Reported Performance Metrics Research Articles

Exploring Artificial Intelligence Biases in Predictive Models for Cancer Diagnosis

The American Society of Clinical Oncology (ASCO) has released the principles for the responsible use of artificial intelligence (AI) in oncology emphasizing fairness, accountability, oversight, equity, and transparency. However, the extent to which these principles are followed is unknown. The goal of this study was to assess the presence of biases and the quality of studies on AI models according to the ASCO principles and examine their potential impact through citation analysis and subsequent research applications. A review of original research articles centered on the evaluation of predictive models for cancer diagnosis published in the ASCO journal dedicated to informatics and data science in clinical oncology was conducted. Seventeen potential bias criteria were used to evaluate the sources of bias in the studies, aligned with the ASCO’s principles for responsible AI use in oncology. The CREMLS checklist was applied to assess the study quality, focusing on the reporting standards, and the performance metrics along with citation counts of the included studies were analyzed. Nine studies were included. The most common biases were environmental and life-course bias, contextual bias, provider expertise bias, and implicit bias. Among the ASCO principles, the least adhered to were transparency, oversight and privacy, and human-centered AI application. Only 22% of the studies provided access to their data. The CREMLS checklist revealed the deficiencies in methodology and evaluation reporting. Most studies reported performance metrics within moderate to high ranges. Additionally, two studies were replicated in the subsequent research. In conclusion, most studies exhibited various types of bias, reporting deficiencies, and failure to adhere to the principles for responsible AI use in oncology, limiting their applicability and reproducibility. Greater transparency, data accessibility, and compliance with international guidelines are recommended to improve the reliability of AI-based research in oncology.

Predicting Glaucoma Progression with Artificial Intelligence: A Meta-Analysis of Machine Learning Models

Introduction: Glaucoma, a leading cause of irreversible blindness, requires early detection and prediction of progression to preserve vision. Artificial intelligence (AI) offers promising tools for analyzing complex ophthalmic data and identifying high-risk individuals. This meta-analysis evaluates the performance of machine learning (ML) models in predicting glaucoma progression. Methods: A systematic search of PubMed, Scopus, and Web of Science databases was conducted for studies published between 2013 and 2024 that investigated the use of ML models to predict glaucoma progression. Studies reporting performance metrics like sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and accuracy were included. Results: Six studies met the inclusion criteria, encompassing 1,250 participants. The pooled sensitivity and specificity of ML models for predicting glaucoma progression were 0.81 (95% CI: 0.78-0.84) and 0.77 (95% CI: 0.73-0.81), respectively. The pooled AUC was 0.88 (95% CI: 0.86-0.90), indicating excellent discriminatory ability. Conclusion: ML models hold significant potential for predicting glaucoma progression with high accuracy. Further research with larger, more diverse datasets is needed to validate these findings and develop clinically applicable tools.

Monitoring performance of clinical artificial intelligence in health care: a scoping review.

The objective of this review was to provide an overview of the diverse methods described, tested, or implemented for monitoring performance of clinical artificial intelligence (AI) systems, while also summarizing the arguments given for or against these methods. The integration of AI in clinical decision-making is steadily growing. Performances of AI systems evolve over time, necessitating ongoing performance monitoring. However, the evidence on specific monitoring methods is sparse and heterogeneous. Thus, an overview of the evidence on this topic is warranted to guide further research on clinical AI monitoring. We included publications detailing metrics or statistical processes employed in systematic, continuous, or repeated initiatives aimed at evaluating or predicting the clinical performance of AI models with direct implications for patient management in health care. No limitations on language or publication date were enforced. We performed systematic database searches in MEDLINE (Ovid), Embase (Ovid), Scopus, and ProQuest Dissertations and Theses Global, supplemented by backward and forward citation searches and gray literature searches. Two or more independent reviewers conducted title and abstract screening, full-text evaluation, and data extraction using a tool developed by the authors. During extraction, the methods identified were divided into subcategories. The results are presented narratively and summarized in tables and graphs. Thirty-nine sources of evidence were included in the review, with the most abundant source types being opinion papers/narrative reviews (33%) and simulation studies (33%). One guideline on the topic was identified, offering limited guidance on specific metrics and statistical methods. The number of sources included increased year by year, with almost 4 times as many sources included in 2023 compared with 2019. The most commonly reported performance metrics were traditional metrics from the medical literature, including area under the receiver operating characteristics curve (AUROC), sensitivity, specificity, and predictive values, although few arguments were given supporting these choices. Some studies reported on metrics and statistical processing specifically designed to monitor clinical AI. This review provides a summary of the methods described for monitoring AI in health care. It reveals a relative scarcity of evidence and guidance for specific practical implementation of performance monitoring of clinical AI. This underscores the imperative for further research, discussion, and guidance regarding the specifics of implementing monitoring for clinical AI. The steady increase in the number of relevant sources published per year suggests that this area of research is gaining increased focus, and the amount of evidence and guidance available will likely increase significantly over the coming years. Open Science Framework https://osf.io/afkrn.

Highly efficient perovskite-based fuel electrodes for solid oxide electrochemical cells via in-situ nanoparticle exsolution and electron conduction enhancement

Developing efficient fuel catalysts exhibiting high electrocatalytic activity and stability is crucial to improving the performance of solid oxide fuel/electrolysis cells for electrochemical energy storage and conversion. The oxide catalysts have been extensively investigated for replacing conventional Ni-based fuel electrodes, owing to their excellent stability and high resistance to coking in the presence of carbon-based fuels, such as during CO2 electrolysis. In this study, we propose a novel strategy to enhance the oxide electrocatalyst performance via nanoparticle exsolution and electron conduction improvement. In this strategy, the A-site deficient Sr0.95Ti0.3(Fe0.9Ru0.1)0.7O3-δ (STFR) was coupled with Sr2Fe1.5Mo0.5O6-δ (SFM) to yield a composite electrode. STFR with in-situ exsolved Fe–Ru nanoparticles provided high catalytically active sites, whereas SFM increased the electron conduction pathways, further boosting the electrode activity. When the composited electrodes were applied to an LSGM electrolyte-supported cell, the Fe–Ru exsolved STFR–SFM exhibited superior activity, surpassing those of previously reported performance metrics, including >1.5 W cm−2 peak power density in fuel cell mode, >1.75 A cm−2 (at 1.3 V) in the steam electrolysis mode, and >2.15 A cm−2 (at 1.3 V) in direct CO2 electrolysis mode at 800 °C. The composite electrode demonstrates excellent electrochemical catalytic activity, remarkable durability, and preferential selectivity toward CO2 electrolysis.

Microplastic predictive modelling with the integration of Artificial Neural Networks and Hidden Markov Models (ANN-HMM).

Microplastic pollution poses a significant threat to our environment, necessitating effective predictive modelling approaches for better management and mitigation. In this study, we introduce a pioneering methodology that fuses the power of Artificial Neural Networks (ANN) and Hidden Markov Models (HMM) for microplastic predictive modelling. Leveraging a comprehensive dataset, our integrated model exhibits exceptional performance, with an Accuracy of 0.96, Precision of 0.96, Recall of 0.97, and an F1 Score of 0.96. The achieved Accuracy underscores the model's proficiency in distinguishing microplastic and non-microplastic entities, promising robust and reliable predictions. Precision, as a measure of correct positive identifications, demonstrates our model's effectiveness in minimizing false positives, a crucial aspect for environmental monitoring. Moreover, the perfect Recall score signifies the model's ability to detect all relevant microplastic instances, addressing concerns about false negatives. The F1 Score encapsulates this dual proficiency, showcasing a harmonious trade-off between precision and recall. Our research not only advances the field of microplastic prediction but also highlights the potential of synergizing ANN and HMM methodologies for comprehensive environmental assessments. The reported performance metrics underscore the practical applicability of our approach, offering a valuable tool for tackling the pervasive issue of microplastic pollution and fostering proactive environmental stewardship.

Improving Triage Accuracy in Prehospital Emergency Telemedicine: Scoping Review of Machine Learning-Enhanced Approaches.

Prehospital telemedicine triage systems combined with machine learning (ML) methods have the potential to improve triage accuracy and safely redirect low-acuity patients from attending the emergency department. However, research in prehospital settings is limited but needed; emergency department overcrowding and adverse patient outcomes are increasingly common. In this scoping review, we sought to characterize the existing methods for ML-enhanced telemedicine emergency triage. In order to support future research, we aimed to delineate what data sources, predictors, labels, ML models, and performance metrics were used, and in which telemedicine triage systems these methods were applied. A scoping review was conducted, querying multiple databases (MEDLINE, PubMed, Scopus, and IEEE Xplore) through February 24, 2023, to identify potential ML-enhanced methods, and for those eligible, relevant study characteristics were extracted, including prehospital triage setting, types of predictors, ground truth labeling method, ML models used, and performance metrics. Inclusion criteria were restricted to the triage of emergency telemedicine services using ML methods on an undifferentiated (disease nonspecific) population. Only primary research studies in English were considered. Furthermore, only those studies using data collected remotely (as opposed to derived from physical assessments) were included. In order to limit bias, we exclusively included articles identified through our predefined search criteria and had 3 researchers (DR, JS, and KS) independently screen the resulting studies. We conducted a narrative synthesis of findings to establish a knowledge base in this domain and identify potential gaps to be addressed in forthcoming ML-enhanced methods. A total of 165 unique records were screened for eligibility and 15 were included in the review. Most studies applied ML methods during emergency medical dispatch (7/15, 47%) or used chatbot applications (5/15, 33%). Patient demographics and health status variables were the most common predictors, with a notable absence of social variables. Frequently used ML models included support vector machines and tree-based methods. ML-enhanced models typically outperformed conventional triage algorithms, and we found a wide range of methods used to establish ground truth labels. This scoping review observed heterogeneity in dataset size, predictors, clinical setting (triage process), and reported performance metrics. Standard structured predictors, including age, sex, and comorbidities, across articles suggest the importance of these inputs; however, there was a notable absence of other potentially useful data, including medications, social variables, and health system exposure. Ground truth labeling practices should be reported in a standard fashion as the true model performance hinges on these labels. This review calls for future work to form a standardized framework, thereby supporting consistent reporting and performance comparisons across ML-enhanced prehospital triage systems.

Enhancing Medical Image Quality Using Fractional Order Denoising Integrated with Transfer Learning

In medical imaging, noise can significantly obscure critical details, complicating diagnosis and treatment. Traditional denoising techniques often struggle to maintain a balance between noise reduction and detail preservation. To address this challenge, we propose an “Efficient Transfer-Learning-Based Fractional Order Image Denoising Approach in Medical Image Analysis (ETLFOD)” method. Our approach uniquely integrates transfer learning with fractional order techniques, leveraging pre-trained models such as DenseNet121 to adapt to the specific needs of medical image denoising. This method enhances denoising performance while preserving essential image details. The ETLFOD model has demonstrated superior performance compared to state-of-the-art (SOTA) techniques. For instance, our DenseNet121 model achieved an accuracy of 98.01%, precision of 98%, and recall of 98%, significantly outperforming traditional denoising methods. Specific results include a 95% accuracy, 98% precision, 99% recall, and 96% F1-score for MRI brain datasets, and an 88% accuracy, 91% precision, 95% recall, and 88% F1-score for COVID-19 lung data. X-ray pneumonia results in the lung CT dataset showed a 92% accuracy, 97% precision, 98% recall, and 93% F1-score. It is important to note that while we report performance metrics in this paper, the primary evaluation of our approach is based on the comparison of original noisy images with the denoised outputs, ensuring a focus on image quality enhancement rather than classification performance.

EEG workload estimation and classification: a systematic review.

Electroencephalography (EEG) has evolved into an indispensable instrument for estimating cognitive workload in various domains. ML and DL techniques have been increasingly employed to develop accurate workload estimation and classification models based on EEG data. The goal of this systematic review is to compile the body of research on EEG workload estimation and classification using ML and DL approaches. The PRISMA procedures were followed in conducting the review, searches were conducted through databases at SpringerLink, ACM Digital Library, IEEE Explore, PUBMED, and Science Direct from the beginning to the end of February 16, 2024. Studies were selected based on predefined inclusion criteria. Data were extracted to capture study design, participant demographics, EEG features, ML/DL algorithms, and reported performance metrics. Out of the 125 items that emerged, 33 scientific papers were fully evaluated. The study designs, participant demographics, and EEG workload measurement and categorization techniques used in the investigations differed. SVM, CNN, and hybrid networks are examples of ML and DL approaches that were often used. Analyzing the accuracy scores achieved by different ML/DL models. Furthermore, a relationship was noted between sample frequency and model accuracy, with higher sample frequencies generally leading to improved performance. The percentage distribution of ML/DL methods revealed that SVMs, CNNs, and RNNs were the most commonly utilized techniques, reflecting their robustness in handling EEG data. The comprehensive review emphasizes how ML may be used to identify mental workload across a variety of disciplines using EEG data. Optimizing practical applications requires multimodal data integration, standardization efforts, and real-world validation studies. These systems will also be further improved by addressing ethical issues and investigating new EEG properties, which will improve human-computer interaction and performance assessment.

Critical Analysis of Data Leakage in WiFi CSI-Based Human Action Recognition Using CNNs.

WiFi Channel State Information (CSI)-based human action recognition using convolutional neural networks (CNNs) has emerged as a promising approach for non-intrusive activity monitoring. However, the integrity and reliability of the reported performance metrics are susceptible to data leakage, wherein information from the test set inadvertently influences the training process, leading to inflated accuracy rates. In this paper, we conduct a critical analysis of a notable IEEE Sensors Journal study on WiFi CSI-based human action recognition, uncovering instances of data leakage resulting from the absence of subject-based data partitioning. Empirical investigation corroborates the lack of exclusivity of individuals across dataset partitions, underscoring the importance of rigorous data management practices. Furthermore, we demonstrate that employing data partitioning with respect to humans results in significantly lower precision rates than the reported 99.9% precision, highlighting the exaggerated nature of the original findings. Such inflated results could potentially discourage other researchers and impede progress in the field by fostering a sense of complacency.

Integrated image and location analysis for wound classification: a deep learning approach

The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative multi-modal network based on a deep convolutional neural network for categorizing wounds into four categories: diabetic, pressure, surgical, and venous ulcers. Our multi-modal network uses wound images and their corresponding body locations for more precise classification. A unique aspect of our methodology is incorporating a body map system that facilitates accurate wound location tagging, improving upon traditional wound image classification techniques. A distinctive feature of our approach is the integration of models such as VGG16, ResNet152, and EfficientNet within a novel architecture. This architecture includes elements like spatial and channel-wise Squeeze-and-Excitation modules, Axial Attention, and an Adaptive Gated Multi-Layer Perceptron, providing a robust foundation for classification. Our multi-modal network was trained and evaluated on two distinct datasets comprising relevant images and corresponding location information. Notably, our proposed network outperformed traditional methods, reaching an accuracy range of 74.79–100% for Region of Interest (ROI) without location classifications, 73.98–100% for ROI with location classifications, and 78.10–100% for whole image classifications. This marks a significant enhancement over previously reported performance metrics in the literature. Our results indicate the potential of our multi-modal network as an effective decision-support tool for wound image classification, paving the way for its application in various clinical contexts.

Deep learning segmentation of the choroid plexus from structural magnetic resonance imaging (MRI): validation and normative ranges across the adult lifespan

BackgroundThe choroid plexus functions as the blood-cerebrospinal fluid (CSF) barrier, plays an important role in CSF production and circulation, and has gained increased attention in light of the recent elucidation of CSF circulation dysfunction in neurodegenerative conditions. However, methods for routinely quantifying choroid plexus volume are suboptimal and require technical improvements and validation. Here, we propose three deep learning models that can segment the choroid plexus from commonly-acquired anatomical MRI data and report performance metrics and changes across the adult lifespan.MethodsFully convolutional neural networks were trained from 3D T1-weighted, 3D T2-weighted, and 2D T2-weighted FLAIR MRI using gold-standard manual segmentations in control and neurodegenerative participants across the lifespan (n = 50; age = 21–85 years). Dice coefficients, 95% Hausdorff distances, and area-under-curve (AUCs) were calculated for each model and compared to segmentations from FreeSurfer using two-tailed Wilcoxon tests (significance criteria: p < 0.05 after false discovery rate multiple comparisons correction). Metrics were regressed against lateral ventricular volume using generalized linear models to assess model performance for varying levels of atrophy. Finally, models were applied to an expanded cohort of adult controls (n = 98; age = 21–89 years) to provide an exemplar of choroid plexus volumetry values across the lifespan.ResultsDeep learning results yielded Dice coefficient = 0.72, Hausdorff distance = 1.97 mm, AUC = 0.87 for T1-weighted MRI, Dice coefficient = 0.72, Hausdorff distance = 2.22 mm, AUC = 0.87 for T2-weighted MRI, and Dice coefficient = 0.74, Hausdorff distance = 1.69 mm, AUC = 0.87 for T2-weighted FLAIR MRI; values did not differ significantly between MRI sequences and were statistically improved compared to current commercially-available algorithms (p < 0.001). The intraclass coefficients were 0.95, 0.95, and 0.96 between T1-weighted and T2-weighted FLAIR, T1-weighted and T2-weighted, and T2-weighted and T2-weighted FLAIR models, respectively. Mean lateral ventricle choroid plexus volume across all participants was 3.20 ± 1.4 cm3; a significant, positive relationship (R2 = 0.54-0.60) was observed between participant age and choroid plexus volume for all MRI sequences (p < 0.001).ConclusionsFindings support comparable performance in choroid plexus delineation between standard, clinically available, non-contrasted anatomical MRI sequences. The software embedding the evaluated models is freely available online and should provide a useful tool for the growing number of studies that desire to quantitatively evaluate choroid plexus structure and function (https://github.com/hettk/chp_seg).

Advancements in cardiac structures segmentation: a comprehensive systematic review of deep learning in CT imaging.

Segmentation of cardiac structures is an important step in evaluation of the heart on imaging. There has been growing interest in how artificial intelligence (AI) methods-particularly deep learning (DL)-can be used to automate this process. Existing AI approaches to cardiac segmentation have mostly focused on cardiac MRI. This systematic review aimed to appraise the performance and quality of supervised DL tools for the segmentation of cardiac structures on CT. Embase and Medline databases were searched to identify related studies from January 1, 2013 to December 4, 2023. Original research studies published in peer-reviewed journals after January 1, 2013 were eligible for inclusion if they presented supervised DL-based tools for the segmentation of cardiac structures and non-coronary great vessels on CT. The data extracted from eligible studies included information about cardiac structure(s) being segmented, study location, DL architectures and reported performance metrics such as the Dice similarity coefficient (DSC). The quality of the included studies was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). 18 studies published after 2020 were included. The DSC scores median achieved for the most commonly segmented structures were left atrium (0.88, IQR 0.83-0.91), left ventricle (0.91, IQR 0.89-0.94), left ventricle myocardium (0.83, IQR 0.82-0.92), right atrium (0.88, IQR 0.83-0.90), right ventricle (0.91, IQR 0.85-0.92), and pulmonary artery (0.92, IQR 0.87-0.93). Compliance of studies with CLAIM was variable. In particular, only 58% of studies showed compliance with dataset description criteria and most of the studies did not test or validate their models on external data (81%). Supervised DL has been applied to the segmentation of various cardiac structures on CT. Most showed similar performance as measured by DSC values. Existing studies have been limited by the size and nature of the training datasets, inconsistent descriptions of ground truth annotations and lack of testing in external data or clinical settings. [www.crd.york.ac.uk/prospero/], PROSPERO [CRD42023431113].

Technological advances in lower-limb tele-rehabilitation: A review of literature.

Tele-rehabilitation is a healthcare practice that leverages technology to provide rehabilitation services remotely to individuals in their own homes or other locations. With advancements in remote monitoring and Artificial Intelligence, automatic tele-rehabilitation systems that can measure joint angles, recognize exercises, and provide feedback based on movement analysis are being developed. Such platforms can offer valuable information to clinicians for improved care planning. However, with various methods and sensors being used, understanding their pros, cons, and performance is important. This paper reviews and compares the performance of recent vision-based, wearable, and pressure-sensing technologies used in lower limb tele-rehabilitation systems over the past 10years (from 2014 to 2023). We selected studies that were published in English and focused on joint angle estimation, activity recognition, and exercise assessment. Vision-based approaches were the most common, accounting for 42% of studies. Wearable technology followed at approximately 37%, and pressure-sensing technology appeared in 21% of studies. Identified gaps include a lack of uniformity in reported performance metrics and evaluation methods, a need for cross-subject validation, inadequate testing with patients and older adults, restricted sets of exercises evaluated, and a scarcity of comprehensive datasets on lower limb exercises, especially those involving movements while lying down.

Feature-Centric Approach for Learning-Based Prediction of Pavement Marking Retroreflectivity from Mobile LiDAR Data

Given the crucial importance of pavement marking retroreflectivity in ensuring visibility for road safety, this research investigates the correlation between pavement marking reflectivity and LiDAR data. Empirical data were collected from eight road sections using both a handheld retroreflectometer and a mobile LiDAR. The approach proposed focuses on extracting important features from pavement marking regions of the LiDAR point cloud. A comprehensive feature extraction and feature selection process was employed. In addition, a well-rounded selection of learning algorithms was evaluated. A rigorous hold-out evaluation was incorporated, ensuring that the reported performance metrics were robustly generalizable. The best performing model was able to achieve an R2 of 0.824 on unseen data. The findings of this study illuminate the potential for leveraging relatively inexpensive mobile LiDAR sensors in combination with machine learning techniques in conducting efficient pavement marking assessments, not only to detect completely degraded markings, but to accurately estimate retroreflective properties.

Data-driven automated classification algorithms for acute health conditions: applying PheNorm to COVID-19 disease.

Automated phenotyping algorithms can reduce development time and operator dependence compared to manually developed algorithms. One such approach, PheNorm, has performed well for identifying chronic health conditions, but its performance for acute conditions is largely unknown. Herein, we implement and evaluate PheNorm applied to symptomatic COVID-19 disease to investigate its potential feasibility for rapid phenotyping of acute health conditions. PheNorm is a general-purpose automated approach to creating computable phenotype algorithms based on natural language processing, machine learning, and (low cost) silver-standard training labels. We applied PheNorm to cohorts of potential COVID-19 patients from 2 institutions and used gold-standard manual chart review data to investigate the impact on performance of alternative feature engineering options and implementing externally trained models without local retraining. Models at each institution achieved AUC, sensitivity, and positive predictive value of 0.853, 0.879, 0.851 and 0.804, 0.976, and 0.885, respectively, at quantiles of model-predicted risk that maximize F1. We report performance metrics for all combinations of silver labels, feature engineering options, and models trained internally versus externally. Phenotyping algorithms developed using PheNorm performed well at both institutions. Performance varied with different silver-standard labels and feature engineering options. Models developed locally at one site also worked well when implemented externally at the other site. PheNorm models successfully identified an acute health condition, symptomatic COVID-19. The simplicity of the PheNorm approach allows it to be applied at multiple study sites with substantially reduced overhead compared to traditional approaches.

2D Covalent Organic Framework Membranes for Liquid-Phase Molecular Separations: State of the Field, Common Pitfalls, and Future Opportunities.

2D covalent organic frameworks (2D COFs) are attractive candidates for next-generation membranes due to their robust linkages and uniform, tunable pores. Many publications have claimed to achieve selective molecular transport through COF pores, but reported performance metrics for similar networks vary dramatically, and in several cases the reported experiments are inadequate to support such conclusions. These issues require a reevaluation of the literature. Published examples of 2D COF membranes for liquid-phase separations can be broadly divided into two categories, each with common performance characteristics: polycrystalline COF films (most >1µm thick) and weakly crystalline or amorphous films (most <500nm thick). Neither category has demonstrated consistent relationships between the designed COF pore structure and separation performance, suggesting that these imperfect materials do not sieve molecules through uniform pores. In this perspective, rigorous practices for evaluating COF membrane structures and separation performance are described, which will facilitate their development toward molecularly precise membranes capable of performing previously unrealized chemical separations. In the absence of this more rigorous standard of proof, reports of COF-based membranes should be treated with skepticism. As methods to control 2D polymerization improve, precise 2D polymer membranes may exhibit exquisite and energy efficient performance relevant for contemporary separation challenges.

The Potential of Machine Learning for Wind Speed and Direction Short-Term Forecasting: A Systematic Review

Wind forecasting, which is essential for numerous services and safety, has significantly improved in accuracy due to machine learning advancements. This study reviews 23 articles from 1983 to 2023 on machine learning for wind speed and direction nowcasting. The wind prediction ranged from 1 min to 1 week, with more articles at lower temporal resolutions. Most works employed neural networks, focusing recently on deep learning models. Among the reported performance metrics, the most prevalent were mean absolute error, mean squared error, and mean absolute percentage error. Considering these metrics, the mean performance of the examined works was 0.56 m/s, 1.10 m/s, and 6.72%, respectively. The results underscore the novel effectiveness of machine learning in predicting wind conditions using high-resolution time data and demonstrated that deep learning models surpassed traditional methods, improving the accuracy of wind speed and direction forecasts. Moreover, it was found that the inclusion of non-wind weather variables does not benefit the model’s overall performance. Further studies are recommended to predict both wind speed and direction using diverse spatial data points, and high-resolution data are recommended along with the usage of deep learning models.

Localization and Classification of Gastrointestinal Tract Disorders Using Explainable AI from Endoscopic Images

Globally, gastrointestinal (GI) tract diseases are on the rise. If left untreated, people may die from these diseases. Early discovery and categorization of these diseases can reduce the severity of the disease and save lives. Automated procedures are necessary, since manual detection and categorization are laborious, time-consuming, and prone to mistakes. In this work, we present an automated system for the localization and classification of GI diseases from endoscopic images with the help of an encoder–decoder-based model, XceptionNet, and explainable artificial intelligence (AI). Data augmentation is performed at the preprocessing stage, followed by segmentation using an encoder–decoder-based model. Later, contours are drawn around the diseased area based on segmented regions. Finally, classification is performed on segmented images by well-known classifiers, and results are generated for various train-to-test ratios for performance analysis. For segmentation, the proposed model achieved 82.08% dice, 90.30% mIOU, 94.35% precision, and 85.97% recall rate. The best performing classifier achieved 98.32% accuracy, 96.13% recall, and 99.68% precision using the softmax classifier. Comparison with the state-of-the-art techniques shows that the proposed model performed well on all the reported performance metrics. We explain this improvement in performance by utilizing heat maps with and without the proposed technique.

Review on Deep Learning Algorithms and Benchmark Datasets for Pairwise Global Point Cloud Registration

Point cloud registration is the process of aligning point clouds collected at different locations of the same scene, which transforms the data into a common coordinate system and forms an integrated dataset. It is a fundamental task before the application of point cloud data. Recent years have witnessed the rapid development of various deep-learning-based global registration methods to improve performance. Therefore, it is appropriate to carry out a comprehensive review of the more recent developments in this area. As the developments require access to large benchmark point cloud datasets, the most widely used public datasets are also reviewed. The performance of deep-learning-based registration methods on the benchmark datasets are summarized using the reported performance metrics in the literature. This forms part of a critical discussion of the strengths and weaknesses of the various methods considered in this article, which supports presentation of the main challenges currently faced in typical global point cloud registration tasks that use deep learning methods. Recommendations for potential future studies on this topic are provided.

An Elite Privilege: Top-Ranked Medical Schools Provide Fewer Comparative Performance Data on Their Students.

The objective of this study was to determine differences in the reporting of performance data on medical student performance evaluations (MSPEs) by medical school ranking. MSPEs from all US allopathic and osteopathic medical schools received by a single diagnostic radiology residency program during the 2021-2022 application cycle were retrospectively reviewed. Preclinical class and core clerkship grades were categorized as pass/fail or multitiered. Comparative summative assessments provided in the MSPEs were recorded. Medical schools were grouped by their US News & World Report rankings, and the proportion of reported performance metrics for each group was compared. Information from 95% of US allopathic medical schools (148 of 155) and 73% of osteopathic medical schools (27 of 37) was collected, on the basis of 1,046 applications received. For preclinical classes, multitiered grading was reported by no schools ranked in the top 10, 17% of schools ranked 11th to 50th, 52% of schools ranked 51st to 100th, and 59% of unranked schools (P < .001). For core clinical clerkships, multitiered grades were reported by 70% of the top 10 ranked schools, 90% of schools ranked 11th to 50th, 94% of those ranked 51st to 100th, and 94% of unranked schools (P= .0463). Comparative summative assessments were reported by none of the top 10 ranked schools, 56% of schools ranked 11th to 50th, 80% of those ranked 51th to 100th, and 81% of unranked schools (P < .001). Higher ranked medical schools are less likely to provide comparative assessment data on their MSPEs, which may disadvantage students from lower ranked medical schools.