Deep learning, reinforcement learning, and world models

Applying artificial intelligence to rare diseases: a literature review highlighting lessons from Fabry disease

BACKGROUND

Use of artificial intelligence (AI) in rare diseases has grown rapidly in recent years. In this review we have outlined the most common machine-learning and deep-learning methods currently being used to classify and analyse large amounts of data, such as standardized images or specific text in electronic health records. To illustrate how these methods have been adapted or developed for use with rare diseases, we have focused on Fabry disease, an X-linked genetic disorder caused by lysosomal α-galactosidase. A deficiency that can result in multiple organ damage.

METHODS

We searched PubMed for articles focusing on AI, rare diseases, and Fabry disease published anytime up to 08 January 2025. Further searches, limited to articles published between 01 January 2021 and 31 December 2023, were also performed using double combinations of keywords related to AI and each organ affected in Fabry disease, and AI and rare diseases.

RESULTS

In total, 20 articles on AI and Fabry disease were included. In the rare disease field, AI methods may be applied prospectively to large populations to identify specific patients, or retrospectively to large data sets to diagnose a previously overlooked rare disease. Different AI methods may facilitate Fabry disease diagnosis, help monitor progression in affected organs, and potentially contribute to personalized therapy development. The implementation of AI methods in general healthcare and medical imaging centres may help raise awareness of rare diseases and prompt general practitioners to consider these conditions earlier in the diagnostic pathway, while chatbots and telemedicine may accelerate patient referral to rare disease experts. The use of AI technologies in healthcare may generate specific ethical risks, prompting new AI regulatory frameworks aimed at addressing these issues to be established in Europe and the United States.

CONCLUSION

AI-based methods will lead to substantial improvements in the diagnosis and management of rare diseases. The need for a human guarantee of AI is a key issue in pursuing innovation while ensuring that human involvement remains at the centre of patient care during this technological revolution.

Reinforcement learning for healthcare operations management: methodological framework, recent developments, and future research directions

With the advancement in computing power and data science techniques, reinforcement learning (RL) has emerged as a powerful tool for decision-making problems in complex systems. In recent years, the research on RL for healthcare operations has grown rapidly. Especially during the COVID-19 pandemic, RL has played a critical role in optimizing decisions with greater degrees of uncertainty. RL for healthcare applications has been an exciting topic across multiple disciplines, including operations research, operations management, healthcare systems engineering, and data science. This review paper first provides a tutorial on the overall framework of RL, including its key components, training models, and approximators. Then, we present the recent advances of RL in the domain of healthcare operations management (HOM) and analyze the current trends. Our paper concludes by presenting existing challenges and future directions for RL in HOM.

Improving robustness by action correction via multi-step maximum risk estimation

Certifying robustness against external uncertainties throughout the control process to reduce the risk of instability is very important. Most existing approaches based on adversarial learning use a fixed parameter to adjust the intensity of adversarial perturbations and design these perturbations in a greedy manner without considering future implications. However, they often lead to severe vulnerabilities when attack budgets vary dynamically or under foresighted attacks. To address the problem, an algorithm that optimizes reinforcement learning policies by extending the focus beyond fixed-strength greedy attacks and estimating the maximum risk value, referred to as Multi-Step Maximum Risk-Aware Robust Deep Reinforcement Learning (MMRAR-RL), is proposed. MMRAR-RL operates in two stages: risk assessment and policy improvement. In the risk assessment stage, the adversary adaptively allocates the attack budget based on the agent's potential subsequent trajectories, planning multi-step perturbations to craft more powerful attacks. MMRAR-RL defines the multi-step perturbation value loss under these dynamic budgets as the difference between the original action-value function and the expected cumulative discounted returns under disturbances. The multi-step perturbation value loss characterizes action risk and directly estimates the maximum risk of a policy through a novel maximal risk Bellman operator. In the policy improvement stage, MMRAR-RL updates the policy based on the maximum action risk value function and a nominal loss function, thereby enhancing robustness against dynamic and foresighted attacks. Experiments demonstrate that MMRAR-RL achieves state-of-the-art performance under strong adversarial conditions, effectively tolerating action perturbations.

Synth-CLIP: Synthetic data make CLIP generalize better in data-limited scenarios

Prompt learning is a powerful technique that enables the transfer of Vision-Language Models (VLMs) like CLIP to downstream tasks. However, when the prompt-based methods are fine-tuned solely on base classes, they often struggle to generalize to novel classes lacking visual samples during training, especially in scenarios with limited training data. To address this challenge, we propose an innovative approach called Synth-CLIP that leverages synthetic data to enhance CLIP's generalization capability for base classes and the general capability for novel classes. Synth-CLIP fine-tunes the pre-trained CLIP model by seamlessly integrating tailored prompts that are both domain-specific and domain-shared, specifically designed for visual samples, reorganizing visual features from real and synthetic domains into the semantic space. This approach efficiently expands the data pool and enriches category diversity. Moreover, based on semantic structure consistency, we introduce a cross-domain feature alignment loss to match the real and synthetic samples in the feature embedding space. By aligning the visual and semantic distributions, the synthetic data from base and novel classes provide crucial discriminative information, enabling the model to rebalance the decision boundaries even in the absence of real novel visual samples. Experimental results on three model generalization tasks demonstrate that our method performs very competitively across various benchmarks. Notably, Synth-CLIP outperforms the recent competitor PromptSRC by an average improvement of 3.0% on novel classes across 11 datasets in open-vocabulary scenarios.

Medical diagnosis based on artificial intelligence and decision support system in the management of health development

BACKGROUND

Medical diagnosis plays a critical role in our daily lives. Every day, over 10 billion cases of both mental and physical health disorders are diagnosed and reported worldwide. To diagnose these disorders, medical practitioners and health professionals employ various assessment tools. However, these tools often face scrutiny due to their complexity, prompting researchers to increase their experimental parameters to provide accurate justifications. Additionally, it is essential for professionals to properly justify, interpret, and analyse the results from these prediction tools.

METHODS

This research paper explores the use of artificial intelligence and advanced analytics in developing Clinical Decision Support Systems (CDSS). These systems are capable of diagnosing and detecting patterns of various medical disorders. Various machine learning algorithms contribute to building these assessment tools, with the Network Pattern Recognition (NEPAR) algorithm being the first to aid in developing CDSS. Over time, researchers have recognised the value of machine learning-based prediction models in successfully justifying medical diagnoses.

RESULTS

The proposed CDSS models have demonstrated the ability to diagnose mental disorders with an accuracy of up to 89% using only 28 questions, without requiring human input. For physical health issues, additional parameters are used to enhance the accuracy of CDSS models.

CONCLUSIONS

Consequently, medical professionals are increasingly relying on these machine learning-based CDSS models, utilising these tools to improve medical diagnosis and assist in decision-making. The different cross-validation values are considered to remove the data biasness.

Complementary roles for hippocampus and anterior cingulate in composing continuous choice

Naturalistic, goal directed behavior often requires continuous actions directed at dynamically changing goals. In this context, the closest analogue to choice is a strategic reweighting of multiple goal-specific control policies in response to shifting environmental pressures. To understand the algorithmic and neural bases of choice in continuous contexts, we examined behavior and brain activity in humans performing a continuous prey-pursuit task. Using a newly developed control-theoretic decomposition of behavior, we find pursuit strategies are well described by a meta-controller dictating a mixture of lower-level controllers, each linked to specific pursuit goals. Examining hippocampus and anterior cingulate cortex (ACC) population dynamics during goal switches revealed distinct roles for the two regions in parameterizing continuous controller mixing and meta-control. Hippocampal ensemble dynamics encoded the controller blending dynamics, suggesting it implements a mixing of goal-specific control policies. In contrast, ACC ensemble activity exhibited value-dependent ramping activity before goal switches, linking it to a meta-control process that accumulates evidence for switching goals. Our results suggest that hippocampus and ACC play complementary roles corresponding to a generalizable mixture controller and meta-controller that dictates value dependent changes in controller mixing.

Cooperative control of self-learning traffic signal and connected automated vehicles for safety and efficiency optimization at intersections

Cooperative control of intersection signals and connected automated vehicles (CAVs) possess the potential for safety enhancement and congestion alleviation, facilitating the integration of CAVs into urban intelligent transportation systems. This research proposes an innovative deep reinforcement learning-based (DRL) cooperative control framework, including signal and speed modules, to dynamically adapt signal timing and CAV velocities for traffic safety and efficiency optimization. Among the DRL-based signal modules, a traffic state prediction model is merged with the current state to augment characteristics and the agent-learning process. A multi-objective reward function is designed to evaluate safety and efficiency using a traffic conflict prediction model and vehicle waiting time. The double deep Q network (DDQN) model is used to design the agent observing the traffic state, learning the optimal signal control policy, and then inputting the signal phase into the speed module. Based on the green duration analysis and constraints of mixed traffic flow of CAVs and human-driven vehicles, a speed planning model is constructed to optimize CAVs' speed and alter traffic state, which in turn affects the agent's next signal decisions. The proposed framework is tested at isolated intersections simulated by two real-world intersections in Changsha, China. The results reveal the superiority of the proposed method over DRL-based traffic signal control (DRL-TSC) in terms of coverage speed and computation time. Compared to actuated signal control, adaptive traffic signal control, and DRL-TSC, the proposed method significantly optimizes traffic safety and efficiency across diverse intersections, temporal spans, and traffic demands. Furthermore, the advantage of the proposed method substantially amplifies with the increased CAV penetration, regardless of the intersection types.

Intersect between brain mechanisms of conditioned threat, active avoidance, and reward

Active avoidance is a core behavior for human coping, and its excess is common across psychiatric diseases. The decision to actively avoid a threat is influenced by cost and reward. Yet, threat, avoidance, and reward have been studied in silos. We discuss behavioral and brain circuits of active avoidance and the interactions with fear and threat. In addition, we present a neural toggle switch model enabling fear-to-anxiety transition and approaching reward vs. avoiding harm decision. To fully comprehend how threat, active avoidance, and reward intersect, it is paramount to develop one shared experimental approach across phenomena and behaviors, which will ultimately allow us to better understand human behavior and pathology.

Artificial Intelligence in Human Reproduction

The use of artificial intelligence (AI) in human reproduction is a rapidly evolving field with both exciting possibilities and ethical considerations. This technology has the potential to improve success rates and reduce the emotional and financial burden of infertility. However, it also raises ethical and privacy concerns. This paper presents an overview of the current and potential applications of AI in human reproduction. It explores the use of AI in various aspects of reproductive medicine, including fertility tracking, assisted reproductive technologies, management of pregnancy complications, and laboratory automation. In addition, we discuss the need for robust ethical frameworks and regulations to ensure the responsible and equitable use of AI in reproductive medicine.

Spectral integrated neural networks (SINNs) for solving forward and inverse dynamic problems

This study introduces an innovative neural network framework named spectral integrated neural networks (SINNs) to address both forward and inverse dynamic problems in three-dimensional space. In the SINNs, the spectral integration technique is utilized for temporal discretization, followed by the application of a fully connected neural network to solve the resulting partial differential equations in the spatial domain. Furthermore, the polynomial basis functions are employed to expand the unknown function, with the goal of improving the performance of SINNs in tackling inverse problems. The performance of the developed framework is evaluated through several dynamic benchmark examples encompassing linear and nonlinear heat conduction problems, linear and nonlinear wave propagation problems, inverse problem of heat conduction, and long-time heat conduction problem. The numerical results demonstrate that the SINNs can effectively and accurately solve forward and inverse problems involving heat conduction and wave propagation. Additionally, the SINNs provide precise and stable solutions for dynamic problems with extended time durations. Compared to commonly used physics-informed neural networks, the SINNs exhibit superior performance with enhanced convergence speed, computational accuracy, and efficiency.

A novel DRL-guided sparse voxel decoding model for reconstructing perceived images from brain activity

BACKGROUND

Due to the sparse encoding character of the human visual cortex and the scarcity of paired training samples for {images, fMRIs}, voxel selection is an effective means of reconstructing perceived images from fMRI. However, the existing data-driven voxel selection methods have not achieved satisfactory results.

NEW METHOD

Here, a novel deep reinforcement learning-guided sparse voxel (DRL-SV) decoding model is proposed to reconstruct perceived images from fMRI. We innovatively describe voxel selection as a Markov decision process (MDP), training agents to select voxels that are highly involved in specific visual encoding.

RESULTS

Experimental results on two public datasets verify the effectiveness of the proposed DRL-SV, which can accurately select voxels highly involved in neural encoding, thereby improving the quality of visual image reconstruction.

COMPARISON WITH EXISTING METHODS

We qualitatively and quantitatively compared our results with the state-of-the-art (SOTA) methods, getting better reconstruction results. We compared the proposed DRL-SV with traditional data-driven baseline methods, obtaining sparser voxel selection results, but better reconstruction performance.

CONCLUSIONS

DRL-SV can accurately select voxels involved in visual encoding on few-shot, compared to data-driven voxel selection methods. The proposed decoding model provides a new avenue to improving the image reconstruction quality of the primary visual cortex.

Quality-diversity based semi-autonomous teleoperation using reinforcement learning

Recent successes in robot learning have significantly enhanced autonomous systems across a wide range of tasks. However, they are prone to generate similar or the same solutions, limiting the controllability of the robot to behave according to user intentions. These limited robot behaviors may lead to collisions and potential harm to humans. To resolve these limitations, we introduce a semi-autonomous teleoperation framework that enables users to operate a robot by selecting a high-level command, referred to as option. Our approach aims to provide effective and diverse options by a learned policy, thereby enhancing the efficiency of the proposed framework. In this work, we propose a quality-diversity (QD) based sampling method that simultaneously optimizes both the quality and diversity of options using reinforcement learning (RL). Additionally, we present a mixture of latent variable models to learn multiple policy distributions defined as options. In experiments, we show that the proposed method achieves superior performance in terms of the success rate and diversity of the options in simulation environments. We further demonstrate that our method outperforms manual keyboard control for time duration over cluttered real-world environments.

Clustering Electrophysiological Predisposition to Binge Drinking: An Unsupervised Machine Learning Analysis

BACKGROUND

The demand for fresh strategies to analyze intricate multidimensional data in neuroscience is increasingly evident. One of the most complex events during our neurodevelopment is adolescence, where our nervous system suffers constant changes, not only in neuroanatomical traits but also in neurophysiological components. One of the most impactful factors we deal with during this time is our environment, especially when encountering external factors such as social behaviors or substance consumption. Binge drinking (BD) has emerged as an extended pattern of alcohol consumption in teenagers, not only affecting their future lifestyle but also changing their neurodevelopment. Recent studies have changed their scope into finding predisposition factors that may lead adolescents into this kind of patterns of consumption.

METHODS

In this article, using unsupervised machine learning (UML) algorithms, we analyze the relationship between electrophysiological activity of healthy teenagers and the levels of consumption they had 2 years later. We used hierarchical agglomerative UML techniques based on Ward's minimum variance criterion to clusterize relations between power spectrum and functional connectivity and alcohol consumption, based on similarity in their correlations, in frequency bands from theta to gamma.

RESULTS

We found that all frequency bands studied had a pattern of clusterization based on anatomical regions of interest related to neurodevelopment and cognitive and behavioral aspects of addiction, highlighting the dorsolateral and medial prefrontal, the sensorimotor, the medial posterior, and the occipital cortices. All these patterns, of great cohesion and coherence, showed an abnormal electrophysiological activity, representing a dysregulation in the development of core resting-state networks. The clusters found maintained not only plausibility in nature but also robustness, making this a great example of the usage of UML in the analysis of electrophysiological activity-a new perspective into analysis that, while contributing to classical statistics, can clarify new characteristics of the variables of interest.

Efficient Reinforcement Learning With the Novel N-Step Method and V-Network

The application of reinforcement learning (RL) in artificial intelligence has become increasingly widespread. However, its drawbacks are also apparent, as it requires a large number of samples for support, making the enhancement of sample efficiency a research focus. To address this issue, we propose a novel N-step method. This method extends the horizon of the agent, enabling it to acquire more long-term effective information, thus resolving the issue of data inefficiency in RL. Additionally, this N-step method can reduce the estimation variance of Q-function, which is one of the factors contributing to estimation errors in Q-function estimation. Apart from high variance, estimation bias in Q-function estimation is another factor leading to estimation errors. To mitigate the estimation bias of Q-function, we design a regularization method based on the V-function, which has been underexplored. The combination of these two methods perfectly addresses the problems of low sample efficiency and inaccurate Q-function estimation in RL. Finally, extensive experiments conducted in discrete and continuous action spaces demonstrate that the proposed novel N-step method, when combined with classical deep Q-network, deep deterministic policy gradient, and TD3 algorithms, is effective, consistently outperforming the classical algorithms.

Deep learning applications in breast cancer histopathological imaging: diagnosis, treatment, and prognosis

Breast cancer is the most common malignant tumor among women worldwide and remains one of the leading causes of death among women. Its incidence and mortality rates are continuously rising. In recent years, with the rapid advancement of deep learning (DL) technology, DL has demonstrated significant potential in breast cancer diagnosis, prognosis evaluation, and treatment response prediction. This paper reviews relevant research progress and applies DL models to image enhancement, segmentation, and classification based on large-scale datasets from TCGA and multiple centers. We employed foundational models such as ResNet50, Transformer, and Hover-net to investigate the performance of DL models in breast cancer diagnosis, treatment, and prognosis prediction. The results indicate that DL techniques have significantly improved diagnostic accuracy and efficiency, particularly in predicting breast cancer metastasis and clinical prognosis. Furthermore, the study emphasizes the crucial role of robust databases in developing highly generalizable models. Future research will focus on addressing challenges related to data management, model interpretability, and regulatory compliance, ultimately aiming to provide more precise clinical treatment and prognostic evaluation programs for breast cancer patients.

The Medicine Revolution Through Artificial Intelligence: Ethical Challenges of Machine Learning Algorithms in Decision-Making

The integration of artificial intelligence (AI) and its autonomous learning processes (or machine learning) in medicine has revolutionized the global health landscape, providing faster and more accurate diagnoses, personalization of medical treatment, and efficient management of clinical information. However, this transformation is not without ethical challenges, which require a comprehensive and responsible approach. There are many fields where AI and medicine intersect, such as health education, patient-doctor interface, data management, diagnosis, intervention, and decision-making processes. For some of these fields, there are some guidelines to regulate them. AI has numerous applications in medicine, including medical imaging analysis, diagnosis, predictive analytics for patient outcomes, drug discovery and development, virtual health assistants, and remote patient monitoring. It is also used in robotic surgery, clinical decision support systems, AI-powered chatbots for triage, administrative workflow automation, and treatment recommendations. Despite numerous applications, there are several problems related to the use of AI identified in the literature in general and in medicine in particular. These problems are data privacy and security, bias and discrimination, lack of transparency (Black Box Problem), integration with existing systems, cost and accessibility disparities, risk of overconfidence in AI, technical limitations, accountability for AI errors, algorithmic interpretability, data standardization issues, unemployment, and challenges in clinical validation. Of the various problems already identified, the most worrying are data bias, the black box phenomenon, questions about data privacy, responsibility for decision-making, security issues for the human species, and technological unemployment. There are still several ethical problems associated with the use of AI autonomous learning algorithms, namely epistemic, normative, and comprehensive ethical problems (overarching). Addressing all these issues is crucial to ensure that the use of AI in healthcare is implemented ethically and responsibly, providing benefits to populations without compromising fundamental values. Ongoing dialogue between healthcare providers and the industry, the establishment of ethical guidelines and regulations, and considering not only current ethical dilemmas but also future perspectives are fundamental points for the application of AI to medical practice. The purpose of this review is to discuss the ethical issues of AI algorithms used mainly in data management, diagnosis, intervention, and decision-making processes.

The analysis of teaching quality evaluation for the college sports dance by convolutional neural network model and deep learning

This study aims to comprehensively analyze and evaluate the quality of college physical dance education using Convolutional Neural Network (CNN) models and deep learning methods. The study introduces a teaching quality evaluation (TQE) model based on one-dimensional CNN, addressing issues such as subjectivity and inconsistent evaluation criteria in traditional assessment methods. By constructing a comprehensive TQE system comprising 24 evaluation indicators, this study innovatively applies deep learning technology to quantitatively assess the quality of physical dance education. This TQE model processes one-dimensional evaluation data by extracting local features through convolutional layers, reducing dimensions via pooling layers, and feeding feature vectors into a classifier through fully connected layers to achieve an overall assessment of teaching quality. Experimental results demonstrate that after 150 iterations of training and validation on the TQE model, convergence is achieved, with mean squared error (MSE) decreasing to 0.0015 and 0.0216 on the training and validation sets, respectively. Comparatively, the TQE model exhibits significantly lower MSE on the training, validation, and test sets compared to the Back-Propagation Neural Network, accompanied by a higher R2 value, indicating superior accuracy and performance in data fitting. Further analysis on robustness, parameter sensitivity, multi-scenario adaptability, and long-term learning capabilities reveals the TQE model's strong resilience and stability in managing noisy data, varying parameter configurations, diverse teaching contexts, and extended time-series data. In practical applications, the TQE model is implemented in physical dance courses at X College to evaluate teaching quality and guide improvement strategies for instructors, resulting in notable enhancements in teaching quality and student satisfaction. In conclusion, this study offers a comprehensive evaluation of university physical dance education quality through a multidimensional assessment system and the application of the 1D-CNN model. It introduces a novel and effective approach to assessing teaching quality, providing a scientific foundation and practical guidance for future educational advancements.

Imaging biobanks: operational limits, medical-legal and ethical reflections

The extraordinary growth of health technologies has determined an increasing interest in biobanks that represent a unique wealth for research, experimentation, and validation of new therapies. "Human" biobanks are repositories of various types of human biological samples. Through years the paradigm has shifted from spontaneous collections of biological material all over the world to institutional, organized, and well-structured forms. Imaging biobanks represent a novel field and are defined by European Society of Radiology as: "organized databases of medical images, and associated imaging biomarkers shared among multiple researchers, linked to other biorepositories". Modern radiology and nuclear medicine can provide multiple imaging biomarkers, that express the phenotype related to certain diseases, especially in oncology. Imaging biobanks, not a mere catalogue of bioimages associated to clinical data, involve advanced computer technologies to implement the emergent field of radiomics and radiogenomics. Since Europe hosts most of the biobanks, juridical and ethical framework, with a specific referral to Italy, is analyzed. Linking imaging biobanks to traditional ones appears to be a crucial step that needs to be driven by medical imaging community under clear juridical and ethical guidelines.

Soybean seed pest damage detection method based on spatial frequency domain imaging combined with RL-SVM

Soybean seeds are susceptible to damage from the Riptortus pedestris, which is a significant factor affecting the quality of soybean seeds. Currently, manual screening methods for soybean seeds are limited to visual inspection, making it difficult to identify seeds that are phenotypically defect-free but have been punctured by stink bugs on the sub-surface. To facilitate the convenient and efficient identification of healthy soybean seeds, this paper proposes a soybean seed pest detection method based on spatial frequency domain imaging combined with RL-SVM. Firstly, soybean optical data is obtained using single integration sphere technique, and the vigor index of soybean seeds is obtained through germination experiments. Then, based on the above two data items using feature extraction algorithms (the successive projections algorithm and the competitive adaptive reweighted sampling algorithm), the characteristic wavelengths of soybeans are identified. Subsequently, the spatial frequency domain imaging technique is used to obtain the sub-surface images of soybean seeds in a forward manner, and the optical coefficients such as the reduced scattering coefficientμ ' s and absorption coefficient μ a of soybean seeds are inverted. Finally, RL-MLR, RL-GRNN, and RL-SVM prediction models are established based on the ratio of the area of insect-damaged sub-surface to the entire seed, soybean varieties, and μ a at three wavelengths (502 nm, 813 nm, and 712 nm) for predicting and identifying soybean the stinging and sucking pest damage levels of soybean seeds. The experimental results show that the spatial frequency domain imaging technique yields small errors in the optical coefficients of soybean seeds, with errors of less than 15% for μ a and less than 10% forμ ' s . After parameter adjustment through reinforcement learning, the Macro-Recall metrics of each model have improved by 10%-15%, and the RL-SVM model achieves a high Macro-Recall value of 0.9635 for classifying the pest damage levels of soybean seeds.

Bioinspired Liquid Metal Based Soft Humanoid Robots

The pursuit of constructing humanoid robots to replicate the anatomical structures and capabilities of human beings has been a long-standing significant undertaking and especially garnered tremendous attention in recent years. However, despite the progress made over recent decades, humanoid robots have predominantly been confined to those rigid metallic structures, which however starkly contrast with the inherent flexibility observed in biological systems. To better innovate this area, the present work systematically explores the value and potential of liquid metals and their derivatives in facilitating a crucial transition towards soft humanoid robots. Through a comprehensive interpretation of bionics, an overview of liquid metals' multifaceted roles as essential components in constructing advanced humanoid robots-functioning as soft actuators, sensors, power sources, logical devices, circuit systems, and even transformable skeletal structures-is presented. It is conceived that the integration of these components with flexible structures, facilitated by the unique properties of liquid metals, can create unexpected versatile functionalities and behaviors to better fulfill human needs. Finally, a revolution in humanoid robots is envisioned, transitioning from metallic frameworks to hybrid soft-rigid structures resembling that of biological tissues. This study is expected to provide fundamental guidance for the coming research, thereby advancing the area.

Artificial Intelligence in Pediatric Emergency Medicine: Applications, Challenges, and Future Perspectives

The dawn of Artificial intelligence (AI) in healthcare stands as a milestone in medical innovation. Different medical fields are heavily involved, and pediatric emergency medicine is no exception. We conducted a narrative review structured in two parts. The first part explores the theoretical principles of AI, providing all the necessary background to feel confident with these new state-of-the-art tools. The second part presents an informative analysis of AI models in pediatric emergencies. We examined PubMed and Cochrane Library from inception up to April 2024. Key applications include triage optimization, predictive models for traumatic brain injury assessment, and computerized sepsis prediction systems. In each of these domains, AI models outperformed standard methods. The main barriers to a widespread adoption include technological challenges, but also ethical issues, age-related differences in data interpretation, and the paucity of comprehensive datasets in the pediatric context. Future feasible research directions should address the validation of models through prospective datasets with more numerous sample sizes of patients. Furthermore, our analysis shows that it is essential to tailor AI algorithms to specific medical needs. This requires a close partnership between clinicians and developers. Building a shared knowledge platform is therefore a key step.

A stochastic world model on gravity for stability inference

The fact that objects without proper support will fall to the ground is not only a natural phenomenon, but also common sense in mind. Previous studies suggest that humans may infer objects' stability through a world model that performs mental simulations with a priori knowledge of gravity acting upon the objects. Here we measured participants' sensitivity to gravity to investigate how the world model works. We found that the world model on gravity was not a faithful replica of the physical laws, but instead encoded gravity's vertical direction as a Gaussian distribution. The world model with this stochastic feature fit nicely with participants' subjective sense of objects' stability and explained the illusion that taller objects are perceived as more likely to fall. Furthermore, a computational model with reinforcement learning revealed that the stochastic characteristic likely originated from experience-dependent comparisons between predictions formed by internal simulations and the realities observed in the external world, which illustrated the ecological advantage of stochastic representation in balancing accuracy and speed for efficient stability inference. The stochastic world model on gravity provides an example of how a priori knowledge of the physical world is implemented in mind that helps humans operate flexibly in open-ended environments.

Exploring the Promise and Challenges of Artificial Intelligence in Biomedical Research and Clinical Practice

ABSTRACT

Artificial intelligence (AI) is poised to revolutionize how science, and biomedical research in particular, are done. With AI, problem-solving and complex tasks using massive data sets can be performed at a much higher rate and dimensionality level compared with humans. With the ability to handle huge data sets and self-learn, AI is already being exploited in drug design, drug repurposing, toxicology, and material identification. AI could also be used in both basic and clinical research in study design, defining outcomes, analyzing data, interpreting findings, and even identifying the most appropriate areas of investigation and funding sources. State-of-the-art AI-based large language models, such as ChatGPT and Perplexity, are positioned to change forever how science is communicated and how scientists interact with one another and their profession, including postpublication appraisal and critique. Like all revolutions, upheaval will follow and not all outcomes can be predicted, necessitating guardrails at the onset, especially to minimize the untoward impact of the many drawbacks of large language models, which include lack of confidentiality, risk of hallucinations, and propagation of mainstream albeit potentially mistaken opinions and perspectives. In this review, we highlight areas of biomedical research that are already being reshaped by AI and how AI is likely to affect it further in the near future. We discuss the potential benefits of AI in biomedical research and address possible risks, some surrounding the creative process, that warrant further reflection.

Machine learning models for predicting biochar properties from lignocellulosic biomass torrefaction

This study developed six machine learning models to predict the biochar properties from the dry torrefaction of lignocellulosic biomass by using biomass characteristics and torrefaction conditions as input variables. After optimization, gradient boosting machines were the optimal model, with the highest coefficient of determination ranging from 0.89 to 0.94. Torrefaction conditions exhibited a higher relative contribution to the yield and higher heating value (HHV) of biochar than biomass characteristics. Temperature was the dominant contributor to the elemental and proximate composition and the yield and HHV of biochar. Feature importance and SHapley Additive exPlanations revealed the effect of each influential factor on the target variables and the interactions between these factors in torrefaction. Software that can accurately predict the element, yield, and HHV of biochar was developed. These findings provide a comprehensive understanding of the key factors and their interactions influencing the torrefaction process and biochar properties.

Advances of machine learning-assisted small extracellular vesicles detection strategy

Detection of extracellular vesicles (EVs), particularly small EVs (sEVs), is of great significance in exploring their physiological characteristics and clinical applications. The heterogeneity of sEVs plays a crucial role in distinguishing different types of cells and diseases. Machine learning, with its exceptional data processing capabilities, offers a solution to overcome the limitations of conventional detection methods for accurately classifying sEV subtypes and sources. Principal component analysis, linear discriminant analysis, partial least squares discriminant analysis, XGBoost, support vector machine, k-nearest neighbor, and deep learning, along with some combined methods such as principal component-linear discriminant analysis, have been successfully applied in the detection and identification of sEVs. This review focuses on machine learning-assisted detection strategies for cell identification and disease prediction via sEVs, and summarizes the integration of these strategies with surface-enhanced Raman scattering, electrochemistry, inductively coupled plasma mass spectrometry and fluorescence. The performance of different machine learning-based detection strategies is compared, and the advantages and limitations of various machine learning models are also evaluated. Finally, we discuss the merits and limitations of the current approaches and briefly outline the perspective of potential research directions in the field of sEV analysis based on machine learning.

Reinforcement Learning Algorithms and Applications in Healthcare and Robotics: A Comprehensive and Systematic Review

Reinforcement learning (RL) has emerged as a dynamic and transformative paradigm in artificial intelligence, offering the promise of intelligent decision-making in complex and dynamic environments. This unique feature enables RL to address sequential decision-making problems with simultaneous sampling, evaluation, and feedback. As a result, RL techniques have become suitable candidates for developing powerful solutions in various domains. In this study, we present a comprehensive and systematic review of RL algorithms and applications. This review commences with an exploration of the foundations of RL and proceeds to examine each algorithm in detail, concluding with a comparative analysis of RL algorithms based on several criteria. This review then extends to two key applications of RL: robotics and healthcare. In robotics manipulation, RL enhances precision and adaptability in tasks such as object grasping and autonomous learning. In healthcare, this review turns its focus to the realm of cell growth problems, clarifying how RL has provided a data-driven approach for optimizing the growth of cell cultures and the development of therapeutic solutions. This review offers a comprehensive overview, shedding light on the evolving landscape of RL and its potential in two diverse yet interconnected fields.

Importance-aware adaptive dataset distillation

Herein, we propose a novel dataset distillation method for constructing small informative datasets that preserve the information of the large original datasets. The development of deep learning models is enabled by the availability of large-scale datasets. Despite unprecedented success, large-scale datasets considerably increase the storage and transmission costs, resulting in a cumbersome model training process. Moreover, using raw data for training raises privacy and copyright concerns. To address these issues, a new task named dataset distillation has been introduced, aiming to synthesize a compact dataset that retains the essential information from the large original dataset. State-of-the-art (SOTA) dataset distillation methods have been proposed by matching gradients or network parameters obtained during training on real and synthetic datasets. The contribution of different network parameters to the distillation process varies, and uniformly treating them leads to degraded distillation performance. Based on this observation, we propose an importance-aware adaptive dataset distillation (IADD) method that can improve distillation performance by automatically assigning importance weights to different network parameters during distillation, thereby synthesizing more robust distilled datasets. IADD demonstrates superior performance over other SOTA dataset distillation methods based on parameter matching on multiple benchmark datasets and outperforms them in terms of cross-architecture generalization. In addition, the analysis of self-adaptive weights demonstrates the effectiveness of IADD. Furthermore, the effectiveness of IADD is validated in a real-world medical application such as COVID-19 detection.

Distributed deep reinforcement learning based on bi-objective framework for multi-robot formation

Improving generalization ability in multi-robot formation can reduce repetitive training and calculation. In this paper, we study the multi-robot formation problem with the ability to generalize the target position. Since the generalization ability of neural network is directly proportional to spatial dimension, we adopt the strategy of using different networks to solve different objectives, so that the network learning can focus on the learning of one objective to obtain better performance. In addition, this paper presents a distributed deep reinforcement learning method based on soft actor-critic algorithm for solving multi-robot formation problem. At the same time, the formation evaluation assignment function is designed to adapt to distributed training. Compared with the original algorithm, the improved algorithm can get higher reward cumulative values. The experimental results show that the proposed algorithm can better maintain the desired formation in the moving process, and the rotation design in the reward function makes the multi-robot system have better flexibility in formation. The comparison of control signal curve shows that the proposed algorithm is more stable. At the end of the experiments, the universality of the proposed algorithm in formation maintenance and formation variations is demonstrated.

Intelligent maneuver strategy for hypersonic vehicles in three-player pursuit-evasion games via deep reinforcement learning

Aiming at the rapid development of anti-hypersonic collaborative interception technology, this paper designs an intelligent maneuver strategy of hypersonic vehicles (HV) based on deep reinforcement learning (DRL) to evade the collaborative interception by two interceptors. Under the meticulously designed collaborative interception strategy, the uncertainty and difficulty of evasion are significantly increased and the opportunity for maneuvers is further compressed. This paper, accordingly, selects the twin delayed deep deterministic gradient (TD3) strategy acting on the continuous action space and makes targeted improvements combining deep neural networks to grasp the maneuver strategy and achieve successful evasion. Focusing on the time-coordinated interception strategy of two interceptors, the three-player pursuit and evasion (PE) problem is modeled as the Markov decision process, and the double training strategy is proposed to juggle both interceptors. In reward functions of the training process, the energy saving factor is set to achieve the trade-off between miss distance and energy consumption. In addition, the regression neural network is introduced into the deep neural network of TD3 to enhance intelligent maneuver strategies' generalization. Finally, numerical simulations are conducted to verify that the improved TD3 algorithm can effectively evade the collaborative interception of two interceptors under tough situations, and the improvements of the algorithm in terms of convergence speed, generalization, and energy-saving effect are verified.

Human versus artificial intelligence-generated arthroplasty literature: A single-blinded analysis of perceived communication, quality, and authorship source

BACKGROUND

Large language models (LLM) have unknown implications for medical research. This study assessed whether LLM-generated abstracts are distinguishable from human-written abstracts and to compare their perceived quality.

METHODS

The LLM ChatGPT was used to generate 20 arthroplasty abstracts (AI-generated) based on full-text manuscripts, which were compared to originally published abstracts (human-written). Six blinded orthopaedic surgeons rated abstracts on overall quality, communication, and confidence in the authorship source. Authorship-confidence scores were compared to a test value representing complete inability to discern authorship.

RESULTS

Modestly increased confidence in human authorship was observed for human-written abstracts compared with AI-generated abstracts (p = 0.028), though AI-generated abstract authorship-confidence scores were statistically consistent with inability to discern authorship (p = 0.999). Overall abstract quality was higher for human-written abstracts (p = 0.019).

CONCLUSIONS

AI-generated abstracts' absolute authorship-confidence ratings demonstrated difficulty in discerning authorship but did not achieve the perceived quality of human-written abstracts. Caution is warranted in implementing LLMs into scientific writing.

The Inheritance of Hearing Loss and Deafness: A Historical Perspective

If the term "genetics" is a relatively recent proposition, introduced in 1905 by English biologist William Bateson, who rediscovered and spread in the scientific community Mendel's principles of inheritance, since the dawn of human civilization the influence of heredity has been recognized, especially in agricultural crops and animal breeding. And, later, in familial dynasties. In this concise review, we outline the evolution of the idea of hereditary hearing loss, up to the current knowledge of molecular genetics and epigenetics.

Exploring the matrix: knowledge, perceptions and prospects of artificial intelligence and machine learning in Nigerian healthcare

Background

Artificial intelligence technology can be applied in several aspects of healthcare delivery and its integration into the Nigerian healthcare value chain is expected to bring about new opportunities. This study aimed at assessing the knowledge and perception of healthcare professionals in Nigeria regarding the application of artificial intelligence and machine learning in the health sector.

Methods

A cross-sectional study was undertaken amongst healthcare professionals in Nigeria with the use of a questionnaire. Data were collected across the six geopolitical zones in the Country using a stratified multistage sampling method. Descriptive and inferential statistical analyses were undertaken for the data obtained.

Results

Female participants (55.7%) were slightly higher in proportion compared to the male respondents (44.3%). Pharmacists accounted for 27.7% of the participants, and this was closely followed by medical doctors (24.5%) and nurses (19.3%). The majority of the respondents (57.2%) reported good knowledge regarding artificial intelligence and machine learning, about a third of the participants (32.2%) were of average knowledge, and 10.6% of the sample had poor knowledge. More than half of the respondents (57.8%) disagreed with the notion that the adoption of artificial intelligence in the Nigerian healthcare sector could result in job losses. Two-thirds of the participants (66.7%) were of the view that the integration of artificial intelligence in healthcare will augment human intelligence. Three-quarters (77%) of the respondents agreed that the use of machine learning in Nigerian healthcare could facilitate efficient service delivery.

Conclusion

This study provides novel insights regarding healthcare professionals' knowledge and perception with respect to the application of artificial intelligence and machine learning in healthcare. The emergent findings from this study can guide government and policymakers in decision-making as regards deployment of artificial intelligence and machine learning for healthcare delivery.

Spatial and Temporal Hierarchy for Autonomous Navigation Using Active Inference in Minigrid Environment

Robust evidence suggests that humans explore their environment using a combination of topological landmarks and coarse-grained path integration. This approach relies on identifiable environmental features (topological landmarks) in tandem with estimations of distance and direction (coarse-grained path integration) to construct cognitive maps of the surroundings. This cognitive map is believed to exhibit a hierarchical structure, allowing efficient planning when solving complex navigation tasks. Inspired by human behaviour, this paper presents a scalable hierarchical active inference model for autonomous navigation, exploration, and goal-oriented behaviour. The model uses visual observation and motion perception to combine curiosity-driven exploration with goal-oriented behaviour. Motion is planned using different levels of reasoning, i.e., from context to place to motion. This allows for efficient navigation in new spaces and rapid progress toward a target. By incorporating these human navigational strategies and their hierarchical representation of the environment, this model proposes a new solution for autonomous navigation and exploration. The approach is validated through simulations in a mini-grid environment.

Large Range of a High-Precision, Independent, Sub-Mirror Three-Dimensional Co-Phase Error Sensing and Correction Method via a Mask and Population Algorithm

The emergence of segmented mirrors is expected to solve the design, processing, manufacturing, testing, and launching of space telescopes of large apertures. However, with the increase in the number of sub-mirrors, the sensing and correction of co-phase errors in segmented mirrors will be very difficult. In this paper, an independent three-dimensional method for sub-mirror co-phase error sensing and correction method is proposed. The method is based on a wide spectral modulation transfer function (MTF), mask, population optimization algorithm, and online model-free correction. In this method, the sensing and correction process of each sub-mirror co-phase error is independent of each other, so the increase in the number of sub-mirrors will not increase the difficulty of the method. This method can sense and correct the co-phase errors of three dimensions of the sub-mirror, including piston, tip, and tilt, even without modeling the optical system, and has a wide detection range and high precision. And the efficiency is high because the sub-mirrors can be corrected simultaneously in parallel. Simulation results show that the proposed method can effectively sense and correct the co-phase errors of the sub-mirrors in the range [-50λ, 50λ] in three dimensions with high precision. The average RMSE value in 100 experiments of the true co-phase error values and the experimental co-phase error values of one of the six sub-mirrors is 2.358 × 10-7λ.

Evaluation of information from artificial intelligence on rotator cuff repair surgery

Purpose

The purpose of this study was to analyze the quality and readability of information regarding rotator cuff repair surgery available using an online AI software.

Methods

An open AI model (ChatGPT) was used to answer 24 commonly asked questions from patients on rotator cuff repair. Questions were stratified into one of three categories based on the Rothwell classification system: fact, policy, or value. The answers for each category were evaluated for reliability, quality and readability using The Journal of the American Medical Association Benchmark criteria, DISCERN score, Flesch-Kincaid Reading Ease Score and Grade Level.

Results

The Journal of the American Medical Association Benchmark criteria score for all three categories was 0, which is the lowest score indicating no reliable resources cited. The DISCERN score was 51 for fact, 53 for policy, and 55 for value questions, all of which are considered good scores. Across question categories, the reliability portion of the DISCERN score was low, due to a lack of resources. The Flesch-Kincaid Reading Ease Score (and Flesch-Kincaid Grade Level) was 48.3 (10.3) for the fact class, 42.0 (10.9) for the policy class, and 38.4 (11.6) for the value class.

Conclusion

The quality of information provided by the open AI chat system was generally high across all question types but had significant shortcomings in reliability due to the absence of source material citations. The DISCERN scores of the AI generated responses matched or exceeded previously published results of studies evaluating the quality of online information about rotator cuff repairs. The responses were U.S. 10th grade or higher reading level which is above the AMA and NIH recommendation of 6th grade reading level for patient materials. The AI software commonly referred the user to seek advice from orthopedic surgeons to improve their chances of a successful outcome.

High-order orbital angular momentum mode-based phase shift-keying communication using phase difference modulation

Orbital angular momentum (OAM) mode offers a promising modulation dimension for high-order shift-keying (SK) communication due to its mode orthogonality. However, the expansion of modulation order through superposing OAM modes is constrained by the mode-field mismatch resulting from the rapidly increased divergence with mode orders. Herein, we address this problem by propose a phase-difference modulation strategy that breaks the limitation of modulation orders via introducing a phase-difference degree of freedom (DoF) beyond OAM modes. Phase-difference modulation exploits the sensitivity of mode interference to phase differences, thereby providing distinct tunable parameters. This enables the generation of a series of codable spatial modes with continuous variation within the same superposed OAM modes by manipulating the interference state. Due to the inherent independence between OAM mode and phase-difference DoF, the number of codable modes increases exponentially, which facilitates establishing ultra-high-order phase shift-keying by discretizing the continuous phase difference and establishing a one-to-one mapping between coding symbols and constructed modes. We show that a phase shift-keying communication link with a modulation order of up to 4 × 104 is achieved by employing only 3 OAM modes (+1, + 2 and +3), and the decode accuracy reaches 99.9%. Since the modulation order is exponentially correlated with the OAM modes and phase differences, the order can be greatly improved by further increasing the superimposed OAM modes, which may provide new insight for high-order OAM-based SK communication.

Dichotomy value iteration with parallel learning design towards discrete-time zero-sum games

In this paper, a novel parallel learning framework is developed to solve zero-sum games for discrete-time nonlinear systems. Briefly, the purpose of this study is to determine a tentative function according to the prior knowledge of the value iteration (VI) algorithm. The learning process of the parallel controllers can be guided by the tentative function. That is to say, the neighborhood of the optimal cost function can be compressed within a small range via two typical exploration policies. Based on the parallel learning framework, a novel dichotomy VI algorithm is established to accelerate the learning speed. It is shown that the parallel controllers will converge to the optimal policy from contrary initial policies. Finally, two typical systems are used to demonstrate the learning performance of the constructed dichotomy VI algorithm.

Data-driven decision-making for precision diagnosis of digestive diseases

Modern omics technologies can generate massive amounts of biomedical data, providing unprecedented opportunities for individualized precision medicine. However, traditional statistical methods cannot effectively process and utilize such big data. To meet this new challenge, machine learning algorithms have been developed and applied rapidly in recent years, which are capable of reducing dimensionality, extracting features, organizing data and forming automatable data-driven clinical decision systems. Data-driven clinical decision-making have promising applications in precision medicine and has been studied in digestive diseases, including early diagnosis and screening, molecular typing, staging and stratification of digestive malignancies, as well as precise diagnosis of Crohn's disease, auxiliary diagnosis of imaging and endoscopy, differential diagnosis of cystic lesions, etiology discrimination of acute abdominal pain, stratification of upper gastrointestinal bleeding (UGIB), and real-time diagnosis of esophageal motility function, showing good application prospects. Herein, we reviewed the recent progress of data-driven clinical decision making in precision diagnosis of digestive diseases and discussed the limitations of data-driven decision making after a brief introduction of methods for data-driven decision making.

Value iteration for streaming data on a continuous space with gradient method in an RKHS

The classical theory of reinforcement learning focused on the tabular setting when states and actions are finite, or for linear representation of the value function in a finite-dimensional approximation. Establishing theory on general continuous state and action space requires a careful treatment of complexity theory of appropriately chosen function spaces and the iterative update of the value function when stochastic gradient descent (SGD) is used. For the classical prediction problem in reinforcement learning based on i.i.d. streaming data in the framework of reproducing kernel Hilbert spaces, we establish polynomial sample complexity taking into account the smoothness of the value function. In particular, we prove that the gradient descent algorithm efficiently computes the value function with appropriately chosen step sizes, with a convergence rate that can be close to 1/N, which is the best possible rate for parametric SGD. The advantages of using the gradient descent algorithm include its computational convenience and it can naturally deal with streaming data.

A Goal-Directed Trajectory Planning Using Active Inference in UAV-Assisted Wireless Networks

Deploying unmanned aerial vehicles (UAVs) as aerial base stations is an exceptional approach to reinforce terrestrial infrastructure owing to their remarkable flexibility and superior agility. However, it is essential to design their flight trajectory effectively to make the most of UAV-assisted wireless communications. This paper presents a novel method for improving wireless connectivity between UAVs and terrestrial users through effective path planning. This is achieved by developing a goal-directed trajectory planning method using active inference. First, we create a global dictionary using traveling salesman problem with profits (TSPWP) instances executed on various training examples. This dictionary represents the world model and contains letters representing available hotspots, tokens representing local paths, and words depicting complete trajectories and hotspot order. By using this world model, the UAV can understand the TSPWP's decision-making grammar and how to use the available letters to form tokens and words at various levels of abstraction and time scales. With this knowledge, the UAV can assess encountered situations and deduce optimal routes based on the belief encoded in the world model. Our proposed method outperforms traditional Q-learning by providing fast, stable, and reliable solutions with good generalization ability.

Spatial-temporal recurrent reinforcement learning for autonomous ships

This paper proposes a spatial-temporal recurrent neural network architecture for deep Q-networks that can be used to steer an autonomous ship. The network design makes it possible to handle an arbitrary number of surrounding target ships while offering robustness to partial observability. Furthermore, a state-of-the-art collision risk metric is proposed to enable an easier assessment of different situations by the agent. The COLREG rules of maritime traffic are explicitly considered in the design of the reward function. The final policy is validated on a custom set of newly created single-ship encounters called 'Around the Clock' problems and the commonly used Imazu (1987) problems, which include 18 multi-ship scenarios. Performance comparisons with artificial potential field and velocity obstacle methods demonstrate the potential of the proposed approach for maritime path planning. Furthermore, the new architecture exhibits robustness when it is deployed in multi-agent scenarios and it is compatible with other deep reinforcement learning algorithms, including actor-critic frameworks.

Improved Artificial Potential Field Algorithm Assisted by Multisource Data for AUV Path Planning

With the development of ocean exploration technology, the exploration of the ocean has become a hot research field involving the use of autonomous underwater vehicles (AUVs). In complex underwater environments, the fast, safe, and smooth arrival of target points is key for AUVs to conduct underwater exploration missions. Most path-planning algorithms combine deep reinforcement learning (DRL) and path-planning algorithms to achieve obstacle avoidance and path shortening. In this paper, we propose a method to improve the local minimum in the artificial potential field (APF) to make AUVs out of the local minimum by constructing a traction force. The improved artificial potential field (IAPF) method is combined with DRL for path planning while optimizing the reward function in the DRL algorithm and using the generated path to optimize the future path. By comparing our results with the experimental data of various algorithms, we found that the proposed method has positive effects and advantages in path planning. It is an efficient and safe path-planning method with obvious potential in underwater navigation devices.

Machine Learning and the Digital Measurement of Psychological Health

Since its inception, the discipline of psychology has utilized empirical epistemology and mathematical methodologies to infer psychological functioning from direct observation. As new challenges and technological opportunities emerge, scientists are once again challenged to define measurement paradigms for psychological health and illness that solve novel problems and capitalize on new technological opportunities. In this review, we discuss the theoretical foundations of and scientific advances in remote sensor technology and machine learning models as they are applied to quantify psychological functioning, draw clinical inferences, and chart new directions in treatment.

Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla

Background and goal

Noninvasive prediction of isocitrate dehydrogenase (IDH) mutation status in glioma guides surgical strategies and individualized management. We explored the capability on preoperatively identifying IDH status of combining a convolutional neural network (CNN) and a novel imaging modality, ultra-high field 7.0 Tesla (T) chemical exchange saturation transfer (CEST) imaging.

Method

We enrolled 84 glioma patients of different tumor grades in this retrospective study. Amide proton transfer CEST and structural Magnetic Resonance (MR) imaging at 7T were performed preoperatively, and the tumor regions are manually segmented, leading to the "annotation" maps that offers the location and shape information of the tumors. The tumor region slices in CEST and T1 images were further cropped out as samples and combined with the annotation maps, which were inputted to a 2D CNN model for generating IDH predictions. Further comparison analysis to radiomics-based prediction methods was performed to demonstrate the crucial role of CNN for predicting IDH based on CEST and T1 images.

Results

A fivefold cross-validation was performed on the 84 patients and 4090 slices. We observed a model based on only CEST achieved accuracy of 74.01% ± 1.15%, and the area under the curve (AUC) of 0.8022 ± 0.0147. When using T1 image only, the prediction performances dropped to accuracy of 72.52% ± 1.12% and AUC of 0.7904 ± 0.0214, which indicates no superiority of CEST over T1. However, when we combined CEST and T1 together with the annotation maps, the performances of the CNN model were further boosted to accuracy of 82.94% ± 1.23% and AUC of 0.8868 ± 0.0055, suggesting the importance of a joint analysis of CEST and T1. Finally, using the same inputs, the CNN-based predictions achieved significantly improved performances above those from radiomics-based predictions (logistic regression and support vector machine) by 10% to 20% in all metrics.

Conclusion

7T CEST and structural MRI jointly offer improved sensitivity and specificity of preoperative non-invasive imaging for the diagnosis of IDH mutation status. As the first study of CNN model on imaging acquired at ultra-high field MR, our results could demonstrate the potential of combining ultra-high-field CEST and CNN for facilitating decision-making in clinical practice. However, due to the limited cases and B1 inhomogeneities, the accuracy of this model will be improved in our further study.

PeakDecoder enables machine learning-based metabolite annotation and accurate profiling in multidimensional mass spectrometry measurements

Multidimensional measurements using state-of-the-art separations and mass spectrometry provide advantages in untargeted metabolomics analyses for studying biological and environmental bio-chemical processes. However, the lack of rapid analytical methods and robust algorithms for these heterogeneous data has limited its application. Here, we develop and evaluate a sensitive and high-throughput analytical and computational workflow to enable accurate metabolite profiling. Our workflow combines liquid chromatography, ion mobility spectrometry and data-independent acquisition mass spectrometry with PeakDecoder, a machine learning-based algorithm that learns to distinguish true co-elution and co-mobility from raw data and calculates metabolite identification error rates. We apply PeakDecoder for metabolite profiling of various engineered strains of Aspergillus pseudoterreus, Aspergillus niger, Pseudomonas putida and Rhodosporidium toruloides. Results, validated manually and against selected reaction monitoring and gas-chromatography platforms, show that 2683 features could be confidently annotated and quantified across 116 microbial sample runs using a library built from 64 standards.

Artificial intelligence applied in pulmonary hypertension: a bibliometric analysis

Introduction

Advances in Artificial Intelligence (AI) offer new Information Technology (IT) opportunities in various applications and fields (industry, health, etc.). The medical informatics scientific community expends tremendous effort on the management of diseases affecting vital organs making it a complex disease (lungs, heart, brain, kidneys, pancreas, and liver). Scientific research becomes more complex when several organs are simultaneously affected, as is the case with Pulmonary Hypertension (PH), which affects both the lungs and the heart. Therefore, early detection and diagnosis of PH are essential to monitor the disease's progression and prevent associated mortality.

Method

The issue addressed relates to knowledge of recent developments in AI approaches applied to PH. The aim is to provide a systematic review through a quantitative analysis of the scientific production concerning PH and the analysis of the networks of this production. This bibliometric approach is based on various statistical, data mining, and data visualization methods to assess research performance using scientific publications and various indicators (e.g., direct indicators of scientific production and scientific impact).

Results

The main sources used to obtain citation data are the Web of Science Core Collection and Google Scholar. The results indicate a diversity of journals (e.g., IEEE Access, Computers in Biology and Medicine, Biology Signal Processing and Control, Frontiers in Cardiovascular Medicine, Sensors) at the top of publications. The most relevant affiliations are universities from United States of America (Boston Univ, Harvard Med Sch, Univ Oxford, Stanford Univ) and United Kingdom (Imperial Coll London). The most cited keywords are "Classification", "Diagnosis", "Disease", "Prediction", and "Risk".

Conclusion

This bibliometric study is a crucial part of the review of the scientific literature on PH. It can be viewed as a guideline or tool that helps researchers and practitioners to understand the main scientific issues and challenges of AI modeling applied to PH. On the one hand, it makes it possible to increase the visibility of the progress made or the limits observed. Consequently, it promotes their wide dissemination. Furthermore, it offers valuable assistance in understanding the evolution of scientific AI activities applied to managing the diagnosis, treatment, and prognosis of PH. Finally, ethical considerations are described in each activity of data collection, treatment, and exploitation to preserve patients' legitimate rights.