Search

A crucial bottleneck in medical artificial intelligence (AI) is high-quality labeled medical datasets. In this paper, we test a large variety of wisdom of the crowd algorithms to label medical images that were initially classified by individuals recruited through an app-based platform. Individuals classified skin lesions from the International Skin Lesion Challenge 2018 into 7 different categories. There was a large dispersion in the geographical location, experience, training, and performance of the recruited individuals. We tested several wisdom of the crowd algorithms of varying complexity from a simple unweighted average to more complex Bayesian models that account for individual patterns of errors. Using a switchboard analysis, we observe that the best-performing algorithms rely on selecting top performers, weighting decisions by training accuracy, and take into account the task environment. These algorithms far exceed expert performance. We conclude by discussing the implications of these approaches for the development of medical AI.

Background: Classifications of AAFD/PCFD have evolved with an increased understanding of the pathology involved. A review of classification systems helps identify deficiencies and respective contributions to the evolution in understanding the classification of AAFD/PCFD. Methods: Using multiple electronic database searches (Medline, PubMed) and Google search, original papers classifying AAFD/PCFD were identified. Nine original papers were identified that met the inclusion criteria. Results: Johnson’s original classification and multiple variants provided a significant leap in understanding and communicating the pathology but remained tibialis posterior tendon-focused. Drawbacks of these classifications include the implication of causality, linearity of progression through stages, an oversimplification of stage 2 deformity, and a failure to understand that multiple tendons react, not just tibialis posterior. Later classifications, such as the PCFD classification, are deformity-centric. Early ligament laxity/instability in normal attitude feet and all stages of cavus feet can present with pain and instability with minor/no deformity. These may not be captured in deformity-based classifications. The authors developed the ‘Triple Classification’ (TC) understanding that primary pathology is a progressive ligament failure/laxity that presents as tendon reactivity, deformity, and painful impingement, variably manifested depending on starting foot morphology. In this classification, starting foot morphology is typed, ligament laxities are staged, and deformity is zoned. Conclusions: This review has used identified deficiencies within classification systems for AAFD/PCFD to delink ligament laxity, deformity, and foot type and develop the ‘Triple classification’. Advantages of the TC may include representing foot types with no deformity, defining complex secondary instabilities, delinking foot types, tendon reactivity/ligament instability, and deformity to represent these independently in a new classification system. Level of Evidence: Level V.

Abstract The COVID-19 pandemic has had a significant impact on students’ academic performance. The effects of the pandemic have varied among students, but some general trends have emerged. One of the primary challenges for students during the pandemic has been the disruption of their study habits. Students getting used to online learning routines might find it even more challenging to perform well in face to face learning. Therefore, assessing various potential risk factors associated with students low performance and its prediction is important for early intervention. As students’ performance data encompass diverse behaviors, standard machine learning methods find it hard to get useful insights for beneficial practical decision making and early interventions. Therefore, this research explores regularized ensemble learning methods for effectively analyzing students’ performance data and reaching valid conclusions. To this end, three pruning strategies are implemented for the random forest method. These methods are based on out-of-bag sampling, sub-sampling and sub-bagging. The pruning strategies discard trees that are adversely affected by the unusual patterns in the students data forming forests of accurate and diverse trees. The methods are illustrated on an example data collected from university students currently studying on campus in a face-to-face modality, who studied during the COVID-19 pandemic through online learning. The suggested methods outperform all the other methods considered in this paper for predicting students at the risk of academic failure. Moreover, various factors such as class attendance, students interaction, internet connectivity, pre-requisite course(s) during the restrictions, etc., are identified as the most significant features.

Abstract Alzheimer’s disease (AD), the predominant form of dementia, is a growing global challenge, emphasizing the urgent need for accurate and early diagnosis. Current clinical diagnoses rely on radiologist expert interpretation, which is prone to human error. Deep learning has thus far shown promise for early AD diagnosis. However, existing methods often overlook focal structural atrophy critical for enhanced understanding of the cerebral cortex neurodegeneration. This paper proposes a deep learning framework that includes a novel structure-focused neurodegeneration CNN architecture named SNeurodCNN and an image brightness enhancement preprocessor using gamma correction. The SNeurodCNN architecture takes as input the focal structural atrophy features resulting from segmentation of brain structures captured through magnetic resonance imaging (MRI). As a result, the architecture considers only necessary CNN components, which comprises of two downsampling convolutional blocks and two fully connected layers, for achieving the desired classification task, and utilises regularisation techniques to regularise learnable parameters. Leveraging mid-sagittal and para-sagittal brain image viewpoints from the Alzheimer’s disease neuroimaging initiative (ADNI) dataset, our framework demonstrated exceptional performance. The para-sagittal viewpoint achieved 97.8% accuracy, 97.0% specificity, and 98.5% sensitivity, while the mid-sagittal viewpoint offered deeper insights with 98.1% accuracy, 97.2% specificity, and 99.0% sensitivity. Model analysis revealed the ability of SNeurodCNN to capture the structural dynamics of mild cognitive impairment (MCI) and AD in the frontal lobe, occipital lobe, cerebellum, temporal, and parietal lobe, suggesting its potential as a brain structural change digi-biomarker for early AD diagnosis. This work can be reproduced using code we made available on GitHub.

Abstract As a preprocessing for machine learning and data mining, Feature Selection plays an important role. Feature selection aims to streamline high-dimensional data by eliminating irrelevant and redundant features, which reduces the potential curse of dimensionality of a given large dataset. When working with datasets containing many features, algorithms that aim to identify the most valuable features to improve dataset accuracy may encounter difficulties because of local optima. Many studies have been conducted to solve this problem. One of the solutions is to use meta-heuristic techniques. This paper presents a combination of the Differential evolution and the sailfish optimizer algorithms (DESFO) to tackle the feature selection problem. To assess the effectiveness of the proposed algorithm, a comparison between Differential Evolution, sailfish optimizer, and nine other modern algorithms, including different optimization algorithms, is presented. The evaluation used Random forest and key nearest neighbors as quality measures. The experimental results show that the proposed algorithm is a superior algorithm compared to others. It significantly impacts high classification accuracy, achieving 85.7% with the Random Forest classifier and 100% with the Key Nearest Neighbors classifier across 14 multi-scale benchmarks. According to fitness values, it gained 71% with the Random forest and 85.7% with the Key Nearest Neighbors classifiers.

Abstract A paper published in Orphanet Journal of Rare Diseases proposes a new classification of osteogenesis imperfecta (OI) based upon underlying pathological mechanisms. The proposed numbering of OI types conflicts with the currently used numbering and is likely to lead to confusion. In addition, classification of OI according to underlying pathogenic mechanisms is not novel.

Abstract Though COVID-19 is no longer a pandemic but rather an endemic, the epidemiological situation related to the SARS-CoV-2 virus is developing at an alarming rate, impacting every corner of the world. The rapid escalation of the coronavirus has led to the scientific community engagement, continually seeking solutions to ensure the comfort and safety of society. Understanding the joint impact of medical and non-medical interventions on COVID-19 spread is essential for making public health decisions that control the pandemic. This paper introduces two novel hybrid machine-learning ensembles that combine supervised and unsupervised learning for COVID-19 data classification and regression. The study utilizes publicly available COVID-19 outbreak and potential predictive features in the USA dataset, which provides information related to the outbreak of COVID-19 disease in the US, including data from each of 3142 US counties from the beginning of the epidemic (January 2020) until June 2021. The developed hybrid hierarchical classifiers outperform single classification algorithms. The best-achieved performance metrics for the classification task were Accuracy = 0.912, ROC-AUC = 0.916, and F1-score = 0.916. The proposed hybrid hierarchical ensemble combining both supervised and unsupervised learning allows us to increase the accuracy of the regression task by 11% in terms of MSE, 29% in terms of the area under the ROC, and 43% in terms of the MPP metric. Thus, using the proposed approach, it is possible to predict the number of COVID-19 cases and deaths based on demographic, geographic, climatic, traffic, public health, social-distancing-policy adherence, and political characteristics with sufficiently high accuracy. The study reveals that virus pressure is the most important feature in COVID-19 spread for classification and regression analysis. Five other significant features were identified to have the most influence on COVID-19 spread. The combined ensembling approach introduced in this study can help policymakers design prevention and control measures to avoid or minimize public health threats in the future.

Abstract Artificial Neural Networks (ANNs) have been used in a multitude of real-world applications given their predictive capabilities, and algorithms based on gradient descent, such as Backpropagation (BP) and variants, are usually considered for their optimisation. However, these algorithms have been shown to get stuck at local optima, and they require a cautious design of the architecture of the model. This paper proposes a novel memetic training method for simultaneously learning the ANNs structure and weights based on the Coral Reef Optimisation algorithms (CROs), a global-search metaheuristic based on corals’ biology and coral reef formation. Three versions based on the original CRO combined with a Local Search procedure are developed: (1) the basic one, called Memetic CRO; (2) a statistically guided version called Memetic SCRO (M-SCRO) that adjusts the algorithm parameters based on the population fitness; (3) and, finally, an improved Dynamic Statistically-driven version called Memetic Dynamic SCRO (M-DSCRO). M-DSCRO is designed with the idea of improving the M-SCRO version in the evolutionary process, evaluating whether the fitness distribution of the population of ANNs is normal to automatically decide the statistic to be used for assigning the algorithm parameters. Furthermore, all algorithms are adapted to the design of ANNs by means of the most suitable operators. The performance of the different algorithms is evaluated with 40 classification datasets, showing that the proposed M-DSCRO algorithm outperforms the other two versions on most of the datasets. In the final analysis, M-DSCRO is compared against four state-of-the-art methods, demonstrating its superior efficacy in terms of overall accuracy and minority class performance.

Background Glaucoma and diabetic retinopathy (DR) are the leading causes of irreversible retinal damage leading to blindness. Early detection of these diseases through regular screening is especially important to prevent progression. Retinal fundus imaging serves as the principal method for diagnosing glaucoma and DR. Consequently, automated detection of eye diseases represents a significant application of retinal image analysis. Compared with classical diagnostic techniques, image classification by convolutional neural networks (CNN) exhibits potential for effective eye disease detection. Methods This paper proposes the use of MATLAB – retrained AlexNet CNN for computerized eye diseases identification, particularly glaucoma and diabetic retinopathy, by employing retinal fundus images. The acquisition of the database was carried out through free access databases and access upon request. A transfer learning technique was employed to retrain the AlexNet CNN for non-disease (Non_D), glaucoma (Sus_G) and diabetic retinopathy (Sus_R) classification. Moreover, model benchmarking was conducted using ResNet50 and GoogLeNet architectures. A Grad-CAM analysis is also incorporated for each eye condition examined. Results Metrics for validation accuracy, false positives, false negatives, precision, and recall were reported. Validation accuracies for the NetTransfer (I-V) and netAlexNet ranged from 89.7% to 94.3%, demonstrating varied effectiveness in identifying Non_D, Sus_G, and Sus_R categories, with netAlexNet achieving a 93.2% accuracy in the benchmarking of models against netResNet50 at 93.8% and netGoogLeNet at 90.4%. Conclusions This study demonstrates the efficacy of using a MATLAB-retrained AlexNet CNN for detecting glaucoma and diabetic retinopathy. It emphasizes the need for automated early detection tools, proposing CNNs as accessible solutions without replacing existing technologies.

Pressure ulcers carry a significant risk in clinical practice. This paper proposes a practical and interpretable approach to estimate the risk levels of pressure ulcers using decision tree models. In order to address the common problem of imbalanced learning in nursing classification datasets, various oversampling configurations are analyzed to improve the data quality prior to modeling. The decision trees built are based on three easily identifiable and clinically relevant pressure ulcer risk indicators: mobility, activity, and skin moisture. Additionally, this research introduces a novel tabular visualization method to enhance the usability of the decision trees in clinical practice. Thus, the primary aim of this approach is to provide nursing professionals with valuable insights for assessing the potential risk levels of pressure ulcers, which could support their decision-making and allow, for example, the application of suitable preventive measures tailored to each patient’s requirements. The interpretability of the models proposed and their performance, evaluated through stratified cross-validation, make them a helpful tool for nursing care in estimating the pressure ulcer risk level.