David vs. Goliath: comparing conventional machine learning and a large language model for assessing students' concept use in a physics problem.

Large language models have been shown to excel in many different tasks across disciplines and research sites. They provide novel opportunities to enhance educational research and instruction in different ways such as assessment. However, these methods have also been shown to have fundamental limitations. These relate, among others, to hallucinating knowledge, explainability of model decisions, and resource expenditure. As such, more conventional machine learning algorithms might be more convenient for specific research problems because they allow researchers more control over their research. Yet, the circumstances in which either conventional machine learning or large language models are preferable choices are not well understood. This study seeks to answer the question to what extent either conventional machine learning algorithms or a recently advanced large language model performs better in assessing students' concept use in a physics problem-solving task. We found that conventional machine learning algorithms in combination outperformed the large language model. Model decisions were then analyzed via closer examination of the models' classifications. We conclude that in specific contexts, conventional machine learning can supplement large language models, especially when labeled data is available.

Data-driven classification and explainable-AI in the field of lung imaging.

Detecting lung diseases in medical images can be quite challenging for radiologists. In some cases, even experienced experts may struggle with accurately diagnosing chest diseases, leading to potential inaccuracies due to complex or unseen biomarkers. This review paper delves into various datasets and machine learning techniques employed in recent research for lung disease classification, focusing on pneumonia analysis using chest X-ray images. We explore conventional machine learning methods, pretrained deep learning models, customized convolutional neural networks (CNNs), and ensemble methods. A comprehensive comparison of different classification approaches is presented, encompassing data acquisition, preprocessing, feature extraction, and classification using machine vision, machine and deep learning, and explainable-AI (XAI). Our analysis highlights the superior performance of transfer learning-based methods using CNNs and ensemble models/features for lung disease classification. In addition, our comprehensive review offers insights for researchers in other medical domains too who utilize radiological images. By providing a thorough overview of various techniques, our work enables the establishment of effective strategies and identification of suitable methods for a wide range of challenges. Currently, beyond traditional evaluation metrics, researchers emphasize the importance of XAI techniques in machine and deep learning models and their applications in classification tasks. This incorporation helps in gaining a deeper understanding of their decision-making processes, leading to improved trust, transparency, and overall clinical decision-making. Our comprehensive review serves as a valuable resource for researchers and practitioners seeking not only to advance the field of lung disease detection using machine learning and XAI but also from other diverse domains.

Human bias and CNNs' superior insights in satellite based poverty mapping.

Satellite imagery is a potent tool for estimating human wealth and poverty, especially in regions lacking reliable data. This study compares a range of poverty estimation approaches from satellite images, spanning from expert-based to fully machine learning-based methodologies. Human experts ranked clusters from the Tanzania DHS survey using high-resolution satellite images. Then expert-defined features were utilized in a machine learning algorithm to estimate poverty. An explainability method was applied to assess the importance and interaction of these features in poverty prediction. Additionally, a convolutional neural network (CNN) was employed to estimate poverty from medium-resolution satellite images of the same locations. Our analysis indicates that increased human involvement in poverty estimation diminishes accuracy compared to machine learning involvement, exemplified with the case of Tanzania. Expert defined features exhibited significant overlap and poor interaction when used together in a classifier. Conversely, the CNN-based approach outperformed human experts, demonstrating superior predictive capability with medium-resolution images. These findings highlight the importance of leveraging machine learning explainability methods to identify predictive elements that may be overlooked by human experts. This study advocates for the integration of emerging technologies with traditional methodologies to optimize data collection and analysis of poverty and welfare.

Deep learning to capture leaf shape in plant images: Validation by geometric morphometrics.

Plant leaves play a pivotal role in automated species identification using deep learning (DL). However, achieving reproducible capture of leaf variation remains challenging due to the inherent "black box" problem of DL models. To evaluate the effectiveness of DL in capturing leaf shape, we used geometric morphometrics (GM), an emerging component of eXplainable Artificial Intelligence (XAI) toolkits. We photographed Ranunculus auricomus leaves directly in situ and after herbarization. From these corresponding leaf images, we automatically extracted DL features using a neural network and digitized leaf shapes using GM. The association between the extracted DL features and GM shapes was then evaluated using dimension reduction and covariation models. DL features facilitated the clustering of leaf images by source populations in both in situ and herbarized leaf image datasets, and certain DL features were significantly associated with biological leaf shape variation as inferred by GM. DL features also enabled leaf classification into morpho-phylogenomic groups within the intricate R. auricomus species complex. We demonstrated that simple in situ leaf imaging and DL reproducibly captured leaf shape variation at the population level, while combining this approach with GM provided key insights into the shape information extracted from images by computer vision, a necessary prerequisite for reliable automated plant phenotyping.

Multimodal brain tumor segmentation and classification from MRI scans based on optimized DeepLabV3+ and interpreted networks information fusion empowered with explainable AI.

Explainable artificial intelligence (XAI) aims to offer machine learning (ML) methods that enable people to comprehend, properly trust, and create more explainable models. In medical imaging, XAI has been adopted to interpret deep learning black box models to demonstrate the trustworthiness of machine decisions and predictions. In this work, we proposed a deep learning and explainable AI-based framework for segmenting and classifying brain tumors. The proposed framework consists of two parts. The first part, encoder-decoder-based DeepLabv3+ architecture, is implemented with Bayesian Optimization (BO) based hyperparameter initialization. The different scales are performed, and features are extracted through the Atrous Spatial Pyramid Pooling (ASPP) technique. The extracted features are passed to the output layer for tumor segmentation. In the second part of the proposed framework, two customized models have been proposed named Inverted Residual Bottleneck 96 layers (IRB-96) and Inverted Residual Bottleneck Self-Attention (IRB-Self). Both models are trained on the selected brain tumor datasets and extracted features from the global average pooling and self-attention layers. Features are fused using a serial approach, and classification is performed. The BO-based hyperparameters optimization of the neural network classifiers is performed and the classification results have been optimized. An XAI method named LIME is implemented to check the interpretability of the proposed models. The experimental process of the proposed framework was performed on the Figshare dataset, and an average segmentation accuracy of 92.68 % and classification accuracy of 95.42 % were obtained, respectively. Compared with state-of-the-art techniques, the proposed framework shows improved accuracy.

Siamese based deep neural network for ADHD detection using EEG signal.

BACKGROUND: Detecting Attention-Deficit/Hyperactivity Disorder (ADHD) in children is crucial for timely intervention and personalized treatment. OBJECTIVE: This study aims to utilize deep learning techniques to analyze brain maps derived from Power Spectral Density (PSD) of Electroencephalography (EEG) signals in pediatric subjects for ADHD detection. METHODS: We employed a Siamese-based Convolutional Neural Network (CNN) to analyze EEG-based brain maps. Gradient-weighted class activation mapping (Grad-CAM) was used as an explainable AI (XAI) visualization method to identify significant features. RESULTS: The CNN model achieved a high classification accuracy of 99.17 %. Grad-CAM analysis revealed that PSD features from the theta band of the frontal and occipital lobes are effective discriminators for distinguishing children with ADHD from healthy controls. CONCLUSION: This study demonstrates the effectiveness of deep learning in ADHD detection and highlights the importance of regional PSD metrics in accurate classification. By utilizing Grad-CAM, we elucidate the discriminative power of specific brain regions and frequency bands, thereby enhancing the understanding of ADHD neurobiology for improved diagnostic precision in pediatric populations.

Clinical usability of deep learning-based saliency maps for occlusion myocardial infarction identification from the prehospital 12-Lead electrocardiogram.

INTRODUCTION: Deep learning (DL) models offer improved performance in electrocardiogram (ECG)-based classification over rule-based methods. However, for widespread adoption by clinicians, explainability methods, like saliency maps, are essential. METHODS: On a subset of 100 ECGs from patients with chest pain, we generated saliency maps using a previously validated convolutional neural network for occlusion myocardial infarction (OMI) classification. Three clinicians reviewed ECG-saliency map dyads, first assessing the likelihood of OMI from standard ECGs and then evaluating clinical relevance and helpfulness of the saliency maps, as well as their confidence in the model's predictions. Questions were answered on a Likert scale ranging from +3 (most useful/relevant) to -3 (least useful/relevant). RESULTS: The adjudicated accuracy of the three clinicians matched the DL model when considering area under the receiver operating characteristics curve (AUC) and F1 score (AUC 0.855 vs. 0.872, F1 score = 0.789 vs. 0.747). On average, clinicians found saliency maps slightly clinically relevant (0.96 ± 0.92) and slightly helpful (0.66 ± 0.98) in identifying or ruling out OMI but had higher confidence in the model's predictions (1.71 ± 0.56). Clinicians noted that leads I and aVL were often emphasized, even when obvious ST changes were present in other leads. CONCLUSION: In this clinical usability study, clinicians deemed saliency maps somewhat helpful in enhancing explainability of DL-based ECG models. The spatial convolutional layers across the 12 leads in these models appear to contribute to the discrepancy between ECG segments considered most relevant by clinicians and segments that drove DL model predictions.

Performance of explainable artificial intelligence in guiding the management of patients with a pancreatic cyst.

BACKGROUND/OBJECTIVES: Pancreatic cyst management can be distilled into three separate pathways - discharge, monitoring or surgery- based on the risk of malignant transformation. This study compares the performance of artificial intelligence (AI) models to clinical care for this task. METHODS: Two explainable boosting machine (EBM) models were developed and evaluated using clinical features only, or clinical features and cyst fluid molecular markers (CFMM) using a publicly available dataset, consisting of 850 cases (median age 64; 65 % female) with independent training (429 cases) and holdout test cohorts (421 cases). There were 137 cysts with no malignant potential, 114 malignant cysts, and 599 IPMNs and MCNs. RESULTS: The EBM and EBM with CFMM models had higher accuracy for identifying patients requiring monitoring (0.88 and 0.82) and surgery (0.66 and 0.82) respectively compared with current clinical care (0.62 and 0.58). For discharge, the EBM with CFMM model had a higher accuracy (0.91) than either the EBM model (0.84) or current clinical care (0.86). In the cohort of patients who underwent surgical resection, use of the EBM-CFMM model would have decreased the number of unnecessary surgeries by 59 % (n = 92), increased correct surgeries by 7.5 % (n = 11), identified patients who require monitoring by 122 % (n = 76), and increased the number of patients correctly classified for discharge by 138 % (n = 18) compared to clinical care. CONCLUSIONS: EBM models had greater sensitivity and specificity for identifying the correct management compared with either clinical management or previous AI models. The model predictions are demonstrated to be interpretable by clinicians.

Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis.

This systematic literature review examines state-of-the-art Explainable Artificial Intelligence (XAI) methods applied to medical image analysis, discussing current challenges and future research directions, and exploring evaluation metrics used to assess XAI approaches. With the growing efficiency of Machine Learning (ML) and Deep Learning (DL) in medical applications, there's a critical need for adoption in healthcare. However, their "black-box" nature, where decisions are made without clear explanations, hinders acceptance in clinical settings where decisions have significant medicolegal consequences. Our review highlights the advanced XAI methods, identifying how they address the need for transparency and trust in ML/DL decisions. We also outline the challenges faced by these methods and propose future research directions to improve XAI in healthcare. This paper aims to bridge the gap between cutting-edge computational techniques and their practical application in healthcare, nurturing a more transparent, trustworthy, and effective use of AI in medical settings. The insights guide both research and industry, promoting innovation and standardisation in XAI implementation in healthcare.

Trusted artificial intelligence for environmental assessments: An explainable high-precision model with multi-source big data.

Environmental assessments are critical for ensuring the sustainable development of human civilization. The integration of artificial intelligence (AI) in these assessments has shown great promise, yet the "black box" nature of AI models often undermines trust due to the lack of transparency in their decision-making processes, even when these models demonstrate high accuracy. To address this challenge, we evaluated the performance of a transformer model against other AI approaches, utilizing extensive multivariate and spatiotemporal environmental datasets encompassing both natural and anthropogenic indicators. We further explored the application of saliency maps as a novel explainability tool in multi-source AI-driven environmental assessments, enabling the identification of individual indicators' contributions to the model's predictions. We find that the transformer model outperforms others, achieving an accuracy of about 98% and an area under the receiver operating characteristic curve (AUC) of 0.891. Regionally, the environmental assessment values are predominantly classified as level II or III in the central and southwestern study areas, level IV in the northern region, and level V in the western region. Through explainability analysis, we identify that water hardness, total dissolved solids, and arsenic concentrations are the most influential indicators in the model. Our AI-driven environmental assessment model is accurate and explainable, offering actionable insights for targeted environmental management. Furthermore, this study advances the application of AI in environmental science by presenting a robust, explainable model that bridges the gap between machine learning and environmental governance, enhancing both understanding and trust in AI-assisted environmental assessments.

Explainability of artificial neural network in predicting career fulfilment among medical doctors in developing nations: Applicability and implications.

BACKGROUND: Career fulfilment among medical doctors is crucial for job satisfaction, retention, and healthcare quality, especially in developing nations with challenging healthcare systems. Traditional career guidance methods struggle to address the complexities of career fulfilment. While recent advancements in machine learning, particularly Artificial Neural Network (ANN) models, offer promising solutions for personalized career predictions, their applicability, interpretability, and impact remain challenging. METHOD: This study explores the applicability, explainability, and implications of ANN models in predicting career fulfillment among medical doctors in developing nations, considering socio-economic, psychological, and professional factors. Box plots visualized data distribution, while Heatmaps assessed data intensity and relationships. Matthew's correlation coefficient and Taylor's chart were used to evaluate model performance. Input feature contributions to ANN predictions were analyzed using permutation importance, SHAP, LIME, and Williams plots. The model was tested on a dataset tailored to medical professionals in Nigeria and China, with evaluation metrics including Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and R2 Score. RESULTS: The ANN model demonstrates strong predictive accuracy, capturing relationships between input factors and outcomes. For Chinese doctors, it achieved an MSE of 0.0004 and R2 of 0.9994, while for Nigerian doctors, it recorded an MSE of 0.0003 and R2 of 0.9998. Key factors for Chinese doctors' satisfaction were IF1 and IF2, while EF1 and EF3 were crucial in preventing dissatisfaction. For Nigerian doctors, IF2 and IF3 drove satisfaction, while EF1 and EF4 were significant in avoiding dissatisfaction. CONCLUSION: The results highlights the ANN model's effectiveness in predicting career fulfillment among medical doctors in developing nations, offering a valuable tool for career guidance, policymaking, and improving job satisfaction, retention, and healthcare quality.

Evaluation of tumor budding with virtual panCK stains generated by novel multi-model CNN framework.

As the global incidence of cancer continues to rise rapidly, the need for swift and precise diagnoses has become increasingly pressing. Pathologists commonly rely on H&E-panCK stain pairs for various aspects of cancer diagnosis, including the detection of occult tumor cells and the evaluation of tumor budding. Nevertheless, conventional chemical staining methods suffer from notable drawbacks, such as time-intensive processes and irreversible staining outcomes. The virtual stain technique, leveraging generative adversarial network (GAN), has emerged as a promising alternative to chemical stains. This approach aims to transform biopsy scans (often H&E) into other stain types. Despite achieving notable progress in recent years, current state-of-the-art virtual staining models confront challenges that hinder their efficacy, particularly in achieving accurate staining outcomes under specific conditions. These limitations have impeded the practical integration of virtual staining into diagnostic practices. To address the goal of producing virtual panCK stains capable of replacing chemical panCK, we propose an innovative multi-model framework. Our approach involves employing a combination of Mask-RCNN (for cell segmentation) and GAN models to extract cytokeratin distribution from chemical H&E images. Additionally, we introduce a tailored dynamic GAN model to convert H&E images into virtual panCK stains, integrating the derived cytokeratin distribution. Our framework is motivated by the fact that the unique pattern of the panCK is derived from cytokeratin distribution. As a proof of concept, we employ our virtual panCK stains to evaluate tumor budding in 45 H&E whole-slide images taken from breast cancer-invaded lymph nodes . Through thorough validation by both pathologists and the QuPath software, our virtual panCK stains demonstrate a remarkable level of accuracy. In stark contrast, the accuracy of state-of-the-art single cycleGAN virtual panCK stains is negligible. To our best knowledge, this is the first instance of a multi-model virtual panCK framework and the utilization of virtual panCK for tumor budding assessment. Our framework excels in generating dependable virtual panCK stains with significantly improved efficiency, thereby considerably reducing turnaround times in diagnosis. Furthermore, its outcomes are easily comprehensible even to pathologists who may not be well-versed in computer technology. We firmly believe that our framework has the potential to advance the field of virtual stain, thereby making significant strides towards improved cancer diagnosis.

Predicting odor from vibrational spectra: a data-driven approach.

This study investigates olfaction, a complex and not well-understood sensory modality. The chemical mechanism behind smell can be described by so far proposed two theories: vibrational and docking theories. The vibrational theory has been gaining acceptance lately but needs more extensive validation. To fill this gap for the first time, we, with the help of data-driven classification, clustering, and Explainable AI techniques, systematically analyze a large dataset of vibrational spectra (VS) of 3018 molecules obtained from the atomistic simulation. The study utlizes image representations of VS using Gramian Angular Fields and Markov Transition Fields, allowing computer vision techniques to be applied for better feature extraction and improved odor classification. Furthermore, we fuse the PCA-reduced fingerprint features with image features, which show additional improvement in classification results. We use two clustering methods, agglomerative hierarchical (AHC) and k-means, on dimensionality reduced (UMAP, MDS, t-SNE, and PCA) VS and image features, which shed further insight into the connections between molecular structure, VS, and odor. Additionally, we contrast our method with an earlier work that employed traditional machine learning on fingerprint features for the same dataset, and demonstrate that even with a representative subset of 3018 molecules, our deep learning model outperforms previous results. This comprehensive and systematic analysis highlights the potential of deep learning in furthering the field of olfactory research while confirming the vibrational theory of olfaction.

Concrete Crack Detection and Segregation: A Feature Fusion, Crack Isolation, and Explainable AI-Based Approach.

Scientific knowledge of image-based crack detection methods is limited in understanding their performance across diverse crack sizes, types, and environmental conditions. Builders and engineers often face difficulties with image resolution, detecting fine cracks, and differentiating between structural and non-structural issues. Enhanced algorithms and analysis techniques are needed for more accurate assessments. Hence, this research aims to generate an intelligent scheme that can recognize the presence of cracks and visualize the percentage of cracks from an image along with an explanation. The proposed method fuses features from concrete surface images through a ResNet-50 convolutional neural network (CNN) and curvelet transform handcrafted (HC) method, optimized by linear discriminant analysis (LDA), and the eXtreme gradient boosting (XGB) classifier then uses these features to recognize cracks. This study evaluates several CNN models, including VGG-16, VGG-19, Inception-V3, and ResNet-50, and various HC techniques, such as wavelet transform, counterlet transform, and curvelet transform for feature extraction. Principal component analysis (PCA) and LDA are assessed for feature optimization. For classification, XGB, random forest (RF), adaptive boosting (AdaBoost), and category boosting (CatBoost) are tested. To isolate and quantify the crack region, this research combines image thresholding, morphological operations, and contour detection with the convex hulls method and forms a novel algorithm. Two explainable AI (XAI) tools, local interpretable model-agnostic explanations (LIMEs) and gradient-weighted class activation mapping++ (Grad-CAM++) are integrated with the proposed method to enhance result clarity. This research introduces a novel feature fusion approach that enhances crack detection accuracy and interpretability. The method demonstrates superior performance by achieving 99.93% and 99.69% accuracy on two existing datasets, outperforming state-of-the-art methods. Additionally, the development of an algorithm for isolating and quantifying crack regions represents a significant advancement in image processing for structural analysis. The proposed approach provides a robust and reliable tool for real-time crack detection and assessment in concrete structures, facilitating timely maintenance and improving structural safety. By offering detailed explanations of the model's decisions, the research addresses the critical need for transparency in AI applications, thus increasing trust and adoption in engineering practice.

Integrating visual and community environments in a motorcycle crash and casualty estimation.

Motorcycle crashes pose a serious problem because their probability of causing casualties is greater than that of passenger vehicle crashes. Therefore, accurately identifying the factors that influence motorcycle crashes is essential for enhancing traffic safety and public health. The aim of this study was to address three major research gaps: first, existing studies have relatively overlooked the built environment in relation to visual factors; second, existing crash prediction models have not fully reflected the differences in built environment characteristics between areas with frequent motorcycle crashes and areas with frequent casualties; and third, multidimensional analysis for variable selection is limited, and the interpretability of the models is insufficient. Therefore, this study proposes a comprehensive framework for motorcycle crash and casualty estimation. The framework uses a data cube model incorporating OLAP operations to provide deeper insights into crash influencing factors at different levels of abstraction. We also utilized the XGBoost model to predict motorcycle high crash spots and casualty risk and integrate visual factors extracted from Google Street View images and community-level urban environments into the model. SHAP techniques were used to analyze and interpret the global and local feature importance of the models. Our results revealed that the factors affecting areas with frequent motorcycle crashes and the factors that affect casualties differ. In particular, visual factors such as vegetation and the sky ratio are important for estimating casualties. We aim to provide practical guidelines for a safe environment for motorcycle crashes.

The Most Effective Interventions for Classification Model Development to Predict Chat Outcomes Based on the Conversation Content in Online Suicide Prevention Chats: Machine Learning Approach.

BACKGROUND: For the provision of optimal care in a suicide prevention helpline, it is important to know what contributes to positive or negative effects on help seekers. Helplines can often be contacted through text-based chat services, which produce large amounts of text data for use in large-scale analysis. OBJECTIVE: We trained a machine learning classification model to predict chat outcomes based on the content of the chat conversations in suicide helplines and identified the counsellor utterances that had the most impact on its outputs. METHODS: From August 2021 until January 2023, help seekers (N=6903) scored themselves on factors known to be associated with suicidality (eg, hopelessness, feeling entrapped, will to live) before and after a chat conversation with the suicide prevention helpline in the Netherlands (113 Suicide Prevention). Machine learning text analysis was used to predict help seeker scores on these factors. Using 2 approaches for interpreting machine learning models, we identified text messages from helpers in a chat that contributed the most to the prediction of the model. RESULTS: According to the machine learning model, helpers' positive affirmations and expressing involvement contributed to improved scores of the help seekers. Use of macros and ending the chat prematurely due to the help seeker being in an unsafe situation had negative effects on help seekers. CONCLUSIONS: This study reveals insights for improving helpline chats, emphasizing the value of an evocative style with questions, positive affirmations, and practical advice. It also underscores the potential of machine learning in helpline chat analysis.

Implications of causality in artificial intelligence.

Over the last decade, investment in artificial intelligence (AI) has grown significantly, driven by technology companies and the demand for PhDs in AI. However, new challenges have emerged, such as the 'black box' and bias in AI models. Several approaches have been developed to reduce these problems. Responsible AI focuses on the ethical development of AI systems, considering social impact. Fair AI seeks to identify and correct algorithm biases, promoting equitable decisions. Explainable AI aims to create transparent models that allow users to interpret results. Finally, Causal AI emphasizes identifying cause-and-effect relationships and plays a crucial role in creating more robust and reliable systems, thereby promoting fairness and transparency in AI development. Responsible, Fair, and Explainable AI has several weaknesses. However, Causal AI is the approach with the slightest criticism, offering reassurance about the ethical development of AI.

Analyzing classification and feature selection strategies for diabetes prediction across diverse diabetes datasets.

Introduction: In the evolving landscape of healthcare and medicine, the merging of extensive medical datasets with the powerful capabilities of machine learning (ML) models presents a significant opportunity for transforming diagnostics, treatments, and patient care. Methods: This research paper delves into the realm of data-driven healthcare, placing a special focus on identifying the most effective ML models for diabetes prediction and uncovering the critical features that aid in this prediction. The prediction performance is analyzed using a variety of ML models, such as Random Forest (RF), XG Boost (XGB), Linear Regression (LR), Gradient Boosting (GB), and Support VectorMachine (SVM), across numerousmedical datasets. The study of feature importance is conducted using methods including Filter-based, Wrapper-based techniques, and Explainable Artificial Intelligence (Explainable AI). By utilizing Explainable AI techniques, specifically Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), the decision-making process of the models is ensured to be transparent, thereby bolstering trust in AI-driven decisions. Results: Features identified by RF in Wrapper-based techniques and the Chi-square in Filter-based techniques have been shown to enhance prediction performance. A notable precision and recall values, reaching up to 0.9 is achieved in predicting diabetes. Discussion: Both approaches are found to assign considerable importance to features like age, family history of diabetes, polyuria, polydipsia, and high blood pressure, which are strongly associated with diabetes. In this age of data-driven healthcare, the research presented here aspires to substantially improve healthcare outcomes.

Emerging research trends in artificial intelligence for cancer diagnostic systems: A comprehensive review.

This review article offers a comprehensive analysis of current developments in the application of machine learning for cancer diagnostic systems. The effectiveness of machine learning approaches has become evident in improving the accuracy and speed of cancer detection, addressing the complexities of large and intricate medical datasets. This review aims to evaluate modern machine learning techniques employed in cancer diagnostics, covering various algorithms, including supervised and unsupervised learning, as well as deep learning and federated learning methodologies. Data acquisition and preprocessing methods for different types of data, such as imaging, genomics, and clinical records, are discussed. The paper also examines feature extraction and selection techniques specific to cancer diagnosis. Model training, evaluation metrics, and performance comparison methods are explored. Additionally, the review provides insights into the applications of machine learning in various cancer types and discusses challenges related to dataset limitations, model interpretability, multi-omics integration, and ethical considerations. The emerging field of explainable artificial intelligence (XAI) in cancer diagnosis is highlighted, emphasizing specific XAI techniques proposed to improve cancer diagnostics. These techniques include interactive visualization of model decisions and feature importance analysis tailored for enhanced clinical interpretation, aiming to enhance both diagnostic accuracy and transparency in medical decision-making. The paper concludes by outlining future directions, including personalized medicine, federated learning, deep learning advancements, and ethical considerations. This review aims to guide researchers, clinicians, and policymakers in the development of efficient and interpretable machine learning-based cancer diagnostic systems.

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.