Artificial Intelligence Models Research Articles

Artificial Intelligence and Large Language Models for the Management of Tobacco Dependence

Artificial Intelligence and Large Language Models for the Management of Tobacco Dependence

Reinforcement learning model for optimizing dexmedetomidine dosing to prevent delirium in critically ill patients

AbstractDelirium can result in undesirable outcomes including increased length of stays and mortality in patients admitted to the intensive care unit (ICU). Dexmedetomidine has emerged for delirium prevention in these patients; however, optimal dosing is challenging. A reinforcement learning-based Artificial Intelligence model for Delirium prevention (AID) is proposed to optimize dexmedetomidine dosing. The model was developed and internally validated using 2416 patients (2531 ICU admissions) and externally validated on 270 patients (274 ICU admissions). The estimated performance return of the AID policy was higher than that of the clinicians’ policy in both derivation (0.390 95% confidence interval [CI] 0.361 to 0.420 vs. −0.051 95% CI −0.077 to −0.025) and external validation (0.186 95% CI 0.139 to 0.236 vs. −0.436 95% CI −0.474 to −0.402) cohorts. Our finding indicates that AID might support clinicians’ decision-making regarding dexmedetomidine dosing to prevent delirium in ICU patients, but further off-policy evaluation is required.

Obstacles to the Full Realization and Adoption of Artificial Intelligence (AI)

Artificial Intelligence (AI) holds transformative potential across various sectors, yet its journey to full realization and widespread adoption is impeded by several significant obstacles. These challenges span technical, ethical, societal, research and development, implementation, and regulatory domains, necessitating a comprehensive and multi-faceted approach to address them.Technical Challenges: AI systems require vast amounts of high-quality, labeled data, which is often unavailable or of poor quality. AI models also struggle to generalize beyond specific tasks, and their opaque decision-making processes hinder trust. Scaling AI to handle large datasets and interactions, while ensuring robustness and security against adversarial attacks, poses major technical hurdles.Ethical and Societal Challenges: AI can perpetuate and amplify biases, leading to unfair outcomes and privacy issues. AI-driven automation risks job displacement, necessitating measures for worker support and retraining. The rapid development of AI outstrips regulatory bodies' abilities to create appropriate frameworks, complicating responsible deployment.Research and Development Challenges: AI struggles to integrate information from different modalities and lacks human-like common sense and reasoning. Improving AI's learning efficiency to reduce its dependence on vast data is a significant research focus.Implementation Challenges: Integrating AI into legacy systems, addressing the talent shortage, and managing the high costs of AI development and deployment are substantial barriers.Ethical and Regulatory Uncertainty: The absence of universally accepted ethical guidelines and varying regulatory landscapes create uncertainty and potential misuse.Addressing these multifaceted obstacles requires a concerted effort from researchers, developers, policymakers, and society to create robust, fair, and transparent AI systems, unlocking AI's full potential and societal benefits.

Application of artificial intelligence in VSD prenatal diagnosis from fetal heart ultrasound images.

Developing a combined artificial intelligence (AI) and ultrasound imaging to provide an accurate, objective, and efficient adjunctive diagnostic approach for fetal heart ventricular septal defects (VSD). 1,451 fetal heart ultrasound images from 500 pregnant women were comprehensively analyzed between January 2016 and June 2022. The fetal heart region was manually labeled and the presence of VSD was discriminated by experts. The principle of five-fold cross-validation was followed in the training set to develop the AI model to assist in the diagnosis of VSD. The model was evaluated in the test set using metrics such as mAP@0.5, precision, recall, and F1 score. The diagnostic accuracy and inference time were also compared with junior doctors, intermediate doctors, and senior doctors. The mAP@0.5, precision, recall, and F1 scores for the AI model diagnosis of VSD were 0.926, 0.879, 0.873, and 0.88, respectively. The accuracy of junior doctors and intermediate doctors improved by 6.7% and 2.8%, respectively, with the assistance of this system. This study reports an AI-assisted diagnostic method for VSD that has a high agreement with manual recognition. It also has a low number of parameters and computational complexity, which can also improve the diagnostic accuracy and speed of some physicians for VSD.

Anti-VEGF treatment outcome prediction based on optical coherence tomography images in neovascular age-related macular degeneration using a deep neural network.

Age-related macular degeneration (AMD) is a major cause of blindness in developed countries, and the number of affected patients is increasing worldwide. Intravitreal injections of anti-vascular endothelial growth factor (VEGF) are the standard therapy for neovascular AMD (nAMD), and optical coherence tomography (OCT) is a crucial tool for evaluating the anatomical condition of the macula. However, OCT has limitations in accurately predicting the degree of functional and morphological improvement following intravitreal injections. Artificial intelligence (AI) has been proposed as a tool for predicting the treatment response of nAMD based on OCT biomarkers. Our study focuses on the development and assessment of an AI model utilizing the DenseNet201 algorithm. The model aims to predict anatomical improvement based on OCT images before, and during anti-VEGF therapy. The training process involves two scenarios: (1) using only preinjection OCT images and (2) utilizing both OCT images before and during anti-VEGF therapy for model training. The outcomes of our investigation, involving 2068 images from a cohort of 517 Korean patients diagnosed with nAMD, indicate that the AI model we introduced surpassed the predictive performance of ophthalmologists. The model exhibited a sensitivity of 0.915, specificity of 0.426, and accuracy of 0.820. Notably, its predictive capabilities were further enhanced with the inclusion of additional OCT images taken after the first and second injections during the loading phase. The treatment prediction performance of the model was the highest when using all input modalities (before injection, and after the first and second injections) and concatenation-based fusion layers. This study highlights the potential of AI in assisting individualized and tailored nAMD treatment.

Natural Language Processing to Adjudicate Heart Failure Hospitalizations in Global Clinical Trials.

Background: Medical record review by a physician clinical events committee is the gold standard for identifying cardiovascular outcomes in clinical trials, but is labor-intensive and poorly reproducible. Automated outcome adjudication by artificial intelligence (AI) could enable larger and less expensive clinical trials, but has not been validated in global studies. Methods: We developed a novel model for automated AI-based heart failure adjudication ("HF-NLP") using hospitalizations from three international clinical outcomes trials. This model was tested on potential heart failure hospitalizations from the DELIVER trial, a cardiovascular outcomes trial comparing dapagliflozin with placebo in 6063 patients with heart failure with mildly reduced or preserved ejection fraction. AI-based adjudications were compared with adjudications from a clinical events committee that followed FDA-based criteria. Results: AI-based adjudication agreed with the clinical events committee in 83% of events. A strategy of human review for events that the AI model deemed uncertain (16%) would have achieved 91% agreement with the clinical events committee while reducing adjudication workload by 84%. The estimated effect of dapagliflozin on heart failure hospitalization was nearly identical with AI-based adjudication (hazard ratio 0.76 [95% CI 0.66-0.88]) compared to clinical events committee adjudication (hazard ratio 0.77 [95% CI 0.67-0.89]). The AI model extracted symptoms, signs, and treatments of heart failure from each medical record in tabular format and quoted sentences documenting them. Conclusions: AI-based adjudication of clinical outcomes has the potential to improve the efficiency of global clinical trials while preserving accuracy and interpretability.

Artificial Intelligence in Achieving Sustainable Development: Expectations of Undergraduate Students

AbstractWhile there has been ample discussion regarding Artificial Intelligence (AI)’s contributions and challenges on the development agenda at the policy level, little is known about how students translate the potential and barriers of AI in achieving Sustainable Development Goals (SDGs). Drawing upon various qualitative data, including class observation, focus group interviews, and learning activity outcomes generated by 240 students across 7 different majors, this case study explores the expected roles of AI as well as barriers to AI adoption for sustainable development perceived by undergraduate students. The study revealed that students anticipated AI to play diverse roles, including data analyst, a bridge to connect people and resources, and a barrier breaker. On the other hand, students addressed multiple barriers to AI adoption for sustainable development including access to high-quality data and lack of a goal-oriented AI model and skills in AI development and use. These findings suggest how AI can be conceptualized and positioned as a development intervention as well as offer implications on AI-driven interventions for SDGs.

The Future of Artificial Intelligence: Trends and Predictions

Artificial Intelligence (AI) has evolved rapidly, transforming diverse industries and societal functions. This paper provides a comprehensive overview of AI's current landscape, examining its advancements, applications, and ethical challenges. Key trends are explored, including innovations in machine learning and deep learning, AI’s expanding role across industries, and its potential for addressing climate change and sustainability. Furthermore, the paper highlights AI's role in enhancing human-machine collaboration, paving the way for systems that augment rather than replace human capabilities. Predictions for AI’s future are discussed, such as the emergence of artificial general intelligence (AGI), advancements in autonomous systems, the impact of quantum computing on AI, and innovations in AI-specific hardware. The paper also examines ethical and societal challenges, such as privacy, algorithmic bias, and the need for global governance, addressing the urgent call for responsible AI. In light of these trends, the paper emphasizes future research directions, encouraging interdisciplinary collaboration and a focus on explainable, robust, and resilient AI models. This work aims to shed light on the transformative potential of AI while advocating for ethical practices to ensure a positive and sustainable impact on society.

Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features.

Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of molecular features. These approaches distill cancer histologic images into high-level features, which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network-HistoXGAN-capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a "virtual biopsy."

Evaluating the Impact of Technological Innovations on Operational Risk Management in Financial Institutions

This study evaluates the impact of technological innovations on operational risk management in financial institutions, focusing on how emerging technologies influence risk identification, mitigation, and management processes. Employing a qualitative approach through literature review and library research, this study synthesizes recent findings on the integration of technologies such as artificial intelligence (AI), blockchain, big data analytics, and cloud computing within financial risk frameworks. Findings indicate that these technologies offer substantial improvements in risk management by enhancing accuracy in risk detection, increasing response speed, and reducing human error. AI and machine learning models, for instance, are shown to enable real-time monitoring and predictive analytics, allowing institutions to identify potential risks before they materialize. Blockchain technology improves transparency and security in transaction processing, thereby mitigating fraud-related risks. Big data analytics provides insights into customer behavior, which can help detect anomalous activities and improve decision-making. However, the study also highlights challenges, including the need for robust cybersecurity measures, potential regulatory gaps, and skill shortages in handling complex technological systems. This study provides insights for financial institutions aiming to balance technological integration with effective risk management, underscoring the need for comprehensive frameworks that align technological advancements with regulatory compliance and organizational capability. Future research should focus on empirical studies assessing the long-term implications of these technologies on risk management efficacy in diverse financial settings.

Advancements in Using AI for Dietary Assessment Based on Food Images: Scoping Review.

To accurately capture an individual's food intake, dietitians are often required to ask clients about their food frequencies and portions, and they have to rely on the client's memory, which can be burdensome. While taking food photos alongside food records can alleviate user burden and reduce errors in self-reporting, this method still requires trained staff to translate food photos into dietary intake data. Image-assisted dietary assessment (IADA) is an innovative approach that uses computer algorithms to mimic human performance in estimating dietary information from food images. This field has seen continuous improvement through advancements in computer science, particularly in artificial intelligence (AI). However, the technical nature of this field can make it challenging for those without a technical background to understand it completely. This review aims to fill the gap by providing a current overview of AI's integration into dietary assessment using food images. The content is organized chronologically and presented in an accessible manner for those unfamiliar with AI terminology. In addition, we discuss the systems' strengths and weaknesses and propose enhancements to improve IADA's accuracy and adoption in the nutrition community. This scoping review used PubMed and Google Scholar databases to identify relevant studies. The review focused on computational techniques used in IADA, specifically AI models, devices, and sensors, or digital methods for food recognition and food volume estimation published between 2008 and 2021. A total of 522 articles were initially identified. On the basis of a rigorous selection process, 84 (16.1%) articles were ultimately included in this review. The selected articles reveal that early systems, developed before 2015, relied on handcrafted machine learning algorithms to manage traditional sequential processes, such as segmentation, food identification, portion estimation, and nutrient calculations. Since 2015, these handcrafted algorithms have been largely replaced by deep learning algorithms for handling the same tasks. More recently, the traditional sequential process has been superseded by advanced algorithms, including multitask convolutional neural networks and generative adversarial networks. Most of the systems were validated for macronutrient and energy estimation, while only a few were capable of estimating micronutrients, such as sodium. Notably, significant advancements have been made in the field of IADA, with efforts focused on replicating humanlike performance. This review highlights the progress made by IADA, particularly in the areas of food identification and portion estimation. Advancements in AI techniques have shown great potential to improve the accuracy and efficiency of this field. However, it is crucial to involve dietitians and nutritionists in the development of these systems to ensure they meet the requirements and trust of professionals in the field.

Backdoor Attacks and Defenses Targeting Multi-Domain AI Models: A Comprehensive Review

Since the emergence of security concerns in artificial intelligence (AI), there has been significant attention devoted to the examination of backdoor attacks. Attackers can utilize backdoor attacks to manipulate model predictions, leading to significant potential harm. However, current research on backdoor attacks and defenses in both theoretical and practical fields still has many shortcomings. To systematically analyze these shortcomings and address the lack of comprehensive reviews, this paper presents a comprehensive and systematic summary of both backdoor attacks and defenses targeting multi-domain AI models. Simultaneously, based on the design principles and shared characteristics of triggers in different domains and the implementation stages of backdoor defense, this paper proposes a new classification method for backdoor attacks and defenses. We use this method to extensively review backdoor attacks in the fields of computer vision and natural language processing, and also examine the current applications of backdoor attacks in audio recognition, video action recognition, multimodal tasks, time series tasks, generative learning, and reinforcement learning, while critically analyzing the open problems of various backdoor attack techniques and defense strategies. Finally, this paper builds upon the analysis of the current state of AI security to further explore potential future research directions for backdoor attacks and defenses.

Utilization of Machine Learning and Explainable Artificial Intelligence (XAI) for Fault Prediction and Diagnosis in Wafer Transfer Robot

Faults in the wafer transfer robots (WTRs) used in semiconductor manufacturing processes can significantly affect productivity. This study defines high-risk components such as bearing motors, ball screws, timing belts, robot hands, and end effectors, and generates fault data for each component based on Fluke’s law. A stacking classifier was applied for fault prediction and severity classification, and logistic regression was used to identify fault components. Additionally, to analyze the frequency bands affecting each failed component and assess the severity of faults involving two mixed components, a hybrid explainable artificial intelligence (XAI) model combining Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) was employed to inform the user about the component causing the fault. This approach demonstrated a high prediction accuracy of 95%, and its integration into real-time monitoring systems is expected to reduce maintenance costs, decrease equipment downtime, and ultimately improve productivity.

Artificial intelligence modeling of biomarker-based physiological age: Impact on phase 1 drug-metabolizing enzyme phenotypes.

Age and aging are important predictors of health status, disease progression, drug kinetics, and effects. The purpose was to develop ensemble learning-based physiological age (PA) models for evaluating drug metabolism. National Health and Nutrition Examination Survey (NHANES) data were modeled with ensemble learning to obtain two PA models, PA-M1 and PA-M2. PA-M1 included body composition, blood and urine biomarkers, and disease variables as predictors. PA-M2 had blood and urine-derived variables as predictors. Activity phenotypes for cytochrome-P450 (CYP) CYP2E1, CYP1A2, CYP2A6, xanthine oxidase (XO), and N-acetyltransferase-2 (NAT-2) and telomere attrition were assessed. Bayesian networks were used to obtain mechanistic systems pharmacology model structures for PA. The study included n = 22,307 NHANES participants (51.5% female, mean age 46.0 years, range: 18-79 years). The PA-M1 and PA-M2 distributions had greater dispersion across age strata with a right skew for younger age strata and a left skew for older age strata. There was no evidence of algorithmic bias based on sex or race/ethnicity. Klotho, lean body mass, glycohemoglobin, and systolic blood pressure were the top four predictors for PA-M1. Glycohemoglobin, serum creatinine, total cholesterol, and urine creatinine were the top four predictors for PA-M2. The models also performed satisfactorily in independent validation. Model-predicted PA was associated with CYP2E1, CYP1A2, CYP2A6, XO, and NAT-2 activity. Telomere attrition was associated with greater PA-M1 and PA-M2. Ensemble learning models provide robust assessments of PA from easily obtained blood and urine biomarkers. PA is associated with Phase I drug-metabolizing enzyme phenotypes.

Exploring the role of Artificial Intelligence in Acute Kidney Injury management: a comprehensive review and future research agenda.

This study reviews the studies utilizing Artificial Intelligence (AI) and AI-driven tools and methods in managing Acute Kidney Injury (AKI). It categorizes the studies according to medical specialties, analyses the gaps in the existing research, and identifies opportunities for future research directions. PRISMA guidelines were adopted using the three most common databases (PubMed, Scopus, and EBSCO), which resulted in 27 eligible studies, published between 2012 and 2023. The study showed significant heterogeneity in the design of the models, with variations in clinical settings, patient characteristics, cohort regions, and statistical methods. Most models were developed for AKI in hospitalized patients, particularly those undergoing surgery or in intensive care units. Compact models with a subset of significant predictors were deemed more clinically applicable than full models with all predictors. The findings suggest that AI tools, such as machine learning (ML) algorithms, have high prediction capabilities despite the dynamic and complex association among the influencing factors and AKI. Based on these findings and the recognized need for broader inclusivity, future studies should consider adopting a more inclusive approach by incorporating diverse healthcare settings, including resource-limited or developing countries. This inclusivity will lead to a more holistic understanding of AKI management challenges and facilitate the development of adaptable and universally applicable AI-driven solutions. Additionally, further investigations should focus on refining AI models to enhance their accuracy and interpretability, promoting seamless integration and implementation of AI-based tools in real-world clinical practice. Addressing these key aspects will elevate the effectiveness and impact of AI-driven approaches in managing AKI.

Leveraging Virtual Containers for High-Powered, Collaborative AI Research in Radiology

Abstract Numerous obstacles confront radiologists interested in the use of artificial intelligence (AI) models within the field of radiology. For example, discrepancies between the radiologist's and an AI developer's hardware and software specifications pose a substantial hindrance to using AI models. Additionally, accessing and using GPU computers can lead to compatibility issues and add to these challenges. Finally, the dissemination of AI models and the ability to download preexisting AI models are not simple tasks due to the size and complexity of most programs. Virtual containers offer a solution to such compatibility issues and provide a simplified way for radiologists to use AI models. Virtual containers are software tools that bundle code, required programs, and necessary software packages to ensure that a program runs identically for all users, regardless of their computing environment. This article outlines the features of virtual containers (compatibility, versatility, and portability) and highlights an applied use case for virtual containers in the development of an AI model.

Deep learning-based automated measurement of hip key angles and auxiliary diagnosis of developmental dysplasia of the hip.

Anteroposterior pelvic radiographs remains the most widely employed method for diagnosing developmental dysplasia of the hip. This study aims to evaluate the accuracy of an artificial intelligence model in measuring angles in pelvic radiographs of the hip. The assessment seeks to demonstrate the efficacy of the artificial intelligence model in diagnosing both developmental dysplasia of the hip and borderline developmental dysplasia of the hip through the analysis of pelvic radiographs. A total of 1,029 patients, including 273 men and 757 women, were retrospectively included in this study. The anteroposterior pelvic radiographs were randomly divided into three sets: the training set (720 cases), the validation set (103 cases), and the test set (206 cases). Key anatomical points on the anteroposterior pelvic radiographs were identified. The Sharp, Tönnis, and Center Edge angles were calculated automatically based on the corresponding criteria. The hip development status was compared between measurements obtained from the artificial intelligence model and those defined manually by two radiologists. The area under the receiver operating characteristic curve was utilized to assess the diagnostic performance of the artificial intelligence model. The results obtained from both manual measurements and the artificial intelligence model demonstrated no significant differences in the Sharp, Tönnis, and Center edge angles (all p > 0.05). The intra-class correlation coefficients and correlation coefficient r values exceeded 0.75, indicating that both the artificial intelligence model and manual measurements exhibited good repeatability and a positive correlation. Notably, the artificial intelligence model provided measurements more faster than those conducted by radiologists (p = 0.001). The artificial intelligence model also demonstrated high diagnostic accuracy, sensitivity, and specificity for developmental dysplasia of the hip. The performance of the artificial intelligence model in diagnosing developmental dysplasia of the hip was robust. Additionally, the results from the artificial intelligence model and manual measurements were largely consistent with clinical diagnosis results (p = 0.01). The artificial intelligence model can effectively evaluate hip conditions by measuring the Sharp, Tönnis, and Center edge angles, which are consistent closely with clinical diagnosis results. The results of the artificial intelligence model measurements demonstrate a high degree of consistency with those obtained through manual measurements. The angles of Sharp, Tönnis, and Center edge, as evaluated by the deep learning-based convolutional neural network model, exhibit robust diagnostic performance in identifying both developmental dysplasia of the hip and borderline developmental dysplasia of the hip. Consequently, the artificial intelligence model has the potential to fully replace manual measurements of these critical hip angles, providing a more efficient and precise alternative for diagnosing both conditions of the hip.

EDI&S SO07 Future of Low-Cost Laparoscopic Cholecystectomy Simulation (LaChSi) Model: Integration of Segmentation-Based Artificial Intelligence Models for Realism Enhancement in Simulation-Based Laparoscopic Cholecystectomy Training in Lower-Middle-Income Countries

Abstract Background To introduce an approach of employing segmentation-based Artificial Intelligence (AI) models to meticulously isolate the silicon-based Laparoscopic Cholecystectomy Simulation Model (LaChSi) model within the laparoscopic trainer box, thereby enhancing realism. To assess the effectiveness of the AI Model to track camera angles to seamlessly replace the background with a virtual environment reminiscent of authentic intra-operative intra-abdominal visuals. Method The proposed methodology integrates a sophisticated segmentation model that identifies and accurately delineates the LaChSi Model within the laparoscopic Trainer box. Simultaneously, the model exhibits the capability to segregate the background, while closely monitoring camera angles for real-time adjustment. Importantly, the model is trained to perform precise segmentation of surgical tools, ensuring a comprehensive and realistic representation of the laparoscopic environment. Results Implementation of the proposed method is thought to demonstrate a notable improvement in trainees’ adaptation to surgical scenarios. The visual transition experienced by trainees moving from simulation-based surgeries to actual surgical environments will significantly reduce disparities increasing the effectiveness of the Laparoscopic simulation training. This will further avoid the need to use sensors and wires on the LaChSi model to simulate the surgical settings. Conclusion As the visual representation in simulations often deviates substantially from the intricate nuances of actual surgical procedures. This study introduces an innovative AI-based model that will contribute to the augmentation of surgical realism within simulation-based training. By effectively integrating segmentation techniques, our approach will minimise visual discontinuities, providing trainees with a more authentic and immersive experience, and ultimately fostering a smoother transition to acute surgical settings.

Methods and Evaluation of AI-Based Meteorological Models for Zenith Tropospheric Delay Prediction

Zenith Tropospheric Delay (ZTD) is a significant error source affecting the accuracy of certain space geodetic measurements. This study evaluates the performance of Artificial Intelligence (AI) based meteorological models, such as Fengwu and Pangu, in estimating real-time ZTD. The results from these AI models were compared with those obtained from the Global Navigation Satellite System (GNSS), the fifth-generation European Centre for Medium-Range Weather Forecasts (ECMWF) Atmospheric Reanalysis (ERA5), and the third generation of the Global Pressure–Temperature data model (GPT3) to assess their accuracy across different time intervals, seasons, and geographic locations. The findings reveal that AI-driven models, particularly Fengwu, offer higher long-term forecasting accuracy. An analysis of data from 81 stations throughout 2023 indicates that Fengwu’s 7-day ZTD forecast achieved an RMSE of 2.85 cm when compared to GNSS-derived ZTD. However, in oceanic regions and areas with complex climatic dynamics, the Fengwu model exhibited a larger error compared to in other land regions. Additionally, seasonal variations and station altitude were found to influence the accuracy of ZTD predictions, emphasizing the need for detailed modeling in complex climatic zones.

Improving global weather and ocean wave forecast with large artificial intelligence models

Improving global weather and ocean wave forecast with large artificial intelligence models