Artificial Intelligence Machine Learning Research Articles

Model Organoids: Integrated Frameworks for the Next Frontier of Healthcare Advancements.

The morphogenetic events leading to tissue formation can be recapitulated using organoids, which allows studying new diseases and modelling personalized medicines. In this review, culture systems comparable to human organs are presented, these organoids are created from pluripotent stem cells or adult stem cells. The efficient and reproducible models of human tissues are discussed for biobanking, precision medicine and basic research. Mechanisms used by these model systems with an overview of models from human cells are also covered. As human physiology is different from animals, culture conditions and tissue limits often become challenging. Organoids offer novel approaches for such cases with rapid screening, transplantation studies and in immunotherapy. Discrepancies with large datasets can be handled with an integrated framework of artificial intelligence or AI and machine learning. An attempt has been made to show the improved effectiveness, simplified iterations, along with image analysis that are possible from this synergy. AI-assisted organoids have the potential to transform healthcare by improving disease understanding and accelerating clinical decision-making through personalized and precision medicine.

Machine Learning Assessment of Background Parenchymal Enhancement in Breast Cancer and Clinical Applications: A Literature Review.

Background Parenchymal Enhancement (BPE) on breast MRI holds promise as an imaging biomarker for breast cancer risk and prognosis. The ability to identify those at greatest risk can inform clinical decisions, promoting early diagnosis and potentially guiding strategies for prevention such as risk-reduction interventions with the use of selective estrogen receptor modulators and aromatase inhibitors. Currently, the standard method of assessing BPE is based on the Breast Imaging-Reporting and Data System (BI-RADS), which involves a radiologist's qualitative categorization of BPE as minimal, mild, moderate, or marked on contrast-enhanced MRI. This approach can be subjective and prone to inter/intra-observer variability, and compromises accuracy and reproducibility. In addition, this approach limits qualitative assessment to 4 categories. More recently developed methods using machine learning/artificial intelligence (ML/AI) techniques have the potential to quantify BPE more accurately and objectively. This paper will review the current machine learning/AI methods to determine BPE, and the clinical applications of BPE as an imaging biomarker for breast cancer risk prediction and prognosis.

Optimization and Multimachine Learning Algorithms to Predict Nanometal Surface Area Transfer Parameters for Gold and Silver Nanoparticles.

Interactions between gold metallic nanoparticles and molecular dyes have been well described by the nanometal surface energy transfer (NSET) mechanism. However, the expansion and testing of this model for nanoparticles of different metal composition is needed to develop a greater variety of nanosensors for medical and commercial applications. In this study, the NSET formula was slightly modified in the size-dependent dampening constant and skin depth terms to allow for modeling of different metals as well as testing the quenching effects created by variously sized gold, silver, copper, and platinum nanoparticles. Overall, the metal nanoparticles followed more closely the NSET prediction than for Förster resonance energy transfer, though scattering effects began to occur at 20 nm in the nanoparticle diameter. To further improve the NSET theoretical equation, an attempt was made to set a best-fit line of the NSET theoretical equation curve onto the Au and Ag data points. An exhaustive grid search optimizer was applied in the ranges for two variables, 0.1≤C≤2.0 and 0≤α≤4, representing the metal dampening constant and the orientation of donor to the metal surface, respectively. Three different grid searches, starting from coarse (entire range) to finer (narrower range), resulted in more than one million total calculations with values C=2.0 and α=0.0736. The results improved the calculation, but further analysis needed to be conducted in order to find any additional missing physics. With that motivation, two artificial intelligence/machine learning (AI/ML) algorithms, multilayer perception and least absolute shrinkage and selection operator regression, gave a correlation coefficient, R2, greater than 0.97, indicating that the small dataset was not overfitting and was method-independent. This analysis indicates that an investigation is warranted to focus on deeper physics informed machine learning for the NSET equations.

Application and Innovation of Artificial Intelligence in Forensic Medicine

As the fourth industrial revolution, artificial intelligence is reshaping many industries. It has become a new cornerstone of digital conversion, and it is no exception in the field of forensic medicine.This paper mainly discusses how artificial intelligence can solve the problems related to forensic medicine.How to use artificial intelligence technology to develop into an auxiliary tool in the field of forensic medicine.This paper summarizes the exploratory data analysis, statistical modeling and machine learning in artificial intelligence, extracts insights and knowledge from the data, and applies them to various fields of forensic medicine.Artificial intelligence will improve the accuracy and efficiency of forensic work: it can automate some tasks and improve the quality of evidence. The comprehensive analysis results show that the artificial intelligence proposed in this paper will be an important auxiliary in the three directions of forensic medicine.

Machine Learning-Based Stroke Prediction: A Critical Analysis

Stroke is a critical public health issue that frequently has long-term impairment and negative effects. Devising innovative methods that enable timely and accurate identification and intervention is crucial. In this regard, machine learning (ML) and deep learning (DL) approaches of artificial intelligence (AI) play a crucial role in reducing the incidence of strokes. This study systematically analyzed articles from 2012 to 2022 using the PRISMA Method. PRISMA is a tool that facilitates researchers' access to an online platform for self-directed learning. The cumulative quantity of articles gathered for ten years reached 1405 from five databases. However, only 79 relevant articles were used for identification. The main objective was to provide a thorough taxonomy that classifies using and implementing machine learning approaches for stroke prediction. The results of this experiment confirm that machine-learning techniques have a great deal of potential for accurate stroke prediction. Nevertheless, challenges such as biased data and algorithms and the need for models that can be adjusted to accommodate various demographics and healthcare systems continue to exist. It is essential to recognize the need for additional research projects that thoroughly explore potential data biases, algorithmic biases, and the generalizability of models across various demographics and healthcare systems. More research is necessary to further the literature on the complete assessment of machine learning models in precisely forecasting stroke occurrences.

Risk Analysis of Mortgage Loan Default for Bank Customers and AI Machine Learning

Abstract Risk Analysis of Mortgage Loan Default for Banks is a crucial issue. On one hand, it concerns the quality of the bank's credit decisions, and on the other hand, it affects the rights of homebuyers to obtain financial support. In 2008, the U.S. subprime mortgage crisis sparked a global financial meltdown. What began with the collapse of the housing market quickly spread throughout the global financial system, resulting in the failure of numerous banks and a widespread economic recession. Recently, the banking sector has increasingly leveraged Artificial Intelligence (AI) and Machine Learning (ML) to enhance decision-making processes, particularly in assessing the risk of mortgage loan defaults. This paper aims to explore the application of ML techniques to predict and analyze the risk of default among bank customers, thereby enabling financial institutions to make more accurate and informed lending decisions. Keywords: Mortgage Loan Default Risk Analysis AI ML K-MANS LTV.

Artificial Intelligence and mass media: negative aspects of content personalization algorithms

The development of artificial intelligence (AI) technologies and machine learning algorithms is increasingly influencing various aspects of social life, gradually finding its place not only in social media but also in journalism (Newman). They are actively being integrated into various fields of mass media, enabling the automation of several processes within media companies, thereby optimizing the work of journalists, editors, and media managers. This topic represents a pertinent issue in the modern information society (Túñez López et al.). AI and its machine learning capabilities have become integral parts of the processes of content creation, analysis, and distribution, bringing new opportunities along with significant challenges. For instance, personalization algorithms allow for the adaptation of information to the individual interests and preferences of each user, increasing their engagement and satisfaction with the content. Thus, social networks and many other internet platforms are personalized for each user based on their demographic profiles and personal data. This article provides an overview of current scientific data on the potential risks associated with the use of content personalization algorithms in mass media. The results and conclusions of the article will help to better understand the nature of these risks and the associated challenges for the field of mass communication.

The Relationship Between Computerized Face and Tongue Image Segmentation and Metabolic Parameters in Patients with Type 2 Diabetes Based on Machine Learning.

We aim to examine and reestablish the correlational and linear regression relationships, as well as the predictive value, between the significant facial and tongue features and the metabolic parameters in type 2 diabetes mellitus (T2DM). From March to May 2024, we studied 269 patients with T2DM in the endocrinology department of Shanghai Pudong Hospital. The patients' facial and tongue characteristics were sampling by a tongue imaging device equipped with artificial intelligence (AI) (XiMaLife, Sinology, China) of automated and advanced machine learning algorithms. Then, the imaging features were examined in relation to the blood examination. Multiple facial and tongue features, as well as dimensional facial and tongue color parameters, were significantly correlated with glycated hemoglobin A1c (HbA1c) (r < 0.3, p < 0.05), glycated albumin (GA) (-0.20 < 0.30, p < 0.05), C-peptide (-0.20.20, p < 0.05), plasma insulin (r < 0.30, p < 0.05), fasting plasma glucose (FPG) (r < 0.3, p < 0.05), significant hepatic and renal function indicators (-0.30 < r < 0.20, p<0.05), cardiac injury markers (-0.30 < r < 0.30, p < 0.05), tumor markers (-0.5 < r < 0.5, p < 0.05), thyroid function (-0.15 < r < 0.55, p < 0.05), and blood cell count, including white blood cells (r < 0.2, p < 0.05), and hemoglobin (Hb) (-0.30 < r < 0.3, 0.0001. The correlational results demonstrated that the tongue's characteristics and signsmay be linked with the dynamic of the metabolic status of T2DM. In order to examine the causal relationships, we performed linear regression analyses, which revealed that various facial and tongue imaging parameters partially determined the metabolic indicators. The predictive value of imaging features was evaluated by receiver operating characteristic curve (ROC) to assess metabolic status in T2DM. This study demonstrated that metabolic status, renal and hepatic, cardiac, and thyroid function, the proportion of blood cells, and Hb in T2DM were intimately associated with facial and tongue features. The precise analysis of facial and tongue features through AI and advanced machine learning could be used to predict T2DM's conditions and progression.

Artificial intelligence machine learning based evaluation of elevated left ventricular end-diastolic pressure: a Cleveland Clinic cohort study.

Left ventricular end-diastolic pressure (LVEDP) is a key indicator of cardiac health. The gold-standard method of measuring LVEDP is invasive intra-cardiac catheterization. Echocardiography is used for non-invasive estimation of left ventricular (LV) filling pressures; however, correlation with invasive LVEDP is variable. We sought to use machine learning (ML) algorithms to predict elevated LVEDP (>20 mmHg) using clinical, echocardiographic, and biomarker parameters. We identified a cohort of 460 consecutive patients from the Cleveland Clinic, without atrial fibrillation or significant mitral valve disease who underwent transthoracic echocardiography within 24 hours of elective heart catheterization between January 2008 and October 2010. We included patients' clinical (e.g., heart rate), echocardiographic (e.g., E/e'), and biomarker [e.g., N-terminal brain natriuretic peptide (NT-proBNP)] profiles. We fit logistic regression (LR), random forest (RF), gradient boosting (GB), support vector machine (SVM), and K-nearest neighbors (KNN) algorithms in a 20-iteration train-validate-test workflow and measured performance using average area under the receiver operating characteristic curve (AUROC). We also predicted elevated tau (>45 ms), the gold-standard parameter for LV diastolic dysfunction, and performed multi-class classification of the patients' cardiac conditions. For each outcome, LR weights were used to identify clinically relevant variables. ML algorithms predicted elevated LVEDP (>20 mmHg) with good performance [AUROC =0.761, 95% confidence interval (CI): 0.725-0.796]. ML models showed excellent performance predicting elevated tau (>45 ms) (AUROC =0.832, 95% CI: 0.700-0.964) and classifying cardiac conditions (AUROC =0.757-0.975). We identified several clinical variables [e.g., diastolic blood pressure, body mass index (BMI), heart rate, left atrial volume, mitral valve deceleration time, and NT-proBNP] relevant for LVEDP prediction. Our study shows ML approaches can robustly predict elevated LVEDP and tau. ML may assist in the clinical interpretation of echocardiographic data.

Industrial data-driven machine learning soft sensing for optimal operation of etching tools

Smart Manufacturing, or Industry 4.0, has gained significant attention in recent decades with the integration of Internet of Things (IoT) and Information Technologies (IT). As modern production methods continue to increase in complexity, there is a greater need to consider what variables can be physically measured. This advancement necessitates the use of physical sensors to comprehensively and directly gather measurable data on industrial processes; specifically, these sensors gather data that can be recontextualized into new process information. For example, artificial intelligence (AI) machine learning-based soft sensors can increase operational productivity and machine tool performance while still ensuring that critical product specifications are met. One industry that has a high volume of labor-intensive, time-consuming, and expensive processes is the semiconductor industry. AI machine learning methods can meet these challenges by taking in operational data and extracting process-specific information needed to meet the high product specifications of the industry. However, a key challenge is the availability of high quality data that covers the full operating range, including the day-to-day variance. This paper examines the applicability of soft sensing methods to the operational data of five industrial etching machines. Data is collected from readily accessible and cost-effective physical sensors installed on the tools that manage and control the operating conditions of the tool. The operational data are then used in an intelligent data aggregation approach that increases the scope and robustness for soft sensors in general by creating larger training datasets comprised of high value data with greater operational ranges and process variation. The generalized soft sensor can then be fine-tuned and validated for a particular machine. In this paper, we test the effects of data aggregation for high performing Feedforward Neural Network (FNN) models that are constructed in two ways: first as a classifier to estimate product PASS/FAIL outcomes and second as a regressor to quantitatively estimate oxide thickness. For PASS/FAIL classification, a data aggregation method is developed to enhance model predictive performance with larger training datasets. A statistical analysis method involving point-biserial correlation and the Mean Absolute Error (MAE) difference score is introduced to select the optimal candidate datasets for aggregation, further improving the effectiveness of data aggregation. For large datasets with high quality data that enable model training for more complex tasks, regression models that predict the oxide thickness of the product are also developed. Two types of models with different loss functions are tested to compare the effects of the Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) loss functions on model performance. Both the classification and regression models can be applied in industrial settings as they provide additional information regarding the process outcome. Individually, these models can reduce the number of metrology steps in semiconductor factories, and when developed further, can empower the development of advanced process control strategies.

Water Resources’ AI–ML Data Uncertainty Risk and Mitigation Using Data Assimilation

Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), learns by training and is restricted by the amount and quality of training data. Training involves a tradeoff between prediction bias and variance controlled by model complexity. Increased model complexity decreases prediction bias, increases variance, and increases overfitting possibilities. Overfitting is a significantly smaller training prediction error relative to the trained model prediction error for an independent validation set. Uncertain data generate risks for AI–ML because they increase overfitting and limit generalization ability. Specious confidence in predictions from overfit models with limited generalization ability, leading to misguided water resource management, is the uncertainty-related negative consequence. Improved data is the way to improve AI–ML models. With uncertain water resource data sets, like stream discharge, there is no quick way to generate improved data. Data assimilation (DA) provides mitigation for uncertainty risks, describes data- and model-related uncertainty, and propagates uncertainty to results using observation error models. A DA-derived mitigation example is provided using a common-sense baseline, derived from an observation error model, for the confirmation of generalization ability and a threshold identifying overfitting. AI–ML models can also be incorporated into DA to provide additional observations for assimilation or as a forward model for prediction and inverse-style calibration or training. The mitigation of uncertain data risks using DA involves a modified bias–variance tradeoff that focuses on increasing solution variability at the expense of increased model bias. Increased variability portrays data and model uncertainty. Uncertainty propagation produces an ensemble of models and a range of predictions.

A Role of Artificial Intelligences in Drug Discovery and Drug Development – A Critical Review.

Artificial intelligence (AI) is lowering the period and cost of the medication research and discovery process Artificial Intelligence is a revolution of medical research in pharmaceutical companies. In a review article, we give a summary of the many artificial intelligence tools of machine learning (ML) and deep learning (DL) techniques that will be used in drug research and discovery in the future. AI techniques and tools are more specifically designed or better programmed to mimic the operations of the human brain. AI is frequently used in drug discovery for de novo drug creation, virtual screening, reaction prediction, and de novo protein design. In addition, the application of AI and techniques of AI. ML is a disease diagnosis, de novo drug design, drug prediction for diseases, and big data prediction using ANN, CNN, and SNN, as well as deep learning. Furthermore, the function, applications, and methods of AI. Technological hurdles also face the contemporary XAI, and “low level” molecular representations (such as SMILES strings) that are useful for machine learning and AI tools are ‘deep chem’ in drug development several cutting-edge methods referred to as Knowledge Base Systems (KBS). The AI-based nanorobots are drug discovery on creating implantable nanorobots for the targeted delivery of medications and genes, factors including sustained release, dose modification, and control release need to be taken into consideration. Finally recent development of ML and DL techniques and AI models are more useful in the drug development and drug discovery process.

Adaptive edge security framework for dynamic IoT security policies in diverse environments

The rapid expansion of Internet of Things (IoT) technologies has introduced significant cybersecurity challenges, particularly at the network edge where IoT devices operate. Traditional security policies designed for static environments fall short of addressing the dynamic, heterogeneous, and resource-constrained nature of IoT ecosystems. Existing dynamic security policy models lack versatility and fail to fully integrate comprehensive risk assessments, regulatory compliance, and AI/ML (artificial intelligence/machine learning)-driven adaptability. We develop a novel adaptive edge security framework that dynamically generates and adjusts security policies for IoT edge devices. Our framework integrates a dynamic security policy generator, a conflict detection and resolution in policy generator, a bias-aware risk assessment system, a regulatory compliance analysis system, and an AI-driven adaptability integration system. This approach produces tailored security policies that adapt to changes in the threat landscape, regulatory requirements, and device statuses. Our study identifies critical security challenges in diverse IoT environments and demonstrates the effectiveness of our framework through simulations and real-world scenarios. We found that our framework significantly enhances the adaptability and resilience of IoT security policies. Our results demonstrate the potential of AI/ML integration in creating responsive and robust security measures for IoT ecosystems. The implications of our findings suggest that dynamic and adaptive security frameworks are essential for protecting IoT devices against evolving cyber threats, ensuring compliance with regulatory standards, and maintaining the integrity and availability of IoT services across various applications.

Artificial Intelligence: Future Aspects in the Pharmaceutical Industry an Overview

Artificial intelligence (AI) has emerged as a potent tool leveraging human-like knowledge to offer swift solutions to intricate challenges. Striking advancements in AI technology and machine learning present a revolutionary opportunity in pharmaceutical drug discovery, formulation, and dosage form testing. By employing AI algorithms that scrutinize vast biological datasets encompassing genomics and proteomics, scientists can pinpoint disease-related targets and forecast their interactions with potential drug candidates. This facilitates a more precise and efficient approach to drug discovery, thereby elevating the chances of successful drug approvals. Moreover, AI holds the potential to curtail development costs by streamlining research and development processes. Machine learning algorithms aid in experimental design and can foresee the pharmacokinetics and toxicity of drug candidates, allowing for the prioritization and refinement of lead compounds, thereby reducing the necessity for extensive and expensive animal testing. Personalized medicine initiatives can be advanced through AI algorithms analyzing real-world patient data, culminating in more efficacious treatment outcomes and enhanced patient compliance. This comprehensive overview delves into the diverse applications of AI in pharmaceutical drug discovery, dosage form design for drug delivery, process refinement, testing, and pharmacokinetics/pharmacodynamics (PK/PD) investigations. It provides a glimpse into various AI-driven methodologies employed in pharmaceutical technology, shedding light on their advantages and limitations. Nonetheless, sustained investments in and exploration of AI within the pharmaceutical sector present promising avenues for enhancing drug development processes and patient care.

Intelligent aeration amount prediction control for wastewater treatment process based on recurrent neural network

The use of machine learning in artificial intelligence to solve industrial problems has been a current trend. Predictions can be made by machine learning algorithms. This greatly improves the efficiency and also the accuracy. With the development of industrialization, the pollution of water resources is becoming more and more serious. How to treat wastewater more cost-effectively to meet the discharge standards has become one of the most urgent problems in the world. In the Anaerobic-Anoxic-Aerobic (AAO) process, the key to reach the standard of sewage treatment with low cost and high efficiency lies in the aeration link. In this study, multiple machine learning methods are used for modeling, and proposed a method employing the long short-term memory (LSTM) neural network model for regression prediction addresses the need for a more accurate prediction approach. By utilizing data from the preceding 100 days, this model replaces manual, experience-based prediction methods, thereby mitigating energy consumption. This model is optimized by training and testing with real wastewater treatment plant data and continuously adjusting the parameters through multiple sets of experiments. This can make the real recorded aeration amount and the actual aeration amount infinitely close. Through the experimental comparison, it is found that the performance of the LSTM neural network model is better, with about 14% higher accuracy than the benchmark model.

A novel hybrid ANN-GB-LR model for predicting oil and gas production rate

The Oil and Gas Production Rate (OGPR) is one of the most significant processes that play an essential role in the oil industry. Predicting OGPR is critical for effective reservoir management and enhancing oil recovery. Traditional methods (TMs) and numerical simulations (NS) often struggle to process and analyze nonlinear, complex, and massive datasets. To avoid these challenges, artificial intelligence (AI) techniques and machine learning (ML) models have been proposed as an alternative solution due to their high efficiency and rapidity in handling complex data. In this study, a new hybrid model is developed by combining the strengths of Artificial Neural Networks (ANN) and Gradient Boosting (GB), using Linear Regression (LR) as a meta-model by stacking technique. It captures nonlinear relationships effectively and manages outliers, enhancing prediction accuracy. The novelty of this study lies in the hybrid ANN-GB-LR model's ability to integrate various machine learning techniques into a robust framework, leveraging the high learning capacity of ANN, the robust handling of outliers by GB, and the straightforward interpretability of LR. This creative combination handles the limitations of individual models and enhances the general predictive performance. The model was trained and tested using actual field data from the Halewah field in Yemen. Evaluation metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2), were utilized to evaluate and compare the hybrid model with other ML models: Random Forest (RF), XGBoost (XGB), LR, Light Gradient Boosting Machine (LGBM), GB, and K-nearest neighbors (KNN). The hybrid ANN-GB-LR model achieved superior results, with an R2 of 0.998, an RMSE of 11.06 for oil flow rate predictions, and an R2 of 0.98 and an RMSE of 172.15 for gas flow rate predictions. These results significantly surpass the other models, demonstrating the hybrid model's outstanding ability to capture complex data and provide accurate predictions. The ANN-GB-LR model surpasses Traditional Methods in predicting OGPRs. It shows a strong and reliable tool for optimizing reservoir management. This study establishes a new standard for predictive modeling in the oil industry, providing a framework for future research to apply hybrid models in handling complex datasets.

Forme Fruste Keratoconus Detection with OCT Corneal Topography Using Artificial Intelligence Algorithms.

Distinguishing early Keratoconus (KC) from normal corneas is challenging owing to their striking similarities. The aim of our study was to identify discriminating parameters to differentiate a normal cornea from a Form Fruste Keratoconus (FFKC) with the Swept-Source (SS) OCT-topography CASIA 2 (Tomey,Japan) using machine learning artificial intelligence algorithms. The study was monocentric, carried out in Bordeaux. This was a retrospective study, case control. Three groups were included: KC group (108 eyes), FFKC (88 eyes) and normal corneas (162 eyes).The data were analyzed and processed using the Dataiku data science platform. Machine learning models (Random Forest, Logistic Regression) were used to develop a multiclass classifier for automated early KC detection. The models were trained using a training database and tested using a test database. Then algorithms were compared to the Ectasia Screening Index (ESI), which is an OCT-topography inherent screening score for ectasia. The Logistic Regression (LR), and Random Forest (RF) detected FFKC with an AUC of 0,99, and 0,98 respectively. The sensitivities of LR (100%), RF (84%) were better than the ESI (28%) for the diagnosis of FFKC. However, ESI has a maximum specificity (100%) compared to the RL (100%) and 90% for RF. This study identified discriminating topographic parameters to be considered in refractive surgery screening on SS-OCT CASIA 2. We developed an algorithm capable of classifying normal eyes versus FFKC cases, with improved performance compared to the ESI score.

Quantitative assessment of brain structural abnormalities in children with autism spectrum disorder based on artificial intelligence automatic brain segmentation technology and machine learning methods

Rationale and objectivesTo explore the characteristics of brain structure in Chinese children with autism spectrum disorder (ASD) using artificial intelligence automatic brain segmentation technique, and to diagnose children with ASD using machine learning (ML) methods in combination with structural magnetic resonance imaging (sMRI) features. MethodsA total of 60 ASD children and 48 age- and sex-matched typically developing (TD) children were prospectively enrolled from January 2023 to April 2024. All subjects were scanned using 3D-T1 sequences. Automated brain segmentation techniques were utilized to obtain the standardized volume of each brain structure (the ratio of the absolute volume of brain structure to the whole brain volume). The standardized volumes of each brain structure in the two groups were statistically compared, and the volume data of brain areas with significant differences were combined with ML methods to diagnose and predict ASD patients. ResultsCompared with the TD group, the volumes of the right lateral orbitofrontal cortex, right medial orbitofrontal cortex, right pars opercularis, right pars triangularis, left hippocampus, bilateral parahippocampal gyrus, left fusiform gyrus, right superior temporal gyrus, bilateral insula, bilateral inferior parietal cortex, right precuneus cortex, bilateral putamen, left pallidum, and right thalamus were significantly increased in the ASD group (P< 0.05). Among six ML algorithms, support vector machine (SVM) and adaboost (AB) had better performance in differentiating subjects with ASD from those TD children, with their average area under curve (AUC) reaching 0.91 and 0.92, respectively. ConclusionAutomatic brain segmentation technology based on artificial intelligence can rapidly and directly measure and display the volume of brain structures in children with autism spectrum disorder and typically developing children. Children with ASD show abnormalities in multiple brain structures, and when paired with sMRI features, ML algorithms perform well in the diagnosis of ASD.

On the Application of Artificial Intelligence/Machine Learning (AI/ML) in Late-Stage Clinical Development.

Whereas AI/ML methods were considered experimental tools in clinical development for some time, nowadays they are widely available. However, stakeholders in the health care industry still need to answer the question which role these methods can realistically play and what standards should be adhered to. Clinical research in late-stage clinical development has particular requirements in terms of robustness, transparency and traceability. These standards should also be adhered to when applying AI/ML methods. Currently there is some formal regulatory guidance available, but this is more directed at settings where a device or medical software is investigated. Here we focus on the application of AI/ML methods in late-stage clinical drug development, i.e. in a setting where currently less guidance is available. This is done via first summarizing available regulatory guidance and work done by regulatory statisticians followed by the presentation of an industry application where the influence of extensive sets of baseline characteristics on the treatment effect can be investigated by applying ML-methods in a standardized manner with intuitive graphical displays leveraging explainable AI methods. The paper aims at stimulating discussions on the role such analyses can play in general rather than advocating for a particular AI/ML-method or indication where such methods could be meaningful.

Coagulation Risk Predicting in Anticoagulant-Free Continuous Renal Replacement Therapy.

Continuous renal replacement therapy (CRRT) is a prolonged continuous extracorporeal blood purification therapy to replace impaired renal function. Typically, CRRT therapy requires routine anticoagulation, but for patients at risk of bleeding and with contraindications to sodium citrate, anticoagulant-free dialysis therapy is necessary. However, this approach increases the risk of CRRT circuit coagulation, leading to treatment interruption and increased resource consumption. In this study, we utilized artificial intelligence machine learning methods to predict the risk of CRRT circuit coagulation based on pre-CRRT treatment metrics. We retrospectively analyzed 212 patients who underwent anticoagulant-free CRRT from October 2022 to October 2023. Patients were categorized into high-risk and low-risk groups based on CRRT circuit coagulation within 24 h. We employed eight machine learning methods to predict the risk of circuit coagulation. The performance of the model was evaluated using the area under the curve (AUC) of the receiver operating characteristic. 5-fold cross-validation was used to validate the machine learning models. Feature importance and SHAP plots were used to interpret the model's performance and key drivers. We identified 88 patients (41.51%) at high risk of circuit coagulation within 24 h of CRRT. Our machine learning models showed excellent predictive performance, with ensemble learning achieving an AUC of 0.863 (95% CI: 0.860-0.868), outperforming individual algorithms. Random forest was the best single-algorithm model, with an AUC of 0.819 (95% CI: 0.814-0.823). The top three features identified as most important by the SHAP summary plot and feature importance graph are platelet, filtration fraction (FF), and triglycerides. We created a model using machine learning to predict the risk of circuit coagulation during anticoagulant-free CRRT therapy. Our model performs well (AUC 0.863) and identifies key factors like platelets, FF, and triglycerides. This facilitates the development of personalized treatment strategies by clinicians aimed at reducing circuit coagulation risk, thereby enhancing patient outcomes and reducing healthcare expenses.