Large Language Models (LLMs) are increasingly central to Alzheimer’s disease (AD) research, particularly for classifying speech-based transcripts. However, a significant factor affecting LLM performance is the choice of a prompting strategy. Despite the known sensitivity of these models, AD research currently lacks a formal framework for assessing prompt quality or stability. Using the ADReSS Challenge dataset, this study evaluates whether prompts used for AD speech-based classification are sensitive to minor linguistic variations and tests whether a prompt optimization framework can reduce this sensitivity. Our results demonstrate that various models are highly sensitive to small changes in prompts. Notably, optimization led to a significant 16.63

The MERS-CoV (Middle East respiratory syndrome coronavirus) is a zoonotic virus with a high mortality rate and a lack of antiviral drugs, underscoring the need for effective therapeutic methods. Viral entry depends on interactions between viral surface proteins and human receptors, with Dipeptidyl Peptidase-4 (DPP4), a transmembrane glycoprotein, acting as the receptor for MERS-CoV. We employed Molecular Dynamics (MD) Simulations to identify critical interface residues under a high-performance computing (HPC) workflow for accelerated results. Target residue pairs were identified through analysis of salt bridge and hydrogen bond occupancy. The stability of these residues was confirmed through three independent MD Simulations at human body temperature and constant pressure. Additionally, binding affinity predictions were calculated to determine the interaction strength between the virus and human receptors. Applying the scientific threshold criteria, we narrowed our results to seven key interaction pairs; two of the identified pairs (Asp510-Arg317, and Arg511-Asp393) are consistent with findings published in previous research studies, and five novel interactions are proposed for future experimental studies with our active collaborators in Pharmacology. The results provide a molecular basis for targeted mutation-based experiments and support the rational design of structure-based inhibitors aimed at disrupting the MERS-CoV-DPP4 complex, thereby facilitating the translation of computational findings into antiviral drug discovery.

Alzheimer's disease and related dementias (ADRD) are neurodegenerative conditions characterized by progressive cognitive and functional decline. AD pathology is associated with extracellular amyloid-β plaques, intracellular tau neurofibrillary tangles, synaptic dysfunction, and neuronal loss. AD accounts for approximately 60-80% of dementia cases globally. In 2022, AD was the seventh leading cause of death in the United States, and the number of Americans aged 65 and older living with Alzheimer's dementia is projected to increase substantially by 2060. Despite decades of research, AD/ADRD data resources remain fragmented across clinical, imaging, genetic, genomic, and therapeutic domains. This paper addresses that gap by providing a centralized review of widely used AD/ADRD databases and computational methods. We first summarize computational approaches used to analyze these datasets, including machine learning (ML), natural language processing (NLP), and biomedical imaging. We then review eight databases classified into three categories: Clinical and Population Data, Genetics and Genomics, and Drug Discovery and Therapeutics. Finally, we discuss real-world applications, including early diagnosis, clinical decision support, personalized medicine, and drug-mechanism analysis. This review identifies opportunities for future work in data harmonization, cross-database compatibility, and robust, generalizable AI models for AD/ADRD research.

In recent years, novel technologies in smart healthcare systems have opened significant opportunities for diagnosis and treatment across various medical fields. Federated Learning (FL), a decentralized machine learning approach, trains shared models using local data from devices like wearables and hospital systems without transferring sensitive information, offering a promising solution to privacy challenges in areas such as cancer prediction, COVID-19 detection, drug discovery, and medical image processing. This literature survey reviews FL architectures (e.g., FedHealth, PerFit), applications, and recent advancements, demonstrating their impact on healthcare through enhanced predictive models for patient care. Key findings include improved accuracy in wearable-based diagnostics and secure multi-institutional collaboration, though limitations persist. We also highlight open challenges, such as security risks, communication costs, and data heterogeneity, which require further research attention.

Alzheimer’s disease represents a growing global health concern, emphasizing the need for early diagnosis to mitigate neurocognitive decline. Speech analysis has emerged as a promising, non-invasive approach, yet limited data availability hinders the development of robust Machine Learning (ML) models. To address this challenge, this study exploits the potentialities of Large Language Models (LLMs)—both their ability to generate synthetic data and their capacity to extract complex linguistic features from speech. We employ GPT-4 to generate synthetic transcripts, thus expanding the ADReSS2020 dataset and enhancing its diversity while preserving semantic and structural coherence. Moreover, we propose a novel multilevel feature extraction framework that integrates Bidirectional Encoder Representations from Transformers (BERT) embeddings fine-tuned with linguistic features obtained through Computerized Language Analysis (CLAN). The study involved two experiments: first, to identify the optimal feature extraction strategy and second, to evaluate the impact of synthetic data generated by GPT-4. In both experiments, the performance of five classifiers was evaluated to determine the most effective configuration. Our results demonstrated that fine-tuned BERT embeddings slightly improve classification performance compared to pre-trained models, highlighting the value of domain-specific fine-tuning. Although adding CLAN-like linguistic features yielded limited benefits, GPT-4-generated synthetic data demonstrated promising potential, particularly when combined with sentence embeddings. Classifiers such as Random Forest showed an improvement in accuracy, increasing from 0.79 to 0.88 when using the augmented dataset. This study paves the way for the use of LLMs to expand the diversity of datasets and improve the robustness of ML models in clinical applications.

In recent years, Internet of Healthcare Things (IoHT) devices have attracted significant attention from computer scientists, healthcare professionals, and patients. These devices enable patients, especially in areas without access to hospitals, to easily record and transmit their health data to medical staff via the Internet. However, the analysis of sensitive health information necessitates a secure environment to safeguard patient privacy. Given the sensitivity of healthcare data, ensuring security and privacy is crucial in this sector. Federated learning (FL) provides a solution by enabling collaborative model training without sharing sensitive health data with third parties. Despite FL addressing some privacy concerns, the privacy of IoHT data remains an area needing further development. In this paper, we propose a privacy-preserving federated learning framework to enhance the privacy of IoHT data. Our approach integrates federated learning with ϵ-differential privacy to design an effective and secure intrusion detection system (IDS) for identifying cyberattacks on the network traffic of IoHT devices. In our FL-based framework, SECIoHT-FL, we employ deep neural network (DNN) including convolutional neural network (CNN) models. We assess the performance of the SECIoHT-FL framework using metrics such as accuracy, precision, recall, F1-score, and privacy budget (ϵ). The results confirm the efficacy and efficiency of the framework. For instance, the proposed CNN model within SECIoHT-FL achieved an accuracy of 95.48% and a privacy budget (ϵ) of 0.34 when detecting attacks on one of the datasets used in the experiments. To facilitate the understanding of the models and the reproduction of the experiments, we provide the explainability of the results by using SHAP and share the source code of the framework publicly as free and open-source software.

Alzheimer’s disease (AD) represents a major public health challenge due to its irreversible progression and increasing prevalence among the aging population. Early diagnosis is crucial, and recent advances in Artificial Intelligence and data analytics have shown promising results in detection methods. This study proposes an approach based on deep neural networks for automatic AD detection from the speech data of the ADReSS2020 dataset, using log-Mel spectrogram representation. To address data limitations and enhance model performance, we applied five data augmentation techniques, which significantly improved accuracy by introducing greater variability in audio characteristics. We evaluated the performance of three models: a CNN-LSTM network and two transfer learning approaches based on ResNet50 and VGG16. Experimental results showed that the CNN-LSTM model performs best, achieving an accuracy of 68%, with a significant improvement of 9.67% over the baseline. ResNet50-LSTM and VGG16-LSTM followed with $\mathbf{6 7} \%$ and $\mathbf{6 6} \%$ accuracy, respectively. This work demonstrates the potential of deep learning-based speech-driven approaches as scalable and noninvasive tools for Alzheimer’s diagnosis and highlights the importance of data enhancement to improve model performance.

Machine learning has brought about a revolutionary transformation in healthcare. It has traditionally been employed to create predictive models through training on locally available data. However, privacy concerns can sometimes impede the collection and integration of data from diverse sources. Conversely, a lack of sufficient data may hinder the construction of accurate models, thereby limiting the ability to produce meaningful outcomes. Especially in the field of healthcare, collecting datasets centrally is challenging due to privacy concerns. Indeed, federated learning (FL) emerges as a sophisticated distributed machine learning approach that comes to the rescue in such scenarios. It allows multiple devices hosted at different institutions, like hospitals, to collaboratively train a global model without sharing raw data. In addition, each device retains its data securely on locally, addressing the challenges of time-consuming annotation and privacy concerns. In this paper, we conducted a comprehensive literature review aimed at identifying the most advanced federated learning applications in cancer research and clinical oncology analysis. Our main goal was to present a comprehensive overview of the development of federated learning in the field of oncology. Additionally, we discuss the challenges and future research directions.

Protein structure prediction is important for understanding their function and behavior. This review study presents a comprehensive review of the computational models used in predicting protein structure. It covers the progression from established protein modeling to state-of-the-art artificial intelligence (AI) frameworks. The paper will start with a brief introduction to protein structures, protein modeling, and AI. The section on established protein modeling will discuss homology modeling, ab initio modeling, and threading. The next section is deep learning-based models. It introduces some state-of-the-art AI models, such as AlphaFold (AlphaFold, AlphaFold2, AlphaFold3), RoseTTAFold, ProteinBERT, etc. This section also discusses how AI techniques have been integrated into established frameworks like Swiss-Model, Rosetta, and I-TASSER. The model performance is compared using the rankings of CASP14 (Critical Assessment of Structure Prediction) and CASP15. CASP16 is ongoing, and its results are not included in this review. Continuous Automated Model EvaluatiOn (CAMEO) complements the biennial CASP experiment. Template modeling score (TM-score), global distance test total score (GDT_TS), and Local Distance Difference Test (lDDT) score are discussed too. This paper then acknowledges the ongoing difficulties in predicting protein structure and emphasizes the necessity of additional searches like dynamic protein behavior, conformational changes, and protein–protein interactions. In the application section, this paper introduces some applications in various fields like drug design, industry, education, and novel protein development. In summary, this paper provides a comprehensive overview of the latest advancements in established protein modeling and deep learning-based models for protein structure predictions. It emphasizes the significant advancements achieved by AI and identifies potential areas for further investigation.

DNA damage is a critical factor contributing to genetic alterations, directly affecting human health, including developing diseases such as cancer and age-related disorders. DNA repair mechanisms play a pivotal role in safeguarding genetic integrity and preventing the onset of these ailments. Over the past decade, substantial progress and pivotal discoveries have been achieved in DNA damage and repair. This comprehensive review paper consolidates research efforts, focusing on DNA repair mechanisms, computational research methods, and associated databases. Our work is a valuable resource for scientists and researchers engaged in computational DNA research, offering the latest insights into DNA-related proteins, diseases, and cutting-edge methodologies. The review addresses key questions, including the major types of DNA damage, common DNA repair mechanisms, the availability of reliable databases for DNA damage and associated diseases, and the predominant computational research methods for enzymes involved in DNA damage and repair.

Stress is considered one of the most prevalent concerns among individuals. Studies have shown that experiencing long-term stress can cause severe health issues such as cardiovascular diseases, hypertension, depression, etc. Preventative measures, such as early stress detection, can help individuals mitigate these health issues. When a person gets stressed, physiological values like blood volume pulse, temperature, and electrodermal activity signals get affected. Machine Learning techniques can be utilized to identify stress by analyzing these physiological signals. This paper presents a machine learning method for detecting stress levels of an individual using the publicly available dataset called "Wearable Stress and Affect Detection"(WESAD), which has physiological data collected from the wrist-worn and chest-worn sensors attached to 15 different subjects. We used physiological signals, including Blood Volume Pulse(BVP), Body Temperature(TEMP), and Electrodermal Activity(EDA) signals, collected from wrist-worn sensors to detect the state of the mind. For the implementation, we used different Machine Learning models, like Logistic Regression, Decision Tree, Random Forest, and Stacking Ensemble Learning technique. During the investigation, personalized models, utilizing individual subject data, and generalized models, amalgamating all subject data, were developed. Evaluation reveals accuracy values reaching up to 99% and 91% for individual subject data and combined data, respectively.

The educational landscape is evolving with the integration of AI, large language models (LLMs), and generative AI, requiring educators to adopt state-of-the-art technologies and strategies in their pedagogical practices. Pedagogical Design Patterns (PDPs) have garnered attention for disseminating best practices and bridging the gap between research and practice. However, their widespread adoption is hindered by limited publicly available resources and fragmented publishing platforms. To address this, we propose leveraging LLMs to recommend pedagogical practices, drawing from existing PDPs. Our model utilizes a local knowledge base and the Retrieval Augmented Generation (RAG) framework to create query contexts for LLM prompts. Initial findings show promise, with an accuracy score of 0.83 and high relevance of recommendations to input queries. This study presents early results of our ongoing project, supporting further development of the model. The proposed system aims to empower novice educators by providing expert wisdom to enrich their teaching methodologies.

With the Industrial Internet of Things (IIoT) continuing to expand, lots of data collection, exchange, and authentication generated from an increasing number of access devices is required with heterogeneity, multidimension, and multiobjective networks as its characteristics. However, traditional IIoT systems are vulnerable to security challenges, such as data leakage, theft, and tampering. As one of the most promising solutions, blockchain has played an essential role in ensuring security and transparency in the IIoT. But there are still some challenges that prevent the secure and effective implementation of blockchain-based IIoT systems in consensus security, consensus efficiency, and consensus application. To address these problems, we propose an effective security blockchain consensus algorithm for heterogeneous IIoT nodes aiming to defend against the consensus attack and improve consensus efficiency. First, we design a blockchain-based IIoT system architecture. Then, we present an identity authentication and transformation protocol to defend against consensus attacks. Furthermore, we introduce a method for constructing communication directed acyclic graphs (DAGs) and transaction set DAGs to enhance transaction throughput. Based on these two DAGs, we propose an efficient and security consensus algorithm (DAG-D). DAG-D employs transaction sets instead of single transactions or blocks, leveraging communication DAG propagation to swiftly confirm transaction set DAGs based on parent transactions for associated confirmation. Experimental results show that our proposed DAG-D outperforms DAG-M, DAG-Avalanche, and DAG-CoDAG, regarding transaction throughput, transaction latency, and communication overhead.

This letter presents a novel communication-efficient and decentralized approach for data analytics in connected vehicles. We extend the paradigm of federated learning (FL) to enable decentralized on-vehicle model training without a central server. To improve communication efficiency, we design a federated regularized nonlinear acceleration-based local training scheme to reduce the communication rounds and a random broadcast gossip-based mechanism to decrease the complexity per iteration. Experimental results demonstrate that our approach significantly reduces the communication cost compared to general gradient descent and momentum-based FL solutions and is promising for efficient data analytics in autonomous vehicle environments.

Breast cancer is the most common type of cancer in women, and early abnormality detection using mammography can significantly improve breast cancer survival rates. Diverse datasets are required to improve the training and validation of deep learning (DL) systems for autonomous breast cancer diagnosis. However, only a small number of mammography datasets are publicly available. This constraint has created challenges when comparing different DL models using the same dataset. The primary contribution of this study is the comprehensive description of a selection of currently available public mammography datasets. The information available on publicly accessible datasets is summarized and their usability reviewed to enable more effective models to be developed for breast cancer detection and to improve understanding of existing models trained using these datasets. This study aims to bridge the existing knowledge gap by offering researchers and practitioners a valuable resource to develop and assess DL models in breast cancer diagnosis.

Breast cancer is a global health concern for women. The detection of breast cancer in its early stages is crucial, and screening mammography serves as a vital leading-edge tool for achieving this goal. In this study, we explored the effectiveness of Resnet 50v2 and Resnet 152v2 deep learning models for classifying mammograms using EMBED datasets for the first time. We preprocessed the datasets and utilized various techniques to enhance the performance of the models. Our results suggest that the choice of model architecture depends on the dataset used, with ResNet152 outperforming ResNet50 in terms of recall score. These findings have implications for cancer screening, where recall is an important metric. Our research highlights the potential of deep learning to improve breast cancer classification and underscores the importance of selecting the appropriate model architecture.

ChatGPT is a recently developed Large Language Model (LLM) and an effective tool to produce human-like dialogue with users and answering to questions. It is trained on a massive amount of online content and can provide textual answers to questions from several domains, such as healthcare. In this paper, we investigate the application of ChatGPT in the healthcare domain and provide an analysis on its limitations and challenges. While ChatGPT can offer valuable support and information, it is crucial to recognize that it should not be seen as a replacement for the expertise and personalized care provided by healthcare professionals. Instead, its purpose lies in augmenting healthcare services and enhancing access to information. It can be a useful tool for providing general guidelines and educational resources. However, when it comes to medical advice or diagnosis, it is essential to consult qualified healthcare professionals who can consider individual factors, interpret complex medical information, and provide tailored recommendations based on a comprehensive understanding of the patient's situation.

Federated learning (FL) is a collaborative artificial intelligence (AI) approach that enables distributed training of AI models without data sharing, thereby promoting privacy by design. However, it is essential to acknowledge that FL only offers a partial solution to safeguard the confidentiality of AI and machine learning (ML) models. Unfortunately, many studies fail to report the results of privacy measurement when applying FL, mainly due to assumptions that privacy is implicitly achieved as FL is a privacy-by-design approach. This trend can also be attributed to the complexity of understanding privacy measurement metrics and methods. This paper presents a survey of privacy measurement in FL, aimed at evaluating its effectiveness in protecting the privacy of sensitive data during the training of AI and ML models. While FL is a promising approach for preserving privacy during model training, ensuring privacy is genuinely achieved in practice is crucial. By evaluating privacy measurement metrics and methods in FL, we can identify the gaps in existing approaches and propose new techniques to enhance FL’s privacy. A comprehensive study investigating “privacy measurement and metrics” in FL is therefore required to support the field’s growth. Our survey provides a critical analysis of the current state of privacy measurement in FL, identifies gaps in existing research, and offers insights into potential research directions. Moreover, this paper presents a case study that evaluates the effectiveness of various privacy techniques in a specific FL scenario. This case study serves as tangible evidence of the real-world implications of privacy measurements, providing insightful and practical guidelines for researchers and practitioners to optimize privacy preservation while balancing other crucial factors such as communication overhead and accuracy. Finally, our paper outlines a future roadmap for advancing privacy in FL, combining traditional techniques with innovative technologies such as quantum computing and Trusted Execution Environments to fortify data protection.

Heart disease is a leading cause of morbidity and mortality worldwide, necessitating the development of innovative diagnostic methodologies for early detection. This study presents a novel deep convolutional neural network model that leverages Mel-spectrograms to accurately classify heart sounds. Our approach demonstrates significant advancements in heart disease detection, achieving high accuracy, specificity, and unweighted average recall scores (UAR), which are critical factors for practical clinical applications. The comparison of our proposed model's performance with a PANN-based model from a previous study highlights the strengths of our approach, particularly in terms of specificity and UAR. The successful application of Mel-spectrograms in conjunction with deep learning techniques illustrates the potential for widespread clinical adoption of our model, ultimately contributing to early detection and improved patient outcomes. Furthermore, we discuss potential avenues for future research to enhance the model's effectiveness, such as incorporating additional features and exploring alternative deep learning architectures. In conclusion, our deep convolutional neural network model, combined with Mel-spectrograms, offers a significant step forward in the field of heart sound classification and the early detection of heart diseases, demonstrating its potential for real-world clinical applications and improved patient outcomes.