Myocardial injury after non-cardiac surgery: a perioperative affair?

Development and validation of a machine learning predictive model for perioperative myocardial injury in cardiac surgery with cardiopulmonary bypass

BACKGROUND

Perioperative myocardial injury (PMI) with different cut-off values has showed to be associated with different prognostic effect after cardiac surgery. Machine learning (ML) method has been widely used in perioperative risk predictions during cardiac surgery. However, the utilization of ML in PMI has not been studied yet. Therefore, we sought to develop and validate the performances of ML for PMI with different cut-off values in cardiac surgery with cardiopulmonary bypass (CPB).

METHODS

This was a second analysis of a multicenter clinical trial (OPTIMAL) and requirement for written informed consent was waived due to the retrospective design. Patients aged 18-70 undergoing elective cardiac surgery with CPB from December 2018 to April 2021 were enrolled in China. The models were developed using the data from Fuwai Hospital and externally validated by the other three cardiac centres. Traditional logistic regression (LR) and eleven ML models were constructed. The primary outcome was PMI, defined as the postoperative maximum cardiac Troponin I beyond different times of upper reference limit (40x, 70x, 100x, 130x) We measured the model performance by examining the area under the receiver operating characteristic curve (AUROC), precision-recall curve (AUPRC), and calibration brier score.

RESULTS

A total of 2983 eligible patients eventually participated in both the model development (n = 2420) and external validation (n = 563). The CatboostClassifier and RandomForestClassifier emerged as potential alternatives to the LR model for predicting PMI. The AUROC demonstrated an increase with each of the four cutoffs, peaking at 100x URL in the testing dataset and at 70x URL in the external validation dataset. However, it's worth noting that the AUPRC decreased with each cutoff increment. Additionally, the Brier loss score decreased as the cutoffs increased, reaching its lowest point at 0.16 with a 130x URL cutoff. Moreover, extended CPB time, aortic duration, elevated preoperative N-terminal brain sodium peptide, reduced preoperative neutrophil count, higher body mass index, and increased high-sensitivity C-reactive protein levels were identified as risk factors for PMI across all four cutoff values.

CONCLUSIONS

The CatboostClassifier and RandomForestClassifer algorithms could be an alternative for LR in prediction of PMI. Furthermore, preoperative higher N-terminal brain sodium peptide and lower high-sensitivity C-reactive protein were strong risk factor for PMI, the underlying mechanism require further investigation.

Hybrid feature selection in a machine learning predictive model for perioperative myocardial injury in noncoronary cardiac surgery with cardiopulmonary bypass

BACKGROUND

Perioperative myocardial injury (PMI) is associated with increased mobility and mortality after noncoronary cardiac surgery. However, limited studies have developed a predictive model for PMI. Therefore, we used hybrid feature selection (FS) methods to establish a predictive model for PMI in noncoronary cardiac surgery with cardiopulmonary bypass (CPB).

METHODS

This was a single-center retrospective study conducted at the Fuwai Hospital in China. Patients aged 18-70 years who underwent elective noncoronary surgery with CPB at our institution from December 2018 to April 2021 were enrolled. The primary outcome was PMI, defined as the postoperative cardiac troponin I (cTnI) levels exceeding 220 times of upper reference limit (URL). Statistical analyses were conducted by Python (Python Software Foundation, version 3.9.7 and integrated development environment Jupyter Notebook 1.1.0) and SPSS software version 26.0 (IBM Corp., Armonk, New York, USA).

RESULTS

A total of 1130 patients were eventually eligible for this study. The incidence of PMI was 20.3% (229/1130) in the overall patients, 20.6% (163/791) in the training dataset, and 19.5% (66/339) in the testing dataset. The logistic regression model performed the best AUC of 0.6893 (95 CI%: 0.6371-0.7382) by the traditional selection method, and the random forest model performed the best AUC of 0.6937 (95 CI%: 0.6416-0.7423) by the union of Wrapper and Embedded method, and the CatBoost model performed the best AUC of 0.6828 (95 CI%: 0.6304-0.7320) by the union of Embedded and forward logistic regression technique, and the Naïve Bayes model achieved the best AUC with 0.7254 (95 CI%: 0.6746-0.7723) by forwarding logistic regression method. Moreover, the decision tree, KNeighborsClassifier, and support vector machine models performed the worse AUC in all selection forms. Furthermore, the SHapley Additive exPlanations plot showed that prolonged CPB, aortic clamp time, and preoperative low platelets count were strongly related to the PMI risk.

CONCLUSIONS

In total, four category feature selection methods were utilized, comprising five individual selection techniques and 15 combined methods. Notably, the combination of logistic regression and embedded methods demonstrated outstanding performance in predicting PMI risk. We also concluded that the machine learning model, including random forest, catboost, and Naive Bayes, were suitable candidates for establishing PMI predictive model. Nevertheless, additional investigation and validation are imperative for substantiating these finding.

Effect of Dexamethasone on Myocardial Injury After Total Knee Arthroplasty: A Substudy of the Randomized Clinical DEX-2-TKA Trial

BACKGROUND

Myocardial injury after noncardiac surgery (MINS) carries a high postoperative mortality. In this preplanned, subgroup analysis of the randomized DEX-2-TKA Trial, we investigated the effect of dexamethasone versus placebo on the concentration of cardiac troponin I and T (TnI and TnT) on the first postoperative morning after total knee arthroplasty. In addition, frequency of MINS, myocardial infarction, and major adverse cardiovascular events where evaluated.

METHODS

We included 290 patients who received either 24 mg of dexamethasone intravenously (given perioperatively) or placebo. Blood samples were analyzed as either TnI or T depending on trial site.

RESULTS

A total of 236 samples were eligible for analysis of TnI and 38 samples for TnT on the first postoperative morning. The median (IQR) TnI concentration was 4.6 ng/L (0-7.2 ng/L) in the dexamethasone group and 4.5ng/l (0-7.0 ng/L) in the placebo group (P = .96) on the first postoperative morning. The median TnT was 9 ng/L (6-11 ng/L) in the dexamethasone group and 8 ng/L (5-10 ng/L) in the placebo group (P = .68). The frequencies of MINS, myocardial infarction, and major adverse cardiovascular events were similar in the compared groups, but these analyses were underpowered.

CONCLUSION

We found no effect of dexamethasone on postoperative concentration of troponin I or T on the first postoperative morning after total knee arthroplasty.

Myocardial Injury after Non-cardiac Surgery - State of the Art

Aproximadamente 300 milhões de cirurgias não cardíacas são realizadas anualmente no mundo, e eventos cardiovasculares adversos são as principais causas de morbimortalidade no período perioperatório e pós-operatório. A lesão miocárdica após cirurgia não cardíaca (MINS, do inglês myocardial injury after non-cardiac surgery) é uma nova entidade clínica associada com desfechos cardiovasculares adversos. MINS é definida como uma lesão miocárdica que pode resultar em necrose secundária à isquemia, com elevação dos biomarcadores. A lesão tem importância prognóstica e ocorre em até 30 dias após a cirurgia não cardíaca. Os critérios diagnósticos para MINS são: níveis elevados de troponina durante ou em até 30 dias após a cirurgia não cardíaca, sem evidência de etiologia não isquêmica, sem que haja necessariamente sintomas isquêmicos ou achados eletrocardiográficos de isquemia. Recentemente, pacientes com maior risco para MINS têm sido identificados por variáveis clínicas e biomarcadores, bem como por protocolos de vigilância quanto ao monitoramento eletrocardiográfico e dosagem de troponina cardíaca. Pacientes idosos com doença aterosclerótica prévia necessitam medir troponina diariamente no período pós-operatório. O objetivo deste trabalho é descrever este novo problema de saúde pública, seu impacto clínico e a abordagem terapêutica contemporânea.

An Italian registry of chest pain patients in the emergency department: clinical predictors of acute coronary syndrome

BACKGROUND

The aim of this study was to describe the population of patients arriving in several Italian Emergency Departments (EDs) complaining of chest pain suggestive of acute coronary syndrome (ACS) in order to evaluate the incidence of ACS in this cohort and the association between ACS and different clinical parameters and risk factors.

METHODS

This is an observational prospective study, conducted from the 1st January to the 31st December 2014 in 11 EDs in Italy. Patients presenting to ED with chest pain, suggestive of ACS, were consecutively enrolled.

RESULTS

Patients with a diagnosis of ACS (N.=1800) resulted to be statistically significant older than those without ACS (NO ACS; N.=4630) (median age: 70 vs. 59, P<0.001), and with a higher prevalence of males (66.1% in ACS vs. 57.5% in NO ACS, P<0.001). ECG evaluation, obtained at ED admission, showed new onset alterations in 6.2% of NO ACS and 67.4% of ACS patients. Multiple logistic regression analysis showed that the following parameters were predictive for ACS: age, gender, to be on therapy for cardio-vascular disease (CVD), current smoke, hypertension, hypercholesterolemia, heart rate, ECG alterations, increased BMI, reduced SaO2.

CONCLUSIONS

Results from this observational study strengthen the importance of the role of the EDs in ruling in and out chest pain patients for the diagnosis of ACS. The analysis put in light important clinical and risk factors that, if promptly recognized, can help Emergency Physicians to identify patients who are more likely to be suffering from ACS.