Search

Objectives: This study was designed to investigate clinical differences between pediatric patients who presented with chest pain, tachycardia, and/or tachypnea who subsequently were or were not diagnosed with myocarditis. The results were used to develop a decision tree to aid in rapid diagnosis of pediatric myocarditis., Methods: A retrospective case-control study was performed using the electronic medical records of children aged 0 to 18 years between the years 2003 and 2020 with a complaint of chest pain, tachycardia, and/or tachypnea. Patients included in the study were those diagnosed with myocarditis and those with suspected myocarditis, which was ultimately ruled out. Demographic and clinical differences between the research groups were analyzed. A decision tree was rendered using the rpart (Recursive Partitioning and Regression Trees) package., Results: Four thousand one hundred twenty-five patients were screened for eligibility. Seventy-three myocarditis patients and 292 nonmyocarditis patients were included. Compared with the control group, the study group was found to have a higher mean respiratory rate (37 ± 23 vs 23 ± 7 breaths per minute) and mean heart rate (121 ± 44 vs 97 ± 25 beats per minute) and lower mean systolic and diastolic blood pressure (102 ± 27/56 ± 17 mm Hg vs 114 ± 14/67 ± 10 mm Hg). The mean white blood cell count was greater in the case group (13 ± 6 vs 10 ± 5 × 10 3 /μL). A decision tree was rendered using simple demographic and clinical variables. The accuracy of the algorithm was 85.2%, with 100% accuracy in patients aged 0 to 2.5 years and 69% in patients aged 2.5 to 18 years., Conclusion: The clinical and laboratory characteristics described in this study were similar to what is described in the literature. The decision tree may aid in the diagnosis of myocarditis in patients 2.5 years and younger. In the population aged 2.5 to 18 years, the decision tree did not constitute an adequate tool for detecting myocarditis., Competing Interests: Disclosure: The authors declare no conflict of interest., (Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.)

Purpose: It has been reported that the estimate of ultrasound attenuation coefficient (AC) is affected by depth of measurement, with linear decrease of values with depth. It is unknown whether backscatter coefficient (BSC) has similar behavior., Methods: This retrospective study was performed with Sequoia US system equipped with ultrasound derived fat fraction (UDFF) algorithm (Siemens Healthineers, Issaquah, WA, USA) that combines BSC with AC. UDFF was obtained positioning upper edge of the region of interest at 1.5,2,3,4,5 cm below liver capsule. BSC data were extracted from UDFF offline. A fractional polynomial regression, which selects the best model considering the polynomial development of the variables of interest, was used. Covariates included were age, sex, skin-to-liver-capsule distance, stiffness. Distance was included as linear factor or with a power ranging from - 2 to 3, and the best fitting model was chosen according to partial F test. Body mass index (BMI) was not included because of collinearity with skin-to-liver capsule distance., Results: 104 individuals (56 females; age: 57.9 ± 13.0 years; BMI: 29.0 ± 6.5 kg/m 2 ; skin-to-liver-capsule distance: 2.3 ± 0.7 cm; liver stiffness: 7.5 ± 5.5 kiloPascal) were studied. Best fitting model for BSC included a combination of depth as linear factor and square root. BSC showed a decrease of - 13.98 dB/cm-steradian for each logarithmic increase of 1 cm depth (coefficient: - 13.98; 95% CI: - 21.016; - 5.379; p = .001). Skin-to-liver-capsule distance and stiffness also were independent predictors of BSC., Conclusions: The estimation of the BSC in the liver exhibits a depth dependence that significantly affects results. A standardized acquisition protocol is needed to compare results and reliably assess changes over time., (© 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Purpose: MR-STAT is a relatively new multiparametric quantitative MRI technique in which quantitative paramater maps are obtained by solving a large-scale nonlinear optimization problem. Managing reconstruction times is one of the main challenges of MR-STAT. In this work we leverage GPU hardware to reduce MR-STAT reconstruction times. A highly optimized, GPU-compatible Bloch simulation toolbox is developed as part of this work that can be utilized for other quantitative MRI techniques as well., Methods: The Julia programming language was used to develop a flexible yet highly performant and GPU-compatible Bloch simulation toolbox called BlochSimulators.jl. The runtime performance of the toolbox is benchmarked against other Bloch simulation toolboxes. Furthermore, a (partially matrix-free) modification of a previously presented (matrix-free) MR-STAT reconstruction algorithm is proposed and implemented using the Julia language on GPU hardware. The proposed algorithm is combined with BlochSimulators.jl and the resulting MR-STAT reconstruction times on GPU hardware are compared to previously presented MR-STAT reconstruction times., Results: The BlochSimulators.jl package demonstrates superior runtime performance on both CPU and GPU hardware when compared to other existing Bloch simulation toolboxes. The GPU-accelerated partially matrix-free MR-STAT reconstruction algorithm, which relies on BlochSimulators.jl, allows for reconstructions of 68 seconds per two-dimensional (2D slice)., Conclusion: By combining the proposed Bloch simulation toolbox and the partially matrix-free reconstruction algorithm, 2D MR-STAT reconstructions can be performed in the order of one minute on a modern GPU card. The Bloch simulation toolbox can be utilized for other quantitative MRI techniques as well, for example for online dictionary generation for MR Fingerprinting., (© 2024 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.)

Cox models with time-dependent coefficients and covariates are widely used in survival analysis. In high-dimensional settings, sparse regularization techniques are employed for variable selection, but existing methods for time-dependent Cox models lack flexibility in enforcing specific sparsity patterns (ie, covariate structures). We propose a flexible framework for variable selection in time-dependent Cox models, accommodating complex selection rules. Our method can adapt to arbitrary grouping structures, including interaction selection, temporal, spatial, tree, and directed acyclic graph structures. It achieves accurate estimation with low false alarm rates. We develop the sox package, implementing a network flow algorithm for efficiently solving models with complex covariate structures. sox offers a user-friendly interface for specifying grouping structures and delivers fast computation. Through examples, including a case study on identifying predictors of time to all-cause death in atrial fibrillation patients, we demonstrate the practical application of our method with specific selection rules., (© 2024 John Wiley & Sons Ltd.)

Estimating causal effects from large experimental and observational data has become increasingly prevalent in both industry and research. The bootstrap is an intuitive and powerful technique used to construct standard errors and confidence intervals of estimators. Its application however can be prohibitively demanding in settings involving large data. In addition, modern causal inference estimators based on machine learning and optimization techniques exacerbate the computational burden of the bootstrap. The bag of little bootstraps has been proposed in non-causal settings for large data but has not yet been applied to evaluate the properties of estimators of causal effects. In this article, we introduce a new bootstrap algorithm called causal bag of little bootstraps for causal inference with large data. The new algorithm significantly improves the computational efficiency of the traditional bootstrap while providing consistent estimates and desirable confidence interval coverage. We describe its properties, provide practical considerations, and evaluate the performance of the proposed algorithm in terms of bias, coverage of the true 95% confidence intervals, and computational time in a simulation study. We apply it in the evaluation of the effect of hormone therapy on the average time to coronary heart disease using a large observational data set from the Women's Health Initiative., (© 2024 John Wiley & Sons Ltd.)

The U.S. Food and Drug Administration (FDA) has launched Project Optimus to shift dose selection from the maximum tolerated dose (MTD) to the dose that produces the optimal risk-benefit tradeoff. One approach highlighted in the FDA's guidance involves conducting a randomized phase II trial following the completion of a phase I trial, where multiple doses (typically including the MTD and one or two doses lower than the MTD) are compared to identify the optimal dose that maximizes the benefit-risk tradeoff. This article focuses on the design of such a multiple-dose randomized trial, specifically the determination of the sample size. We generalized the standard definitions of type I error and power to accommodate the unique characteristics of dose optimization and derived a decision rule along with an algorithm to determine the optimal sample size. The resulting design is referred to as MERIT (Multiple-dosE RandomIzed Trial design for dose optimization based on toxicity and efficacy). Simulation studies demonstrate that MERIT has desirable operating characteristics, and a sample size between 20 and 40 per dosage arm often offers reasonable power and type I errors to ensure patient safety and benefit. To facilitate the implementation of the MERIT design, we provide software, available at https://www.trialdesign.org., (© 2024 John Wiley & Sons Ltd.)

➤ No single test has demonstrated absolute accuracy for the diagnosis of periprosthetic joint infection (PJI).➤ Physicians rely on a combination of serological tests, synovial markers, and clinical findings plus clinical judgment to help to guide preoperative decision-making.➤ Several organizations have proposed criteria for the diagnosis of hip or knee PJI on which we now rely.➤ Given that shoulder arthroplasty has only recently become popular, it is possible that a shoulder-specific definition of PJI will be introduced in the coming years.➤ Although a number of serum and synovial markers have demonstrated high accuracy for the diagnosis of PJI of the hip and knee, further research is needed in order to identify markers that may be more suitable for the diagnosis of shoulder PJI and for the potential development and identification of specific serological tests as screening tools for PJI., Competing Interests: Disclosure: The Disclosure of Potential Conflicts of Interest forms are provided with the online version of the article ( http://links.lww.com/JBJS/I24 )., (Copyright © 2024 by The Journal of Bone and Joint Surgery, Incorporated.)

Contemporary pose estimation methods enable precise measurements of behavior via supervised deep learning with hand-labeled video frames. Although effective in many cases, the supervised approach requires extensive labeling and often produces outputs that are unreliable for downstream analyses. Here, we introduce 'Lightning Pose', an efficient pose estimation package with three algorithmic contributions. First, in addition to training on a few labeled video frames, we use many unlabeled videos and penalize the network whenever its predictions violate motion continuity, multiple-view geometry and posture plausibility (semi-supervised learning). Second, we introduce a network architecture that resolves occlusions by predicting pose on any given frame using surrounding unlabeled frames. Third, we refine the pose predictions post hoc by combining ensembling and Kalman smoothing. Together, these components render pose trajectories more accurate and scientifically usable. We released a cloud application that allows users to label data, train networks and process new videos directly from the browser., (© 2024. The Author(s), under exclusive licence to Springer Nature America, Inc.)

Objective: The Visiopharm artificial intelligence (AI) algorithm for oestrogen receptor (ER) immunohistochemistry (IHC) in whole slide images (WSIs) has been successfully validated in surgical pathology. This study aimed to assess its efficacy in cytology specimens., Methods: The study cohort comprised 105 consecutive cytology specimens with metastatic breast carcinoma. ER IHC WSIs were seamlessly integrated into the Visiopharm platform from the Image Management System (IMS) during our routine digital workflow, and an AI algorithm was employed for analysis. ER AI scores were compared with pathologists' manual consensus scores. Optimization steps were implemented and evaluated to reduce discordance., Results: The overall concordance between pathologists' scores and AI scores was excellent (99/105, 94.3%). Six cases exhibited discordant results, including two false-negative (FN) cases due to abundant histiocytes incorrectly counted as negatively stained tumour cells by AI, two FN cases owing to weak staining, and two false-positive (FP) cases where pigmented macrophages were erroneously counted as positively stained tumour cells by AI. The Pearson correlation coefficient of ER-positive percentages between pathologists' and AI scores was 0.8483. Optimization steps, such as lowering the cut-off threshold and additional training using higher input magnification, significantly improved accuracy., Conclusions: The automated ER AI algorithm demonstrated excellent concordance with pathologists' assessments and accurately differentiated ER-positive from ER-negative metastatic breast carcinoma cytology cases. However, precision in identifying tumour cells in cytology specimens requires further enhancement., (© 2024 John Wiley & Sons Ltd.)

Purpose: Clinical benefits result from electronic patient-reported outcome (ePRO) systems that enable remote symptom monitoring. Although clinically useful, real-time alert notifications for severe or worsening symptoms can overburden nurses. Thus, we aimed to algorithmically identify likely non-urgent alerts that could be suppressed., Methods: We evaluated alerts from the PRO-TECT trial (Alliance AFT-39) in which oncology practices implemented remote symptom monitoring. Patients completed weekly at-home ePRO symptom surveys, and nurses received real-time alert notifications for severe or worsening symptoms. During parts of the trial, patients and nurses each indicated whether alerts were urgent or could wait until the next visit. We developed an algorithm for suppressing alerts based on patient assessment of urgency and model-based predictions of nurse assessment of urgency., Results: 593 patients participated (median age = 64 years, 61% female, 80% white, 10% reported never using computers/tablets/smartphones). Patients completed 91% of expected weekly surveys. 34% of surveys generated an alert, and 59% of alerts prompted immediate nurse actions. Patients considered 10% of alerts urgent. Of the remaining cases, nurses considered alerts urgent more often when patients reported any worsening symptom compared to the prior week (33% of alerts with versus 26% without any worsening symptom, p = 0.009). The algorithm identified 38% of alerts as likely non-urgent that could be suppressed with acceptable discrimination (sensitivity = 80%, 95% CI [76%, 84%]; specificity = 52%, 95% CI [49%, 55%])., Conclusion: An algorithm can identify remote symptom monitoring alerts likely to be considered non-urgent by nurses, and may assist in fostering nurse acceptance and implementation feasibility of ePRO systems., (© 2024. The Author(s), under exclusive licence to Springer Nature Switzerland AG.)

Background: Quantification of metabolites concentrations in institutional unit (IU) is important for inter-subject and long-term comparisons in the applications of magnetic resonance spectroscopy (MRS). Recently, deep learning (DL) algorithms have found a variety of applications on the process of MRS data. A quantification strategy compatible to DL base MRS spectral processing method is, therefore, useful., Materials and Methods: This study aims to investigate whether metabolite concentrations quantified using a convolutional neural network (CNN) based method, coupled with a scaling procedure that normalizes spectral signals for CNN input and linear regression, can effectively reflect variations in metabolite concentrations in IU across different brain regions with varying signal-to-noise ratios (SNR) and linewidths (LW). An error index based on standard error (SE) is proposed to indicate the confidence levels associated with metabolite predictions. In vivo MRS spectra were acquired from three brain regions of 43 subjects using a 3T system., Results: The metabolite concentrations in IU of five major metabolites, quantified using CNN and LCModel, exhibit similar ranges with Pearson's correlation coefficients ranging from 0.24 to 0.78. The SE of the metabolites shows a positive correlation with Cramer-Rao lower bound (CRLB) (r=0.46) and  absolute CRLB (r=0.81), calculated by multiplying CRLBs with the quantified metabolite content., Conclusion: In conclusion, the CNN based method with the proposed scaling procedures can be employed to quantify in vivo MRS spectra and derive metabolites concentrations in IU. The SE can be used as error index, indicating predicted uncertainties for metabolites and sharing information similar to the absolute CRLB., (© 2023. The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB).)

One of the most widely used measures of scientific impact is the number of citations. However, due to its heavy-tailed distribution, citations are fundamentally difficult to predict but can be improved. This study was aimed at investigating the factors and parts influencing the citation number of a scientific paper in the otology field. Therefore, this work proposes a new solution that utilizes machine learning and natural language processing to process English text and provides a paper citation as the predicted results. Different algorithms are implemented in this solution, such as linear regression, boosted decision tree, decision forest, and neural networks. The application of neural network regression revealed that papers' abstracts have more influence on the citation numbers of otological articles. This new solution has been developed in visual programming using Microsoft Azure machine learning at the back end and Programming Without Coding Technology at the front end. We recommend using machine learning models to improve the abstracts of research articles to get more citations. [ABSTRACT FROM AUTHOR]

The concept, development and assessment of computational thinking have increasingly become the focus of research in recent years. Most of this type of research focuses on older children or adults. Preschool age is a sensitive period when many skills develop intensively, so the development of computational thinking skills can already begin at this age. The increased interest in this field requires the development of appropriate assessments. Currently, there are only a limited number of computational thinking assessments for preschool children. Based on this shortcoming, an assessment tool, named AlgoPaint Unplugged Computational Thinking Assessment for Preschool, was created addressed for 4-7 years old children. It is a paper-pencil-based test, which examines the following computational thinking domains: algorithms and debugging. Regarding computational concepts, simple instructions, simple and nested loops, and conditionals are included in the test. For the preliminary testing, AlgoPaint test was applied by 11 preschool teachers with 56 preschool age children. The test was also evaluated by 6 experts in algorithmic thinking working at universities. Based on the feedback given by the teachers and the experts, and the results of the children, AlgoPaint Computational Thinking Test was revised and completed. The revised version of the test is included in the appendix of the paper.

Firstly, this paper analyzes the role of AI in the reading management of English language and literature, establishes the implicit knowledge base of neural network, designs the auxiliary reading system for learning English language and literature, and optimizes the English language and literature management model of AI. The experimental results show that its reading efficiency is increased by 0.48%, and the performance of the credibility model is improved by 0.53% compared with the original system, which greatly optimizes the running time of the system. To some extent, it helps users to manage their time in English language and literature reading, and greatly improves users' reading efficiency and quality. Based on this advantage of AI algorithm, this paper introduces that the algorithm optimizes the reading management model and the training process of neural grid, and constructs a model of English language and literature assisted reading system based on AI. The system can better meet the needs of users in English language and literature reading management.

In this paper, we continue describing the project and the experimentation of "Ricerca Operativa Applicazioni Reali" (ROAR; in English, Real Applications of Operations Research), a three-year project for higher secondary schools, introduced. ROAR is composed of three teaching units, addressed to Grades 10, 11, and 12, respectively, having the main aim to improve students' interest, motivation, and skills related to Science, Technology, Engineering, and Mathematics disciplines by integrating mathematics and computer science through operations research. In a previous paper, we reported on the design and implementation of the first unit, started in Spring 2021 at the scientific high school IIS Antonietti in Iseo (Brescia, Italy), in a Grade-10 class. Here, we focus on the second unit, carried out in Winter/Spring 2022 with the same students, now in a Grade-11 class. In particular, we describe objectives, prerequisites, topics and methods, the organization of the lectures, digital technologies used, and a challenging final project. Moreover, we analyze the feedback from students and teachers involved in the experimentation.

The innovation capability largely determines the initiative for future development of a region. Higher school is the main position for training innovative talents. Accurate and comprehensive assessment of innovation cultivation capability is an important basis of higher schools for continuous improvement. Thus, this paper focuses on assessing innovative talent cultivation capability. First, by CIPP model (Context, Input, Process and Product Evaluation), an assessment indicator system is built, consisting of 89 indicators in 21 categories. Then, based on indicator characteristics, this paper uses public data statistics, database retrieving, student survey, teacher survey, support personnel and expert investigation, to collect indicator values. After this, by a powerful machine learning algorithm, gradient Boosting regression tree, a capability assessment model is established. And based on collected data, established model is compared with several regression models in innovative talent cultivation capability assessing. Results confirm the performance superiority of our solution.

Systematic reviews and meta-analyses are crucial for advancing research, yet they are time-consuming and resource-demanding. Although machine learning and natural language processing algorithms may reduce this time and these resources, their performance has not been tested in education and educational psychology, and there is a lack of clear information on when researchers should stop the reviewing process. In this study, we conducted a retrospective screening simulation using 27 systematic reviews in education and educational psychology. We evaluated the sensitivity, specificity, and estimated time savings of several learning algorithms and heuristic stopping criteria. The results showed, on average, a 58% (SD = 19%) reduction in the screening workload of irrelevant records when using learning algorithms for abstract screening and an estimated time savings of 1.66 days (SD = 1.80). The learning algorithm random forests with sentence bidirectional encoder representations from transformers outperformed other algorithms. This finding emphasizes the importance of incorporating semantic and contextual information during feature extraction and modeling in the screening process. Furthermore, we found that 95% of all relevant abstracts within a given dataset can be retrieved using heuristic stopping rules. Specifically, an approach that stops the screening process after classifying 20% of records and consecutively classifying 5% of irrelevant papers yielded the most significant gains in terms of specificity (M = 42%, SD = 28%). However, the performance of the heuristic stopping criteria depended on the learning algorithm used and the length and proportion of relevant papers in an abstract collection. Our study provides empirical evidence on the performance of machine learning screening algorithms for abstract screening in systematic reviews in education and educational psychology.

Purpose: This paper aims to center the experiences of three cohorts (n = 40) of Black high school students who participated in a critical race technology course that exposed anti-blackness as the organizing logic and default setting of digital and artificially intelligent technology. This paper centers the voices, experiences and technological innovations of the students, and in doing so, introduces a new type of digital literacy: critical race algorithmic literacy. Design/methodology/approach: Data for this study include student interviews (called "talk backs"), journal reflections and final technology presentations. Findings: Broadly, the data suggests that critical race algorithmic literacies prepare Black students to critically read the algorithmic word (e.g. data, code, machine learning models, etc.) so that they can not only resist and survive, but also "rebuild" and "reimagine" the algorithmic world. Originality/value: While critical race media literacy draws upon critical race theory in education - a theorization of race, and a critique of white supremacy and multiculturalism in schools - critical race algorithmic literacy is rooted in critical race technology theory, which is a theorization of blackness as a technology and a critique of algorithmic anti-blackness as the organizing logic of schools and AI systems.

This paper proposes an online learning platform learner DM method based on the improved fuzzy C clustering (FCM) algorithm, constructs a learner feature database, and combines clustering analysis and SPSS statistical methods to statistically summarize the big data of law, thus improving the deficiencies of static and absolute classification of students in the student model. In the experiment paper, the improved algorithm is implemented and the experimental data is analyzed. The results show that the learner behavior feature extraction model in this paper has fewer errors and higher recall rate. Compared with the traditional CF algorithm, the error rate is reduced by 19.64% and the recall rate is increased by 22.85%. This study provides better targeted teaching programs and case resources for legal case teaching and promotes the innovation of legal case teaching mode.

The application of computer technology has revolutionized and promoted the traditional mode of piano teaching. Nowadays, many companies and institutions have begun to apply computer technology to online piano teaching. This paper analyzes the difficulties faced by students in piano teaching and the development of piano assistant practice and summarizes the demands of parents, teachers, students, and principals for online piano teaching system. Based on this, this paper designs and implements an online piano teaching system without special hardware. This system improves the existing maximum logarithm MPa algorithm and improves the detection performance while keeping the complexity low. Combined with the special structure of parallel projection, a generalized automaton model of hybrid system is proposed, and five elements are used to describe the continuous and discrete behaviors in the hybrid subsystem. It not only keeps the advantage of low complexity of the original Max log MPa algorithm, but also obtains better detection performance.

Modern e-learning system is a representative service form in innovative service industry. This paper designs a personalized service domain system, optimizes various parameters and can be applied to different education quality evaluation, and proposes a decision tree recommendation algorithm. Information gain is carried out through many existing principles of improved decision tree algorithm, and the information gain of the algorithm determines the inheritance of information. The process of modern e-learning system is based on personalized teaching and humanized intelligent interaction. This paper theoretically analyzes the improvement performance of the existing e-learning system in teaching quality evaluation and shows a good classification effect. This model provides reference materials for the expansion of education and teaching and provides a feasible practical model for personalized teaching in online schools. The authors provide good educational conditions and environment for students and cultivate all-around talents for the society.

As the cradle of cultivating talents, universities are facing great opportunities and challenges in their education. Among them, IPE (ideological and political education), as an important foundation for the future growth of university students, is of great significance. This paper discusses the relationship between IPE and psychological fitness education in university teaching. This paper expounds the necessity and feasibility of playing the role of psychological fitness education in IPECU (ideological and political education in colleges and universities). Based on this, this paper gives the strategy of infiltrating psychological fitness education into IPE. This paper combines NN (neural network) method to construct an assessment model of IPE quality. In this paper, MATLAB is used for simulation and comparative analysis. The final experiment shows that the RMSE of this algorithm is 0.512, MAE is 1.089, and the accuracy of the algorithm is 0.958.

This study explores the transformative potential of Generative AI (GenAI) and ChatBots in educational interaction, communication, and the broader implications of human-GenAI collaboration. By examining the related literature through data mining and analytical methods, the paper identifies three main research themes: the revolutionary role of GenAI-powered ChatBots in educational interactions, their capability to enrich social learning, and their dual role as both support and assistance within educational settings. This research further highlights the impact of human-GenAI interaction in education from social, psychological, and cultural perspectives, focusing on social presence as a fundamental component of the teaching and learning process. It discusses the integration of GenAI and ChatBots into education and considers whether this marks the dawn of an algorithmic renaissance that elevates educational experiences or an apocalypse that threatens the very essence of human learning and interaction.

Predictive student models are increasingly used in learning environments due to their ability to enhance educational outcomes and support stakeholders in making informed decisions. However, predictive models can be biased and produce unfair outcomes, leading to potential discrimination against certain individuals and harmful long-term implications. This has prompted research on fairness metrics meant to capture and quantify such biases. Nonetheless, current metrics primarily focus on predictive performance comparisons between groups, without considering the behavior of the models or the severity of the biases in the outcomes. To address this gap, we proposed a novel metric in a previous work (Verger et al., 2023) named "Model Absolute Density Distance" (MADD), measuring algorithmic unfairness as the difference of the probability distributions of the model's outcomes. In this paper, we extended our previous work with two major additions. Firstly, we provided theoretical and practical considerations on a hyperparameter of MADD, named "bandwidth," useful for optimal measurement of fairness with this metric. Secondly, we demonstrated how MADD can be used not only to measure unfairness but also to mitigate it through postprocessing of the model's outcomes while preserving its accuracy. We experimented with our approach on the same task of predicting student success in online courses as our previous work, and obtained successful results. To facilitate replication and future usages of MADD in different contexts, we developed an open-source Python package called maddlib (https://pypi.org/project/maddlib/). Altogether, our work contributes to advancing the research on fair student models in education.

In this paper, we present an extended evaluation of a course recommender system designed to support students who struggle in the first semesters of their studies and are at risk of dropping out. The system, which was developed in earlier work using a student-centered design, is based on the explainable k-nearest neighbor algorithm and recommends a set of courses that have been passed by the majority of successful neighbors, that is, students who graduated from the study program. In terms of the number of recommended courses, we found a discrepancy between the number of courses that struggling students are recommended to take and the actual number of courses they take. This indicates that there may be an alternative path that these students could consider. However, the recommended courses align well with the courses taken by students who successfully graduated. This suggests that even students who are performing well could still benefit from the course recommender system designed for at-risk students. In the present work, we investigate a second type of success--a specific minimum number of courses passed--and compare the results with our first approach from previous work. With the second type, the information about success might be already available after one semester instead of after graduation which allows faster growth of the database and faster response to curricular changes. The evaluation of three different study programs in terms of dropout risk reduction and recommendation quality suggests that course recommendations based on students passing at least three courses in the following semester can be an alternative to guide students on a successful path.

Background: Image registration technology has become an important medical image preprocessing step with the wide application of computer-aided diagnosis technology in various medical image analysis tasks., Purpose: We propose a multiscale feature fusion registration based on deep learning to achieve the accurate registration and fusion of head magnetic resonance imaging (MRI) and solve the problem that general registration methods cannot handle the complex spatial information and position information of head MRI., Methods: Our proposed multiscale feature fusion registration network consists of three sequentially trained modules. The first is an affine registration module that implements affine transformation; the second is to realize non-rigid transformation, a deformable registration module composed of top-down and bottom-up feature fusion subnetworks in parallel; and the third is a deformable registration module that also realizes non-rigid transformation and is composed of two feature fusion subnetworks in series. The network decomposes the deformation field of large displacement into multiple deformation fields of small displacement by multiscale registration and registration, which reduces the difficulty of registration. Moreover, multiscale information in head MRI is learned in a targeted manner, which improves the registration accuracy, by connecting the two feature fusion subnetworks., Results: We used 29 3D head MRIs for training and seven volumes for testing and calculated the values of the registration evaluation metrics for the new algorithm to register anterior and posterior lateral pterygoid muscles. The Dice similarity coefficient was 0.745 ± 0.021, the Hausdorff distance was 3.441 ± 0.935 mm, the Average surface distance was 0.738 ± 0.098 mm, and the Standard deviation of the Jacobian matrix was 0.425 ± 0.043. Our new algorithm achieved a higher registration accuracy compared with state-of-the-art registration methods., Conclusions: Our proposed multiscale feature fusion registration network can realize end-to-end deformable registration of 3D head MRI, which can effectively cope with the characteristics of large deformation displacement and the rich details of head images and provide reliable technical support for the diagnosis and analysis of head diseases., (© 2023 American Association of Physicists in Medicine.)

Background: Recent developments in alpha and beta emitting radionuclide therapy highlight the importance of developing efficient methods for patient-specific dosimetry. Traditional tabulated methods such as Medical Internal Radiation Dose (MIRD) estimate the dose at the organ level while more recent numerical methods based on Monte Carlo (MC) simulations are able to calculate dose at the voxel level. A precalculated MC (PMC) approach was developed in this work as an alternative to time-consuming fully simulated MC. Once the spatial distribution of alpha and beta emitters is determined using imaging and/or numerical methods, the PMC code can be used to achieve an accurate voxelized 3D distribution of the deposited energy without relying on full MC calculations., Purpose: To implement the PMC method to calculate energy deposited by alpha and beta particles emitted from the Ra-224 decay chain., Methods: The GEANT4 (version 10.7) MC toolkit was used to generate databases of precalculated tracks to be integrated in the PMC code as well as to benchmark its output. In this regard, energy spectra of alpha and beta particles emitted by the Ra-224 decay chain were generated using GAMOS (version 6.2.0) and imported into GEANT4 macro files. Either alpha or beta emitting sources were defined at the center of a homogeneous phantom filled with various materials such as soft tissue, bone, and lung where particles were emitted either mono-directionally (for database generation) or isotropically (for benchmarking). Two heterogeneous phantoms were used to demonstrate PMC code compatibility with boundary crossing events. Each precalculated database was generated step-by-step by storing particle track information from GEANT4 simulations followed by its integration in a PMC code developed in MATLAB. For a user-defined number of histories, one of the tracks in a given database was selected randomly and rotated randomly to reflect an isotropic emission. Afterward, deposited energy was divided between voxels based on step length in each voxel using a ray-tracing approach. The radial distribution of deposited energy was benchmarked against fully simulated MC calculations using GEANT4. The effect of the GEANT4 parameter StepMax on the accuracy and speed of the code was also investigated., Results: In the case of alpha decay, primary alpha particles show the highest contribution (>99%) in deposited energy compared to their secondary particles. In most cases, protons act as the main secondary particles in the deposition of energy. However, for a lung phantom, using a range cutoff parameter of 10 µm on primary alpha particles yields a higher contribution of secondary electrons than protons. Differences between deposited energy calculated by PMC and fully simulated MC are within 2% for all alpha and beta emitters in homogeneous and heterogeneous phantoms. Additionally, statistical uncertainties are less than 1% for voxels with doses higher than 5% of the maximum dose. Moreover, optimization of the parameter StepMax is necessary to achieve the best tradeoff between code accuracy and speed., Conclusions: The PMC code shows good performance for dose calculations deposited by alpha and beta emitters. As a stand-alone algorithm, it is suitable to be integrated into clinical treatment planning systems., (© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Recently, artificial intelligence (AI) techniques have been increasingly used to overcome the challenges in drug discovery. Although traditional AI techniques generally have high accuracy rates, there may be difficulties in explaining the decision process and patterns. This can create difficulties in understanding and making sense of the outputs of algorithms used in drug discovery. Therefore, using explainable AI (XAI) techniques, the causes and consequences of the decision process are better understood. This can help further improve the drug discovery process and make the right decisions. To address this issue, Explainable Artificial Intelligence (XAI) emerged as a process and method that securely captures the results and outputs of machine learning (ML) and deep learning (DL) algorithms. Using techniques such as SHAP (SHApley Additive ExPlanations) and LIME (Locally Interpretable Model-Independent Explanations) has made the drug targeting phase clearer and more understandable. XAI methods are expected to reduce time and cost in future computational drug discovery studies. This review provides a comprehensive overview of XAI-based drug discovery and development prediction. XAI mechanisms to increase confidence in AI and modeling methods. The limitations and future directions of XAI in drug discovery are also discussed., (© 2023 John Wiley & Sons Ltd.)

The so-coined fourth paradigm in science has reached the sensing area, with the use of machine learning (ML) toward data-driven improvements in sensitivity, reproducibility, and accuracy, along with the determination of multiple targets from a single measurement using multi-output regression models. Particularly, the use of supervised ML models trained on large data sets produced by electrical and electrochemical bio/sensors has emerged as an impacting trend in the literature by allowing accurate analyses even in the presence of usual issues such as electrode fouling, poor signal-to-noise ratio, chemical interferences, and matrix effects. In this trend article, apart from an outlook for the coming years, we present examples from the literature that demonstrate how helpful ML algorithms can be for dispensing the adoption of experimental methods to address the aforesaid interfering issues, ultimately contributing to translate testing technologies into on-site, practical, and daily applications., (© 2023. Springer-Verlag GmbH Germany, part of Springer Nature.)

Objective: To describe the development of a platform for image collection and annotation that resulted in a multi-sourced international image dataset of oral lesions to facilitate the development of automated lesion classification algorithms., Materials and Methods: We developed a web-interface, hosted on a web server to collect oral lesions images from international partners. Further, we developed a customised annotation tool, also a web-interface for systematic annotation of images to build a rich clinically labelled dataset. We evaluated the sensitivities comparing referral decisions through the annotation process with the clinical diagnosis of the lesions., Results: The image repository hosts 2474 images of oral lesions consisting of oral cancer, oral potentially malignant disorders and other oral lesions that were collected through MeMoSA ® UPLOAD. Eight-hundred images were annotated by seven oral medicine specialists on MeMoSA ® ANNOTATE, to mark the lesion and to collect clinical labels. The sensitivity in referral decision for all lesions that required a referral for cancer management/surveillance was moderate to high depending on the type of lesion (64.3%-100%)., Conclusion: This is the first description of a database with clinically labelled oral lesions. This database could accelerate the improvement of AI algorithms that can promote the early detection of high-risk oral lesions., (© 2022 Wiley Periodicals LLC.)