Alramzana Nujum Navaz

The exponential growth of biomedical literature necessitates advanced methods for Literature-Based Discovery (LBD) to uncover hidden, meaningful relationships and generate novel hypotheses. This research integrates Large Language Models (LLMs), particularly transformer-based models, to enhance LBD processes. Leveraging LLMs’ capabilities in natural language understanding, information extraction, and hypothesis generation, we propose a framework that improves the scalability and precision of traditional LBD methods. Our approach integrates LLMs with semantic enhancement tools, continuous learning, domain-specific fine-tuning, and robust data cleansing processes, enabling automated analysis of vast text and identification of subtle patterns. Empirical validations, including scenarios on the effects of garlic on blood pressure and nutritional supplements on health outcomes, demonstrate the effectiveness of our LLM-based LBD framework in generating testable hypotheses. This research advances LBD methodologies, fosters interdisciplinary research, and accelerates discovery in the biomedical domain. Additionally, we discuss the potential of LLMs in drug discovery, highlighting their ability to extract and present key information from the literature. Detailed comparisons with traditional methods, including Swanson’s ABC model, highlight our approach’s advantages. This comprehensive approach opens new avenues for knowledge discovery and has the potential to revolutionize research practices. Future work will refine LLM techniques, explore Retrieval-Augmented Generation (RAG), and expand the framework to other domains, with a focus on dehallucination.

The widespread adoption of edge computing for resource-constrained devices presents challenges in computational straggler issues, primarily due to the heterogeneity of edge node resources. This research addresses these issues by introducing a novel resource-aware federated hybrid profiling approach. This approach involves classifying edge node resources with relevant performance metrics and leveraging their capabilities to optimize performance and improve Quality of Service (QoS), particularly in real-time eHealth applications. Such paradigms include Federated Patient Similarity Network (FPSN) models that distribute processing at each edge node and fuse the built PSN matrices in the cloud, presenting a unique challenge in terms of optimizing training and inference times, while ensuring efficient and timely updates at the edge nodes. To address this concern, we propose a resource-aware federated hybrid profiling approach that measures the available static and dynamic resources of the edge nodes. By selecting nodes with the appropriate resources, we aim to optimize the FPSN to ensure the highest possible Quality of Service (QoS) for its users. We conducted experiments using edge performance metrics, i.e., accuracy, training convergence, memory and disk usage, execution time, and network statistics. These experiments uniquely demonstrate our work’s contribution to optimizing resource allocation and enhancing the performance of eHealth applications in real-time contexts using edge computing.

Continuous monitoring of patients involves collecting and analyzing sensory data from a multitude of sources. To overcome communication overhead, ensure data privacy and security, reduce data loss, and maintain efficient resource usage, the processing and analytics are moved close to where the data are located (e.g., the edge). However, data quality (DQ) can be degraded because of imprecise or malfunctioning sensors, dynamic changes in the environment, transmission failures, or delays. Therefore, it is crucial to keep an eye on data quality and spot problems as quickly as possible, so that they do not mislead clinical judgments and lead to the wrong course of action. In this article, a novel approach called federated data quality profiling (FDQP) is proposed to assess the quality of the data at the edge. FDQP is inspired by federated learning (FL) and serves as a condensed document or a guide for node data quality assurance. The FDQP formal model is developed to capture the quality dimensions specified in the data quality profile (DQP). The proposed approach uses federated feature selection to improve classifier precision and rank features based on criteria such as feature value, outlier percentage, and missing data percentage. Extensive experimentation using a fetal dataset split into different edge nodes and a set of scenarios were carefully chosen to evaluate the proposed FDQP model. The results of the experiments demonstrated that the proposed FDQP approach positively improved the DQ, and thus, impacted the accuracy of the federated patient similarity network (FPSN)-based machine learning models. The proposed data-quality-aware federated PSN architecture leveraging FDQP model with data collected from edge nodes can effectively improve the data quality and accuracy of the federated patient similarity network (FPSN)-based machine learning models. Our profiling algorithm used lightweight profile exchange instead of full data processing at the edge, which resulted in optimal data quality achievement, thus improving efficiency. Overall, FDQP is an effective method for assessing data quality in the edge computing environment, and we believe that the proposed approach can be applied to other scenarios beyond patient monitoring.

Public wellbeing has always been crucial. Many governments around the globe prioritize the impact of their decisions on public wellbeing. In this paper, we propose an end-to-end public wellbeing analytics framework designed to predict the public’s wellbeing status and infer insights through the continuous analysis of social media content over several temporal events and across several locations. The proposed framework implements a novel distant supervision approach designed specifically to generate wellbeing-labeled datasets. In addition, it implements a wellbeing prediction model trained on contextualized sentence embeddings using BERT. Wellbeing predictions are visualized using several spatiotemporal analytics that can support decision-makers in gauging the impact of several government decisions and temporal events on the public, aiding in improving the decision-making process. Empirical experiments evaluate the effectiveness of the proposed distant supervision approach, the prediction model, and the utility of the produced analytics in gauging the public wellbeing status in a specific context.

Continuous monitoring of patients involves collecting and analyzing sensory data from a multitude of sources. To overcome communication overhead, ensure data privacy and security, reduce data loss, and maintain efficient resource usage the processing and analytics are moved close to where the data is located (e.g., the Edge). Data quality (DQ) can be degraded because of imprecise or malfunctioning sensors, dynamic changes in the environment, transmission failures, or delays. Therefore, can mislead clinical judgments and cause incorrect actions, if not managed properly. In this paper, inspired by Federated Learning (FL), we propose a novel approach using Federated Data Quality (FDQ) Profiling to assess DQ at the edge considering a global quality profile aggregated based on local profiles. We conducted experiments to evaluate the effect of FDQ profiling on DQ improvement considering the assessment of outlier detection and unbalanced data. The results demonstrated that the improved DQ has a positive impact on the accuracy of four conventional machine learning models.

Precision medicine can be defined as the comparison of a new patient with existing patients that have similar characteristics and can be referred to as patient similarity. Several deep learning models have been used to build and apply patient similarity networks (PSNs). However, the challenges related to data heterogeneity and dimensionality make it difficult to use a single model to reduce data dimensionality and capture the features of diverse data types. In this paper, we propose a multi-model PSN that considers heterogeneous static and dynamic data. The combination of deep learning models and PSN allows ample clinical evidence and information extraction against which similar patients can be compared. We use the bidirectional encoder representations from transformers (BERT) to analyze the contextual data and generate word embedding, where semantic features are captured using a convolutional neural network (CNN). Dynamic data are analyzed using a long-short-term-memory (LSTM)-based autoencoder, which reduces data dimensionality and preserves the temporal features of the data. We propose a data fusion approach combining temporal and clinical narrative data to estimate patient similarity. The experiments we conducted proved that our model provides a higher classification accuracy in determining various patient health outcomes when compared with other traditional classification algorithms.

Sensitive patient data is generated from a variety of sources and then transferred to a cloud for processing. Therefore, it is exposed to security and privacy and may lead to an increase in communication costs. Edge computing will ease computing pressure through distributed computational capabilities while improving security and privacy. In this paper, we propose a Federated PSN (FPSN) model where the model is moved directly to the edge to minimize computation and communication costs. PSN has been applied as a successful approach in categorizing and diagnosing patients based on similarities against some clinical and non-clinical features. Our proposed model distributes processing at each edge node, then fuses the constructed PSN matrices at the cloud premises, which significantly reduce the model’s training and inference time and ensures quick model updates with the local client/nodes. In this paper, we propose: (i) an algorithm to evaluate patient’s data similarity at the edge; and (ii) an algorithm to implement the federated similarity network fusion at the Cloud. We conducted a set of experiments to evaluate our FPSN model against other machine learning algorithms using a COVID-19 dataset. The results obtained prove that the FPSN model accuracy is higher than the distributed PSNs at various edges and higher than the accuracies of other classification models.

Cardio Vascular Diseases (CVD) is the leading cause of death globally and is increasing at an alarming rate, according to the American Heart Association’s Heart Attack and Stroke Statistics-2021. This increase has been further exacerbated because of the current coronavirus (COVID-19) pandemic, thereby increasing the pressure on existing healthcare resources. Smart and Connected Health (SCH) is a viable solution for the prevalent healthcare challenges. It can reshape the course of healthcare to be more strategic, preventive, and custom-designed, making it more effective with value-added services. This research endeavors to classify state-of-the-art SCH technologies via a thorough literature review and analysis to comprehensively define SCH features and identify the enabling technology-related challenges in SCH adoption. We also propose an architectural model that captures the technological aspect of the SCH solution, its environment, and its primary involved stakeholders. It serves as a reference model for SCH acceptance and implementation. We reflected the COVID-19 case study illustrating how some countries have tackled the pandemic differently in terms of leveraging the power of different SCH technologies, such as big data, cloud computing, Internet of Things, artificial intelligence, robotics, blockchain, and mobile applications. In combating the pandemic, SCH has been used efficiently at different stages such as disease diagnosis, virus detection, individual monitoring, tracking, controlling, and resource allocation. Furthermore, this review highlights the challenges to SCH acceptance, as well as the potential research directions for better patient-centric healthcare.

Cardiovascular diseases (CVD) are the principal cause of death globally. Electrocardiography (ECG) is a widely adopted tool to quantify heart activities to detect any heart abnormalities. Arrhythmia is one of these CVDs that heavily relies on continuous ECG recordings in order to detect and predict irregularities in the heart rhythms. Various Deep Learning (DL) approaches has been heavily used to classify and predict different heart rhythms. However, most of the proposed works do not consider the various hyperparameter optimization and tuning to get the full potential of the DL model and achieve higher accuracy. Besides, very few works implemented the full monitoring cycle and close the loop to propose some clinical and non-clinical recommendations. Therefore, in this paper, we adopt the Convolutional Neural Network (CNN) model and we apply various parameter optimization to capture various properties of the data, the training, and the model. We also close the monitoring loop and suggest tailored recommendations for each category of arrhythmia that go beyond simple to more deeper diagnosis using the Global Registry of Acute Coronary Events (GRACE), and the European Guidelines on CVDs prevention in clinical practice (ESC/EAS 2016). We conducted a set of experiments to evaluate our model and the set of hyperparameter optimization we have experienced and the results we have obtained showed significant improvement in the prediction accuracy after a couple of optimization iterations.