Dataset Information

Machine learning approach identified clusters for patients with low cardiac output syndrome and outcomes after cardiac surgery.

ABSTRACT:

Background

Low cardiac output syndrome (LCOS) is the most serious physiological abnormality with high mortality for patients after cardiac surgery. This study aimed to explore the multidimensional data of clinical features and outcomes to provide individualized care for patients with LCOS.

Methods

The electronic medical information of the intensive care units (ICUs) was extracted from a tertiary hospital in South China. We included patients who were diagnosed with LCOS in the ICU database. We used the consensus clustering approach based on patient characteristics, laboratory data, and vital signs to identify LCOS subgroups. The consensus clustering method involves subsampling from a set of items, such as microarrays, and determines to cluster of specified cluster counts (k). The primary clinical outcome was in-hospital mortality and was compared between the clusters.

Results

A total of 1,205 patients were included and divided into three clusters. Cluster 1 (n = 443) was defined as the low-risk group [in-hospital mortality =10.1%, odds ratio (OR) = 1]. Cluster 2 (n = 396) was defined as the medium-risk group [in-hospital mortality =25.0%, OR = 2.96 (95% CI = 1.97-4.46)]. Cluster 3 (n = 366) was defined as the high-risk group [in-hospital mortality =39.2%, OR = 5.75 (95% CI = 3.9-8.5)].

Conclusion

Patients with LCOS after cardiac surgery could be divided into three clusters and had different outcomes.

SUBMITTER: Zhao X

PROVIDER: S-EPMC9434347 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning approach identified clusters for patients with low cardiac output syndrome and outcomes after cardiac surgery.

Zhao Xu X Gu Bowen B Li Qiuying Q Li Jiaxin J Zeng Weiwei W Li Yagang Y Guan Yanping Y Huang Min M Lei Liming L Zhong Guoping G

Frontiers in cardiovascular medicine 20220818

<h4>Background</h4>Low cardiac output syndrome (LCOS) is the most serious physiological abnormality with high mortality for patients after cardiac surgery. This study aimed to explore the multidimensional data of clinical features and outcomes to provide individualized care for patients with LCOS.<h4>Methods</h4>The electronic medical information of the intensive care units (ICUs) was extracted from a tertiary hospital in South China. We included patients who were diagnosed with LCOS in the ICU ...[more]

PMID: 36061544

Similar Datasets

Project description:BackgroundThis study aimed to develop machine learning models to predict Low Cardiac Output Syndrome (LCOS) in patients following cardiac surgery using machine learning algorithms.MethodsThe clinical data of cardiac surgery patients in Nanjing First Hospital between June 2019 and November 2020 were retrospectively extracted from the electronic medical records. Six conventional machine learning algorithms, including logistic regression, support vector machine, decision tree, random forest, extreme gradient boosting and light gradient boosting machine, were employed to construct the LCOS predictive models with all predictive features (full models) and selected predictive features (reduced models). The discrimination of these models was evaluated by the area under the receiver operating characteristic curve (AUC) and the calibration of the models was assessed by the calibration curve. Shapley Additive explanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) were used to interpret the predictive models.ResultsData from 1,585 patients [982 (62.0%) were male, aged 18 to 88, 212 (13.4%) with LCOS] were employed to train and validate the LCOS models. Among the full models, the RF model (AUC: 0.909, 95% CI: 0.875-0.943; Sensitivity: 0.849, 95% CI: 0.724-0.933; Specificity: 0.835, 95% CI: 0.796-0.869) and the XGB model (AUC: 0.897, 95% CI: 0.859-0.935; Sensitivity: 0.830, 95% CI: 0.702-0.919; Specificity: 0.809, 95% CI: 0.768-0.845) exhibited well predictive power for LCOS. Eleven predictive features including left ventricular ejection fraction (LVEF), first post-operative blood lactate (Lac), left ventricular diastolic diameter (LVDd), cumulative time of mean artery blood pressure (MABP) lower than 65 mmHg (MABP < 65 time), hypertension history, platelets level (PLT), age, blood creatinine (Cr), total area under curve above threshold central venous pressure (CVP) 12 mmHg and 16 mmHg, and blood loss during operation were used to build the reduced models. Among the reduced models, RF model (AUC: 0.895, 95% CI: 0.857-0.933; Sensitivity: 0.830, 95% CI: 0.702-0.919; Specificity: 0.806, 95% CI: 0.765-0.843) revealed the best performance. SHAP and LIME plot showed that LVEF, Lac, LVDd and MABP < 65 time significantly contributed to the prediction model.ConclusionIn this study, we successfully developed several machine learning models to predict LCOS after surgery, which may avail to risk stratification, early detection and management of LCOS after cardiac surgery.

Project description:BackgroundLow cardiac output syndrome (LCOS) is an important complication of cardiac surgery. It is associated with increased morbidity and mortality. The incidence of LCOS after surgery is high in patients with congenital heart disease (CHD). Therefore, determining the risk factors of LCOS has clinical significance for the management of CHD. This study aimed to analyze the risk factors of LCOS.MethodsWe conducted a retrospective analysis of children with CHD who underwent cardiac surgery at Shanghai Children's Medical Center between January 1, 2014, and December 31, 2017. Demographic characteristics and baseline data were extracted from the health data resource center of the hospital, which integrates clinical routine data including medical records, diagnoses, orders, surgeries, laboratory tests, imaging, nursing, and other subsystems. Logistic regressions were performed to analyze the risk factors of LCOS.ResultsOverall, 8660 infants with CHD were included, and 864 (9.98%) had LCOS after surgery. The multivariate regression analysis identified that age (OR 0.992, 95% CI: 0.988-0.997, p = 0.001), tricuspid regurgitation (1.192, 1.072-1.326, p = 0.001), Risk Adjustment in Congenital Heart Surgery-1 risk grade (1.166, 1.011-1.345, p = 0.035), aortic shunt (left-to-right: 1.37, 1.005-1.867, p = 0.046; bi-directional: 1.716, 1.138-2.587, p = 0.01), atrial shunt (left-to-right: 1.407, 1.097-1.805, p = 0.007; right-to-left: 3.168, 1.944-5.163, p < 0.001; bi-directional: 1.87, 1.389-2.519, p < 0.001), ventricular level shunt (left-to-right: 0.676, 0.486-0.94, p = 0.02; bi-directional: 2.09, 1.611-2.712, p < 0.001), residual shunt (3.489, 1.502-8.105, p = 0.004), left ventricular outflow tract obstruction (3.934, 1.673-9.254, p = 0.002), right ventricular outflow tract obstruction (3.638, 1.225-10.798, p = 0.02), circulating temperature (mild hypothermia: 1.526, 95% CI: 1.205-1.934, p < 0.001; middle and low temperature: 1.738, 1.236-2.443, p = 0.001), duration of cardiopulmonary bypass (1.009, 1.006-1.012, p < 0.001), myocardial preservation using histidine-tryptophan-ketoglutarate (1.677, 1.298-2.167, p < 0.001), and mitral insufficiency (1.714, 1.239-2.37, p < 0.001) were independent risk predictors of LCOS.ConclusionsThe incidence of postoperative LCOS in CHD children remains high. Circulation temperature, myocardial preservation using histidine-tryptophan-ketoglutarate, and usage of residual shunt after surgery were independent risk predictors for LCOS.

Project description:BackgroundComorbid conditions are very common in rheumatoid arthritis (RA) and several prior studies have clustered them using machine learning (ML). We applied various ML algorithms to compare the clusters of comorbidities derived and to assess the value of the clusters for predicting future clinical outcomes.MethodsA large US-based RA registry, CorEvitas, was used to identify patients for the analysis. We assessed the presence of 24 comorbidities, and ML was used to derive clusters of patients with given comorbidities. K-mode, K-mean, regression-based, and hierarchical clustering were used. To assess the value of these clusters, we compared clusters across different ML algorithms in clinical outcome models predicting clinical disease activity index (CDAI) and health assessment questionnaire (HAQ-DI). We used data from the first 3 years of the 6-year study period to derive clusters and assess time-averaged values for CDAI and HAQ-DI during the latter 3 years. Model fit was assessed via adjusted R2 and root mean square error for a series of models that included clusters from ML clustering and each of the 24 comorbidities separately.Results11,883 patients with RA were included who had longitudinal data over 6 years. At baseline, patients were on average 59 (SD 12) years of age, 77% were women, CDAI was 11.3 (SD 11.9, moderate disease activity), HAQ-DI was 0.32 (SD 0.42), and disease duration was 10.8 (SD 9.9) years. During the 6 years of follow-up, the percentage of patients with various comorbidities increased. Using five clusters produced by each of the ML algorithms, multivariable regression models with time-averaged CDAI as an outcome found that the ML-derived comorbidity clusters produced similarly strong models as models with each of the 24 separate comorbidities entered individually. The same patterns were observed for HAQ-DI.ConclusionsClustering comorbidities using ML algorithms is not computationally complex but often results in clusters that are difficult to interpret from a clinical standpoint. While ML clustering is useful for modeling multi-omics, using clusters to predict clinical outcomes produces models with a similar fit as those with individual comorbidities.

Project description:BackgroundPrevious studies have shown beneficial effects of levosimendan in high-risk patients undergoing cardiac surgery. Two large randomized controlled trials (RCTs), however, showed no advantages of levosimendan.MethodsWe performed a systematic review and meta-analysis (MEDLINE and Embase from inception until March 30, 2017), investigating whether levosimendan offers advantages compared with placebo in high-risk cardiac surgery patients, as defined by preoperative left ventricular ejection fraction (LVEF) ≤ 35% and/or low cardiac output syndrome (LCOS). The primary outcomes were mortality at longest follow-up and need for postoperative renal replacement therapy (RRT). Secondary postoperative outcomes investigated included myocardial injury, supraventricular arrhythmias, development of LCOS, acute kidney injury (AKI), duration of mechanical ventilation, intensive care unit and hospital lengths of stay, and incidence of hypotension during drug infusion.ResultsSix RCTs were included in the meta-analysis, five of which investigated only patients with LVEF ≤ 35% and one of which included predominantly patients with LCOS. Mortality was similar overall (OR 0.64 [0.37, 1.11], p = 0.11) but lower in the subgroup with LVEF < 35% (OR 0.51 [0.32, 0.82], p = 0.005). Need for RRT was reduced by levosimendan both overall (OR 0.63 [0.42, 0.94], p = 0.02) and in patients with LVEF < 35% (OR 0.55 [0.31, 0.97], p = 0.04). Among secondary outcomes, we found lower postoperative LCOS in patients with LVEF < 35% receiving levosimendan (OR 0.49 [0.27, 0.89], p = 0.02), lower overall AKI (OR 0.62 [0.42, 0.92], p = 0.02), and a trend toward lower mechanical support, both overall (p = 0.07) and in patients with LVEF < 35% (p = 0.05).ConclusionsLevosimendan reduces mortality in patients with preoperative severely reduced LVEF but does not affect overall mortality. Levosimendan reduces the need for RRT after high-risk cardiac surgery.

Dataset Information

Machine learning approach identified clusters for patients with low cardiac output syndrome and outcomes after cardiac surgery.

Background

Methods

Results

Conclusion

Publications

Machine learning approach identified clusters for patients with low cardiac output syndrome and outcomes after cardiac surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets