Intelligent Assessment Research Articles

Heterogeneous group decision-making method with continuous probabilistic hesitant fuzzy information for intelligent system reliability assessment

Heterogeneous group decision-making method with continuous probabilistic hesitant fuzzy information for intelligent system reliability assessment

Abstract 4137689: Artificial Intelligence Assessment of Diastolic Dysfunction by Electrocardiogram: Outcomes in Cardiac Intensive Care Unit Patients

Background: Left ventricular diastolic dysfunction (LVDD) predicts mortality in cardiac intensive care unit (CICU) patients. A novel artificial intelligence enhanced electrocardiogram (AIECG) algorithm can predict LVDD and mortality in general populations but has not been examined in the cardiac intensive care unit (CICU). We aim to assess if LVDD by AI-ECG is associated with in-hospital and one-year mortality in CICU patients. Methods: In this retrospective cohort study, we included consecutive unique adults admitted to the Mayo Clinic CICU from 2007 to 2018 with an admission AIECG, which AI assigned LVDD grade (0 to 3). Medial mitral E/e’ ratio >15 on transthoracic echocardiogram (TTE) defined elevated filling pressures. AIECG and TTE assessment of LVDD were used to assign patients to four groups based on TTE as gold standard: true and false negative, and true and false positive. In-hospital mortality was evaluated using multivariable logistic regression. One-year survival was evaluated using Kaplan-Meier curves and multivariable Cox proportional-hazards. Results: We included 11,868 patients (median age 69.5 years, 37.7% females); 48% had heart failure and 44% had acute coronary syndromes. AIECG LVDD grades were: grade 0 (normal), 33%; grade 1, 7%; grade 2, 39%; grade 3, 21%. In-hospital (adjusted OR) and one-year (adjusted HR) mortality increased in each higher AIECG LVDD grade (Figure A/B), before and after adjustment including TTE measurements. Patients with grade 2-3 LVDD by AIECG and medial mitral E/e’ ratio >15 by TTE (true positive) had the highest in-hospital (adjusted OR 2.5 [1.7-3.9]) and one-year (adjusted HR 1.9 [1.5-2.5]) mortality (Figure C/D), and mortality was elevated similarly in patients with either grade 2-3 LVDD by AIECG (false positive) or medial mitral E/e’ ratio >15 by TTE (false negative). Conclusions: The AIECG LVDD grade was strongly associated with in-hospital and one-year mortality in CICU patients, even after adjusting for clinical variables and TTE measurements. Patients with concordant AIECG and TTE for elevated filling pressures (true positive) were at highest risk.

A deep learning-based method for assessing tricuspid regurgitation using continuous wave Doppler spectra

Transthoracic echocardiography (TTE) is widely recognized as one of the principal modalities for diagnosing tricuspid regurgitation (TR). The diagnostic procedures associated with conventional methods are intricate and labor-intensive, with human errors leading to measurement variability, with outcomes critically dependent on the operators’ diagnostic expertise. In this study, we present an innovative assessment methodology for evaluating TR severity utilizing an end-to-end deep learning system. This deep learning system comprises a segmentation model of single cardiac cycle TR continuous wave (CW) Doppler spectra and a classification model of the spectra, trained on the TR CW Doppler spectra from a cohort of 11,654 patients. The efficacy of this intelligent assessment methodology was validated on 1500 internal cases and 573 external cases. The receiver operating characteristic (ROC) curves of the internal validation results indicate that the deep learning system achieved the areas under curve (AUCs) of 0.88, 0.84, and 0.89 for mild, moderate, and severe TR, respectively. The ROC curves of the external validation results demonstrate that the system attained the AUCs of 0.86, 0.79, and 0.87 for mild, moderate, and severe TR, respectively. Our study results confirm the feasibility and efficacy of this novel intelligent assessment method for TR severity.

Emotional Intelligence of Chinese Teachers and its Impact on Classroom Dynamics and Student Engagement

This research investigates the correlation between teachers' emotional intelligence and classroom dynamics, as well as the level of involvement shown by students in a university environment through a descriptive correlational methodology. Using Daniel Goleman's framework, the assessment focused on many aspects of emotional intelligence, including self-awareness, self-regulation, motivation, empathy, and social skills. The study also assessed the dynamics inside the classroom, including how it was managed, the instructional tactics used, the overall atmosphere, the level of differentiation, and the effectiveness of communication. Additionally, it examined the level of student involvement, including the meaningfulness of activities, the students' sense of competence, the support for their autonomy, the extent of collaborative learning, and their orientation towards mastery. Validated self-designed questionnaires were used to gather data from 30 instructors and 900 students. The findings reveal that instructors assessed their emotional intelligence as moderate, with empathy being the greatest and social skills being the lowest. Students evaluated classroom dynamics as somewhat successful in managing, creating an atmosphere, adapting to individual needs, and effectively using teaching methods and communicating. The engagement levels were moderate for meaningful activities and mastery orientation but low for competence, autonomy support, and collaborative learning. Correlation analysis indicated that there were no significant connections between teachers' overall emotional intelligence and students' assessments of classroom dynamics or participation. This implies that emotional intelligence does not directly impact these elements.

Application of Academic Analytical Models in Education Management

Objective: The primary objective of the current study is to provide an analytical systematic review on the application of academic analytical models in educational management and how the related techniques can be used to enhance quality outcomes and learning processes. Methodology: The study adopted the methodological framework outlined by the Joanna Briggs Institute (2015) and was informed by Arksey and O’Malley’s (2005) approach of summary and dissemination of research findings and, in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Findings: Learning analytics has emerged as the most relevant educational concept with the potential of collecting, analyzing and reporting data on learners, educators and administrators for efficient educational management processes. Analytics in education enhances the capabilities of the educators of determining the learners’ performances and identification of areas for improvement to make data-driven learning decisions. Conclusions: The application of analytical models in educational management is based on different domains such as customized learning, intelligent tutoring systems, predictive modelling, automated grading and assessments, and natural language processing. Received: 26 July 2024 / Accepted: 25 October 2024 / Published: 05 November 2024

Towards Achilles Tendon Injury Prevention in Athletes with Structural MRI Biomarkers: A Machine Learning Approach.

Recent advancements in artificial intelligence have proven their effectiveness in orthopaedic settings, especially in tasks like medical image analysis. This study compares human musculoskeletal radiologists to artificial intelligence in a novel, detailed, short, and cost-effective examination of Achilles tendon magnetic resonance images to uncover potential disparities in their reasoning approaches. Aiming to identify relationships between the structured assessment of the Achilles tendon and its function that could support injury prevention. We examined 72 athletes to investigate the link between Achilles tendon structure, as visualised in magnetic resonance images using a precise T2*-weighted gradient echo sequence with very short echo times, and its functional attributes. The acquired data were analysed using advanced artificial intelligence techniques and reviewed by radiologists. Additionally, we conducted statistical assessments to explore relationships with functional studies in four meaningful groups: dynamic strength, range of motion, muscle torque and stabilography. The results show notable linear or non-linear relationships between functional indicators and structural alterations (maximal obtained Spearman correlation coefficients ranged from 0.3 to 0.36 for radiological assessment and from 0.33 to 0.49 for artificial intelligence assessment, while maximal normalised mutual information ranged from 0.52 to 0.57 for radiological assessment and from 0.42 to 0.6 for artificial intelligence assessment). Moreover, when artificial intelligence-based magnetic resonance assessment was utilised as an input, the associations consistently proved more robust, or the count of significant relationships surpassed that derived from radiological assessment. Ultimately, utilising only structural parameters as inputs enabled us to explain up to 59% of the variance within specific functional groups. This analysis revealed that structural parameters influence four key functional aspects related to the Achilles tendon. Furthermore, we found that relying solely on subjective radiologist opinions limited our ability to reason effectively, in contrast to the structured artificial intelligence assessment. Cross-sectional studies.

A multimodal deep learning-based algorithm for specific fetal heart rate events detection.

This study aims to develop a multimodal deep learning-based algorithm for detecting specific fetal heart rate (FHR) events, to enhance automatic monitoring and intelligent assessment of fetal well-being. We analyzed FHR and uterine contraction signals by combining various feature extraction techniques, including morphological features, heart rate variability features, and nonlinear domain features, with deep learning algorithms. This approach enabled us to classify four specific FHR events (bradycardia, tachycardia, acceleration, and deceleration) as well as four distinct deceleration patterns (early, late, variable, and prolonged deceleration). We proposed a multi-model deep neural network and a pre-fusion deep learning model to accurately classify the multimodal parameters derived from Cardiotocography signals. These accuracy metrics were calculated based on expert-labeled data. The algorithm achieved a classification accuracy of 96.2 % for acceleration, 94.4 % for deceleration, 90.9 % for tachycardia, and 85.8 % for bradycardia. Additionally, it achieved 67.0 % accuracy in classifying the four distinct deceleration patterns, with 80.9 % accuracy for late deceleration and 98.9 % for prolonged deceleration. The proposed multimodal deep learning algorithm serves as a reliable decision support tool for clinicians, significantly improving the detection and assessment of specific FHR events, which are crucial for fetal health monitoring.

Development and cultural adaptation of the Saudi pediatric speech intelligibility test.

To report the development and administration of the Saudi pediatric speech intelligibility (SPSI) test. This study was carried out at King Abdullah Ear Specialist Center, King Saud University, Riyadh, Saudi Arabia, between 2021 and 2023. A pilot study was carried out in 5 regions of Saudi Arabia including 100 normal hearing children aged 7-11 years old, with 20 children from each region. The final test materials were voice-recorded by a native Saudi radio announcer, and a software-based application for administering the SPSI was developed. During the pilot study, minor adjustments were carried out to the test for more clarity. The developed SPSI software is an android-based application that includes features like automatic result calculation, data saving, and individual user accounts for examiners to review results. The SPSI test comprises 4-word cards and 2 sentence cards, each with 5 pictures, and operates in 3 modes: quiet, background noise, and competing sentences. The SPSI test has been developed in an android-based software using the Saudi local dialects. It can facilitate comprehensive and accurate assessment of speech intelligibility, particularly in children with hearing impairments.

Experimental performance verification of an intelligent detection and assessment scheme for disturbances and imbalances of three-phase synchronous machine output using coherence estimators

In this article, power quality disturbances, such as voltage and current unbalances, series and shunt faults, are monitored in three-phase synchronous machines. Because the imbalances affect machine efficiency and service life, it is essential to figure out whether the three-phase voltages/currents are balanced or unbalanced. An integrated detection algorithm is proposed to detect the unbalanced voltages/currents and various abnormal conditions precisely and quickly, which is based on the coherence estimator. Most existing detection methods require more than one cycle time to determine the contingency conditions, while the proposed technique detects these situations in a fast and discrete protection system. The suggested scheme acquires instantaneous measurements of the three-phase voltages and currents taken at the synchronous machine terminals in order to calculate fifteen coherence coefficients that are utilized to detect and assess any unbalance or trouble accurately and swiftly. A new proposal for imbalance and disturbance indicators based on the coherence estimators is developed in this study. Multiple test cases have been conducted to validate the proposed algorithm capabilities using a real power system, which includes a motor-generator set, a three-phase load and measurement transformers. The experimental results have been revealed that the relay reliability and accuracy percentages have been found to be 98.28% and 98.52%, respectively. The quantitative findings of the imbalance and disturbance assessment are recorded.

Integration of AI in Education and Didactic Childhood Advancement and Progress

The state of education in our country has been a contentious topic for many years. Numerous reforms have been done but there are still some problems – inefficient learning resources, is but one of the many. Due to inexperience on this topic this problem continues to plague the education system. However, taking an informed and educated approach with the interests of the students prioritized, we believe that many of these problems could be solved with the use of Artificial Intelligence (AI). Its proper integration into the education system could aid in the improvement of efficiency of learning resources, through the use of various tools like chatbots, adaptive learning systems and intelligent assessment systems. By implementing the use of AI in a world where learning resources are scarce, there can be standardized learning throughout the country regardless of availability of learning materials. The main agenda of this study is to explore ways of implementing the use of Artificial Intelligence into educational systems to integrate the use of learning materials, hence bringing about improved quality of education. We are fully aware of the problems facing the implementations of this study but we are ready to conduct rigorous research to combat them.

Artificial intelligence assessment of heart failure and mortality after acute stroke

Abstract Background/Introduction The adverse cardiovascular outcomes following a stroke have shown significant associations with post-stroke mortality. However, studies focusing on predicting heart failure and its impact on long-term mortality are scarce. Purpose To address this gap, we employed an commercially approved artificial intelligence/machine learning enabled software as a medical device (AiTiALVSD version 1.00.00) which uses only 12 lead electrocardiogram data, resulting probability score for predicting left ventricular systolic dysfunction. We derived the AiTiALVSD probability score from initial ECGs at stroke admission, and assess its implications for prediction of heart failure and long-term mortality. Methods We collected data from 335 ischemic stroke patients admitted to a cardiovascular center during acute periods between 2013 and 2019. The AiTiALVSD score was employed to predict heart failure with reduced ejection fraction and heart failure with mild reduced ejection fraction, analyzed through logistic regression. Subsequently, we used the Cox Hazard proportional model, incorporating the AiTiALVSD score and clinical factors, to predict long-term mortality. Results The model incorporating the AiTiALVSD score with clinical variables demonstrated a higher AUC for predicting heart failure (0.905 [95% CI, 0.827-0.927] vs. 0.828 [95% CI, 0.749-0.907], p<0.004) than clinical variables alone. Moreover, for long-term mortality prediction, this model outperformed the conventional mortality score (AUC, 0.884 [95% CI, 0.836-0.933] vs. 0.755 [95% CI, 0.690-0.820], p<0.001). Conclusion Multivariable models which combine the AiTiALVSD score with clinical factors, effectively predicts heart failure and long-term mortality. This model could enhance therapeutic strategy tailoring by providing acute phase prognostic predictions for individual stroke patients.Prediction performance for heart failurePrediction performance for mortality

Study on the balance and gait characteristics of subjects with generalized joint hypermobility residing in high-altitude using wearable devices: a cross-sectional study

PurposeTo investigate the characteristics of balance and gait functions in Generalized Joint Hypermobility (GJH) subjects residing in high-altitude areas.MethodsThis study included 61 university students (28 with GJH and 33 healthy controls) all from the high-altitude region of Linzhi, Tibet Autonomous Region. The Riablo™ wearable intelligent rehabilitation assessment and training system was used to assess static balance (with eyes open and closed) and gait function (during flat walking) in both groups.ResultsCompared to healthy subjects, GJH subjects exhibited significantly impaired balance, indicated by an increased distance of the center of pressure position from the ideal center of gravity(EO: P = 0.007, EC: P = 0.031) and greater amplitude of center of pressure displacements (EO: P = 0.043, EC: P = 0.032). Gait velocity(P = 0.007), stride length(P = 0.012), and swing stance phase of the gait cycle(P = 0.046) were significantly reduced in GJH subjects compared to healthy subjects. A significant increase in the flat-foot phase of the gait cycle(P = 0.022) was observed in GJH subjects compared to healthy subjects.ConclusionThe current study demonstrated that GJH subjects residing in high-altitude areas exhibit impairments in balance and gait, providing a basis for training and prevention strategies tailored for this population. And this study used the wearable intelligent rehabilitation evaluation and training system in high-altitude areas, providing methodological references for scientific research on balance and gait function under non laboratory conditions.Trial registrationControlled Trials No.102772023RT133, Registered 13 October 2023.

Intelligent Computer-Assisted Language Assessment (ICALA) in philosophy-based language instruction: unraveling the effects on critical thinking, self-evaluation, academic resilience, and speaking development

Few empirical research has attempted to determine the impact of Intelligent Computer-Assisted Language Assessment (ICALA) in philosophy-based language instruction (PBLI) on critical thinking, self-evaluation, and academic resilience, despite the significant role that higher-order thinking skills play in influencing English as a Foreign Language (EFL) learners’ cognition, including their learning processes. This research addresses this knowledge vacuum by examining how ICALA in PBLI influences the development of the four primary abilities associated with critical thinking, self-evaluation, and academic resilience. A quasi-experimental strategy was used in this study among 81 EFL learners. The participants were split into two groups: one to participate in the experiment and another to serve as a control. The books for both groups were revised or supplemented according to the underlying PBLI principles. The control group (CG) students were exposed to paper format assessment. In comparison, the experimental group (EG) attended ICALA. The statistical significance of the differences between the two groups was determined using multivariate analysis of variance (MANOVA). The results demonstrated that the learners in EG outperformed their peers in CG foreign language-speaking development. Moreover, they received better critical thinking, self-evaluation, and academic resilience results.

The blue sky of AI-assisted language assessment: autonomy, academic buoyancy, psychological well-being, and academic success are involved

Artificial intelligence (AI) transforms the educational landscape by radically changing how lessons are taught and students are evaluated. In light of these facts, it is critical to consider learners’ emotional and mental wellness as the building blocks of education. Given these facts, it is imperative to consider learners’ emotional and mental well-being as the fundamental components of education. The key goal of this investigation was to investigate the relationships between learner autonomy (LA), academic buoyancy (AB), psychological well-being (PW), and academic success (AS) in Intelligent Computer-Assisted Language Assessment (ICALA). The current study was conducted on a cohort of 391 students registered in courses at private language institutions in Al-Kharj, Saudi Arabia, who were at the intermediate proficiency level. The following instruments were administered: the Academic Buoyancy Scale, the learner autonomy instrument, the learner psychological well-being, and the academic assessment. Then, to evaluate data and quantify the interaction between LA, AB, PW, and AS, confirmatory factor analysis (CFA) and structural equation modeling (SEM) were applied. The findings underscored the significance of LA and AB in achieving a balance in the PW of EFL pupils, particularly when utilizing ICALA for language acquisition. Additionally, the instructional implications of this study and potential avenues for future research are extensively investigated.

Reflecting the voices of EFL teachers in the world of Intelligent Computer-Assisted Language Assessment (ICALA): an insight into teacher immunity, reflective teaching, job satisfaction, and L2-teacher grit

Artificial intelligence (AI) and Intelligent Computer-Assisted Language Assessment (ICALA) are transforming the educational landscape by radically changing how lessons are taught and students are evaluated. As the masterminds behind the curriculum, it is critical to consider the emotional and mental health of teachers who applied ICALA as part of their language instruction. To this end, this study’s primary objective was to examine the connections between ICALA, teacher immunity, reflective teaching, job satisfaction, and l2-teacher grit. To achieve this goal, 221 English as a foreign language (EFL) university teachers from Afghanistan participated in the current research. The research outcomes identified and quantified the influences of teacher immunity and reflective teaching on job satisfaction and L2 teacher grit by data screening utilizing confirmatory factor analysis (CFA) and structural equation modeling (SEM). According to the results, TI and RT are vital in implementing AI into language assessment by maintaining an uninterrupted JS and L2TG. The study’s ramifications are further elaborated upon.

Advancing Mental Health Care: Intelligent Assessments and Automated Generation of Personalized Advice via M.I.N.I and RoBERTa

Advancing Mental Health Care: Intelligent Assessments and Automated Generation of Personalized Advice via M.I.N.I and RoBERTa

The AI Assessment Scale (AIAS) in action: A pilot implementation of GenAI-supported assessment

The rapid adoption of generative artificial intelligence (GenAI) technologies in higher education has raised concerns about academic integrity, assessment practices and student learning. Banning or blocking GenAI tools has proven ineffective, and punitive approaches ignore the potential benefits of these technologies. As a result, assessment reform has become a pressing topic in the GenAI era. This paper presents the findings of a pilot study conducted at British University Vietnam exploring the implementation of the Artificial Intelligence Assessment Scale (AIAS), a flexible framework for incorporating GenAI into educational assessments. The AIAS consists of five levels, ranging from “no AI” to “full AI,” enabling educators to design assessments that focus on areas requiring human input and critical thinking. The pilot study results indicate a significant reduction in academic misconduct cases related to GenAI and enhanced student engagement with GenAI technology. The AIAS facilitated a shift in pedagogical practices, with faculty members incorporating GenAI tools into their modules and students producing innovative multimodal submissions. The findings suggest that the AIAS can support the effective integration of GenAI in higher education, promoting academic integrity while leveraging technology’s potential to enhance learning experiences. Implications for practice or policy: Higher education institutions should adopt flexible frameworks like the AIAS to guide ethical integration of GenAI into assessment practices. Educators should design assessments that leverage GenAI capabilities, while supporting critical thinking and human input. Institutional policies related to GenAI should be developed in consultation with stakeholders and regularly updated to keep pace with technological advancements. Policymakers should prioritise research funding into the impacts of GenAI on higher education to inform evidence-based practices.

Cloud Model-Based Intelligent Construction Management Level Assessment of Prefabricated Building Projects

Intelligent construction is vital for achieving new building industrialization by enhancing prefabricated buildings through integrated, digital, and intelligent management across production and construction processes. Despite its significance, detailed research on evaluating the intelligent construction management (ICM) level of prefabricated projects remains limited. This study aims to develop a comprehensive, multi-level, multi-dimensional ICM assessment system. By reviewing the literature, engaging in expert discussions, and conducting case studies—specifically using a project in Guangzhou as an example—this study employs the Analytic Hierarchy Process (AHP) and entropy weight methods to assign indicator weights. Utilizing cloud model theory, it establishes evaluation standards for intelligent construction management. This model identifies the project’s ICM level, suggests practical improvement methods, and validates its applicability. This work not only advances theoretical understanding but also provides a practical framework for assessing ICM levels in prefabricated projects, thus contributing significantly to the field by offering new research perspectives and empirical evidence.

Assessment of emotional intelligence and perceived stress in pharmacy students at a Nigerian university

Background: Emotional intelligence (EI) is essential in personal lives and professional relations. Its influence on academic performance has been demonstrated. This study assessed EI and perceived stress in undergraduate pharmacy students at a Nigerian university. Methods: A cross-sectional study was conducted in a Nigerian federal university among pharmacy students enrolled via convenient sampling. EI was measured through the Schutte Self‑Report Emotional Intelligence Test (SSEIT), a 33‑item validated instrument with four subscales consisting of 30 positive questions and three negative questions. Perceived stress was assessed using the Perceived Stress Scale (PSS‑10), a 10‑item validated stress assessment tool. Results: A total of 740 questionnaires were returned and analysed. More than half of the respondents were female (55.3%), single (94.1%), and between 22 and 25 years old (59.1%). About 25% of pharmacy students were in the 200 level. The means of EI and perceived stress were 126.2 ± 15.9 and 20.5 ± 5.0, respectively. Most students had high EI (53.0%) and high perceived stress (58.2%). Conclusion: Pharmacy students demonstrated high emotional intelligence and perceived stress.

ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ В ДИСТАНЦИОННОМ ОБУЧЕНИИ: НОВЫЕ ПОДХОДЫ И ИНСТРУМЕНТЫ

This article discusses new approaches and tools based on artificial intelligence that can be effectively used in teaching. In particular, the analysis will be carried out on adaptive learning, intelligent knowledge assessment systems, virtual assistants and chatbots, as well as the use of analytical data to predict student academic success. Particular attention is paid to how these technologies can improve the quality of the educational process, improve interaction between students and teachers, and provide a more personalized experience. The article also discusses the challenges and problems associated with the implementation of AI in the educational process, including data protection issues, ethical aspects of the use of AI, as well as issues of technology availability in different regions.