Artificial Intelligence Techniques Research Articles

Imputing Data Gaps in Economic Surveys Using Fuzzy Sets and Artificial Intelligence Technique

Imputing Data Gaps in Economic Surveys Using Fuzzy Sets and Artificial Intelligence Technique

A systematic scoping review exploring variation in practice in specimen mammography for Intraoperative Margin Analysis in Breast Conserving Surgery and the role of artificial intelligence in optimising diagnostic accuracy

PurposeSpecimen Mammography (SM) is commonly used in Breast Conserving Surgery (BCS) for intraoperative margin analysis. A systematic scoping review was conducted to identify sources of methodological variation in Specimen Mammography Interpretation (SMI) and assess the role of Artificial Intelligence (AI) techniques to optimise Diagnostic Accuracy (DA). MethodsEmbase, Pubmed, Cochrane and web of science databases were searched. Studies were included if SM was used for margin analysis for BCS with reported DA compared with pathological margin status and data extracted. Results1242 unique studies were identified, of which 40 were included. 39/40 studies did not utilise AI for SMI, with 4 studies comparing 2 relevant techniques, giving 43 non-AI study arms for analysis. There was wide variation in SM techniques, including number of views and location of SM. Specialist performing SMI in usual clinical practice was surgeon (13/39 studies;33 %), radiologist(s) (16/39;41 %), surgeon and radiologist (3/39;8 %) or not stated (7/39;18 %) which differed from the study specialist in 15/39 (38 %) of studies. Diagnostic accuracy in studies ranged from sensitivity 19–91.7 % and specificity 25–100 %. ConclusionsThere is marked variation in current techniques used for SM for intraoperative margin analysis with correspondingly disparate DA. Only 1 study applied AI to SMI, and we identify how AI could optimise SMI and a template for future work to apply AI techniques to SMI, reduce unwarranted variation and optimise DA.

Artificial intelligence-based prediction of pathogen emergence and evolution in the world of synthetic biology.

The emergence of new techniques in both microbial biotechnology and artificial intelligence (AI) is opening up a completely new field for monitoring and sometimes even controlling the evolution of pathogens. However, the now famous generative AI extracts and reorganizes prior knowledge from large datasets, making it poorly suited to making predictions in an unreliable future. In contrast, an unfamiliar perspective can help us identify key issues related to the emergence of new technologies, such as those arising from synthetic biology, whilst revisiting old views of AI or including generative AI as a generator of abduction as a resource. This could enable us to identify dangerous situations that are bound to emerge in the not-too-distant future, and prepare ourselves to anticipate when and where they will occur. Here, we emphasize the fact that amongst the many causes of pathogen outbreaks, often driven by the explosion of the human population, laboratory accidents are a major cause of epidemics. This review, limited to animal pathogens, concludes with a discussion of potential epidemic origins based on unusual organisms or associations of organisms that have rarely been highlighted or studied.

Circular supply chain for smart production in Industry 4.0

Sustainable practices in industrial engineering are not just ideal but necessary. The push for Circular Supply Chain (CSC) in Industry 4.0 has become increasingly vital. Motivated by this, this study proposed the UNISONE framework, integrated with advanced smart production technologies grounded in CSC principles. The proposed framework resulted in enhanced operational efficiency and a sustainable production system that significantly minimizes waste. The research was validated through an empirical study within a bearing factory, successfully demonstrating the framework’s efficacy and creating value within the CSC paradigm. Key findings include the impact of different signal-to-noise ratios on model performance, with peak test accuracy at a noise ratio of 0.6, and the best results of 85.32% accuracy achieved by combining sparse and noise reduction autoencoder techniques in generative artificial intelligence. This study underscores the framework’s potential to address industrial engineering challenges and promote scalable, efficient, and eco-conscious manufacturing, benefiting both the environment and the economy.

Advances and prospects of multi-modal ophthalmic artificial intelligence based on deep learning: a review.

In recent years, ophthalmology has emerged as a new frontier in medical artificial intelligence (AI) with multi-modal AI in ophthalmology garnering significant attention across interdisciplinary research. This integration of various types and data models holds paramount importance as it enables the provision of detailed and precise information for diagnosing eye and vision diseases. By leveraging multi-modal ophthalmology AI techniques, clinicians can enhance the accuracy and efficiency of diagnoses, and thus reduce the risks associated with misdiagnosis and oversight while also enabling more precise management of eye and vision health. However, the widespread adoption of multi-modal ophthalmology poses significant challenges. In this review, we first summarize comprehensively the concept of modalities in the field of ophthalmology, the forms of fusion between modalities, and the progress of multi-modal ophthalmic AI technology. Finally, we discuss the challenges of current multi-modal AI technology applications in ophthalmology and future feasible research directions. In the field of ophthalmic AI, evidence suggests that when utilizing multi-modal data, deep learning-based multi-modal AI technology exhibits excellent diagnostic efficacy in assisting the diagnosis of various ophthalmic diseases. Particularly, in the current era marked by the proliferation of large-scale models, multi-modal techniques represent the most promising and advantageous solution for addressing the diagnosis of various ophthalmic diseases from a comprehensive perspective. However, it must be acknowledged that there are still numerous challenges associated with the application of multi-modal techniques in ophthalmic AI before they can be effectively employed in the clinical setting.

Using Generative AI for Strategic HR Planning: How AI Can Elevate Your People Strategy

This article explores how generative artificial intelligence (AI) technologies such as machine learning and deep learning can be applied to enhance strategic human resource (HR) planning. Drawing from academic literature and industry case studies, the article outlines key techniques of gen AI and principles for responsible implementation. It then discusses specific opportunities for gen AI to elevate HR processes like recruiting, training, performance management, compensation planning, and cultural transformation from descriptive to prescriptive levels through data-driven decision making and insights. Aligning AI goals with organizational values around diversity, ethics and worker well-being is emphasized. The essay aims to translate technical concepts into practical recommendations while arguing that when guided properly, gen AI shows strong potential to empower HR leaders and elevate their people strategy through personalization, prediction, continuous improvement and robust measurement of ROI.

Constructing three-dimension digital rock with porosity information constraint: A double-network-cycled style-based deep-learning approach

Understanding reservoir properties from geophysical responses necessitates the construction of accurate petrophysical templates based on adequate petrophysical data. However, engineering coring is often limited by complex subsurface conditions and high costs. Artificial intelligence (AI) techniques offer an efficient and economical way to synthesize digital samples. Nevertheless, traditional deep learning approaches may suffer from mode collapse, particularly when generating samples with complex structures from a limited number of training samples. To address this challenge, we propose novel Generative Adversarial Networks (GANs) to controllably generate 3D digital rock samples according to porosity distribution. By employing a style-transfer generator, multi-scale information of 3D digital rock is integrated into the generation process, effectively reducing the risk of mode collapse. Embedding the generator into a double-network-cycled framework further enhances the controllability of conditional information in the generated samples. Our analysis shows that the minimum error between the generated samples and the desired samples in terms of porosity is only 0.07%. A clear contrast is observed in morphological parameters, and differences in pore structure lead to significant variations in mechanical and hydraulic properties between original samples and synthetic samples with similar porosity. This indicates that the property contrast is likely caused by differences in pore structures rather than porosity. These findings will assist in future studies on the effect of pore structure on petrophysical properties and improve the utility of rock physics templates in geophysical inversion.

AI-Based Risk Assessments in Forensic Auditing: Benefits, Challenges and Future Implications

Forensic auditing is a critical component of ensuring financial integrity and detecting fraud within organizations. Traditional methods of risk assessment in forensic auditing often rely on manual processes, which can be time-consuming, labour-intensive, and prone to human error. In recent years, the integration of artificial intelligence (AI) techniques has revolutionized the field, offering more efficient and accurate risk assessment capabilities. This abstract explores the role of AI-based risk assessment in forensic auditing, highlighting its benefits, challenges, and future implications. AI-based risk assessment leverages advanced algorithms and machine learning models to analyse large volumes of financial data, identify patterns, anomalies, and potential red flags indicative of fraudulent activities. By automating repetitive tasks such as data collection, classification, and analysis, AI streamlines the auditing process, enabling forensic auditors to focus on interpreting results and making informed decisions. One of the primary advantages of AI-based risk assessment is its ability to detect complex fraud schemes that may go unnoticed by traditional methods. Machine learning algorithms can detect subtle deviations from expected behaviour, flagging transactions or activities that exhibit unusual patterns or characteristics. Moreover, AI systems can adapt and learn from new data, continuously improving their detection capabilities over time. Another benefit of AI-based risk assessment is its scalability and efficiency. With the increasing volume and complexity of financial transactions, manual auditing processes struggle to keep pace. AI, on the other hand, can analyse vast datasets in a fraction of the time it would take a human auditor, allowing organizations to conduct more comprehensive and timely audits.

Digital transformation technologies for conveyor belts predictive maintenance: a review

The availability of condition-monitoring data has increased due to internet of things (IoT) technologies, providing information on various parameters like vibration, temperature, current, and voltage. Cloud computing and big data facilitate the prevention of failures and estimation of remaining useful life through advanced mathematical models and artificial intelligence (AI) techniques. These enable prompt and suitable maintenance actions. This article conducts a systematic review of digital transformation technologies, including cloud computing, edge computing, AI, machine learning (ML), and TinyML, in predictive maintenance for conveyor belt systems. This article reviews how these digital transformation technologies improve predictive maintenance strategies for conveyor belts. The systematic review summarizes the results and challenges of various methodologies used in conveyor belt systems and suggests areas for further research. This paper aimed to serve as a useful resource for researchers, practitioners, and industry professionals seeking insights into current predictive maintenance technologies for conveyor belt systems. The takeaways of the review are expected to ignite discussion on efficient and proactive maintenance strategies and promote the development of innovative solutions for ensuring the reliability and longevity of conveyor belt systems in the digital era.

An enhanced AI-based model for financial fraud detection

The research seeks to identify complex fraudulent activities. Artificial intelligence (AI) techniques, such as machine learning and deep learning, have shown significant potential in enhancing the accuracy and efficiency of fraud detection models. This study introduces a novel AI-based fraud detection model that combines both supervised and unsupervised learning methods. The proposed machine learning system uses these techniques to detect fraudulent transactions. The supervised learning component is trained using a labeled dataset that includes both fraudulent and non-fraudulent transactions. The dataset used in the research contains 284,807 credit card transactions. After preparing the data, four Python-based models were developed. The K-Nearest Neighbors (KNN) model successfully predicted 99.94% of credit card transactions as valid or fraudulent. A random forest (RF) model was also used to assess the legitimacy of transactions, achieving an accuracy score of 99.96% correctly classifying nearly all data points. The Support Vector Machine (SVM) model achieved 99.94% accuracy, misclassifying only 51 cases. The logistic regression (LR) model attained an accuracy of 99.92% with 70 misclassifications and 99.91% with 77 misclassifications. These models demonstrate high accuracy and efficiency.

Imaging Recommendations for Diagnosis, Staging, and Management of Primary Central Nervous System Neoplasms in Adults

Central nervous system (CNS) neoplasms are a vast and diverse group of tumors in adults with variable prognoses depending on histology and increasingly understood molecular features. There has been a major paradigm shift in the approach towards these neoplasms ever since the implications of these molecular features have been recognized. Gliomas are the major group of primary CNS neoplasms in adults, and glioblastomas are a significant cause of morbidity and mortality, especially in older patients. Apart from gliomas, meningiomas and pituitary tumors are other major groups. This review aims to elucidate the role of imaging in the screening, diagnosis, management, and follow-up of major primary CNS neoplasms, with an elaborate discussion on the role of artificial intelligence and advanced imaging techniques and future directions likely to play a pivotal role in this ever-evolving subspecialty of oncology.

Utilizing customized CNN for brain tumor prediction with explainable AI

Timely diagnosis of brain tumors using MRI and its potential impact on patient survival are critical issues addressed in this study. Traditional DL models often lack transparency, leading to skepticism among medical experts owing to their "black box" nature. This study addresses this gap by presenting an innovative approach for brain tumor detection. It utilizes a customized Convolutional Neural Network (CNN) model empowered by three advanced explainable artificial intelligence (XAI) techniques: Shapley Additive Explana-tions (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Gradient-weighted Class Activation Mapping (Grad-CAM). The study utilized the BR35H dataset, which includes 3060 brain MRI images encompassing both tumorous and non-tumorous cases. The proposed model achieved a remarkable training accuracy of 100 % and validation accuracy of 98.67 %. Precision, recall, and F1 score metrics demonstrated exceptional performance at 98.50 %, confirming the accuracy of the model in tumor detection. Detailed result analysis, including a confusion matrix, comparison with existing models, and generalizability tests on other datasets, establishes the superiority of the proposed approach and sets a new benchmark for accuracy. By integrating a customized CNN model with XAI techniques, this research enhances trust in AI-driven medical diagnostics and offers a promising pathway for early tumor detection and potentially life-saving interventions.

The Integration of Machine Learning in Central Banks: Implications and Innovations

The effectiveness of using artificial intelligence (AI) techniques to lessen the negative effects of economic cycles is examined in this study article. Economic cycles, which are defined by variations in the level of economic activity, present important difficulties for decision-makers in government, business, and society at large. This research investigates many approaches to reducing economic cycles, such as forecasting, policy creation, and adaptive decision-making, by utilizing AI, namely machine learning algorithms. The first section of the paper reviews the body of research on economic cycles and how artificial intelligence might be used to address them. After that, it explores certain AI methods including neural networks, time series analysis, and natural language processing, explaining how they might be used for risk management and economic forecasting. Additionally, the study investigates AI-driven policy interventions, examining how machine learning algorithms might be used to optimize monetary and fiscal policies in order to sustain growth and prevent economic downturns. The study also addresses the difficulties and constraints that come with using AI technologies in economic management, such as problems with algorithmic biases, data quality, and legal considerations. It highlights how crucial interdisciplinary cooperation and openness are to creating AI-driven solutions that are reliable, moral, and socially conscious. This research paper offers insights into the possible advantages and disadvantages of employing AI tools for damping economic cycles through empirical analysis and case studies. In order to fully realize AI's promise in fostering resilience and stability in the economy, it ends by presenting future research areas and policy suggestions. Keywords: artificial intelligence, trend, economic cycles, resilience

Unveiling the Role of Artificial Intelligence (AI) in Polycystic Ovary Syndrome (PCOS) Diagnosis: A Comprehensive Review.

Polycystic Ovary Syndrome (PCOS) is one of the most widespread endocrine and metabolic disorders affecting women of reproductive age. Major symptoms include hyperandrogenism, polycystic ovary, irregular menstruation cycle, excessive hair growth, etc., which sometimes may lead to more severe complications like infertility, pregnancy complications and other co-morbidities such as diabetes, hypertension, sleep apnea, etc. Early detection and effective management of PCOS are essential to enhance patients' quality of life and reduce the chances of associated health complications. Artificial intelligence (AI) techniques have recently emerged as a popular methodology in the healthcare industry for diagnosing and managing complex diseases such as PCOS. AI utilizes machine learning algorithms to analyze ultrasound images and anthropometric and biochemical test result data to diagnose PCOS quickly and accurately. AI can assist in integrating different data sources, such as patient histories, lab findings, and medical records, to present a clear and complete picture of an individual's health. This information can help the physician make more informed and efficient diagnostic decisions. This review article provides a comprehensive analysis of the evolving role of AI in various aspects of the management of PCOS, with a major focus on AI-based diagnosis tools.

Prediction of California Bearing Ratio of nano-silica and bio-char stabilized soft sub-grade soils using explainable machine learning

This study investigates the prediction of the California Bearing Ratio (CBR) for nano-silica and bio-char stabilized soft sub-grade soils using explainable machine learning (ML) models. The research involves experimentally determining CBR values for soft sub-grade soils treated with varying proportions of nano-silica and bio-char. This data, along with soil properties such as grain size distribution, moisture content, and nano-silica and bio-char content, serve as inputs for training and testing various ML models. Among the 12 ML models evaluated, the Gradient Boosting Regression exhibits superior performance, achieving high accuracy (R2 = 0.92) and low error rates (MSE = 0.45). The utilization of explainable artificial intelligence (XAI) techniques provides insight into the significant input features influencing CBR predictions, thereby enhancing the interpretability and reliability of the models.. The research findings, highlight the efficacy of machine intelligence in accurately predicting the CBR values of nano-silica and bio-char stabilized soft sub-grade soils. This research has significant implications for geotechnical engineering, offering a data-driven methodology to optimize soil stabilization practices and contribute to sustainable infrastructure development.

Integration of parametric design tools with artificial intelligence in the construction industry - a review

Background: Technology continues to reshape the design and execution of construction projects in today's global scenario. Objective: The objectives of the research are focused on providing insight into the most prominent Parametric Design (PD) tools in the construction sector, accurately identifying the Artificial Intelligence (AI) techniques and algorithms used in the PD of buildings and structures, and prominently highlighting the benefits derived from the collaboration between these tools and AI in the context of construction. Methods: The present review is carried out using the Prisma methodology, with a specific search string, and applied to the determined scientific databases, between the years 2015 and 2023 and using exclusion and inclusion criteria. Results: The research concludes that the integration of parametric tools and AI, with special attention to Rhinoceros 3D + Grasshopper, has a significant impact on building through adaptive and complex models. Collaboration with artificial neural networks (ANN) and convolutional neural networks (CNN) enables detailed simulations and automations. Conclusions: The benefits are numerous: optimized designs, automation, improved quality and efficient decision-making, all of which drive innovation in construction projects.

Predicting HER2 Status Associated with Breast Cancer Aggressiveness Using Four Machine Learning Models.

Breast cancer (BC) is a heterogeneous disease with various biological and clinical subtypes. HER2 status (human epidermal growth factor receptor 2) is a crucial biomarker, associated with aggressive tumor behavior and poor prognosis. Advanced algorithmic models can aid in predicting cancer growth and metastasis, serving as valuable clinical tools for classification and treatment. Effective treatment strategies in oncology rely on accurate decision-making and early identification of factors associated with positive outcomes. Breast cancer (BC) presents challenges in understanding its contributing factors and establishing precise diagnostic methods. Our research introduces a novel method utilizing machine learning (ML) techniques to explore the relationship between various clinical and molecular variables focusing on predicting the status of the human epidermal growth factor receptor 2 (HER2), a key aggressiveness biomarker in BC. This objective aligns with leveraging artificial intelligence (AI) to support decision-making and address diagnostic considerations during treatment. Four ML models, namely logistic regression, random forest, LightGBM, and CatBoost, were implemented and evaluated using Python. The dataset was compiled by extracting medical records of BC patients, covering the period from 2018 to 2020. The model's predictive performance was evaluated using accuracy, precision, recall, and F1-score as performance metrics. The models achieved varying accuracies between 86.36 and 95.45%. The logistic regression model achieved an accuracy of 90.90% while the random forest and LightGBM models achieved an accuracy of 86.36%. The CatBoost model outperformed others with a greater accuracy of 95.45%, indicating its superior predictive capabilities for HER2 status. The ML models demonstrated potential in predicting HER2 status, enabling early detection and facilitating personalized treatment strategies. Our findings emphasize the significance of AI and ML techniques in improving BC outcomes and guiding decision-making. Further research is required to explore the broader applications of ML in predicting comprehensive BC outcomes in diverse healthcare settings and among heterogeneous populations.

Investigating the Applications of AI in Oncology from NIH Funded Projects: Case study of Lung Cancer and Pancreatic Cancer

ABSTRACTThis poster aims to conduct an examination of the applications of Artificial Intelligence (AI) in oncology. We collect projects from National Institutes of Health (NIH) which delve into how AI applications and techniques are used in cancer research between 2018 to 2024. Results show AI's ability to enhance lung and pancreatic cancer through novel imaging techniques and data processing. We find that refined medical imaging can be done with AI‐driven techniques such as machine learning or deep learning to improve diagnostic accuracy potentially leading to better survival rates for patients involved. Additionally, this reveals how AI transformed oncology studies underlining the movement toward complex diagnostic algorithms that allow accurate stage assignments. Consequently, these forms of teamwork are essential when determining as well as making reliable Cancer care systems by developing strong AI systems with interpretation abilities using supportive NIH funding.

Exploring the Artificial Intelligence and Its Impact in Pharmaceutical Sciences: Insights Toward the Horizons Where Technology Meets Tradition.

The technological revolutions in computers and the advancement of high-throughput screening technologies have driven the application of artificial intelligence (AI) for faster discovery of drug molecules with more efficiency, and cost-friendly finding of hit or lead molecules. The ability of software and network frameworks to interpret molecular structures' representations and establish relationships/correlations has enabled various research teams to develop numerous AI platforms for identifying new lead molecules or discovering new targets for already established drug molecules. The prediction of biological activity, ADME properties, and toxicity parameters in early stages have reduced the chances of failure and associated costs in later clinical stages, which was observed at a high rate in the tedious, expensive, and laborious drug discovery process. This review focuses on the different AI and machine learning (ML) techniques with their applications mainly focused on the pharmaceutical industry. The applications of AI frameworks in the identification of molecular target, hit identification/hit-to-lead optimization, analyzing drug-receptor interactions, drug repurposing, polypharmacology, synthetic accessibility, clinical trial design, and pharmaceutical developments are discussed in detail. We have also compiled the details of various startups in AI in this field. This review will provide a comprehensive analysis and outline various state-of-the-art AI/ML techniques to the readers with their framework applications. This review also highlights the challenges in this field, which need to be addressed for further success in pharmaceutical applications.

How quickly do patients with cancer view the results of their imaging studies?

419 Background: The 21 st Century Cures Act requires electronic health data to be available to patients. However, such data are useful to patients only if they access it. For example, imaging data can indicate the effectiveness of treatment and progression of disease and engagement with this information empowers patients to become more active in their care. While prior studies have explored the prevalence and timing of patient access to clinical notes, the timing of patient access to other data types remains unknown. We analyzed how rapidly oncology patients access the results of their imaging studies. Methods: Memorial Sloan Kettering Cancer Center (MSK) is a cancer center in New York that provides 700,000 imaging studies annually. At the time of this analysis, MSK had an internally developed patient portal, MyMSK, which notified patients via email about the presence of new data in the portal. The default timing for notifications was daily at 8 a.m. (patients could change notifications to be real-time, but very few did). We selected an arbitrary 7-day period (4/1/2023-4/7/2023) for analysis. For that week, for all imaging studies performed at MSK, we measured the time from when the report was available in the database (and thus available to the patient in MyMSK) to the time the report was read by either a patient or a proxy. The day the imaging study was performed was defined as “Day 0”. We determined (i) the proportion of imaging study reports that were read by 8 a.m. on Day 1, i.e., before any notification was sent to the patient, (ii) the proportion of reports that were read on Day 1 between 8 a.m. and 5 p.m., (iii) the proportion of reports that were read after 5 p.m. on Day 1, and (iv) the proportion not yet read by 8/23/2023 (when the data were collected). Results: In this one-week period, a total of 7,110 patients had 10,298 imaging studies. The average age of the patients was 61.4 years, 61.3% were female, 85.5% were non-Hispanic, 75.8% were White, and 95.1% reported English as their preferred language. Of the 10,298 imaging reports, 3203 (31.1%) were read before 8 a.m. on Day 1, 2090 (20.3%) were read between 8 a.m. and 5 p.m. on Day 1, 2389 (23.2%) were read after 5 p.m. on Day 1, and 2616 (25.4%) were not read as of 8/23/2023. Conclusions: This analysis indicates that a substantial proportion of cancer patients seek the results of imaging studies very soon after the tests are performed. Almost a third of the time, the patient read the report before any notification arrived. In oncology, it is easy to imagine patients frequently refreshing their portal to see if results have been posted. It is vital for provider organizations to understand the eagerness with which patients await results. Organizations may also want to develop methods to answer questions patients may have about their results prior to speaking with providers; this may be a key opportunity to leverage emerging artificial intelligence techniques.