Artificial Intelligence-based Tools Research Articles

Ethical use of artificial intelligence based tools in higher education: are future business leaders ready?

AbstractThis study examined the ethical use of Artificial Intelligence-based Tools (AIT) in higher education, focusing on graduate business students. Drawing from a diverse sample of students from the United States of America (USA) and the United Arab Emirates (UAE), the research explored how cultural values shaped perceptions and behaviors towards ethical use of AIT. Structural Topic Modeling (STM), a machine learning technique to identify themes in open-ended responses, was used to assess the influence of culture as a covariate. Culture was classified into ten clusters comprising a group of countries, and findings were interpreted using Hofstede’s cultural framework. The study revealed significant variations in ethical perceptions across cultural clusters. For example, students from the Southern Asia cluster viewed the use of AIT to answer questions as more ethical, while students from Latin Europe were less likely to perceive it as ethical. Conversely, students from Latin Europe were more inclined to consider the use of AIT to understand concepts as ethical, compared to their Southern Asian counterparts. The findings highlight the importance of understanding cultural perceptions when integrating AIT in higher education. Addressing a significant gap in the existing educational literature, this research contributes to the broader discussion on the ethical implications of AI in education and offers practical strategies for fostering a culturally sensitive and inclusive approach while utilizing a novel methodology within the field.

Using Artificial Intelligence-Based Tools to Improve the Literature Review Process: Pilot Test with the Topic “Hybrid Meat Products”

Conducting a literature review is a mandatory initial stage in scientific research on a specific topic. However, this task is becoming much more complicated in certain areas (such as food science and technology) due to the huge increase in the number of scientific publications. Different tools based on artificial intelligence could be very useful for this purpose. This paper addresses this challenge by developing and checking different tools applicated to an emerging topic in food science and technology: “hybrid meat products”. The first tool to be applied was based on Natural Language Processing and was used to select and reduce the initial number of papers obtained from a traditional bibliographic search (using common scientific databases such as Web Science and Scopus) from 938 to 178 (a 87% reduction). The second tool was a project based on the interplay between Retrieval-Augmented Generation (RAG) and LLAMA 3, which was used to answer key questions relating to the topic under review (“hybrid meat products”) but limiting the context to the scientific review obtained after applying the first AI tool. This new strategy for reviewing scientific literature could be a major advance on from the traditional literature review procedure, making it faster, more open, more accessible to everyone, more effective, more objective, and more efficient—all of which help to fulfill the principles of open science.

An Artificial Intelligence-Based Tool for Enhancing Pectoral Muscle Segmentation in Mammograms: Addressing Class Imbalance and Validation Challenges in Automated Breast Cancer Diagnosis.

Breast cancer remains a major health concern worldwide, requiring the advancement of early detection methods to improve prognosis and treatment outcomes. In this sense, mammography is regarded as the gold standard in breast cancer screening and early detection. However, in a scenario where extensive analysis is required, a large set of mammograms conducted by radiologists may carry out false negative or false positive diagnoses. Therefore, artificial intelligence has emerged in recent years as a method for enhancing timing in breast cancer diagnosis. Nonetheless, preprocessing stages are required to prepare the mammography dataset to enhance learning models to correctly identify breast anomalies. In this paper, we introduce a novel method employing convolutional neural networks (CNNs) to segment the pectoral muscle in 1288 mediolateral oblique mammograms (MLOs), thereby addressing class imbalance and overfitting between classes, and dataset augmentation based on translation, rotation, and scale transformation. The effectiveness of the model was assessed through a confusion matrix and performance metrics, highlighting an average Dice coefficient of 0.98 and a Jaccard index of 0.96. The outcomes demonstrate the model capability to accurately identify three classes: pectoral muscle, breast, and background. This study emphasizes the importance of tackling class imbalance problems and augmenting data for the training of models for reliable early breast cancer detection.

A Machine Learning Framework for Condition-Based Maintenance of Marine Diesel Engines: A Case Study

The development of artificial intelligence-based tools is having a big impact on industry. In this context, the maintenance operations of important assets and industrial resources are changing, both from a theoretical and a practical perspective. Namely, conventional maintenance reacts to faults and breakdowns as they occur or schedules the necessary inspections of systems and their parts at fixed times by using statistics on component failures, but this can be improved by a predictive maintenance based on the real component’s health status, which is inspected by appropriate sensors. In this way, maintenance time and costs are saved. Improvements can be achieved even in the marine industry, in which complex ship propulsion systems are produced for operation in many different scenarios. In more detail, data-driven models, through machine learning (ML) algorithms, generate the expected values of monitored variables for comparison with real measurements on the asset, for a diagnosis based on the difference between expectations and observations. The first step towards realization of predictive maintenance is choosing the ML algorithm. This selection is often not the consequence of an in-depth analysis of the different algorithms available in the literature. For that reason, here the authors propose a framework to support an initial implementation stage of predictive maintenance based on a benchmarking of the most suitable ML algorithms. The comparison is tested to predict failures of the oil circuit in a diesel marine engine as a case study. The algorithms are compared by considering not only the mean squared error between the algorithm predictions and the data, but also the response time, which is a crucial variable for maintenance. The results clearly indicate the framework well supports predictive maintenance and the prediction error and running time are appropriate variables to choose the most suitable ML algorithm for prediction. Moreover, the proposed framework can be used to test different algorithms, on the basis of more performance indexes, and to apply predictive maintenance to other engine components.

Examining the Professional Knowledge on Ethical Integration of Artificial Intelligence-Based Tools on Higher Education Instructors' Attitudes Toward Artificial Intelligence in the Context of the Fourth Industrial Revolution

Examining the Professional Knowledge on Ethical Integration of Artificial Intelligence-Based Tools on Higher Education Instructors' Attitudes Toward Artificial Intelligence in the Context of the Fourth Industrial Revolution

Technology-enabled Justice in Indian Courts: New Dilemmas and Way Forward

The adoption of technology in Indian courts has improved and increased the rate of data collection, particularly from court proceedings. Data is now available in accessible formats, making them valuable for developing artificial intelligence-based tools. While the potential for risks and harms from incomplete or biased datasets is known and documented, there are also system-level issues that emerge from this datafication and adoption of advanced technologies in justice delivery systems. They can lead to an over-reliance on quantifiable aspects of the system, hinder the development of legal theory and lead to the commercialisation of case data. With advances in data processing and analytics, earlier open-by-default models for case data need a careful rethink, considering the potential for misuse of personal and sensitive information and commercialisation of publicly available data. Adequate safeguards rooted in a legal basis and built through wide stakeholder deliberation are needed to meet the ends of technology-enabled justice.

A Handheld Tool for the Rapid Morphological Identification of Mosquito Species (VectorCam) for Community-Based Malaria Vector Surveillance: Summative Usability Study.

Malaria impacts nearly 250 million individuals annually. Specifically, Uganda has one of the highest burdens, with 13 million cases and nearly 20,000 deaths. Controlling the spread of malaria relies on vector surveillance, a system where collected mosquitos are analyzed for vector species' density in rural areas to plan interventions accordingly. However, this relies on trained entomologists known as vector control officers (VCOs) who identify species via microscopy. The global shortage of entomologists and this time-intensive process cause significant reporting delays. VectorCam is a low-cost artificial intelligence-based tool that identifies a mosquito's species, sex, and abdomen status with a picture and sends these results electronically from surveillance sites to decision makers, thereby deskilling the process to village health teams (VHTs). This study evaluates the usability of the VectorCam system among VHTs by assessing its efficiency, effectiveness, and satisfaction. The VectorCam system has imaging hardware and a phone app designed to identify mosquito species. Two users are needed: (1) an imager to capture images of mosquitos using the app and (2) a loader to load and unload mosquitos from the hardware. Critical success tasks for both roles were identified, which VCOs used to train and certify VHTs. In the first testing phase (phase 1), a VCO and a VHT were paired to assume the role of an imager or a loader. Afterward, they swapped. In phase 2, two VHTs were paired, mimicking real use. The time taken to image each mosquito, critical errors, and System Usability Scale (SUS) scores were recorded for each participant. Overall, 14 male and 6 female VHT members aged 20 to 70 years were recruited, of which 12 (60%) participants had smartphone use experience. The average throughput values for phases 1 and 2 for the imager were 70 (SD 30.3) seconds and 56.1 (SD 22.9) seconds per mosquito, respectively, indicating a decrease in the length of time for imaging a tray of mosquitos. The loader's average throughput values for phases 1 and 2 were 50.0 and 55.7 seconds per mosquito, respectively, indicating a slight increase in time. In terms of effectiveness, the imager had 8% (6/80) critical errors and the loader had 13% (10/80) critical errors in phase 1. In phase 2, the imager (for VHT pairs) had 14% (11/80) critical errors and the loader (for VHT pairs) had 12% (19/160) critical errors. The average SUS score of the system was 70.25, indicating positive usability. A Kruskal-Wallis analysis demonstrated no significant difference in SUS (H value) scores between genders or users with and without smartphone use experience. VectorCam is a usable system for deskilling the in-field identification of mosquito specimens in rural Uganda. Upcoming design updates will address the concerns of users and observers.

Being diagnosed with a rhabdomyosarcoma in the era of artificial intelligence: Whom can we trust?

In the era of big data, young patients may be overwhelmed by artificial intelligence-based tools, like chatbots. Five clinical experts were asked to evaluate the performance of the most currently used chatbots in providing information on a rare cancer affecting young people, like rhabdomyosarcoma. Generally speaking, despite their high performance in giving general information about the disease, these chatbots were considered by the experts to be inadequate in providing suggestions on cancer treatments and specialized centers, and also lacking in "sensitivity." Efforts are planned by the pediatric oncology community to improve the quality of data used to train these tools.

Does ChatGPT generate fake results? Challenges in retrieving content through ChatGPT

PurposeChatGPT is a new development in this technological era. This artificial intelligence-based tool responds to individuals’ queries and produces the requested content within seconds. Therefore, it is becoming popular among academics, the research community and library professionals. This study aims to test (through personal interaction with the tool) the authenticity of the ChatGPT’s produced records. Another objective of the research is to check the relevance between the individuals’ queries and the tool’s results. The research also intends to identify the challenges in retrieving information through ChatGPT.Design/methodology/approachThe five researchers from different countries and organizations experienced ChatGPT by asking questions on more than 70 subjects. The responses were recorded in Notepad and converted into MS Excel and MS Access to standardize and analyze the data. The investigators consulted 11 reputed databases/sources, including Web of Science and Scopus, to assess the authenticity of the data retrieved through ChatGPT.FindingsThe findings confirmed that over 90% of results produced by ChatGPT were fake (the information did not exist in the literature). Similarly, the study sheds light on the discrepancies, such as irrelevant and incomplete information in the data generated by ChatGPT.Originality/valueThis is a unique study that shares the findings based on the different regions’ researchers’ personal experiences with ChatGPT. The researchers covered different subject areas (above 70) while asking questions to ChatGPT. The paper shares implications for researchers, students, faculty members, academic/research organizations and policymakers.

The Future of Nanotechnology-Driven Electrochemical and Electrical Point-of-Care Devices and Diagnostic Tests.

Point-of-care (POC) devices have become rising stars in the biosensing field, aiming at prognosis and diagnosis of diseases with a positive impact on the patient but also on healthcare and social care systems. Putting the patient at the center of interest requires the implementation of noninvasive technologies for collecting biofluids and the development of wearable platforms with integrated artificial intelligence-based tools for improved analytical accuracy and wireless readout technologies. Many electrical and electrochemical transducer technologies have been proposed for POC-based sensing, but several necessitate further development before being widely deployable. This review focuses on recent innovations in electrochemical and electrical biosensors and their growth opportunities for nanotechnology-driven multidisciplinary approaches. With a focus on analytical aspects to pave the way for future electrical/electrochemical diagnostics tests, current limitations and drawbacks as well as directions for future developments are highlighted.

Evaluating artificial intelligence-enhanced digital urine cytology for bladder cancer diagnosis.

This study evaluated the diagnostic effectiveness of the AIxURO platform, an artificial intelligence-based tool, to support urine cytology for bladder cancer management, which typically requires experienced cytopathologists and substantial diagnosis time. One cytopathologist and two cytotechnologists reviewed 116 urine cytology slides and corresponding whole-slide images (WSIs) from urology patients. They used three diagnostic modalities: microscopy, WSI review, and AIxURO, per The Paris System for Reporting Urinary Cytology (TPS) criteria. Performance metrics, including TPS-guided and binary diagnosis, inter- and intraobserver agreement, and screening time, were compared across all methods and reviewers. AIxURO improved diagnostic accuracy by increasing sensitivity (from 25.0%-30.6% to 63.9%), positive predictive value (PPV; from 21.6%-24.3% to 31.1%), and negative predictive value (NPV; from 91.3%-91.6% to 95.3%) for atypical urothelial cell (AUC) cases. For suspicious for high-grade urothelial carcinoma (SHGUC) cases, it improved sensitivity (from 15.2%-27.3% to 33.3%), PPV (from 31.3%-47.4% to 61.1%), and NPV (from 91.6%-92.7% to 93.3%). Binary diagnoses exhibited an improvement in sensitivity (from 77.8%-82.2% to 90.0%) and NPV (from 91.7%-93.4% to 95.8%). Interobserver agreement across all methods showed moderate consistency (κ=0.57-0.61), with the cytopathologist demonstrating higher intraobserver agreement than the two cytotechnologists across the methods (κ=0.75-0.88). AIxURO significantly reduced screening time by 52.3%-83.2% from microscopy and 43.6%-86.7% from WSI review across all reviewers. Screening-positive (AUC+) cases required more time than negative cases across all methods and reviewers. AIxURO demonstrates the potential to improve both sensitivity and efficiency in bladder cancer diagnostics via urine cytology. Its integration into the cytopathological screening workflow could markedly decrease screening times, which would improve overall diagnostic processes.

O-003 COC classifier: a new artificial intelligence-based tool for identifying mature oocytes from cumulus- oocyte-complexes

Abstract Study question Can the use of artificial intelligence (AI) enhance the prediction of mature oocytes (MII) from Cumulus-Oocytes-Complexes (COC) significantly surpassing the accuracy of well-trained embryologists? Summary answer The development of a COC classifier, an AI-based tool, improves the prediction of mature oocytes from COCs graded as 3 and 4 before oocyte denudation. What is known already Determining the maturity of Metaphase II oocytes before denudation is a challenge in assisted reproduction due to the presence of a dense cumulus mass surrounding the oocyte and obstructing proper manual scoring, a critical step in intracytoplasmic sperm injection (ICSI) due to risk of granulosa cells removal from immature oocytes. Although there is a certain correlation between COC morphology and nuclear oocyte maturity, it is not 100% accurate. It is reported that approximately 90% of MII oocytes are expected in expanded COCs (grade 1), while in COCs grade 4, more immature oocytes are predicted and only 25% are MII oocytes. Study design, size, duration 931 COC's from 145 patients were submitted to COC grading by both, manual and a new “COC classifier” from October to January 2023. 4 groups were formed according to Ebner criteria, 2008. Grade 1: 192 COC's (suspected mature), fluffy and radiant corona and cumulus; Grade 2: 318 COC's showing fluffy cumulus (suspected mature); Grade 3: 208 COC's with radiant corona (expected mature) and grade 4: 213 COC's (suspected immature) with dense cumulus without visible oocyte. Participants/materials, setting, methods Prospective study included 145 patients (39.3 years ±3.2) from September to December 2023. After COC obtention, excess of granulosa cells, dark and blood cells were removed. 3 hours after egg collection, COCs were photographed and scored manually by 9 well trained embryologists. Before denudation, obtained COCs were classified in 4 morphological stages according to Ebner et al, 2008. Finally, the taken photos from COC's were analysed by the COC classifier, a sypervised deep learning algorithm. Main results and the role of chance After COC's classification as following: Group 1 (suspected mature), fluffy and radiant corona and cumulus with visible oocyte; Group 2, COC's showing dense corona (oocyte clearly visible) but fluffy cumulus (suspected mature); Group 3, COC's with radiant corona (oocyte visible, expected mature); Group 4, COC's (suspected immature) with dense corona and cumulus without visible oocyte. The new software presented an MII oocyte accuracy of 79.16% for group 1, 87.1% for group 2, 83.17% for group 3, and 73.23% for group 4. In comparison, manual COCs grading by nine experienced embryologists yielded accuracy rates of 73.5% MII oocytes in group 1, 79.5% for group 2, 50.3% for group 3, and 46.9% for group 4. Statistical analysis, using the chi-square test, was performed to compare the accuracy rates between the COC classifier and manual grading. The results revealed significant differences in favor of the COC classifier when compared to manual method for the groups 3 and 4 (p < 0.001). These results indicate a superior performance of the COC classifier in predicting MII oocytes for groups with highest rates of inmture oocytes. However, for groups 1 and 2, there were no statistically significant differences between the COC classifier and manual grading. Limitations, reasons for caution Further validation through a large-scale, prospective, randomized study is necessary to confirm the efficacy and reliability of the new COC classifier, particularly in patients with oocyte cohorts enriched with grade 3 and 4 COCs. Ongoing research is currently being conducted in our laboratory. Wider implications of the findings The new COC classifier, an AI-based tool, developed by our group, offers a non-invasive and efficient method in predicting mature oocytes before denudation by identifying more MII oocytes from patients’ cohorts enriched with grade 3 and 4 COC's, postponing denudation and injection timing or destinating them to conventional IVF Trial registration number 5678765

Utilization of artificial intelligence in minimally invasive right adrenalectomy: recognition of anatomical landmarks with deep learning

Background The primary surgical approach for removing adrenal masses is minimally invasive adrenalectomy. Recognition of anatomical landmarks during surgery is critical for minimizing complications. Artificial intelligence-based tools can be utilized to create real-time navigation systems during laparoscopic and robotic right adrenalectomy. In this study, we aimed to develop deep learning models that can identify critical anatomical structures during minimally invasive right adrenalectomy. Methods In this experimental feasibility study, intraoperative videos of 20 patients who underwent minimally invasive right adrenalectomy in a tertiary care center between 2011 and 2023 were analyzed and used to develop an artificial intelligence-based anatomical landmark recognition system. Semantic segmentation of the liver, the inferior vena cava (IVC), and the right adrenal gland were performed. Fifty random images per patient during the dissection phase were extracted from videos. The experiments on the annotated images were performed on two state-of-the-art segmentation models named SwinUNETR and MedNeXt, which are transformer and convolutional neural network (CNN)-based segmentation architectures, respectively. Two loss function combinations, Dice-Cross Entropy and Dice-Focal Loss were experimented with for both of the models. The dataset was split into training and validation subsets with an 80:20 distribution on a patient basis in a 5-fold cross-validation approach. To introduce a sample variability to the dataset, strong-augmentation techniques were performed using intensity modifications and perspective transformations to represent different surgery environment scenarios. The models were evaluated by Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) which are widely used segmentation metrics. For pixelwise classification performance, accuracy, sensitivity and specificity metrics were calculated on the validation subset. Results Out of 20 videos, 1000 images were extracted, and the anatomical landmarks (liver, IVC, and right adrenal gland) were annotated. Randomly distributed 800 images and 200 images were selected for the training and validation subsets, respectively. Our benchmark results show that the utilization of Dice-Cross Entropy Loss with the transformer-based SwinUNETR model achieved 78.37%, whereas the CNN-based MedNeXt model reached a 77.09% mDSC score. Conversely, MedNeXt reaches a higher mIoU score of 63.71% than SwinUNETR by 62.10% on a three-region prediction task. Conclusion Artificial intelligence-based systems can predict anatomical landmarks with high performance in minimally invasive right adrenalectomy. Such tools can later be used to create real-time navigation systems during surgery in the near future.

Review of Artificial Intelligence-Based Tools in EFL Classroom

Review of Artificial Intelligence-Based Tools in EFL Classroom

Radiographic diagnosis of periodontal diseases - Current evidence versus innovations.

Accurate diagnosis of periodontal and peri-implant diseases relies significantly on radiographic examination, especially for assessing alveolar bone levels, bone defect morphology, and bone quality. This narrative review aimed to comprehensively outline the current state-of-the-art in radiographic diagnosis of alveolar bone diseases, covering both two-dimensional (2D) and three-dimensional (3D) modalities. Additionally, this review explores recent technological advances in periodontal imaging diagnosis, focusing on their potential integration into clinical practice. Clinical probing and intraoral radiography, while crucial, encounter limitations in effectively assessing complex periodontal bone defects. Recognizing these challenges, 3D imaging modalities, such as cone beam computed tomography (CBCT), have been explored for a more comprehensive understanding of periodontal structures. The significance of the radiographic assessment approach is evidenced by its ability to offer an objective and standardized means of evaluating hard tissues, reducing variability associated with manual clinical measurements and contributing to a more precise diagnosis of periodontal health. However, clinicians should be aware of challenges related to CBCT imaging assessment, including beam-hardening artifacts generated by the high-density materials present in the field of view, which might affect image quality. Integration of digital technologies, such as artificial intelligence-based tools in intraoral radiography software, the enhances the diagnostic process. The overarching recommendation is a judicious combination of CBCT and digital intraoral radiography for enhanced periodontal bone assessment. Therefore, it is crucial for clinicians to weigh the benefits against the risks associated with higher radiation exposure on a case-by-case basis, prioritizing patient safety and treatment outcomes.

The affordances of artificial intelligence-based tools for supporting 21st-century skills:

Twenty-first-century skills should be integrated into higher education to prepare students for complex working-life challenges. Artificial intelligence (AI)-powered tools have the potential to optimise skill development among higher education students. Therefore, it is important to conceptualise relevant affordances of AI systems for 21st-century skills development in higher education. This study aimed to present an overview of journal articles published in the Web of Science database that specifically addressed the affordances of AI-based tools for 21st-century skills development. Four distinct categories of AI-based tools (intelligent tutoring systems, chatbots, AI-powered dashboards and automated grading systems) were identified as capable of promoting six main 21st-century skills (collaboration, communication, creativity, critical thinking, information and communication technology and problem-solving). The review revealed that the utilisation of AI-based tools might contribute to the simultaneous development of multiple 21st-century skills (e.g., collaboration and critical thinking). The results showed that adaptive feedback from AI plays a significant role as a facilitator in the development of 21st-century skills. Furthermore, the utilisation of diverse functional AI affordances (e.g., prediction and profiling) might contribute to the development of various skills. AI-based technologies appeared to target the 21st-century skills of problem-solving and its subskills the most. Implications for practice or policy: More functional affordances of AI (e.g., prediction and profiling) should be employed in AI-based tools. This could support higher education students’ 21st-century skills. AI-based tools (e.g., chatbots and intelligent tutors) interact with end users through their data. AI systems have the potential to promote 21st-century skills by using students’ multimodal data. AI technologies should be more integrated into the social sciences and humanities in the higher education context to support students’ 21st-century skills.

Artificial Neural Network (ANN)-Based Water Quality Index (WQI) for Assessing Spatiotemporal Trends in Surface Water Quality—A Case Study of South African River Basins

Artificial neural networks (ANNs) are powerful data-oriented “black-box” algorithms capable of assessing and delineating linear and multifaceted non-linear correlations between the dependent and explanatory variables. Through the years, neural networks have proven to be effective and robust analytical techniques for establishing artificial intelligence-based tools for modelling, estimating, and projecting spatial and temporal variations in water bodies. Accordingly, ANN-based algorithms gained increased attention and have emerged as practical alternatives to traditional approaches for hydro-chemical analysis. ANNs are among the widely used computer systems for modelling surface water quality. Considering their wide recognition, resilience, flexibility, and accuracy, the current study employs a neural network-based methodology to construct a novel water quality index (WQI) model suitable for analysing South African rivers. The feed-forward, back-propagated multilayered perceptron model has three parallel-distributed neuron layers interconnected with seventy weighted links orientated laterally from left to right. First, the input layer includes thirteen neuro-nodes symbolising thirteen explanatory variables, including NH3, Ca, Cl, Chl-a, EC, F, CaCO3, Mg, Mn, NO3, pH, SO4, and turbidity (NTU). Second, the hidden layer consists of eleven neuro-nodes accountable for computational tasks. Lastly, the output layer features one neuron responsible for conveying network outcomes using a single-digit WQI rating extending from zero to one hundred, where zero represents substandard water quality and one hundred denotes exceptional water quality. The AI-based model was developed using water quality data obtained from six monitoring locations within four drainage basins under the management of the Umgeni Water Board in the KwaZulu-Natal Province of South Africa. The dataset comprises 416 samples randomly divided into training, testing, and validation sets using a proportional split of 70:15:15%. The Broyden–Fletcher–Goldfarb–Shanno (BFGS) technique was utilised to conduct backpropagation training and adjust synapse weights. The dependent variables are the WQI scores from the universal water quality index (UWQI) model developed specifically for South African river basins. The ANN demonstrated enhanced efficiency through an overall correlation coefficient (R) of 0.985. Furthermore, the neural network attained R-values of 0.987, 0.992, and 0.977 for the training, testing, and validation intervals. The ANN model achieved a Nash–Sutcliffe efficiency (NSE) value of 0.974 and coefficient of determination (R2) of 0.970. Sensitivity analysis provided additional validation of the preparedness and computational competence of the ANN model. The typical target-to-output error tolerance for the ANN model is 0.242, demonstrating an adequate predictive ability to deliver results comparable with the target UWQI, having the lowest and highest index ratings of 75.995 and 94.420, respectively. Accordingly, the three-layer neural network is scientifically sound, with index values and water quality evaluations corresponding to the UWQI results. The current research project seeks to document the processes used and the outcomes obtained.

Artificial intelligence-based tools with automated segmentation and measurement on CT images to assist accurate and fast diagnosis in acute pancreatitis.

To develop an artificial intelligence (AI) tool with automated pancreas segmentation and measurement of pancreatic morphological information on CT images to assist improved and faster diagnosis in acute pancreatitis. This study retrospectively contained 1124 patients suspected for AP and received non-contrast and enhanced abdominal CT examination between September 2013 and September 2022. Patients were divided into training (N = 688), validation (N = 145), testing dataset [N = 291; N = 104 for normal pancreas, N = 98 for AP, N = 89 for AP complicated with PDAC (AP&PDAC)]. A model based on convolutional neural network (MSAnet) was developed. The pancreas segmentation and measurement were performed via eight open-source models and MSAnet based tools, and the efficacy was evaluated using dice similarity coefficient (DSC) and intersection over union (IoU). The DSC and IoU for patients with different ages were also compared. The outline of tumour and oedema in the AP and were segmented by clustering. The diagnostic efficacy for radiologists with or without the assistance of MSAnet tool in AP and AP&PDAC was evaluated using receiver operation curve and confusion matrix. Among all models, MSAnet based tool showed best performance on the training and validation dataset, and had high efficacy on testing dataset. The performance was age-affected. With assistance of the AI tool, the diagnosis time was significantly shortened by 26.8% and 32.7% for junior and senior radiologists, respectively. The area under curve (AUC) in diagnosis of AP was improved from 0.91 to 0.96 for junior radiologist and 0.98 to 0.99 for senior radiologist. In AP&PDAC diagnosis, AUC was increased from 0.85 to 0.92 for junior and 0.97 to 0.99 for senior. MSAnet based tools showed good pancreas segmentation and measurement performance, which help radiologists improve diagnosis efficacy and workflow in both AP and AP with PDAC conditions. This study developed an AI tool with automated pancreas segmentation and measurement and provided evidence for AI tool assistance in improving the workflow and accuracy of AP diagnosis.

Beyond the AJR: Clinical Application of Artificial Intelligence-Based Tools for ARIA Detection and Severity Scoring.

Beyond the AJR: Clinical Application of Artificial Intelligence-Based Tools for ARIA Detection and Severity Scoring.

An Artificial Intelligence-based tool to predict “unhealthy” wine and olive oil

The application of Artificial Intelligence (AI) in the agri-food industry has witnessed significant advancements, particularly in healthy food, quality assessment, and geographical origin determination of agri-products such as wine and olive oils, whose international market is constantly growing. This paper explores the applicability of Machine Learning (ML) models for predicting “unhealthy” wines and olive oils. As for the healthy factor, two main characteristics of wines and olive oils were evaluated: their quality and their geographical origin. In the study, 3 ML algorithms were compared (Random Forest, Linear Discriminant Analysis, and K-Nearest Neighbors) to predict just by observing their chemical characteristics: i) the quality of red and white wine and ii) the geographical origins of wine and olive oils. Real datasets were used for these case studies. The Synthetic Minority Over-sampling Technique (SMOTE) was used to manage imbalanced data, and well-adopted AI metrics were collected to evaluate the accuracy of the predictions made by the 3 ML algorithms. 3 datasets were analyzed: dataset #01 contains ∼7000 data entries related to 2 types of wine (red and white Portuguese wines) and 11 wine's chemical characteristics; dataset #02 contains 178 data entries related to 3 different Italian vineyards and 13 wine's chemical characteristics; dataset #03 contains 572 data entries related to 9 different Italian geographical regions for olive oil and 7 fatty acid characteristics. A total of ∼7700 data points, 5 wines and 9 olive oil types, and 31 chemical characteristics were analyzed. 12 quality metrics were collected per each dataset analysis. The designed ML models achieved good accuracy (>0.65) in predicting the wine quality, a very high accuracy (>0.99) in predicting its vineyard, and a very good accuracy (>0.97) in predicting the origin of olive oil. Moreover, an AI-based tool has been developed that stakeholders can use to predict the quality and geographical origin of wine and olive oil to avoid possible fraudulent and unhealthy product labels. The obtained prediction results showcase AI and ML's potential to help the agri-food industry, providing valuable insights and innovations for producers, distributors, and consumers alike. Integrating AI and ML in the agri-food industry may enhance product quality, consumer trust, and market transparency.