Systems In Healthcare Research Articles

Explainable AI-Powered IoT Systems for Predictive and Preventive Healthcare - A Framework for Personalized Health Management and Wellness Optimization

Explainable AI-Powered IoT Systems for Predictive and Preventive Healthcare - A Framework for Personalized Health Management and Wellness Optimization

AI and professional liability assessment in healthcare. A revolution in legal medicine?

The adoption of advanced artificial intelligence (AI) systems in healthcare is transforming the healthcare-delivery landscape. Artificial intelligence may enhance patient safety and improve healthcare outcomes, but it presents notable ethical and legal dilemmas. Moreover, as AI streamlines the analysis of the multitude of factors relevant to malpractice claims, including informed consent, adherence to standards of care, and causation, the evaluation of professional liability might also benefit from its use. Beginning with an analysis of the basic steps in assessing professional liability, this article examines the potential new medical-legal issues that an expert witness may encounter when analyzing malpractice cases and the potential integration of AI in this context. These changes related to the use of integrated AI, will necessitate efforts on the part of judges, experts, and clinicians, and may require new legislative regulations. A new expert witness will be likely necessary in the evaluation of professional liability cases. On the one hand, artificial intelligence will support the expert witness; however, on the other hand, it will introduce specific elements into the activities of healthcare workers. These elements will necessitate an expert witness with a specialized cultural background. Examining the steps of professional liability assessment indicates that the likely path for AI in legal medicine involves its role as a collaborative and integrated tool. The combination of AI with human judgment in these assessments can enhance comprehensiveness and fairness. However, it is imperative to adopt a cautious and balanced approach to prevent complete automation in this field.

A Comprehensive Analysis of Speech Recognition Systems in Healthcare: Current Research Challenges and Future Prospects

A Comprehensive Analysis of Speech Recognition Systems in Healthcare: Current Research Challenges and Future Prospects

Neurosurgery, Explainable AI, and Legal Liability.

One of the challenges of AI technologies is its "black box" nature, or the lack of explainability and interpretability of these technologies. This chapter explores whether AI systems in healthcare generally, and in neurosurgery specifically, should be explainable, for what purposes, and whether the current XAI ("explainable AI") approaches and techniques are able to achieve these purposes. The chapter concludes that XAI techniques, at least currently, are not the only and not necessarily the best way to achieve trust in AI and ensure patient autonomy or improved clinical decision, and they are of limited significance in determining liability. Instead, we argue, we need more transparency around AI systems, their training and validation, as this information is likely to better achieve these goals.

Audio- and Video-Based Human Activity Recognition Systems in Healthcare

Audio- and Video-Based Human Activity Recognition Systems in Healthcare

Intelligence Augmentation and capability co-elevation in healthcare enabled by reasoned transparency

Artificial intelligence (AI) systems in healthcare can have a significant impact on the performance of the actors involved, encouraging, for example, increasingly early diagnoses, personalized treatments and more accurate data management and processing techniques. However, these results may depend on increasingly profitable human-machine interactions, Intelligence Augmentation, and potential in terms of capability co-elevation. Starting from this assumption, this study aims to understand which can be the Intelligence Augmentation and capability co- elevation driver in healthcare. This conceptual paper has been carried out with the conceptual goal of delineating, so, to address the research question, a deductive reasoning approach was applied and the methodological approach followed has been based on the description of the theoretical background, definition of evidence from an illustrative case, Livongo Health, addressed by analyzing secondary data extrapolated from the website contents, and development conclusions. From the illustration case, insights have been outlined to understand how to achieve the objectives of Intelligence Augmentation and capability co-elevation: it has been observed how the reasoned transparency in AI systems can be understood as an enabling factor.

Responsible and ethical application of artificial intelligence systems in healthcare through a case study in diagnostics and personalized medicine

Responsible and ethical application of artificial intelligence systems in healthcare through a case study in diagnostics and personalized medicine

Multidose Drug Dispensing in Community Healthcare Settings for Patients With Multimorbidity and Polypharmacy.

Multidose drug dispensing (MDD) is the dispensing of different drugs in dose bags containing one, some, or all units of medicine that a patient needs to take at specific times. The aim of this narrative review is to provide an overview of the literature describing the use of MDD systems in community healthcare settings in patients with multimorbidity and polypharmacy. A literature search identified 14 studies examining adherence, medication knowledge, quality of drug prescription (including inappropriate drug use, drug-drug interactions), medication incidents, and drug changes after MDD initiation, as well as healthcare professional (HCP) and patient perspectives. There are limited data on MDD in community healthcare settings, particularly on outcomes such as adherence. Studies are mostly from Northern Europe. Patients selected for MDD are more likely to be older, female, cognitively impaired, and have a higher number of disease diagnoses and drugs than those who do not receive drugs through MDD. MDD is generally initiated for patients who have decreased capacity for medication management. Several advantages of MDD have been reported by patients and HCPs, and studies indicate that MDD can be improved by medication review, defining clear roles and responsibilities of HCPs in the medication management chain, and comprehensive follow-up of patients. Future development, implementation, and assessment of MDD systems in community healthcare should be designed in collaboration with HCPs and patients, to identify ways to optimize the systems and improve patient outcomes.

Advances in Biointegrated Wearable and Implantable Optoelectronic Devices for Cardiac Healthcare.

With the prevalence of cardiovascular disease, it is imperative that medical monitoring and treatment become more instantaneous and comfortable for patients. Recently, wearable and implantable optoelectronic devices can be seamlessly integrated into human body to enable physiological monitoring and treatment in an imperceptible and spatiotemporally unconstrained manner, opening countless possibilities for the intelligent healthcare paradigm. To achieve biointegrated cardiac healthcare, researchers have focused on novel strategies for the construction of flexible/stretchable optoelectronic devices and systems. Here, we overview the progress of biointegrated flexible and stretchable optoelectronics for wearable and implantable cardiac healthcare devices. Firstly, the device design is addressed, including the mechanical design, interface adhesion, and encapsulation strategies. Next, the practical applications of optoelectronic devices for cardiac physiological monitoring, cardiac optogenetics, and nongenetic stimulation are presented. Finally, an outlook on biointegrated flexible and stretchable optoelectronic devices and systems for intelligent cardiac healthcare is discussed.

Deconstructing demographic bias in speech-based machine learning models for digital health.

Machine learning (ML) algorithms have been heralded as promising solutions to the realization of assistive systems in digital healthcare, due to their ability to detect fine-grain patterns that are not easily perceived by humans. Yet, ML algorithms have also been critiqued for treating individuals differently based on their demography, thus propagating existing disparities. This paper explores gender and race bias in speech-based ML algorithms that detect behavioral and mental health outcomes. This paper examines potential sources of bias in the data used to train the ML, encompassing acoustic features extracted from speech signals and associated labels, as well as in the ML decisions. The paper further examines approaches to reduce existing bias via using the features that are the least informative of one's demographic information as the ML input, and transforming the feature space in an adversarial manner to diminish the evidence of the demographic information while retaining information about the focal behavioral and mental health state. Results are presented in two domains, the first pertaining to gender and race bias when estimating levels of anxiety, and the second pertaining to gender bias in detecting depression. Findings indicate the presence of statistically significant differences in both acoustic features and labels among demographic groups, as well as differential ML performance among groups. The statistically significant differences present in the label space are partially preserved in the ML decisions. Although variations in ML performance across demographic groups were noted, results are mixed regarding the models' ability to accurately estimate healthcare outcomes for the sensitive groups. These findings underscore the necessity for careful and thoughtful design in developing ML models that are capable of maintaining crucial aspects of the data and perform effectively across all populations in digital healthcare applications.

Artificial intelligence (AI) or augmented intelligence? How big data and AI are transforming healthcare: Challenges and opportunities.

The sanctity of the doctor-patient relationship is deeply embedded in tradition - the Hippocratic oath, medical ethics, professional codes of conduct, and legislation - all of which are being disrupted by big data and 'artificial' intelligence (AI). The transition from paper-based records to electronic health records, wearables, mobile health applications and mobile phone data has created new opportunities to scale up data collection. Databases of unimaginable magnitude can be harnessed to develop algorithms for AI and to refine machine learning. Complex neural networks now lie at the core of ubiquitous AI systems in healthcare. A transformed healthcare environment enhanced by innovation, robotics, digital technology, and improved diagnostics and therapeutics is plagued by ethical, legal and social challenges. Global guidelines are emerging to ensure governance in AI, but many low- and middle-income countries have yet to develop context- specific frameworks. Legislation must be developed to frame liability and account for negligence due to robotics in the same way human healthcare providers are held accountable. The digital divide between high- and low-income settings is significant and has the potential to exacerbate health inequities globally.

Искусственный интеллект в здравоохранении России: сбор и подготовка данных для машинного обучения.

This scientific article draws attention to the importance of collecting and preparing high-quality medical data for the development of artificial intelligence (AI) systems in Russian healthcare. Materials and methods. The main emphasis is on the need to create a unified federal standard for collecting structured digitized medical data, which will unify the processes of collecting and generating datasets for medical organizations. Results. The article proposes the introduction of digital assistants, including pre-medical diagnostic questionnaires, mobile applications and software modules for medical examinations, which will reduce the time spent filling out medical documentation and ensure the collection of more complete and accurate information. The next step is to reengineer the health data collection process, including patient engagement via smartphones and personal health assistants. The article identifies methodological problems such as unreliability, incompleteness and lack of extensional knowledge in the collected data, and proposes a roadmap for the development of a health data collection system, including the creation of digital standards, data collection methods and the development of AI-based decision support. Conclusions. Solving the described problems and the data development plan are important for the successful implementation of the national project «Data Economy», supporting the development and application of AI systems in the medical field.

Features of Classification of Crimes Committed by Persons using Artificial Intelligence Technologies in Healthcare

Recognizing positive possibilities of artificial intelligence technologies in healthcare, as well as current ways to use them, the author identifies the main forms of implementation of digital innovation: physical form in the form of a medical robot and intellectual form in the form of software, registered as medical devices. It is stated that the legal issues related to bringing to justice for actions related to the use of intelligent systems in healthcare, which led to negative consequences, including harm to the life and health of patients, have yet to be resolved. According to the current legal regulation in Russia it is a medical organization and a medical professional using artificial intelligence systems or medical robotics equipped with digital technologies who are held liable for the harm caused to the life and (or) health of citizens while providing them with medical care. In turn, system developers, as well as those who train a system based on artificial intelligence (developers of artificial intelligence systems), are not held liable. The problems of classification of crimes committed by medical professionals using artificial intelligence technologies in healthcare are considered. A medical worker providing medical care using artificial intelligence may be the subject of a crime under Part 2 of Article 109 and part 2 of Article 118 of the Criminal Code of the Russian Federation, but not under Article 238 of the Criminal Code of the Russian Federation. In addition, the rules for the classification of crimes committed by other entities (the operator of information systems) using artificial intelligence technologies are formulated.

In-depth Historical Analysis of Healthcare Screening Systems

Purpose: The management facilitated by Triage Systems raises numerous inquiries for both healthcare professionals and users, rendering it an increasingly pertinent concern. In Portugal, emergency services cater to millions of individuals annually. The dynamic shifts in care are abundant and contingent on the specific nature of the healthcare required. Change, therefore, stands as a perpetual element in the realm of medicine, with alterations unfolding at an accelerating pace and growing complexity. Within the realm of emergency services, Triage serves as the inaugural stage in the healthcare delivery process. It necessitates a meticulous and rigorous approach, a task reserved for adept professionals who are adequately prepared for responsibility. The intricate nature of Triage underscores its pivotal role, setting the tone for the subsequent stages of healthcare provision. As the landscape of healthcare continues to evolve, the effectiveness and precision of Triage become even more crucial, emphasizing the need for ongoing training and adaptability among healthcare professionals.
 Design/Method/Approach: The methodology of the research consists of a thorough literature review to compare different screening systems in healthcare, to better understand the current situation.
 Findings: The findings indicate that the Screening System is both valid and beneficial. Nevertheless, ongoing adjustments in service management are required to enhance its effectiveness and alignment.
 Theoretical Implications: This paper explores how healthcare screening systems have evolved over time, tracing their roots from historical practices to modern technologies. It identifies paradigm shifts in healthcare thinking, policy and technology that have influenced the development of screening systems.
 Practical Implications: The screening system is a vital process mandated for all individuals seeking assistance in the emergency department, serving to ascertain the severity of their clinical condition. The primary goal of this assessment is to delve into the historical evolution of Screening Systems in Healthcare. Presently, in Portugal, the Manchester Sorting System stands out as the predominant and widely utilized approach.
 Originality/Value: The study provides a comprehensive comparative analysis of healthcare screening systems.
 Research Limitations/Future Research: Future studies could perform other types of analyses. Namely, qualitative ones in which health professionals gave opinions.
 Paper Type: Conceptual
 JEL Classification: I1, M1

Cost-effective Digital Prescription using Pharmaceutical Knowledge Graph

In the current era of the advancing medical domain and the ever-evolving use of technology in fields of pharmaceutical research, remote monitoring, and decision support systems in healthcare, prescription management has transformed from handwritten prescriptions to digital ones. This transition however does not imply that these prescriptions are comprehensive and provide optimized treatment outcomes. These digital prescriptions still reflect the formerly used handwritten prescriptions. Thus, recipients face the daunting challenge of making cost-effective, holistic, informed, and personalized decisions without compromising the legitimacy and authenticity of the original prescription, all due to a lack of readily available alternative medicine options. This problem can be addressed by utilizing the knowledge graph that we built, which contains carefully curated medical information collected from reliable and diverse sources, ensuring the authenticity and relevance of the information. Delving into the intricate interconnections among diverse medical entities and their properties, the medical knowledge graph presents an invaluable solution, empowering the generation of smart digital prescriptions in a fast and precise manner. Specifically, this study focuses on the transformative potential of digital prescriptions, elucidating their role in streamlining healthcare processes and enhancing communication between healthcare providers and patients. By leveraging the insights derived from our medical knowledge graph, we aim to contribute to the advancement of digital prescription systems, fostering more effective, personalized, and technology-driven healthcare solutions.

SUPPLY CHAIN MANAGEMENT IN THE MEDICAL TOURISM NETWORKING SYSTEM: A REVIEW

The science development in the medicine field, brings the new methods and systems for health care and medical treatment, and also brings the convenience in transportation and communication. Accordingly, a new field of tourism emerges, that is the medical tourism. Medical tourism is an emerging tourism trend that has recently gained increasing popularity. The idea of medical tourism is that when individuals travel abroad to seek for medical services while at the same time have the intention of healing and relaxation. In practice, this particular field involves many stakeholders that collaborate each other to serve the customer. Consequently, the medical tourism industry depends mainly on the networking system. For that reason, one of the most beneficial management methods for coordinating and integrating these relevant parties in this particular field is through Supply Chain Management (SCM) in that SCM covers the management of numerous activities multiple role-players from various divisional functions and organizations. Accordingly, this paper aims to explore the system that supports medical tourism, particularly by searching the literature and sources of information related to this particular field. Several selected studies suggested a medical tourism supply chain conceptual model to develop better understanding of medical tourism system as a whole.

One size doesn’t always fit all: professional perspectives of serious incident management systems in mental healthcare

PurposeThe need to develop effective approaches for responding to healthcare incidents for the purpose of learning and improving patient safety has been recognised in current national policy. However, research into this topic is limited. This study aims to explore the perspectives of professionals in mental health trusts in England about what works well and what could be done better when implementing serious incident management systems.Design/methodology/approachThis was a qualitative study using semi-structured interviews. In total, 15 participants were recruited, comprising patient safety managers, serious incident investigators and executive directors, from five mental health trusts in England. The interview data were analysed using a qualitative-descriptive approach to develop meaningful themes. Quotes were selected and presented based on their representation of the data.FindingsParticipants were dissatisfied with current systems to manage serious incidents, including the root cause analysis approach, which they felt were not adequate for assisting learning and improvement. They described concerns about the capability of serious incident investigators, which was felt to impact on the quality of investigations. Processes to support people adversely affected by serious incidents were felt to be an important part of incident management systems to maximise the learning impact of investigations.Originality/valueFindings of this study provide translatable implications for mental health trusts and policymakers, informed by insights into how current approaches for learning from healthcare incidents can be transformed. Further research will build a more comprehensive understanding of mechanisms for responding to healthcare incidents.

Optimizing Medical Gas Pipeline Systems in Healthcare: Lessons from the COVID-19 Era

Optimizing Medical Gas Pipeline Systems in Healthcare: Lessons from the COVID-19 Era

Instagram and lumbar discectomy surgery: An evaluation of patients’ perception of surgery in social media

Background/Aim: Most scoring systems in healthcare take into account the physical condition and pain status of a patient, but the impact of society on the individual is ignored. The aim of our study was to evaluate the social media posts made by patients regarding lumbar discectomy surgery. The objective was to identify and explore concerns and issues that may not be immediately evident during clinical evaluations but are significant to the patients themselves. Methods: Public posts with the hashtags #discectomy, #lumbardisectomy, and #discectomyrecovery were examined on the Instagram application. The tone of the post, return to sports (RTS), rehabilitation or physical therapy (PT), return to work (RTW), incision site (e.g., scarring, sutures, and dressing), pain, activities of daily living (ADL), and X-ray/magnetic resonance imaging (MRI) data were evaluated. The "Instagram likes ratio" was determined by dividing the total number of likes received for each post by the number of followers. Results: 272 posts were assessed, and 77.9% of them exhibited a positive tone. The topic that was most frequently discussed was ADL, which was discussed in 24.6% of the posts. Statistical analysis demonstrated a significant association between positive tone and ADL, as well as positive tone and RTS (P<0.001). A statistically significant correlation was observed between negative tone and neurological deficits, pain, and X-ray/MRI findings (P<0.001). Conclusion: Our study offers a unique perspective on the experience and satisfaction of patients who have undergone lumbar discectomy. Neurologic deficits and pain were notably significant in the negative posts. However, in general, the majority of the posts maintained a positive tone. The results could provide insights into patients' experiences and perspectives that can potentially inform healthcare professionals in providing more comprehensive and patient-centered care.

Human centric attention with deep multiscale feature fusion framework for activity recognition in Internet of Medical Things

Recent advancements in the Internet of Medical Things (IoMT) have revolutionized the healthcare sector, making it an active research area in the academic and industrial sectors. Following these advances, an automatic Human Activity Recognition (HAR) is now integrated into the IoMT, facilitating remote patient monitoring systems for smart healthcare. However, implementing HAR via computer vision is intricate due to complex spatiotemporal patterns, single stream fusion, and clutter backgrounds. Mainstream approaches practice pre-trained CNN model, which extract non-salient features due to their generalized weight optimization and limited discriminative feature fusion. In addition, their sequential models have inadequate performance in complex scenarios due to the vanishing gradients encountered during backpropagation across multiple layers. In response to these challenges, we propose a multiscale feature fusion framework for both indoor and outdoor environments to enhance HAR in healthcare monitoring systems, which is mainly composed of two stages: First, the proposed Human Centric Attentional Fusion (HCAF) network is fused with the intermediate convolutional feature of lightweight MobileNetV3 backbone to enriches spatial learning capabilities for accurate HAR. Next, a Deep Multiscale Features Fusion (DMFF) network is proposed that enhanced the long-range temporal dependencies by redesigning the traditional bidirectional LSTM network into a residual fashion followed by Sequential Multihead Attention (SMA) to eliminate non-relevant information and optimized spatiotemporal feature vectors. The performance of the proposed fusion model is evaluated on benchmark healthcare and general activity datasets. In the healthcare, we used Multiple Camera Fall and UR Fall Detection datasets that achieved 99.941% and 100% accuracy. Despite this, our fusion strategy is rigorously evaluated over three challenging general HAR datasets, including HMDB51,UCF101, and UCF50, demonstrating 74.942%, 97.337%, and 96.156% superior performance compared to State-of-The-Art (SOTA) methods. The run time analysis shows that the proposed method is 2x times faster than the existing methods.