Machine Learning Models for Predicting In-Hospital Mortality in Acute Aortic Dissection Patients

Streamlining Acute Abdominal Aortic Dissection Management-An AI-based CT Imaging Workflow

Life-threatening acute aortic dissection (AD) demands timely diagnosis for effective intervention. To streamline intrahospital workflows, automated detection of AD in abdominal computed tomography (CT) scans seems useful to assist humans. We aimed at creating a robust convolutional neural network (CNN)-based pipeline capable of real-time screening for signs of abdominal AD in CT. In this retrospective study, abdominal CT data from AD patients presenting with AD and from non-AD patients were collected (n 195, AD cases 94, mean age 65.9 years, female ratio 35.8%). A CNN-based algorithm was developed with the goal of enabling a robust, automated, and highly sensitive detection of abdominal AD. Two sets from internal (n = 32, AD cases 16) and external sources (n = 1189, AD cases 100) were procured for validation. The abdominal region was extracted, followed by the automatic isolation of the aorta region of interest (ROI) and highlighting of the membrane via edge extraction, followed by classification of the aortic ROI as dissected/healthy. A fivefold cross-validation was employed on the internal set, and an ensemble of the 5 trained models was used to predict the internal and external validation set. Evaluation metrics included receiver operating characteristic curve (AUC) and balanced accuracy. The AUC, balanced accuracy, and sensitivity scores of the internal dataset were 0.932 (CI 0.891-0.963), 0.860, and 0.885, respectively. For the internal validation dataset, the AUC, balanced accuracy, and sensitivity scores were 0.887 (CI 0.732-0.988), 0.781, and 0.875, respectively. Furthermore, for the external validation dataset, AUC, balanced accuracy, and sensitivity scores were 0.993 (CI 0.918-0.994), 0.933, and 1.000, respectively. The proposed automated pipeline could assist humans in expediting acute aortic dissection management when integrated into clinical workflows.

The relationship between uric acid and in-hospital mortality in patients with type A acute aortic dissection: A retrospective single-center study

OBJECTIVE

To measure the preoperative uric acid (UA) concentration in patients with type A aortic dissection (TAAD), and to assess its value in predicting in-hospital mortality.

METHODS

A total of 747 patients with TAAD between January 2016 and December 2022 were enrolled. The patients were divided into a survivor group and a non-survivor group. The clinical data of the two groups were compared. Univariate and multiple logistic regression analyses were performed to determine risk factors related to in-hospital mortality.

RESULTS

Compared with survivors, non-survivors had significantly higher serum uric acid levels (486.84 ± 127.59 vs 419.49 ± 141.02, P = 0.040). The incidence of in-hospital death increased along with higher UA levels (3.8% vs 0.7%, P = 0.007). Serum UA ≥ 373.5 μmol/L had 89.5% sensitivity and 41.3% specificity for predicting in-hospital death (area under the curve = 0.659, 95% CI: 0.554-0.765, P < 0.05). In the multivariable logistic model, Serum UA ≥ 373.5 μmol/L was independently associated with in-hospital mortality (OR = 1.022, 95% CI: 1.000-1.044, P = 0.048).

CONCLUSION

Serum UA resulted as an independent predictor of adverse prognosis in patients with TAAD, and thus could be used as an effective tool for the risk-stratification of patients with TAAD.

Establishing and Validating a Morphological Prediction Model Based on CTA to Evaluate the Incidence of Type-B Dissection

Background: Many patients with Type B aortic dissection (TBAD) may not show noticeable symptoms until they become intervention and help prevent critically ill, which can result in fatal outcomes. Thus, it is crucial to screen people at high risk of TBAD and initiate the necessary preventive and therapeutic measures before irreversible harm occurs. By developing a prediction model for aortic arch morphology, it is possible to accurately identify those at high risk and take prompt action to prevent the adverse consequences of TBAD. This approach can facilitate timely the development of serious illnesses. Method: The predictive model was established in a primary population consisting of 173 patients diagnosed with acute Stanford TBAD, with data collected from January 2017 and December 2018, as well as 534 patients with healthy aortas, with data collected from April 2018 and December 2018. Explicitly, the data were randomly separated into the derivation set and validation set in a 7:3 ratio. Geometric and anatomical features were extracted from a three-dimensional multiplanar reconstruction of the aortic arch. The LASSO regression model was utilized to minimize the data dimension and choose relevant features. Multivariable logistic regression analysis and backward stepwise selection were employed for predictive model generation, combining demographic and clinical features as well as geometric and anatomical features. The predictive model's performance was evaluated by examining its calibration, discrimination, and clinical benefit. Finally, we also conducted internal verification. Results: After applying LASSO logistic regression and backward stepwise selection, 12 features were entered into the prediction model. Age, aortic arch angle, total thoracic aorta distance, ascending aorta tortuosity, aortic arch tortuosity, distal descending aorta tortuosity, and type III arch were protective factors, while male sex, hypertension, aortic arch height, and aortic arch distance were risk factors. The model exhibited satisfactory discrimination (AUC, 0.917 [95% CI, 0.890-0.945]) and good calibration in the derivation set. Applying the predictive model to the validation set also provided satisfactory discrimination (AUC, 0.909 [95% CI, 0.864-0.953]) and good calibration. The TBAD nomogram for clinical use was established. Conclusions: This study demonstrates that a multivariable logistic regression model can be used to predict TBAD patients.

Emerging role of radiogenomics in genetically triggered thoracic aortic aneurysm and dissection: a narrative review

Background and Objective

Thoracic aortic aneurysm and dissection (TAAD) and its complications are life-threatening conditions. Hypertension and atherosclerosis had all along been recognized as the predominant risk factors for the development of TAAD. However, it was increasingly reported that genetic factors, such as single nucleotide polymorphisms (SNPs), are playing an important role in the disease development. The development of next-generation sequencing (NGS) and the rapid growth in radiomics provide a promising new platform to evaluate genetically triggered thoracic aortic aneurysm and dissection (GTAAD) from a new angle. This review is to present an overview of currently available knowledge regarding the use of radiomics and radiogenomics in GTAAD.

Methods

We performed literature searches in PubMed, EMBASE and Cochrane database from 2012 to 2022 regarding the use of radiomics and radiogenomics in GTAAD.

Key Content and Findings

There were only 13 studies on radiomics and 4 studies on radiogenomics integration retrieved from the search and it signifies there is still a significant knowledge gap in this field of translational medicine. An overview of the current knowledge of GTAAD, the workflow and role of radiomics, the radiogenomics integration for GTAAD including its potential role in the development of polygenic scores, as well as the implications, challenges, and limitations of radiogenomics research were discussed.

Conclusions

In the contemporary era, radiogenomics has been emerging as a state-of-the art approach to establish statistical correlation with radiomics features with genomic information in diagnosis, risk modeling and prediction and treatment decision in TAAD.

Machine learning-based prediction of in-ICU mortality in pneumonia patients

Conventional severity-of-illness scoring systems have shown suboptimal performance for predicting in-intensive care unit (ICU) mortality in patients with severe pneumonia. This study aimed to develop and validate machine learning (ML) models for mortality prediction in patients with severe pneumonia. This retrospective study evaluated patients admitted to the ICU for severe pneumonia between January 2016 and December 2021. The predictive performance was analyzed by comparing the area under the receiver operating characteristic curve (AU-ROC) of ML models to that of conventional severity-of-illness scoring systems. Three ML models were evaluated: (1) logistic regression with L2 regularization, (2) gradient-boosted decision tree (LightGBM), and (3) multilayer perceptron (MLP). Among the 816 pneumonia patients included, 223 (27.3%) patients died. All ML models significantly outperformed the Simplified Acute Physiology Score II (AU-ROC: 0.650 [0.584-0.716] vs 0.820 [0.771-0.869] for logistic regression vs 0.827 [0.777-0.876] for LightGBM 0.838 [0.791-0.884] for MLP; P < 0.001). In the analysis for NRI, the LightGBM and MLP models showed superior reclassification compared with the logistic regression model in predicting in-ICU mortality in all length of stay in the ICU subgroups; all age subgroups; all subgroups with any APACHE II score, PaO₂/FiO₂ ratio < 200; all subgroups with or without history of respiratory disease; with or without history of CVA or dementia; treatment with mechanical ventilation, and use of inotropic agents. In conclusion, the ML models have excellent performance in predicting in-ICU mortality in patients with severe pneumonia. Moreover, this study highlights the potential advantages of selecting individual ML models for predicting in-ICU mortality in different subgroups.

Risk factors for in-hospital death in 2,179 patients with acute aortic dissection

Background

This study aims to investigate the risk factors for in-hospital death in patients with acute aortic dissection (AAD) and to provide a straightforward prediction model to assist clinicians in determining the outcome of AAD patients.

Methods

Retrospective analysis was carried out on 2,179 patients admitted for AAD from March 5, 1999 to April 20, 2018 in Wuhan Union Hospital, China. The risk factors were investigated with univariate and multivariable logistic regression analysis.

Results

The patients were divided into two groups: Group A, 953patients (43.7%) with type A AAD; Group B, 1,226 patients (56.3%) with type B AAD. The overall in-hospital mortality rate was 20.3% (194/953) and 4% (50/1,226) in Group A and B respectively. The multivariable analysis included the variables that were statistically significant predictors of in-hospital death (P < 0.05). In Group A, hypotension (OR = 2.01, P = 0.001) and liver dysfunction (OR = 12.95, P < 0.001) were independent risk factors. Tachycardia (OR = 6.08, P < 0.001) and liver dysfunction (OR = 6.36, P < 0.05) were independent risk factors for Group B mortality. The risk factors of Group A were assigned a score equal to their coefficients, and the score of -0.5 was the best point of the risk prediction model. Based on this analysis, we derived a predictive model to help clinicians determine the prognosis of type A AAD patients.

Conclusions

This study investigate the independent factors associated with in-hospital death in patients with type A or B aortic dissection, respectively. In addition, we develop the prediction of the prognosis for type A patients and assist clinicians in choosing treatment strategies.

Prediction of preoperative in-hospital mortality rate in patients with acute aortic dissection by machine learning: a two-centre, retrospective cohort study

OBJECTIVES

To conduct a comprehensive analysis of demographic information, medical history, and blood pressure (BP) and heart rate (HR) variability during hospitalisation so as to establish a predictive model for preoperative in-hospital mortality of patients with acute aortic dissection (AD) by using machine learning techniques.

DESIGN

Retrospective cohort study.

SETTING

Data were collected from the electronic records and the databases of Shanghai Ninth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine and the First Affiliated Hospital of Anhui Medical University between 2004 and 2018.

PARTICIPANTS

380 inpatients diagnosed with acute AD were included in the study.

PRIMARY OUTCOME

Preoperative in-hospital mortality rate.

RESULTS

A total of 55 patients (14.47%) died in the hospital before surgery. The results of the areas under the receiver operating characteristic curves, decision curve analysis and calibration curves indicated that the eXtreme Gradient Boosting (XGBoost) model had the highest accuracy and robustness. According to the SHapley Additive exPlanations analysis of the XGBoost model, Stanford type A, maximum aortic diameter >5.5 cm, high variability in HR, high variability in diastolic BP and involvement of the aortic arch had the greatest impact on the occurrence of in-hospital deaths before surgery. Moreover, the predictive model can accurately predict the preoperative in-hospital mortality rate at the individual level.

CONCLUSION

In the current study, we successfully constructed machine learning models to predict the preoperative in-hospital mortality of patients with acute AD, which can help identify high-risk patients and optimise the clinical decision-making. Further applications in clinical practice require the validation of these models using a large-sample, prospective database.

TRIAL REGISTRATION NUMBER

ChiCTR1900025818.

Deep Learning Prediction for Distal Aortic Remodeling After Thoracic Endovascular Aortic Repair in Stanford Type B Aortic Dissection

PURPOSE

This study aimed to develop a deep learning model for predicting distal aortic remodeling after proximal thoracic endovascular aortic repair (TEVAR) in patients with Stanford type B aortic dissection (TBAD) using computed tomography angiography (CTA).

METHODS

A total of 147 patients with acute or subacute TBAD who underwent proximal TEVAR at a single center were retrospectively reviewed. The boundary of aorta was manually segmented, and the point clouds of each aorta were obtained. Prediction of negative aortic remodeling or reintervention was accomplished by a convolutional neural network (CNN) and a point cloud neural network (PC-NN), respectively. The discriminatory value of the established models was mainly evaluated by the area under the receiver operating characteristic curve (AUC) in the test set.

RESULTS

The mean follow-up time was 34.0 months (range: 12-108 months). During follow-up, a total of 25 (17.0%) patients were identified as having negative aortic remodeling, and 16 (10.9%) patients received reintervention. The AUC (0.876) by PC-NN for predicting negative aortic remodeling was superior to that obtained by CNN (0.612, p=0.034) and similar to the AUC by PC-NN combined with clinical features (0.884, p=0.92). As to reintervention, the AUC by PC-NN was significantly higher than that by CNN (0.805 vs 0.579; p=0.042), and AUCs by PC-NN combined with clinical features and PC-NN alone were comparable (0.836 vs 0.805; p=0.81).

CONCLUSION

The CTA-based deep learning algorithms may assist clinicians in automated prediction of distal aortic remodeling after TEVAR for acute or subacute TBAD.

CLINICAL IMPACT

Negative aortic remodeling is the leading cause of late reintervention after proximal thoracic endovascular aortic repair (TEVAR) for Stanford type B aortic dissection (TBAD), and possesses great challenge to endovascular repair. Early recognizing high-risk patients is of supreme importance for optimizing the follow-up interval and therapy strategy. Currently, clinicians predict the prognosis of these patients based on several imaging signs, which is subjective. The computed tomography angiography-based deep learning algorithms may incorporate abundant morphological information of aorta, provide with a definite and objective output value, and finally assist clinicians in automated prediction of distal aortic remodeling after TEVAR for acute or subacute TBAD.

Medical record data-enabled machine learning can enhance prediction of left atrial appendage thrombosis in nonvalvular atrial fibrillation

BACKGROUND

As a major complication of non-valvular atrial fibrillation (NVAF), left atrial appendage (LAA) thrombosis is associated with cerebral ischemic strokes, as well as high morbidity. Due to insufficient incorporation of risk factors, most current scoring methods are limited to the analysis of relationships between clinical characteristics and LAA thrombosis rather than detecting potential risk. Therefore, this study proposes a clinical data-driven machine learning method to predict LAA thrombosis of NVAF.

METHODS

Patients with NVAF from January 2014 to June 2022 were enrolled from Southwest Hospital. We selected 40 variables for analysis, including demographic data, medical history records, laboratory results, and the structure of LAA. Three machine learning algorithms were adopted to construct classifiers for the prediction of LAA thrombosis risk. The most important variables related to LAA thrombosis and their influences were recognized by SHapley Addictive exPlanations method. In addition, we compared our model with CHADS2 and CHADS2-VASc scoring methods.

RESULTS

A total of 713 participants were recruited, including 127 patients with LAA thrombosis and 586 patients with no obvious thrombosis. The consensus models based on Random Forest and eXtreme Gradient Boosting LAA thrombosis prediction (RXTP) achieved the best accuracy of 0.865, significantly outperforming CHADS2 score and CHA2DS2-VASc score (0.757 and 0.754, respectively). The SHAP results showed that B-type natriuretic peptide, left atrial appendage width, C-reactive protein, Fibrinogen and estimated glomerular filtration rate are closely related to the risk of LAA thrombosis in nonvalvular atrial fibrillation.

CONCLUSIONS

The RXTP-NVAF model is the most effective model with the greatest ROC value and recall rate. The summarized risk factors obtained from SHAP enable the optimization of the treatment strategy, thereby preventing thromboembolism events and the occurrence of cardiogenic ischemic stroke.

A Novel Inflammation-Based Risk Score Predicts Mortality in Acute Type A Aortic Dissection Surgery: The Additive Anti-inflammatory Action for Aortopathy and Arteriopathy Score

OBJECTIVE

To develop an inflammation-based risk stratification tool for operative mortality in patients with acute type A aortic dissection.

METHODS

Between January 1, 2016 and December 31, 2021, 3124 patients from Beijing Anzhen Hospital were included for derivation, 571 patients from the same hospital were included for internal validation, and 1319 patients from other 12 hospitals were included for external validation. The primary outcome was operative mortality according to the Society of Thoracic Surgeons criteria. Least absolute shrinkage and selection operator regression were used to identify clinical risk factors. A model was developed using different machine learning algorithms. The performance of the model was determined using the area under the receiver operating characteristic curve (AUC) for discrimination, calibration curves, and Brier score for calibration. The final model (5A score) was tested with respect to the existing clinical scores.

RESULTS

Extreme gradient boosting was selected for model training (5A score) using 12 variables for prediction-the ratio of platelet to leukocyte count, creatinine level, age, hemoglobin level, prior cardiac surgery, extent of dissection extension, cerebral perfusion, aortic regurgitation, sex, pericardial effusion, shock, and coronary perfusion-which yields the highest AUC (0.873 [95% confidence interval (CI) 0.845-0.901]). The AUC of 5A score was 0.875 (95% CI 0.814-0.936), 0.845 (95% CI 0.811-0.878), and 0.852 (95% CI 0.821-0.883) in the internal, external, and total cohort, respectively, which outperformed the best existing risk score (German Registry for Acute Type A Aortic Dissection score AUC 0.709 [95% CI 0.669-0.749]).

CONCLUSION

The 5A score is a novel, internally and externally validated inflammation-based tool for risk stratification of patients before surgical repair, potentially advancing individualized treatment.

TRIAL REGISTRATION

clinicaltrials.gov Identifier: NCT04918108.

Circulating biomarker-based risk stratifications individualize arch repair strategy of acute Type A aortic dissection via the XGBoosting algorithm

Aims

The incremental usefulness of circulating biomarkers from different pathological pathways for predicting mortality has not been evaluated in acute Type A aortic dissection (ATAAD) patients. We aim to develop a risk prediction model and investigate the impact of arch repair strategy on mortality based on distinct risk stratifications.

Methods and results

A total of 3771 ATAAD patients who underwent aortic surgery retrospectively included were randomly divided into training and testing cohorts at a ratio of 7:3 for the development and validation of the risk model based on multiple circulating biomarkers and conventional clinical factors. Extreme gradient boosting was used to generate the risk models. Subgroup analyses were performed by risk stratifications (low vs. middle-high risk) and arch repair strategies (proximal vs. extensive arch repair). Addition of multiple biomarkers to a model with conventional factors fitted an ABC risk model consisting of platelet-leucocyte ratio, mean arterial pressure, albumin, age, creatinine, creatine kinase-MB, haemoglobin, lactate, left ventricular end-diastolic dimension, urea nitrogen, and aspartate aminotransferase, with adequate discrimination ability {area under the receiver operating characteristic curve (AUROC): 0.930 [95% confidence interval (CI) 0.906-0.954] and 0.954, 95% CI (0.930-0.977) in the derivation and validation cohort, respectively}. Compared with proximal arch repair, the extensive repair was associated with similar mortality risk among patients at low risk [odds ratio (OR) 1.838, 95% CI (0.559-6.038); P = 0.316], but associated with higher mortality risk among patients at middle-high risk [OR 2.007, 95% CI (1.460-2.757); P < 0.0001].

Conclusion

In ATAAD patients, the simultaneous addition of circulating biomarkers of inflammatory, cardiac, hepatic, renal, and metabolic abnormalities substantially improved risk stratification and individualized arch repair strategy.