Systems In Healthcare Research Articles

A Comprehensive Survey on Requirements and Design of AI-Powered Clinical Intelligence Systems in Healthcare

With the increasing complexity of healthcare services, artificial intelligence (AI) is emerging as a vital tool to support medical practitioners by providing real-time clinical insights, automating routine documentation, and enhancing patient engagement. This survey investigates the design requirements, technical challenges, and ethical considerations for AI-powered clinical intelligence systems intended for healthcare environments. Our study is based on a survey conducted with healthcare professionals, patients, and AI researchers, capturing diverse perspectives on functionality, usability, data privacy, and ethical concerns. This paper synthesizes these insights into a detailed requirement analysis that can guide the development of clinically effective, ethically sound, and user-centric AI systems. Through this analysis, we aim to lay the groundwork for creating AIdriven tools that improve clinical workflows, foster better patient outcomes, and support healthcare professionals in delivering quality care.

Synergizing Ai and ERP for Predictive Supply Chain Management and Quality Assurance in Healthcare

This article explores the transformative potential of integrating Artificial Intelligence (AI) with Enterprise Resource Planning (ERP) systems in healthcare, focusing on applications in predictive supply chain management and quality assurance. The healthcare industry faces increasing pressure to improve efficiency while maintaining high-quality care, and AI-ERP integration offers a compelling solution. By combining ERP's comprehensive data management capabilities with AI's predictive and analytical power, healthcare organizations can enhance operational efficiency, improve decision-making, and ultimately deliver better patient outcomes. The article examines current implementations, case studies, and future projections to provide a comprehensive overview of how this technological synergy can help healthcare providers navigate the complex challenges of modern healthcare delivery, from optimizing inventory levels to ensuring regulatory compliance and proactive risk management.

1.L. Scientific session: Public Health data in support of healthy ageing policies

Abstract As Europe grapples with an ageing population, the imperative of health policies that promote healthy ageing is increasingly critical. This workshop aims to explore the significant role of public health data in shaping and supporting such policies. By integrating insights from administrative records to sophisticated research infrastructures, we will highlight the multifaceted uses of data in public health, particularly in the realms of non-communicable diseases and health-related behaviours in older populations. The session will open by examining how administrative records have been utilised within Lombardy’s regional health system to understand the epidemiology and access to care for people living with dementia. The discussion will then cover the advantages and challenges associated with integrating health data from diverse sources, emphasising the importance of quality, privacy, and the potential for real-time surveillance and response systems in healthcare. Following this, the focus will shift to the determinants of good health among older adults, presenting findings from a comprehensive cross-sectional study that identifies key factors contributing to what can be termed as “superhero” health status: seniors who maintain excellent physical and mental health. This analysis will delve into socioeconomic, behavioural, and environmental factors that influence health outcomes in the elderly, providing evidence-based recommendations for public health interventions and highlighting the potentialities of ad hoc surveys in examining health outcomes during emergencies. Thirdly, the workshop will also address the impact of significant life transitions on health behaviours, specifically the transition to retirement and its effects on alcohol consumption. Leveraging longitudinal data from a pan-European multidisciplinary research infrastructure, it will be demonstrated how retirement affects daily habits and lifestyles, including changes in alcohol consumption patterns. This segment will explore the implications of these findings for public health planning and policy formulation. In conclusion, there will be a discussion about healthcare system policies that support healthy ageing and the global impact of ageing on economics and health economics. These discussions will draw from the presented data sources and studies to suggest ways in which public health policies can be designed to reduce disparities and improve overall health outcomes among the elderly. This workshop is designed to provide a comprehensive overview of how data-driven insights can inform effective public health strategies and interventions to support an ageing society. By exploring various aspects of health data application, from individual behaviour to systemic policy adjustments, the session aims to highlight the critical role of data in promoting sustainable health and well-being in older adults, especially in the context of increasing life expectancy and prolonged retirement periods. Key messages • Harnessing data from diverse sources is crucial for understanding and enhancing healthy ageing processes. • Utilising longitudinal studies and robust data to design informed public health policies is essential for effective ageing interventions.

Smart Green Cotton Textiles with Hierarchically Responsive Conductive Network for Personal Healthcare and Thermal Management.

Whereas cotton as an abundant natural cellulose has been widely used for sustainable and skin-friendly textiles and clothes, developing cotton fabrics with smart functions that could respond to various stimuli is still eagerly desired while remaining a great challenge. Herein, smart multiresponsive cotton fabric with hierarchically copper nanowire interwoven MXene conductive networks that are seamlessly assembled along a 3D woven fabric template for efficient personal healthcare and thermal comfort regulation is successfully developed. The robust hierarchically interwoven conductive network was "glued" and protected by organic conductive polymer poly(3,4-ethylenedioxythiophene) along a 3D interconnected fabric template to enhance interfacial adherent and environmental stability. Benefiting from the robust multiresponsive hierarchically interwoven conductive network, smart cotton fabric exhibits real-time response to various external stimuli (light/electrical/heat/temperature/stress), and the details of human activities can be accurately recognized and monitored. Furthermore, the porous structure of 3D smart fabric induced strong capillary force and confinement to phase change materials PEG, which exhibits a wide range of phase transition temperatures for efficient thermal comfort regulation. After further encapsulation with transparent fluorosilicone resin, the smart cotton fabric exhibits excellent self-cleaning performance with water/oil repellent. The smart multiresponsive cotton fabrics hold great promise in next-generation wearable systems for efficient personal healthcare and thermal management.

Integration of Neuro-Fuzzy Systems in Medical Diagnostics and Data Security - A Review

Adaptive Neuro-Fuzzy Systems (ANFS) have become increasingly prevalent in a variety of fields due to their ability to process complex and uncertain data with high accuracy. This research article reviews three major contributions of ANFS: their application in deep neuro-fuzzy systems (DNFS) for healthcare and industrial systems, neuro-fuzzy logic controllers for paralysis estimation, and ANFIS-based solutions for secure cloud storage in medical IoT (MIoT). The findings emphasize the importance of ANFS in improving decision-making, diagnosis, and data security. This paper concludes with a discussion on challenges, future research directions, and the need for optimization in real-time applications.

Ontology extension by online clustering with large language model agents.

An ontology is a structured framework that categorizes entities, concepts, and relationships within a domain to facilitate shared understanding, and it is important in computational linguistics and knowledge representation. In this paper, we propose a novel framework to automatically extend an existing ontology from streaming data in a zero-shot manner. Specifically, the zero-shot ontology extension framework uses online and hierarchical clustering to integrate new knowledge into existing ontologies without substantial annotated data or domain-specific expertise. Focusing on the medical field, this approach leverages Large Language Models (LLMs) for two key tasks: Symptom Typing and Symptom Taxonomy among breast and bladder cancer survivors. Symptom Typing involves identifying and classifying medical symptoms from unstructured online patient forum data, while Symptom Taxonomy organizes and integrates these symptoms into an existing ontology. The combined use of online and hierarchical clustering enables real-time and structured categorization and integration of symptoms. The dual-phase model employs multiple LLMs to ensure accurate classification and seamless integration of new symptoms with minimal human oversight. The paper details the framework's development, experiments, quantitative analyses, and data visualizations, demonstrating its effectiveness in enhancing medical ontologies and advancing knowledge-based systems in healthcare.

Technology readiness assessment: Case of clinical decision support systems in healthcare

Clinical Decision Support Systems (CDSS) play a critical role in modern healthcare by supporting healthcare providers in making well-informed decisions, improving patient safety and outcomes, enhancing efficiency, and promoting evidence-based practices. Their integration into clinical workflows can lead to more effective and patient-centered care. CDSS is essential tools for healthcare organizations as well as for healthcare providers to improve clinical care. However, successful implementation of CDSS can be challenging. Therefore, before implementing CDSS, it is crucial to assess the readiness of healthcare organizations to implement these tools. CDSS is essential tools in healthcare for several compelling reasons. For instance, enhanced patient safety, improved diagnostic accuracy, optimized treatment plans, consistency in care, and support for complex decisions. This study's aim is to develop a model that will help healthcare organizations identify the challenges of implementing CDSS, and to assess their readiness for such an implementation in a comprehensive and multi-dimensional manner. Through a literature review, the first step of this research explores the concept of clinical decision support and CDSS, discussing their features, characteristics, and organizational hurdles to implementation. It also provides perspectives on CDSS adoption in the context of information systems and health technology. The review helped to identify research gaps, objectives, and questions. To address these gaps and to attempt to answer the research questions, a Hierarchical Decision Model (HDM) is proposed. The model allows us to assess the readiness of healthcare organizations for CDSS implementation. It presents four perspectives and sixteen criteria for a multi-dimensional assessment. The methodology involves expert panels for the HDM model's refinement, validation, and quantification. Two case studies are then presented to demonstrate the HDM model's application to identify real-world CDSS implementation challenges and to provide insights and recommendations. The research contributions are evaluated against the identified gaps in the literature review, with limitations and future research presented. In conclusion, this research provides valuable insights into CDSS implementation readiness assessment and highlights the need for careful consideration and planning. The proposed HDM model offers a valuable framework for healthcare organizations to evaluate their readiness for CDSS implementation.

The Integration of AI-Driven Decision Support Systems in Healthcare: Enhancements, Challenges, and Future Directions

Artificial Intelligence (AI) is transforming the healthcare landscape by enhancing diagnostic accuracy, operational efficiency, and patient management through AI-driven Decision Support Systems (AI-DSS). These systems leverage vast datasets, including electronic health records and various biomolecular markers, to provide evidence-based recommendations for clinical practice. Despite their potential, challenges such as data quality, algorithmic bias, and ethical concerns persist. This paper explores the capabilities of AI-DSS in healthcare, the methodologies underpinning their operation, and the ethical considerations that accompany their implementation. Additionally, the paper discusses future trends in AI integration within healthcare, emphasizing the importance of ongoing collaboration between healthcare professionals and AI researchers to address existing limitations and opti-mize patient outcomes. Keywords: Artificial Intelligence, Decision Support Systems, Healthcare, Diagnostic Accuracy, Predictive Analytics, Ethical Considerations, Data Privacy, Machine Learning, Personalized Medicine

Перспективы применения технологий искусственного интеллекта для цифровой трансформации здравоохранения.

Introduction. Currently, the digital transformation of healthcare is one of the priority areas of industry development. In Russia, there is a high readiness and interest of both managers and doctors in the practical application of various digital products, including decision support systems using AI technologies. Materials and methods. The authors analyzed the scientific research and practical developments available in Russia in order to systematize and identify the most popular scenarios for the use of artificial intelligence systems. Results. The most promising areas for the development of artificial intelligence systems for healthcare in Russia are: Improved diagnostics. AI systems can analyze medical images, laboratory test data and clinical histories, identify patholo- gies and offer accurate diagnoses, which helps doctors make more informed decisions. Personalized treatment. The use of AI allows taking into account the individual characteristics of patients and offering optimal treatment regimens based on the analysis of numerous factors, such as genetic data, medical history and response to therapy. Disease prediction. AI can help determine the likelihood of developing certain diseases in a particular patient based on their individual risk factors, allowing for preventive measures or early treatment. Automation and optimization of processes. AI can reduce the workload of medical personnel, automate routine tasks, improve medical data management, and ensure more efficient resource allocation. Conclusions. The proposed scenarios and areas of AI application are most likely to impact the achievement of targets and objectives set out in the national project "Healthcare" – which is a priority for the implementation of AI.

Preparation of Baicalin Liposomes Using Microfluidic Technology and Evaluation of Their Antitumor Activity by a Zebrafish Model.

Baicalin (BCL), a well-known flavonoid molecule, has numerous therapeutic applications. However, its low water solubility and bioavailability limit its applicability. Microfluidics is a new method for liposome preparation that provides efficient and rapid control of the process, improving the stability and controllability. This study used microfluidic techniques to create baicalin liposomes (BCL-LPs), first screening for optimal total flow rates (TFR) and flow rate ratios (FRR), and then optimizing the phospholipid concentration, phospholipid-to-cholesterol ratio, and Tween-80 concentration using univariate and response surface methodology approaches. The study found that the ideal phospholipid content was 9.5%, the phospholipid-to-cholesterol ratio was 9:1 (w:w), and the Tween-80 concentration was 15%. BCL-LPs achieved 95.323% ± 0.481% encapsulation efficiency under the optimum circumstances. Characterization indicated that the BCL-LPs were spherical and uniform in size, with a mean diameter of 62.32 nm ± 0.42, a polydispersity index of 0.092 ± 0.009, and a zeta potential of -25.000 mV ± 0.216. In vitro experiments found that BCL-LPs had a better slow-release effect and stability than the BCL monomer. In zebrafish bioassays, BCL-LPs performed better than BCL monomer in terms of biological activity and bioavailability. The established method provided a feasible medicine delivery platform for BCL and could apply for the transport and encapsulation of more natural compounds, expanding the applications of drug delivery systems in healthcare and cancer therapies.

Cocreative Development of Robotic Interaction Systems for Health Care: Scoping Review.

Robotic technologies present challenges to health care professionals and are therefore rarely used. Barriers such as lack of controllability and adaptability and complex control functions affect the human-robot relationship. In addition to educational opportunities, the possibility of individual adaptation can improve the usability and practical implementation of robotics. Previous work has focused on developments from a technology-centered perspective and has included user interests too late in the process. This study addresses the following research question: What cocreative research approaches are used in the field of nursing robotics to improve the usability, intended use, and goal-directed application of robotic developments for nurses and to support the nursing process? This scoping review provides an overview of the topic and the research activities taking place within it. Five databases and the reference lists of the identified publications were searched for studies without further restrictions. Studies were included if they developed and evaluated interaction and control platforms for robotic systems in health care in a cocreative way with end users. The search resulted in 419 hits, of which 3 publications were included. All publications were feasibility or user studies that were mainly carried out in the European Union. The 3 interaction and control platforms presented were all prototypes and not commercially available. In addition to those in need of care, all studies also included family carers and health care professionals. Robotic interaction and control platforms in health care are rarely, if ever, developed and evaluated with feasibility or user studies that include prototypes and end users. While the involvement of end users is crucial, this review emphasizes that all stakeholders, including health care professionals, should participate in the development process to ensure a holistic understanding of application needs and a focus on user experiences and practical health care needs. It is emphasized that the active involvement of end users in the development process is critical to effectively meeting the needs of the target group.

Behavioral Design in Healthcare: Synthesis of Technical Sciences and Humanities

The scientific and practical potential of behavioral economics and behavioral design in Russia is underutilized, and the use of their methods can be significantly expanded, both in the scientific field and in practice. One of the promising areas of their application, with significant experience accumulated in the West, is healthcare. Behavioral design in healthcare is an example of an effective synthesis of the achievements of the humanities and technical sciences with an interdisciplinary approach that constructively combines economic, psychological, and technological methods of scientific knowledge. The use of behavioral design technologies, including digital and neural interfaces, is a promising direction for creating competitive products and services in healthcare. The theory of solving inventive problems can help speed up the process of implementation in practice. Behavioral design technologies in healthcare can be considered from such positions as physical design – the design of medical equipment, devices, and drug labels – as well as design for error-proofing in organizing processes based on reducing the negative impact of the human factor. The behavioral design of error-proofing systems in healthcare is implemented through functions such as forced control, error failure, warning, and touch alert.

Application Of Robotic Systems In Healthcare And Reduced Infection Risk In Cancer Patients In Postoperative Oncology Surgical Patients

This research aims to investigate the impact of robotic systems in oncology surgery, focusing on sensitive cases such as brain and colon cancer. The study includes a group of 5 male and female patients, and data is collected post-surgery, particularly after patient recovery. The significant advantages of robotic surgery are documented in observational tables and charts. The findings suggest a promising future for robotic systems in surgery, with reduced recorded risks

Practical implementation of generative artificial intelligence systems in healthcare: A United States perspective

Practical implementation of generative artificial intelligence systems in healthcare: A United States perspective

Comprehensive Review of Deep Learning Algorithms for Embedded Healthcare Applications

The integration of deep learning algorithms into embedded healthcare applications has emerged as a promising avenue for revolutionizing medical diagnostics, monitoring, and treatment. This review explores the performance, suitability, and implications of various deep learning algorithms within the context of embedded healthcare systems. Leveraging a diverse range of algorithms including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Transformer Networks, and more. The study presents an overview of embedded systems in healthcare, which leverage Deep learning algorithms to enhance their performance and enable physicians to provide prompt and accurate responses to patients.

Photoacoustic Quantification of Tissue Oxygenation Using Conditional Invertible Neural Networks.

Intelligent systems in interventional healthcare depend on the reliable perception of the environment. In this context, photoacoustic tomography (PAT) has emerged as a non-invasive, functional imaging modality with great clinical potential. Current research focuses on converting the high-dimensional, not human-interpretable spectral data into the underlying functional information, specifically the blood oxygenation. One of the largely unexplored issues stalling clinical advances is the fact that the quantification problem is ambiguous, i.e. that radically different tissue parameter configurations could lead to almost identical photoacoustic spectra. In the present work, we tackle this problem with conditional Invertible Neural Networks (cINNs). Going beyond traditional point estimates, our network is used to compute an approximation of the conditional posterior density of tissue parameters given the photoacoustic spectrum. To this end, an automatic mode detection algorithm extracts the plausible solution from the sample-based posterior. According to a comprehensive validation study based on both synthetic and real images, our approach is well-suited for exploring ambiguity in quantitative PAT.

Recommender System for E-Health

Introduction; E-healthcare management services can be significantly enhanced through the implementation of recommender systems, as highlighted in various research papers. These systems, such as Healthcare Recommender Systems (HRS) and Health Care Recommender Systems (HCRS), utilize advanced algorithms and machine learning techniques to provide personalized health recommendations based on user input and medical data. Objective; Recommend healthcare services based on patient's state. Model healthcare information network for efficient service recommendation.Methodology; Recommends healthcare services based on patient's critical situation and requirements. Offers re-configurable healthcare workflows to medical staff. Machine learning method classification is applied using decision tree and its result is presented which reflects 70 to 75% accuracy in predictive models which ensure that health recommender system is a full proof system.Result; Hospital recommender systems represent a significant advancement in healthcare, providing personalized and data-driven recommendations to patients.Conclusion; The integration of recommender systems in e-healthcare management services holds great potential in improving personalized patient care, promoting health awareness, and optimizing the quality of healthcare recommendations. In this paper author analyzed and estimated the level of accuracy of recommendation systems in healthcare for personalized medical treatment. It surveys current applications, challenges, and future directions in this field.

Automated machine learning with interpretation: A systematic review of methodologies and applications in healthcare

AbstractMachine learning (ML) has achieved substantial success in performing healthcare tasks in which the configuration of every part of the ML pipeline relies heavily on technical knowledge. To help professionals with borderline expertise to better use ML techniques, Automated ML (AutoML) has emerged as a prospective solution. However, most models generated by AutoML are black boxes that are challenging to comprehend and deploy in healthcare settings. We conducted a systematic review to examine AutoML with interpretation systems for healthcare. We searched four databases (MEDLINE, EMBASE, Web of Science, and Scopus) complemented with seven prestigious ML conferences (AAAI, ACL, ICLR, ICML, IJCAI, KDD, and NeurIPS) that reported AutoML with interpretation for healthcare before September 1, 2023. We included 118 articles related to AutoML with interpretation in healthcare. First, we illustrated AutoML techniques used in the included publications, including automated data preparation, automated feature engineering, and automated model development, accompanied by a real‐world case study to demonstrate the advantages of AutoML over classic ML. Then, we summarized interpretation methods: feature interaction and importance, data dimensionality reduction, intrinsically interpretable models, and knowledge distillation and rule extraction. Finally, we detailed how AutoML with interpretation has been used for six major data types: image, free text, tabular data, signal, genomic sequences, and multi‐modality. To some extent, AutoML with interpretation provides effortless development and improves users' trust in ML in healthcare settings. In future studies, researchers should explore automated data preparation, seamless integration of automation and interpretation, compatibility with multi‐modality, and utilization of foundation models.

Rule-Based Threat Analysis Methodology for Cyber-Physical Systems in Healthcare

Cyber-physical system (CPS) integration in the field of contemporary healthcare has completely changed patient monitoring and management. But because these systems are linked, they are vulnerable to different kinds of cyber attacks, which calls for strong security protocols. This work aims to proactively identify and reduce possible security risks by proposing a Rule- Based Threat Analysis Methodology (RBTAM) specifically designed for CPS in healthcare environments. RBTAM uses formalized rules to methodically evaluate threats in the physical and cyberspaces. Its foundations are in discrete mathematics. The process starts with identifying the parts and vulnerabilities of the system, then rules capturing possible threat scenarios are formulated. Among the many things covered by these regulations are denial of service, hardware malfunctions, data tampering, and unauthorized access. By means of an extensive analysis process, RBTAM assesses the probability and consequences of threats found on the availability, confidentiality, and integrity of healthcare systems. Through the facilitation of the prioritization of mitigation measures, this analysis helps healthcare professionals to efficiently distribute resources and reduce possible hazards to data security and patient safety. Important elements of RBTAM are the creation of threat scenarios specific to healthcare settings, the development of security rules based on system architecture, and the incorporation of real-time monitoring systems to identify and address new threats. Furthermore, the approach stresses feedback loops for ongoing improvement, which guarantees flexibility to changing cyberthreats and technology developments. We provide a case study of RBTAM application in a simulated CPS healthcare setting to illustrate its effectiveness. Results show that by efficiently identifying and reducing possible security risks, RBTAM improves the general resistance of healthcare systems to cyberattacks. In the ever-connected healthcare environment, RBTAM provides healthcare professionals and system administrators the tools and insights they need to protect patient well-being and data integrity through a proactive and methodical approach to threat analysis in CPS healthcare.

Exploring the Interplay of Dataset Size and Imbalance on CNN Performance in Healthcare: Using X-rays to Identify COVID-19 Patients.

Convolutional Neural Network (CNN) systems in healthcare are influenced by unbalanced datasets and varying sizes. This article delves into the impact of dataset size, class imbalance, and their interplay on CNN systems, focusing on the size of the training set versus imbalance-a unique perspective compared to the prevailing literature. Furthermore, it addresses scenarios with more than two classification groups, often overlooked but prevalent in practical settings. Initially, a CNN was developed to classify lung diseases using X-ray images, distinguishing between healthy individuals and COVID-19 patients. Later, the model was expanded to include pneumonia patients. To evaluate performance, numerous experiments were conducted with varied data sizes and imbalance ratios for both binary and ternary classifications, measuring various indices to validate the model's efficacy. The study revealed that increasing dataset size positively impacts CNN performance, but this improvement saturates beyond a certain size. A novel finding is that the data balance ratio influences performance more significantly than dataset size. The behavior of three-class classification mirrored that of binary classification, underscoring the importance of balanced datasets for accurate classification. This study emphasizes the fact that achieving balanced representation in datasets is crucial for optimal CNN performance in healthcare, challenging the conventional focus on dataset size. Balanced datasets improve classification accuracy, both in two-class and three-class scenarios, highlighting the need for data-balancing techniques to improve model reliability and effectiveness. Our study is motivated by a scenario with 100 patient samples, offering two options: a balanced dataset with 200 samples and an unbalanced dataset with 500 samples (400 healthy individuals). We aim to provide insights into the optimal choice based on the interplay between dataset size and imbalance, enriching the discourse for stakeholders interested in achieving optimal model performance. Recognizing a single model's generalizability limitations, we assert that further studies on diverse datasets are needed.