Search

This study explores the effectiveness of Explainable Artificial Intelligence (XAI) for predicting suicide risk from medical tabular data. Given the common challenge of limited datasets in health-related Machine Learning (ML) applications, we use data augmentation in tandem with ML to enhance the identification of individuals at high risk of suicide. We use SHapley Additive exPlanations (SHAP) for XAI and traditional correlation analysis to rank feature importance, pinpointing primary factors influencing suicide risk and preventive measures. Experimental results show the Random Forest (RF) model is excelling in accuracy, F1 score, and AUC (>97% across metrics). According to SHAP, anger issues, depression, and social isolation emerge as top predictors of suicide risk, while individuals with high incomes, esteemed professions, and higher education present the lowest risk. Our findings underscore the effectiveness of ML and XAI in suicide risk assessment, offering valuable insights for psychiatrists and facilitating informed clinical decisions. [ABSTRACT FROM AUTHOR]

Objectives: Coronary artery calcium (CAC) scores derived from computed tomography (CT) scans are used for cardiovascular risk stratification. Artificial intelligence (AI) can assist in CAC quantification and potentially reduce the time required for human analysis. This study aimed to develop and evaluate a fully automated model that identifies and quantifies CAC. Methods: Fully convolutional neural networks for automated CAC scoring were developed and trained on 2439 cardiac CT scans and validated using 771 scans. The model was tested on an independent set of 1849 cardiac CT scans. Agatston CAC scores were further categorised into five risk categories (0, 1–10, 11–100, 101–400, and > 400). Automated scores were compared to the manual reference standard (level 3 expert readers). Results: Of 1849 scans used for model testing (mean age 55.7 ± 10.5 years, 49% males), the automated model detected the presence of CAC in 867 (47%) scans compared with 815 (44%) by human readers (p = 0.09). CAC scores from the model correlated very strongly with the manual score (Spearman's r = 0.90, 95% confidence interval [CI] 0.89–0.91, p < 0.001 and intraclass correlation coefficient = 0.98, 95% CI 0.98–0.99, p < 0.001). The model classified 1646 (89%) into the same risk category as human observers. The Bland–Altman analysis demonstrated little difference (1.69, 95% limits of agreement: −41.22, 44.60) and there was almost excellent agreement (Cohen's κ = 0.90, 95% CI 0.88–0.91, p < 0.001). Model analysis time was 13.1 ± 3.2 s/scan. Conclusions: This artificial intelligence–based fully automated CAC scoring model shows high accuracy and low analysis times. Its potential to optimise clinical workflow efficiency and patient outcomes requires evaluation. Key Points: • Coronary artery calcium (CAC) scores are traditionally assessed using cardiac computed tomography and require manual input by human operators to identify calcified lesions. • A novel artificial intelligence (AI)–based model for fully automated CAC scoring was developed and tested on an independent dataset of computed tomography scans, showing very high levels of correlation and agreement with manual measurements as a reference standard. • AI has the potential to assist in the identification and quantification of CAC, thereby reducing the time required for human analysis. [ABSTRACT FROM AUTHOR]

Residual inflammation in cardiovascular organs is thought to be one of the catalysts for the increased risk of cardiovascular complications seen following pneumonia. To test this hypothesis, we investigated changes in plaque characteristics and inflammatory features in ApoE−/− mouse aorta and heart following pneumonia. Male ApoE−/− mice were fed a high fat diet for 8 weeks before intranasal inoculation with either Streptococcus pneumoniae serotype 4 (test group) or phosphate buffered saline (control group). Mice were sacrificed at 2-, 7- and 28-days post-challenge. Changes in plaque burden and characteristics in aortic root and thoracic aorta were characterized by Oil red O and Trichrome stains. Inflammatory changes were investigated by FDG-PET imaging and immunofluorescence staining. We found TIGR4-infected mice present with increased plaque presence in the aortic root and thoracic aorta at 2- and 28-days post-inoculation, respectively. Aortic wall remodelling was also more pronounced in mice challenged with pneumococci at 28 days post-inoculation. Aortic root plaques of infected mice had reduced collagen and smooth muscle cells, consistent with an unstable plaque phenotype. Pneumonia alters plaque burden, plaque characteristics, and aortic wall remodelling in ApoE−/− mice. These effects caused by Streptococcus pneumoniae TIGR4, may contribute to the increased risk of cardiovascular complications seen in survivors of this infection. [ABSTRACT FROM AUTHOR]

Missing data is a major problem in real-world datasets, which hinders the performance of data analytics. Conventional data imputation schemes such as univariate single imputation replace missing values in each column with the same approximated value. These univariate single imputation techniques underestimate the variance of the imputed values. On the other hand, multivariate imputation explores the relationships between different columns of data, to impute the missing values. Reinforcement Learning (RL) is a machine learning paradigm where the agent learns by taking actions and receiving rewards in response, to achieve its goal. In this work, we propose an RL-based approach to impute missing data by learning a policy to impute data through an action-reward-based experience. Our approach imputes missing values in a column by working only on the same column (similar to univariate single imputation) but imputes the missing values in the column with different values thus keeping the variance in the imputed values. We report superior performance of our approach, compared with other imputation techniques, on a number of datasets. [ABSTRACT FROM AUTHOR]

Background: Rubidium-82 positron emission tomography (82Rb PET) MPI is considered a noninvasive reference standard for the assessment of myocardial perfusion in coronary artery disease (CAD) patients. Our main goal was to compare the diagnostic performance of static rest/ vasodilator stress CT myocardial perfusion imaging (CT-MPI) to stress/ rest 82Rb PET-MPI for the identification of myocardial ischemia. Methods: Forty-four patients with suspected or diagnosed CAD underwent both static CT-MPI and 82Rb PET-MPI at rest and during pharmacological stress. The extent and severity of perfusion defects on PET-MPI were assessed to obtain summed stress score, summed rest score, and summed difference score. The extent and severity of perfusion defects on CT-MPI was visually assessed using the same grading scale. CT-MPI was compared with PET-MPI as the gold standard on a per-territory and a per-patient basis. Results: On a per-patient basis, there was moderate agreement between CT-MPI and PET-MPI with a weighted 0.49 for detection of stress induced perfusion abnormalities. Using PET-MPI as a reference, static CT-MPI had 89% sensitivity (SS), 58% specificity (SP), 71% accuracy (AC), 88% negative predictive value (NPV), and 59% positive predictive value (PPV) to diagnose stress-rest perfusion deficits on a per-patient basis. On a per-territory analysis, CT-MPI had 73% SS, 65% SP, 67% AC, 90.8% NPV, and 34% PPV to diagnose perfusion deficits. Conclusions: CT-MPI has high sensitivity and good overall accuracy for the diagnosis of functionally significant CAD using 82Rb PET-MPI as the reference standard. CT-MPI may play an important role in assessing the functional significance of CAD especially in combination with CCTA. [ABSTRACT FROM AUTHOR]

Our aim was to investigate the usefulness of machine learning approaches on linked administrative health data at the population level in predicting older patients' one-year risk of acute coronary syndrome and death following the use of non-steroidal anti-inflammatory drugs (NSAIDs). Patients from a Western Australian cardiovascular population who were supplied with NSAIDs between 1 Jan 2003 and 31 Dec 2004 were identified from Pharmaceutical Benefits Scheme data. Comorbidities from linked hospital admissions data and medication history were inputs. Admissions for acute coronary syndrome or death within one year from the first supply date were outputs. Machine learning classification methods were used to build models to predict ACS and death. Model performance was measured by the area under the receiver operating characteristic curve (AUC-ROC), sensitivity and specificity. There were 68,889 patients in the NSAIDs cohort with mean age 76 years and 54% were female. 1882 patients were admitted for acute coronary syndrome and 5405 patients died within one year after their first supply of NSAIDs. The multi-layer neural network, gradient boosting machine and support vector machine were applied to build various classification models. The gradient boosting machine achieved the best performance with an average AUC-ROC of 0.72 predicting ACS and 0.84 predicting death. Machine learning models applied to linked administrative data can potentially improve adverse outcome risk prediction. Further investigation of additional data and approaches are required to improve the performance for adverse outcome risk prediction. [ABSTRACT FROM AUTHOR]

A total of 113 patients were included in the final analysis, with 42 patients in the AVF group and 71 patients in the non-AVF group. Keywords: Arteriovenous fistula; End-stage renal failure; Diastolic function EN Arteriovenous fistula End-stage renal failure Diastolic function 200 201 2 01/19/23 20230201 NES 230201 I To the Editor i Haemodialysis access in end-stage renal failure (ESRF) patients is provided by an arteriovenous fistula (AVF) [[1]]. [Extracted from the article]