Traditional Assessment Methods Research Articles

Through the Lens of Age: Using Dog Photographs to Uncover Welfare and Stress

This study evaluated the potential of using dogs’ apparent age, judged from photographs, as a non-invasive tool for assessing their welfare. Traditional welfare assessment methods often rely on behavioral and physiological indicators, which can be resource-intensive and invasive. This research explored whether apparent age, a measure used in humans to predict health and longevity, can also serve as an indicator of welfare in dogs by investigating its association with relative telomere length (RTL), a biomarker of biological aging. Photographs of 60 domestic dogs were evaluated by canine specialists and general volunteers via the citizen science platform Zooniverse. Participants estimated the age of 20 dogs from three different age categories: young (0–2 years), adult (2–5 years), and senior (6+ years). The accuracy of these predictions was compared to the dogs’ chronological ages and RTLs. Generalized linear models were used to assess factors influencing prediction accuracy, including the dogs’ age, sex, and origin. Results indicated that both specialists and volunteers reliably estimated the age of senior dogs, with no significant differences in accuracy between groups. Dogs with accurate apparent age estimates had RTLs matching their chronological age, while those with premature aging signs had shorter RTLs. This suggests apparent age could be a practical, non-invasive welfare assessment tool, offering a potentially accessible method for new welfare assessment protocols.

A Hybrid Deep Learning Model for Enhanced Structural Damage Detection: Integrating ResNet50, GoogLeNet, and Attention Mechanisms

Quick and accurate structural damage detection is essential for maintaining the safety and integrity of infrastructure, especially following natural disasters. Traditional methods of damage assessment, which rely on manual inspections, can be labor-intensive and subject to human error. This paper introduces a hybrid deep learning model that combines the capabilities of ResNet50 and GoogLeNet, further enhanced by a convolutional block attention module (CBAM), proposed to improve both the accuracy and performance in detecting structural damage. For training purposes, a diverse dataset of images depicting both structural damage cases and undamaged cases was used. To further enhance the robustness, data augmentation techniques were also employed. In this research, precision, recall, F1-score, and accuracy were employed to evaluate the effectiveness of the introduced hybrid deep learning model. Our findings indicate that the hybrid deep neural network introduced in this study significantly outperformed standalone architectures such as ResNet50 and GoogLeNet, making it a highly effective solution for applications in disaster response and infrastructure maintenance.

Using a Device-Free Wi-Fi Sensing System to Assess Daily Activities and Mobility in Low-Income Older Adults: Protocol for a Feasibility Study.

Older adults belonging to racial or ethnic minorities with low socioeconomic status are at an elevated risk of developing dementia, but resources for assessing functional decline and detecting cognitive impairment are limited. Cognitive impairment affects the ability to perform daily activities and mobility behaviors. Traditional assessment methods have drawbacks, so smart home technologies (SmHT) have emerged to offer objective, high-frequency, and remote monitoring. However, these technologies usually rely on motion sensors that cannot identify specific activity types. This group often lacks access to these technologies due to limited resources and technology experience. There is a need to develop new sensing technology that is discreet, affordable, and requires minimal user engagement to characterize and quantify various in-home activities. Furthermore, it is essential to explore the feasibility of developing machine learning (ML) algorithms for SmHT through collaborations between clinical researchers and engineers and involving minority, low-income older adults for novel sensor development. This study aims to examine the feasibility of developing a novel channel state information-based device-free, low-cost Wi-Fi sensing system, and associated ML algorithms for localizing and recognizing different patterns of in-home activities and mobility in residents of low-income senior housing with and without mild cognitive impairment. This feasibility study was conducted in collaboration with a wellness care group, which serves the healthy aging needs of low-income housing residents. Prior to this feasibility study, we conducted a pilot study to collect channel state information data from several activity scenarios (eg, sitting, walking, and preparing meals) using the proposed Wi-Fi sensing system continuously over a week in apartments of low-income housing residents. These activities were videotaped to generate ground truth annotations to test the accuracy of the ML algorithms derived from the proposed system. Using qualitative individual interviews, we explored the acceptability of the Wi-Fi sensing system and implementation barriers in the low-income housing setting. We use the same study protocol for the proposed feasibility study. The Wi-Fi sensing system deployment began in November 2022, with participant recruitment starting in July 2023. Preliminary results will be available in the summer of 2025. Preliminary results are focused on the feasibility of developing ML models for Wi-Fi sensing-based activity and mobility assessment, community-based recruitment and data collection, ground truth, and older adults' Wi-Fi sensing technology acceptance. This feasibility study can make a contribution to SmHT science and ML capabilities for early detection of cognitive decline among socially vulnerable older adults. Currently, sensing devices are not readily available to this population due to cost and information barriers. Our sensing device has the potential to identify individuals at risk for cognitive decline by assessing their level of physical function by tracking their in-home activities and mobility behaviors, at a low cost. DERR1-10.2196/53447.

Machine-learning-based prediction of cardiovascular events for hyperlipidemia population with lipid variability and remnant cholesterol as biomarkers.

Dyslipidemia poses a significant risk for the progression to cardiovascular diseases. Despite the identification of numerous risk factors and the proposal of various risk scales, there is still an urgent need for effective predictive models for the onset of cardiovascular diseases in the hyperlipidemic population, which are essential for the prevention of CVD. We carried out a retrospective cohort study with 23,548 hyperlipidemia patients in Shenzhen Health Information Big Data Platform, including 11,723 CVD onset cases in a 3-year follow-up. The population was randomly divided into 70% as an independent training dataset and remaining 30% as test set. Four distinct machine-learning algorithms were implemented on the training dataset with the aim of developing highly accurate predictive models, and their performance was subsequently benchmarked against conventional risk assessment scales. An ablation study was also carried out to analyze the impact of individual risk factors to model performance. The non-linear algorithm, LightGBM, excelled in forecasting the incidence of cardiovascular disease within 3years, achieving an area under the 'receiver operating characteristic curve' (AUROC) of 0.883. This performance surpassed that of the conventional logistic regression model, which had an AUROC of 0.725, on identical datasets. Concurrently, in direct comparative analyses, machine-learning approaches have notably outperformed the three traditional risk assessment methods within their respective applicable populations. These include the Framingham cardiovascular disease risk score, 2019 ESC/EAS guidelines for the management of dyslipidemia and the 2016 Chinese recommendations for the management of dyslipidemia in adults. Further analysis of risk factors showed that the variability of blood lipid levels and remnant cholesterol played an important role in indicating an increased risk of CVD. We have shown that the application of machine-learning techniques significantly enhances the precision of cardiovascular risk forecasting among hyperlipidemic patients, addressing the critical issue of disease prediction's heterogeneity and non-linearity. Furthermore, some recently-suggested biomarkers, including blood lipid variability and remnant cholesterol are also important predictors of cardiovascular events, suggesting the importance of continuous lipid monitoring and healthcare profiling through big data platforms.

An IoT-Based Framework for Automated Assessing and Reporting of Light Sensitivities in Children with Autism Spectrum Disorder

Identification of light sensitivities, manifesting either as hyper-sensitive (over-stimulating) or hypo-sensitive (under-stimulating) in children with autism spectrum disorder (ASD), is crucial for the development of personalized sensory environments and therapeutic strategies. Traditional methods for identifying light sensitivities often depend on subjective assessments and manual video coding methods, which are time-consuming, and very keen observations are required to capture the diverse sensory responses of children with ASD. This can lead to challenges for clinical practitioners in addressing individual sensory needs effectively. The primary objective of this work is to develop an automated system using Internet of Things (IoT), computer vision, and data mining techniques for assessing visual sensitivities specifically associated with light (color and illumination). For this purpose, an Internet of Things (IoT)-based light sensitivities assessing system (IoT-LSAS) was designed and developed using a visual stimulating device, a bubble tube (BT). The IoT-LSAS integrates various electronic modules for (i) generating colored visual stimuli with different illumination levels and (ii) capturing images to identify children’s emotional responses during sensory stimulation sessions. The system is designed to operate in two different modes: a child control mode (CCM) and a system control mode (SCM). Each mode uses a distinct approach for assessing light sensitivities, where CCM uses a preference-based approach, and SCM uses an emotional response tracking approach. The system was tested on a sample of 20 children with ASD, and the results showed that the IoT-LSAS effectively identified light sensitivities, with a 95% agreement rate in the CCM and a 90% agreement rate in the SCM when compared to the practitioner’s assessment report. These findings suggest that the IoT-LSAS can be used as an alternative to traditional assessment methods for diagnosing light sensitivities in children with ASD, significantly reducing the practitioner’s time required for diagnosis.

Objective assessment of docking site consolidation in bone transport: the role of pixel value ratio in predicting healing outcomes

BackgroundThe management of docking site healing in bone transport remains a significant challenge in orthopedic surgery. Traditional assessment methods rely heavily on qualitative radiographic evaluations. This study investigates the utility of pixel value ratio (PVR), an objective quantitative measure, in assessing bone healing at the docking site during bone transport.MethodsThis retrospective study included 47 patients who underwent bone transport for lower limb reconstruction between January 2015 and January 2020. Patients were categorized into bone union (n = 35) and nonunion (n = 12) groups based on docking site outcomes. PVR was calculated using two methods (PVR1 and PVR2) at six time points over 24 months post-docking. Subgroup analyses were performed based on gender, age, and surgical site.ResultsOf 47 patients, 35 achieved bone union and 12 experienced nonunion. Both PVR1 and PVR2 were consistently lower in the union group compared to the nonunion group at all time points (p < 0.001). In the union group, PVR1 ranged from 1.064 ± 0.050 to 1.108 ± 0.062, while PVR2 ranged from 0.926 ± 0.079 to 0.946 ± 0.062. In the nonunion group, PVR1 ranged from 1.204 ± 0.057 to 1.273 ± 0.020, and PVR2 from 1.039 ± 0.060 to 1.148 ± 0.022. Subgroup analyses revealed that males had significantly lower PVR values compared to females, and tibial cases had lower PVR values compared to femoral cases in both union and nonunion groups (p < 0.05). All juvenile patients achieved union, compared to 71.4% of adults (p < 0.01).ConclusionPVR demonstrates significant potential as an objective tool for assessing docking site healing in bone transport procedures. The distinct patterns observed between union and nonunion cases provide a foundation for developing clinical guidelines to monitor and predict healing outcomes. Integration of PVR assessment into clinical practice could improve decision-making and optimize treatment protocols in bone transport procedures.

Redefining student assessment in Nigerian tertiary institutions: The impact of AI technologies on academic performance and developing countermeasures

Integrating artificial AI technologies in education has revolutionised teaching, learning, and assessment worldwide. In Nigerian tertiary institutions, students increasingly rely on AI tools for assignments, research, and exam preparation, raising concerns about the integrity of traditional assessment methods. This paper explores the impact of AI technologies on academic performance and the challenges they pose to accurately evaluating student capabilities. It argues for the urgent need to redefine assessment strategies in Nigerian higher education to preserve academic standards while harnessing the benefits of AI. The study highlights ethical concerns such as data privacy, access inequality, and over-reliance on AI tools, which can undermine critical thinking skills. It provides countermeasures and policy recommendations, including establishing AI usage guidelines, promoting equitable access to technology, and integrating assessments that prioritise critical thinking and problem-solving skills. By adopting these innovative policies, Nigerian tertiary institutions can enhance the quality of education and ensure that students develop genuine skills and academic excellence. This paper calls for immediate action to align education with the realities of the AI age, ensuring sustainable and authentic student outcomes.

Employing the Artificial Intelligence Object Detection Tool YOLOv8 for Real-Time Pain Detection: A Feasibility Study.

Effective pain management is crucial for patient care, impacting comfort, recovery, and overall well-being. Traditional subjective pain assessment methods can be challenging, particularly in specific patient populations. This research explores an alternative approach using computer vision (CV) to detect pain through facial expressions. The study implements the YOLOv8 real-time object detection model to analyze facial expressions indicative of pain. Given four pain datasets, a dataset of pain-expressing faces was compiled, and each image was carefully labeled based on the presence of pain-associated Action Units (AUs). The labeling distinguished between two classes: pain and no pain. The pain category included specific AUs (AU4, AU6, AU7, AU9, AU10, and AU43) following the Prkachin and Solomon Pain Intensity (PSPI) scoring method. Images showing these AUs with a PSPI score above 2 were labeled as expressing pain. The manual labeling process utilized an open-source tool, makesense.ai, to ensure precise annotation. The dataset was then split into training and testing subsets, each containing a mix of pain and no-pain images. The YOLOv8 model underwent iterative training over 10 epochs. The model's performance was validated using precision, recall, and mean Average Precision (mAP) metrics, and F1 score. When considering all classes collectively, our model attained a mAP of 0.893 at a threshold of 0.5. The precision for "pain" and "nopain" detection was 0.868 and 0.919, respectively. F1 scores for the classes "pain", "nopain", and "all classes" reached a peak value of 0.80. Finally, the model was tested on the Delaware dataset and in a real-world scenario. Despite limitations, this study highlights the promise of using real-time computer vision models for pain detection, with potential applications in clinical settings. Future research will focus on evaluating the model's generalizability across diverse clinical scenarios and its integration into clinical workflows to improve patient care.

Exploration of Diversified Assessment Models for Business English Courses

As one of the important courses in majors such as international trade and business management, the assessment method of Business English directly affects students' learning enthusiasm and the cultivation of practical application ability. The traditional single assessment method often focuses on the memorization of theoretical knowledge and test-taking skills, and ignores the assessment of students' practical application ability of Business English. Therefore, it is particularly important to explore diversified assessment models to comprehensively and objectively evaluate students' business English level. This paper aims to explore the construction and implementation of diversified assessment models for Business English courses. By analyzing the problems existing in the current assessment methods, this paper proposes the necessity, design principles and specific implementation strategies of diversified assessment models, in order to provide a reference for the teaching reform of Business English courses.

Enhancing the Precision of the Self-Compassion Scale Short Form (SCS-SF) with Rasch Methodology

Abstract Objectives Precise measurement of self-compassion is essential for informing well-being–related policies. Traditional assessment methods have led to inconsistencies in the factor structure of self-compassion scales. We used Rasch methodology to enhance measurement precision and assess the psychometric properties of the Self-Compassion Scale Short Form (SCS-SF), including its invariance across Ghana, Germany, India, and New Zealand. Method We employed the Partial Credit Rasch model to analyse responses obtained from 1000 individuals randomly selected (i.e. 250 from each country) from a total convenience sample of 1822 recruited from the general populations of Germany, Ghana, India, and New Zealand. Results The initial identification of local dependency among certain items led to a significant misfitting of the SCS-SF to the Rasch model (χ2 (108) = 260.26, p &lt; 0.001). We addressed this issue by merging locally dependent items, using testlets. The solution with three testlets resulted in optimal fit of the SCS-SF to the Rasch model (χ2 (27) = 23.84, p = 0.64), showing evidence of unidimensionality, strong sample targeting (M = 0.20; SD = 0.72), and good reliability (Person Separation Index = 0.71), including invariance across sociodemographic factors. We then developed ordinal-to-interval conversion tables based on the Rasch model’s person estimates. The SCS-SF showed positive correlations with measures of compassion towards others, optimism, and positive affect, alongside negative associations with psychological distress and negative affect. Conclusions The current study supports the reliability, as well as the structural, convergent, and external validity of the SCS-SF. By employing the ordinal-to-interval conversion tables published here, the precision of the measure is significantly enhanced, offering a robust tool for investigating self-compassion across different cultures.

Artificial Intelligence-Powered Risk Assessment in Supply Chain Safety

The increasing complexity and globalization of supply chains necessitate robust risk management strategies to ensure safety and resilience. Traditional risk assessment methods often fall short in dynamically adapting to the rapidly changing conditions and voluminous data inherent in modern supply chains. This study explores the potential of Artificial Intelligence (AI)-powered risk assessment to address these limitations in the context of Malaysia's supply chain industry. By employing AI technologies such as machine learning, IoT, and predictive analytics, organizations can significantly enhance their risk management capabilities, improving predictive accuracy, real-time monitoring, and overall operational efficiency. Through a qualitative analysis involving in-depth interviews with supply chain managers, AI experts, and technology vendors, the study identifies the strategies employed for AI integration, the perceived effectiveness of these technologies, and the challenges faced in implementation. The findings highlight the importance of robust data governance, the development of explainable AI models, and continuous skill development to overcome barriers related to data quality, model interpretability, and high implementation costs. The study concludes with recommendations for fostering a safer and more resilient logistics environment in Malaysia, emphasizing the need for comprehensive AI adoption frameworks and scalable solutions for small and medium-sized enterprises.

Comprehensive Analysis of Phenotypic Traits in Chinese Cabbage Using 3D Point Cloud Technology

Studies on the phenotypic traits and their associations in Chinese cabbage lack precise and objective digital evaluation metrics. Traditional assessment methods often rely on subjective evaluations and experience, compromising accuracy and reliability. This study develops an innovative, comprehensive trait evaluation method based on 3D point cloud technology, with the aim of enhancing the precision, reliability, and standardization of the comprehensive phenotypic traits of Chinese cabbage. By using multi-view image sequences and structure-from-motion algorithms, 3D point clouds of 50 plants from each of the 17 Chinese cabbage varieties were reconstructed. Color-based region growing and 3D convex hull techniques were employed to measure 30 agronomic traits. Comparisons between 3D point cloud-based measurements of the plant spread, plant height, leaf area, and leaf ball volume and traditional methods yielded R2 values greater than 0.97, with root mean square errors of 1.27 cm, 1.16 cm, 839.77 cm3, and 59.15 cm2, respectively. Based on the plant spread and plant height, a linear regression prediction of Chinese cabbage weights was conducted, yielding an R2 value of 0.76. Integrated optimization algorithms were used to test the parameters, reducing the measurement time from 55 min when using traditional methods to 3.2 min. Furthermore, in-depth analyses including variation, correlation, principal component analysis, and clustering analyses were conducted. Variation analysis revealed significant trait variability, with correlation analysis indicating 21 pairs of traits with highly significant positive correlations and 2 pairs with highly significant negative correlations. The top six principal components accounted for 90% of the total variance. Using the elbow method, k-means clustering determined that the optimal number of clusters was four, thus classifying the 17 cabbage varieties into four distinct groups. This study provides new theoretical and methodological insights for exploring phenotypic trait associations in Chinese cabbage and facilitates the breeding and identification of high-quality varieties. Compared with traditional methods, this system provides significant advantages in terms of accuracy, speed, and comprehensiveness, with its low cost and ease of use making it an ideal replacement for manual methods, being particularly suited for large-scale monitoring and high-throughput phenotyping.

Impact of Agroforestry Practices on Soil Microbial Diversity and Nutrient Cycling in Atlantic Rainforest Cocoa Systems.

Microorganisms are critical indicators of soil quality due to their essential role in maintaining ecosystem services. However, anthropogenic activities can disrupt the vital metabolic functions of these microorganisms. Considering that soil biology is often underestimated and traditional assessment methods do not capture its complexity, molecular methods can be used to assess soil health more effectively. This study aimed to identify the changes in soil microbial diversity and activity under different cocoa agroforestry systems, specially focusing on taxa and functions associated to carbon and nitrogen cycling. Soils from three different cocoa agroforestry systems, including a newly established agroforestry with green fertilization (GF), rubber (Hevea brasiliensis)-cocoa intercropping (RC), and cocoa plantations under Cabruca (cultivated under the shave of native forest) (CAB) were analyzed and compared using metagenomic and metaproteomic approaches. Samples from surrounding native forest and pasture were used in the comparison, representing natural and anthropomorphic ecosystems. Metagenomic analysis revealed a significant increase in Proteobacteria and Basidiomycota and the genes associated with dissimilatory nitrate reduction in the RC and CAB areas. The green fertilization area showed increased nitrogen cycling activity, demonstrating the success of the practice. In addition, metaproteomic analyses detected enzymes such as dehydrogenases in RC and native forest soils, indicating higher metabolic activity in these soils. These findings underscore the importance of soil management strategies to enhance soil productivity, diversity, and overall soil health. Molecular tools are useful to demonstrate how changes in agricultural practices directly influence the microbial community, affecting soil health.

Functional excitation-inhibition ratio for social anxiety analysis and severity assessment.

Social anxiety disorder (SAD) is a prevalent psychiatric condition characterized by an intense fear of and avoidance of social situations. Traditional assessment methods for SAD primarily rely on subjective self-report questionnaires and clinical interviews, which can be prone to biases and inaccuracies. This study aims to explore the functional excitation-inhibition (fEI) ratio derived from EEG data as a potential objective biomarker for assessing SAD severity. Resting-state EEG data were collected from 20 control subjects and 60 individuals with varying degrees of SAD severity (mild, moderate, and severe). The fEI ratio was estimated across different EEG bands and analyzed, focusing on differences between control subjects and SAD groups. Significantly higher fEI ratios were observed in the alpha and low beta EEG bands in individuals with SAD compared to controls, especially within the prefrontal cortex. Additionally, a positive correlation was found between the fEI ratio and the severity of social anxiety symptoms across SAD severity levels. The findings indicate that the fEI ratio in the alpha and low beta bands may serve as a promising biomarker for assessing SAD severity. These results contribute to a deeper understanding of the neural mechanisms underlying social anxiety, offering a potentially more objective approach to SAD assessment compared to traditional methods.

ChatGPT versus human essayists: an exploration of the impact of artificial intelligence for authorship and academic integrity in the humanities

Generative AI has prompted educators to reevaluate traditional teaching and assessment methods. This study examines AI’s ability to write essays analysing Old English poetry; human markers assessed and attempted to distinguish them from authentic analyses of poetry by first-year undergraduate students in English at the University of Oxford. Using the standard UK University grading system, AI-written essays averaged a score of 60.46, whilst human essays achieved 63.57, a margin of difference not statistically significant (p = 0.10). Notably, student submissions applied a nuanced understanding of cultural context and secondary criticism to their close reading, while AI essays often described rather than analysed, lacking depth in the evaluation of poetic features, and sometimes failing to properly recognise key aspects of passages. Distinguishing features of human essays included detailed and sustained analysis of poetic style, as well as spelling errors and lack of structural cohesion. AI essays, on the other hand, exhibited a more formal structure and tone but sometimes fell short in incisive critique of poetic form and effect. Human markers correctly identified the origin of essays 79.41% of the time. Additionally, we compare three purported AI detectors, finding that the best, ‘Quillbot’, correctly identified the origin of essays 95.59% of the time. However, given the high threshold for academic misconduct, conclusively determining origin remains challenging. The research also highlights the potential benefits of generative AI’s ability to advise on structuring essays and suggesting avenues for research. We advocate for transparency regarding AI’s capabilities and limitations, and this study underscores the importance of human critical engagement in teaching and learning in Higher Education. As AI’s proficiency grows, educators must reevaluate what authentic assessment is, and consider implementing dynamic, holistic methods to ensure academic integrity.

Expression and role of CNIH2 in prostate cancer.

Prostate cancer is one of the most common cancers in men and poses a significant threat to global male health. Traditional prostate cancer assessment methods have certain limitations, necessitating the identification of new prognostic factors and treatment targets. Our study revealed that low expression of the cornichon family AMPA receptor auxiliary protein 2 (CNIH2) gene was associated with a better progression-free survival rate in prostate cancer patients. The area under the receiver operating characteristic (ROC) curve (AUC) showed that the prognostic ability of the CNIH2 gene was high at 1, 3, and 5 years. The gene was an independent prognostic factor according to multivariate analysis. Functional verification experiments showed that knocking down the CNIH2 gene could inhibit the proliferation, migration and invasion of prostate cancer cells and could also inhibit tumor growth in nude mice. Our study is the first to reveal the important role of the CNIH2 gene in prostate cancer. This discovery provides a new research direction for individualized treatment and prognostic evaluation of prostate cancer.

Translational Quotient as an Innovative Outcome Parameter to Assess the Effectiveness of Training Methods: A Feasibility Study in Assessing the Baseline Psychiatric Skills of Primary Care Doctors in their Real-world Live Outpatient Clinic

Background: The effectiveness of training methods in medical education is critical, particularly for primary care physicians (PCPs) who frequently encounter psychiatric issues in their practice. Traditional assessment methods often fail to evaluate skill acquisition in real-world clinical practice. The Translational Quotient (TQ) is proposed as an innovative outcome measure to assess PCPs’ ability to apply psychiatric skills in their live outpatient consultation among their general patients. This study aims to evaluate the feasibility of using the TQ in real-world outpatient clinics and to understand the baseline psychiatric skills among PCPs using TQ. Methods: Actively practicing MBBS-qualified PCPs enrolled in the Diploma in Primary Care Psychiatry (DPCP) program across various districts were invited to participate. Baseline TQ assessments were conducted in the PCPs’ live clinics, with psychiatrists observing live consultations either remotely or in-person for the first five consecutive general consultations. Each consultation was scored using a standardized TQ proforma, which evaluated six criteria: elicitation of psychiatric symptoms, clinical reasoning, medication choices, counseling, time management, and overall clinical skills. Results: A total of 25 PCPs participated, with an average baseline TQ score of 15.7% (4.72 out of 30). Most participants (72%) scored 5 or less, highlighting significant gaps in psychiatric skills. Analysis revealed no significant associations between TQ scores and PCP demographics such as age, gender, and prior psychiatric training, but regional differences were noted, with lower scores in Karnataka compared to Bihar. Conclusions: The TQ is a feasible and practical tool for assessing real-world psychiatric skills among PCPs. The baseline scores indicate a pressing need for targeted psychiatric training to bridge the treatment gap in primary care. Future training programs should focus on enhancing diagnostic accuracy, treatment planning, and patient communication to improve mental healthcare outcomes in primary care settings.

Assessment and learning outcomes for generative AI in higher education: A scoping review on current research status and trends

Generative artificial intelligence (GenAI) impacts higher education assessment and learning outcomes, which are closely related and intertwined. Literature suggests that educators and researchers have many varied concerns regarding student assessment in the higher education GenAI context, such as how to assess students’ learning and the new (refocused) learning outcomes that emerged in GenAI-facilitated learning environments. To provide evidence-based insights into and answers to these concerns, we conducted a scoping review by collating literature in relevant research areas. Following a five-stage scoping review framework, we collaboratively collected and coded 34 studies. The three assessment approaches identified in the review were traditional assessment, innovative and refocused assessment and GenAI-incorporated assessment. The new, refocused learning outcomes identified were career-driven competencies and lifelong learning skills. The review also revealed that most research designs were qualitatively oriented (e.g., with exploratory design, descriptive research, ethnographic research and phenomenological research). This study proposes a holistic diagram showing the current research status and trends. It suggests five future research directions: innovative assessment designs, collaborations among assessment approaches, new learning outcomes, relationships between assessment approaches and learning outcomes, and quantitative or mixed research studies. Implications for practice or policy: Traditional assessment methods in higher education do not operate effectively in the GenAI era. Innovative and refocused assessment and GenAI-incorporated assessment are promising strategies to assess student learning. Career-driven competencies and lifelong learning skills are new focused learning outcomes evolved from the use of GenAI. More quantitative and mixed research studies should be conducted to provide additional empirical evidence on the impact of GenAI on student assessment and learning outcomes.

Thematic control and criteria-based assessment of foreign language writing skills using artificial intelligence technologies

Importance. Currently, there is a tendency that when teaching a foreign language, teachers are increasingly resorting to the use of artificial intelligence technologies to plan training sessions, generate educational content, as well as to conduct automated testing of formed communication skills. The monitoring of academic achievements and assessment is one of the key components of the organization of the educational process. Traditional methods of control and assessment require significant time and labor-intensive costs from the teacher, while artificial intelligence technologies make it possible to simplify and automate routine tasks: check tests and written papers, analyze them and identify mistakes, provide feedback. Thanks to the integration of natural language processing (NLP) technologies into chatbots and adaptive intelligent learning systems, it becomes possible on a daily basis to check texts created by students, evaluate them from the point of view of grammatical and lexical correctness, as well as identify stylistic and factual errors in real time. The purpose of this work is to test the applicability of artificial intelligence technologies for thematic control and criteria-based assessment of educational achievements using the example of productive and reproductive writing.Research Methods. In carrying out this study, the following groups of methods were used: theoretical methods aimed at familiarizing with scientific and methodological literature on the topic of research, analysis and classification of theoretical and methodological material for conducting thematic control and criterion assessment in foreign language classes, as well as empirical methods that allowed modeling pedagogical control and assessment processes using artificial intelligence technologies, observation, analysis and description of the results obtained.Definition of Concepts. The main concepts used in the study are “control of educational results” and its variety “thematic control”, “criterion assessment”.Results and Discussion. In the course of the study, various types of monitoring educational results using artificial intelligence technologies were considered: preliminary, current, intermediate, thematic, final. The choice of thematic control is due to the opportunity to trace its applicability within the framework of a single lesson in a foreign language and identify the main difficulties in using this form of control. The following criteria for evaluating writing skills are used to evaluate learning outcomes using artificial intelligence technologies: a) the structure of the written text; b) compliance with the main topic; c) coherence; d) relevance; e) grammatical correctness; f) lexical correctness; g) ethics of writing and stylistic correctness.Conclusion. Artificial intelligence technologies at the present stage have a high degree of adaptability and include a wide range of software and hardware solutions that allow for such important pedagogical procedures as monitoring educational achievements and evaluation in accordance with user-defined evaluation criteria. The obtained results are proposed to be used in research devoted to the study of modern methods of monitoring educational achievements in the methodology of teaching foreign languages using artificial intelligence technologies.

Performance of Machine Learning, Artificial Neural Network (ANN), and stacked ensemble models in predicting Water Quality Index (WQI) from surface water quality parameters, climatic and land use data

Assessing water quality is essential for managing freshwater resources, safeguarding ecosystems, and guaranteeing public health. Traditional water quality assessment methods suffer from seasonal sampling, multi-parameter requirements, and labor-intensive sampling processes, which are major constraints for the frequent monitoring of vast river basins. To overcome this issue, the study modeled the remote sensing-based climatic and land use parameters with Principal Component Analysis (PCA) to leverage Artificial Neural Networks (ANN) and machine learning (ML) algorithms to predict the Water Quality Index (WQI). The Weighted Arithmetic Water Quality Index (WAWQI) method was used to calculate the WQI of the Godavari River Basin for the available 19 stream water quality parameters (SWQPs). Further, PCA was applied to reduce the dimensionality of the parameters from 19 to 6. These results led to the development of two modeling methods to predict the WQI. In the first method, the correlation-based model was developed to predict WQI by evaluating six SWQPs. The second method, the causal-effect model, uses land use and meteorological factors to determine WQI using causality. Using advanced AutoML techniques, the initial pool of 40 ML models was meticulously evaluated and refined, culminating in the selection of the top three exemplary models such as Extreme Gradient Boosting (XGB), Extra Trees (ET), and Random Forest (RF). In both methods, XGB models show better prediction, with the coefficient of determination (R2) value of 0.95 during training and 0.83 during testing in method one. Whereas in the second method, R2 of 0.93 in training and 0.80 in testing are obtained. Further, XGB, ET, and ANN outputs were stacked with each model to enhance these results in both methods. Among these three stacked models, the stacked ANN_ML model performed better compared to stacked XGB_ML and stacked ET_ML. In the first method, the stacked ANN_ML model predicts R2 values of 0.95 and 0.91 for training and testing. In the second method, 0.95 and 0.90 for training and testing are obtained using stacked ANN_ML model. These findings emphasize the stacked model prediction ability to capture nonlinear relationships in the parameters and the novel approach of land use and climate parameters based WQI prediction, which replace the laborious, time-consuming SWQP measurements.