostic relationship was found between donor troponin and primary graft failure, short- to long-term mortality, cardiac allograft vasculopathy, and pediatric graft loss. CONCLUSIONS: Elevated donor troponin is not associated with an increased short- or long-term mortality postcardiac transplant despite increasing the risk of graft rejection at 1 y. Accordingly, an elevated donor troponin in isolation should not exclude donation.
RESUMEN
The neutrophil-lymphocyte ratio (NLR) and platelet-lymphocyte ratio (PLR) are emerging haematological inflammatory biomarkers. However, their significance in retinal vein occlusion (RVO) and its subtypes, branch and central RVO (BRVO and CRVO, respectively), is uncertain. This systematic review and meta-analysis aimed to clarify the association of NLR and PLR with RVO. We searched MEDLINE (Ovid), EMBASE (Ovid) and the Cochrane Library for studies investigating the association of NLR and PLR with RVO from inception to 2 December 2020. We used random-effects inverse-variance modelling to generate pooled effect measures. We used bivariate Bayesian modelling to meta-analyse the ability of NLR and PLR to differ between individuals with and without RVO and performed meta-regression and sensitivity analyses to explore inter-study heterogeneity. Eight studies published encompassing 1059 patients were included for analysis. Both NLR and PLR were significantly elevated in RVO, with pooled mean differences of 0.63 (95% confidence interval (CI) 0.31-0.95) and 21.49 (95% CI 10.03-32.95), respectively. The pooled sensitivity, specificity and area under the Bayesian summary receiver operating characteristic curve were, respectively, 0.629 (95% credible interval (CrI) 0.284-0.872), 0.731 (95% CrI 0.373-0.934) and 0.688 (95% CrI 0.358-0.872) for NLR; and 0.645 (95% CrI 0.456-0.779), 0.616 (95% CrI 0.428-0.761) and 0.621 (95% CrI 0.452-0.741) for PLR. Mean and variability of age and diabetes mellitus prevalence partially explained between-study heterogeneity. NLR and PLR are significantly elevated in RVO. Future research is needed to investigate the potential prognostic value and independence of these findings.