Explainable artificial intelligence in deep learning-based detection of aortic elongation on chest X-ray images.

Aims: Aortic elongation can result from age-related changes, congenital factors, aneurysms, or conditions affecting blood vessel elasticity. It is associated with cardiovascular diseases and severe complications like aortic aneurysms and dissection. We assess qualitatively and quantitatively explainable methods to understand the decisions of a deep learning model for detecting aortic elongation using chest X-ray (CXR) images. Methods and results: In this study, we evaluated the performance of deep learning models (DenseNet and EfficientNet) for detecting aortic elongation using transfer learning and fine-tuning techniques with CXR images as input. EfficientNet achieved higher accuracy (86.7% ± 2.1), precision (82.7% ± 2.7), specificity (89.4% ± 1.7), F1 score (82.5% ± 2.9), and area under the receiver operating characteristic (92.7% ± 0.6) but lower sensitivity (82.3% ± 3.2) compared with DenseNet. To gain insights into the decision-making process of these models, we employed gradient-weighted class activation mapping and local interpretable model-agnostic explanations explainability methods, which enabled us to identify the expected location of aortic elongation in CXR images. Additionally, we used the pixel-flipping method to quantitatively assess the model interpretations, providing valuable insights into model behaviour. Conclusion: Our study presents a comprehensive strategy for analysing CXR images by integrating aortic elongation detection models with explainable artificial intelligence techniques. By enhancing the interpretability and understanding of the models' decisions, this approach holds promise for aiding clinicians in timely and accurate diagnosis, potentially improving patient outcomes in clinical practice.

Few-shot genes selection: subset of PAM50 genes for breast cancer subtypes classification.

BACKGROUND: In recent years, researchers have made significant strides in understanding the heterogeneity of breast cancer and its various subtypes. However, the wealth of genomic and proteomic data available today necessitates efficient frameworks, instruments, and computational tools for meaningful analysis. Despite its success as a prognostic tool, the PAM50 gene signature's reliance on many genes presents challenges in terms of cost and complexity. Consequently, there is a need for more efficient methods to classify breast cancer subtypes using a reduced gene set accurately. RESULTS: This study explores the potential of achieving precise breast cancer subtype categorization using a reduced gene set derived from the PAM50 gene signature. By employing a "Few-Shot Genes Selection" method, we randomly select smaller subsets from PAM50 and evaluate their performance using metrics and a linear model, specifically the Support Vector Machine (SVM) classifier. In addition, we aim to assess whether a more compact gene set can maintain performance while simplifying the classification process. Our findings demonstrate that certain reduced gene subsets can perform comparable or superior to the full PAM50 gene signature. CONCLUSIONS: The identified gene subsets, with 36 genes, have the potential to contribute to the development of more cost-effective and streamlined diagnostic tools in breast cancer research and clinical settings.

An Interpretable Approach with Explainable AI for Heart Stroke Prediction.

Heart strokes are a significant global health concern, profoundly affecting the wellbeing of the population. Many research endeavors have focused on developing predictive models for heart strokes using ML and DL techniques. Nevertheless, prior studies have often failed to bridge the gap between complex ML models and their interpretability in clinical contexts, leaving healthcare professionals hesitant to embrace them for critical decision-making. This research introduces a meticulously designed, effective, and easily interpretable approach for heart stroke prediction, empowered by explainable AI techniques. Our contributions include a meticulously designed model, incorporating pivotal techniques such as resampling, data leakage prevention, feature selection, and emphasizing the model's comprehensibility for healthcare practitioners. This multifaceted approach holds the potential to significantly impact the field of healthcare by offering a reliable and understandable tool for heart stroke prediction. In our research, we harnessed the potential of the Stroke Prediction Dataset, a valuable resource containing 11 distinct attributes. Applying these techniques, including model interpretability measures such as permutation importance and explainability methods like LIME, has achieved impressive results. While permutation importance provides insights into feature importance globally, LIME complements this by offering local and instance-specific explanations. Together, they contribute to a comprehensive understanding of the Artificial Neural Network (ANN) model. The combination of these techniques not only aids in understanding the features that drive overall model performance but also helps in interpreting and validating individual predictions. The ANN model has achieved an outstanding accuracy rate of 95%.

Using Explainable Artificial Intelligence to Obtain Efficient Seizure-Detection Models Based on Electroencephalography Signals.

Epilepsy is a condition that affects 50 million individuals globally, significantly impacting their quality of life. Epileptic seizures, a transient occurrence, are characterized by a spectrum of manifestations, including alterations in motor function and consciousness. These events impose restrictions on the daily lives of those affected, frequently resulting in social isolation and psychological distress. In response, numerous efforts have been directed towards the detection and prevention of epileptic seizures through EEG signal analysis, employing machine learning and deep learning methodologies. This study presents a methodology that reduces the number of features and channels required by simpler classifiers, leveraging Explainable Artificial Intelligence (XAI) for the detection of epileptic seizures. The proposed approach achieves performance metrics exceeding 95% in accuracy, precision, recall, and F1-score by utilizing merely six features and five channels in a temporal domain analysis, with a time window of 1 s. The model demonstrates robust generalization across the patient cohort included in the database, suggesting that feature reduction in simpler models-without resorting to deep learning-is adequate for seizure detection. The research underscores the potential for substantial reductions in the number of attributes and channels, advocating for the training of models with strategically selected electrodes, and thereby supporting the development of effective mobile applications for epileptic seizure detection.

Explaining One-Dimensional Convolutional Models in Human Activity Recognition and Biometric Identification Tasks.

Due to wearables' popularity, human activity recognition (HAR) plays a significant role in people's routines. Many deep learning (DL) approaches have studied HAR to classify human activities. Previous studies employ two HAR validation approaches: subject-dependent (SD) and subject-independent (SI). Using accelerometer data, this paper shows how to generate visual explanations about the trained models' decision making on both HAR and biometric user identification (BUI) tasks and the correlation between them. We adapted gradient-weighted class activation mapping (grad-CAM) to one-dimensional convolutional neural networks (CNN) architectures to produce visual explanations of HAR and BUI models. Our proposed networks achieved 0.978 and 0.755 accuracy, employing both SD and SI. The proposed BUI network achieved 0.937 average accuracy. We demonstrate that HAR's high performance with SD comes not only from physical activity learning but also from learning an individual's signature, as in BUI models. Our experiments show that CNN focuses on larger signal sections in BUI, while HAR focuses on smaller signal segments. We also use the grad-CAM technique to identify database bias problems, such as signal discontinuities. Combining explainable techniques with deep learning can help models design, avoid results overestimation, find bias problems, and improve generalization capability.

Evaluating Time Influence over Performance of Machine-Learning-Based Diagnosis: A Case Study of COVID-19 Pandemic in Brazil.

Efficiently recognising severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) symptoms enables a quick and accurate diagnosis to be made, and helps in mitigating the spread of the coronavirus disease 2019. However, the emergence of new variants has caused constant changes in the symptoms associate with COVID-19. These constant changes directly impact the performance of machine-learning-based diagnose. In this context, considering the impact of these changes in symptoms over time is necessary for accurate diagnoses. Thus, in this study, we propose a machine-learning-based approach for diagnosing COVID-19 that considers the importance of time in model predictions. Our approach analyses the performance of XGBoost using two different time-based strategies for model training: month-to-month and accumulated strategies. The model was evaluated using known metrics: accuracy, precision, and recall. Furthermore, to explain the impact of feature changes on model prediction, feature importance was measured using the SHAP technique, an XAI technique. We obtained very interesting results: considering time when creating a COVID-19 diagnostic prediction model is advantageous.

Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers.

PROBLEM: An application of Explainable Artificial Intelligence Methods for COVID CT-Scan classifiers is presented. MOTIVATION: It is possible that classifiers are using spurious artifacts in dataset images to achieve high performances, and such explainable techniques can help identify this issue. AIM: For this purpose, several approaches were used in tandem, in order to create a complete overview of the classificatios. METHODOLOGY: The techniques used included GradCAM, LIME, RISE, Squaregrid, and direct Gradient approaches (Vanilla, Smooth, Integrated). MAIN RESULTS: Among the deep neural networks architectures evaluated for this image classification task, VGG16 was shown to be most affected by biases towards spurious artifacts, while DenseNet was notably more robust against them. Further impacts: Results further show that small differences in validation accuracies can cause drastic changes in explanation heatmaps for DenseNet architectures, indicating that small changes in validation accuracy may have large impacts on the biases learned by the networks. Notably, it is important to notice that the strong performance metrics achieved by all these networks (Accuracy, F1 score, AUC all in the 80 to 90% range) could give users the erroneous impression that there is no bias. However, the analysis of the explanation heatmaps highlights the bias.

Algorithmic Probability-Guided Machine Learning on Non-Differentiable Spaces.

We show how complexity theory can be introduced in machine learning to help bring together apparently disparate areas of current research. We show that this model-driven approach may require less training data and can potentially be more generalizable as it shows greater resilience to random attacks. In an algorithmic space the order of its element is given by its algorithmic probability, which arises naturally from computable processes. We investigate the shape of a discrete algorithmic space when performing regression or classification using a loss function parametrized by algorithmic complexity, demonstrating that the property of differentiation is not required to achieve results similar to those obtained using differentiable programming approaches such as deep learning. In doing so we use examples which enable the two approaches to be compared (small, given the computational power required for estimations of algorithmic complexity). We find and report that 1) machine learning can successfully be performed on a non-smooth surface using algorithmic complexity; 2) that solutions can be found using an algorithmic-probability classifier, establishing a bridge between a fundamentally discrete theory of computability and a fundamentally continuous mathematical theory of optimization methods; 3) a formulation of an algorithmically directed search technique in non-smooth manifolds can be defined and conducted; 4) exploitation techniques and numerical methods for algorithmic search to navigate these discrete non-differentiable spaces can be performed; in application of the (a) identification of generative rules from data observations; (b) solutions to image classification problems more resilient against pixel attacks compared to neural networks; (c) identification of equation parameters from a small data-set in the presence of noise in continuous ODE system problem, (d) classification of Boolean NK networks by (1) network topology, (2) underlying Boolean function, and (3) number of incoming edges.

Local Interpretable Model-Agnostic Explanations for Classification of Lymph Node Metastases.

An application of explainable artificial intelligence on medical data is presented. There is an increasing demand in machine learning literature for such explainable models in health-related applications. This work aims to generate explanations on how a Convolutional Neural Network (CNN) detects tumor tissue in patches extracted from histology whole slide images. This is achieved using the "locally-interpretable model-agnostic explanations" methodology. Two publicly-available convolutional neural networks trained on the Patch Camelyon Benchmark are analyzed. Three common segmentation algorithms are compared for superpixel generation, and a fourth simpler parameter-free segmentation algorithm is proposed. The main characteristics of the explanations are discussed, as well as the key patterns identified in true positive predictions. The results are compared to medical annotations and literature and suggest that the CNN predictions follow at least some aspects of human expert knowledge.