Healthcare Decision-making Process Research Articles

FIT calculator: a multi-risk prediction framework for medical outcomes using cardiorespiratory fitness data

Accurately predicting patients' risk for specific medical outcomes is paramount for effective healthcare management and personalized medicine. While a substantial body of literature addresses the prediction of diverse medical conditions, existing models predominantly focus on singular outcomes, limiting their scope to one disease at a time. However, clinical reality often entails patients concurrently facing multiple health risks across various medical domains. In response to this gap, our study proposes a novel multi-risk framework adept at simultaneous risk prediction for multiple clinical outcomes, including diabetes, mortality, and hypertension. Leveraging a concise set of features extracted from patients' cardiorespiratory fitness data, our framework minimizes computational complexity while maximizing predictive accuracy. Moreover, we integrate a state-of-the-art instance-based interpretability technique into our framework, providing users with comprehensive explanations for each prediction. These explanations afford medical practitioners invaluable insights into the primary health factors influencing individual predictions, fostering greater trust and utility in the underlying prediction models. Our approach thus stands to significantly enhance healthcare decision-making processes, facilitating more targeted interventions and improving patient outcomes in clinical practice. Our prediction framework utilizes an automated machine learning framework, Auto-Weka, to optimize machine learning models and hyper-parameter configurations for the simultaneous prediction of three medical outcomes: diabetes, mortality, and hypertension. Additionally, we employ a local interpretability technique to elucidate predictions generated by our framework. These explanations manifest visually, highlighting key attributes contributing to each instance's prediction for enhanced interpretability. Using automated machine learning techniques, the models simultaneously predict hypertension, mortality, and diabetes risks, utilizing only nine patient features. They achieved an average AUC of 0.90 ± 0.001 on the hypertension dataset, 0.90 ± 0.002 on the mortality dataset, and 0.89 ± 0.001 on the diabetes dataset through tenfold cross-validation. Additionally, the models demonstrated strong performance with an average AUC of 0.89 ± 0.001 on the hypertension dataset, 0.90 ± 0.001 on the mortality dataset, and 0.89 ± 0.001 on the diabetes dataset using bootstrap evaluation with 1000 resamples.

Towards Transparent Healthcare: Advancing Local Explanation Methods in Explainable Artificial Intelligence.

This paper focuses on the use of local Explainable Artificial Intelligence (XAI) methods, particularly the Local Rule-Based Explanations (LORE) technique, within healthcare and medical settings. It emphasizes the critical role of interpretability and transparency in AI systems for diagnosing diseases, predicting patient outcomes, and creating personalized treatment plans. While acknowledging the complexities and inherent trade-offs between interpretability and model performance, our work underscores the significance of local XAI methods in enhancing decision-making processes in healthcare. By providing granular, case-specific insights, local XAI methods like LORE enhance physicians' and patients' understanding of machine learning models and their outcome. Our paper reviews significant contributions to local XAI in healthcare, highlighting its potential to improve clinical decision making, ensure fairness, and comply with regulatory standards.

CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare

In the era of modern healthcare, swiftly generating medical question summaries is crucial for informed and timely patient care. Despite the increasing complexity and volume of medical data, existing studies have focused solely on text-based summarization, neglecting the integration of visual information. Recognizing the untapped potential of combining textual queries with visual representations of medical conditions, we introduce the Multimodal Medical Question Summarization (MMQS) Dataset. This dataset, a major contribution of our work, pairs medical queries with visual aids, facilitating a richer and more nuanced understanding of patient needs. We also propose a framework, utilizing the power of Contrastive Language Image Pretraining(CLIP) and Large Language Models(LLMs), consisting of four modules that identify medical disorders, generate relevant context, filter medical concepts, and craft visually aware summaries. Our comprehensive framework harnesses the power of CLIP, a multimodal foundation model, and various general-purpose LLMs, comprising four main modules: the medical disorder identification module, the relevant context generation module, the context filtration module for distilling relevant medical concepts and knowledge, and finally, a general-purpose LLM to generate visually aware medical question summaries. Leveraging our MMQS dataset, we showcase how visual cues from images enhance the generation of medically nuanced summaries. This multimodal approach not only enhances the decision-making process in healthcare but also fosters a more nuanced understanding of patient queries, laying the groundwork for future research in personalized and responsive medical care. Disclaimer: The article features graphic medical imagery, a result of the subject's inherent requirements.

Web-Based Geographic Information System for Location Based Healthcare Service Delivery within Akure Metropolis

Purpose: This research project addresses the pressing issue of healthcare access within Akure Metropolis, Nigeria, through the development of a web-based Health Geoinformation System (HGS). Akure, like many urban centers in developing countries, faces significant challenges in healthcare delivery, including uneven distribution of facilities and limited access to reliable health information. In response to these challenges, this study leverages Geographical Information System (GIS) technology to create an innovative solution aimed at enhancing accessibility and information dissemination. Grounded in the context of Nigeria's healthcare system, the research identifies the need for an integrated approach to address the complex spatial dynamics of healthcare provision.
 Materials and Methods: Methodologically, the project combines primary data collection on the characteristics of health facilities in Akure with secondary data sources, including existing health records. A total of 100 healthcare facilities were located and identified for this study, with comprehensive information collected through three sets of questionnaires directed to healthcare facility managers and professionals, hospital management bodies, and the public. The data collection process employed Binary Logistic Regression to test research hypotheses, with charts utilized to represent public responses to the posed questions. Spatial representation and analysis were central to this study, with techniques such as Nearest Neighbor Analysis employed to assess the distribution and accessibility of health facilities.
 Findings: The results from this analysis revealed significant spatial patterns and disparities in healthcare facility distribution within Akure Metropolis. Notably, the study found that a developed web-based system having user-friendly functionalities like facility search, mapping, and route selection, among others, aids individuals in making informed decisions about their healthcare options.
 Implications to Theory, Practice and Policy: The results underline the potential of web-based systems to enhance healthcare access and decision-making processes in urban areas like Akure and further emphasize the significance of incorporating GIS technology into healthcare service delivery.

Making causal inferences from transactional data: A narrative review of opportunities and challenges when implementing the target trial framework.

The target trial framework has emerged as a powerful tool for addressing causal questions in clinical practice and in public health. In the healthcare sector, where decision-making is increasingly data-driven, transactional databases, such as electronic health records (EHR) and insurance claims, present an untapped potential for answering complex causal questions. This narrative review explores the potential of the integration of the target trial framework with real-world data to enhance healthcare decision-making processes. We outline essential elements of the target trial framework, and identify pertinent challenges in data quality, privacy concerns, and methodological limitations, proposing solutions to overcome these obstacles and optimize the framework's application.

A comprehensive review of data analytics in healthcare management: Leveraging big data for decision-making

This research paper presents a comprehensive review of data analytics in healthcare management, focusing on leveraging big data for decision-making. The literature review explores the historical evolution of data analytics, emphasizing its growing importance in clinical support, resource allocation, and operational efficiency within the healthcare sector. The paper discusses fundamental concepts, methodologies, and emerging trends, including integrating artificial intelligence, real-time analytics, and the impact of wearable technologies. Challenges such as data quality, privacy, and interoperability are identified, along with recommendations for future research. The findings underscore the pivotal role of data analytics in transforming healthcare decision-making processes, with implications for precision medicine, preventive healthcare, and enhanced patient outcomes.

Interpretable Medical Imagery Diagnosis with Self-Attentive Transformers: A Review of Explainable AI for Health Care

Recent advancements in artificial intelligence (AI) have facilitated its widespread adoption in primary medical services, addressing the demand–supply imbalance in healthcare. Vision Transformers (ViT) have emerged as state-of-the-art computer vision models, benefiting from self-attention modules. However, compared to traditional machine learning approaches, deep learning models are complex and are often treated as a “black box” that can cause uncertainty regarding how they operate. Explainable artificial intelligence (XAI) refers to methods that explain and interpret machine learning models’ inner workings and how they come to decisions, which is especially important in the medical domain to guide healthcare decision-making processes. This review summarizes recent ViT advancements and interpretative approaches to understanding the decision-making process of ViT, enabling transparency in medical diagnosis applications.

Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records.

This study aimed to develop and validate predictive models using electronic health records (EHR) data to determine whether hospitalized COVID-19-positive patients would be admitted to alternative medical care or discharged home. We conducted a retrospective cohort study using deidentified data from the University of Florida Health Integrated Data Repository. The study included 1,578 adult patients (≥18 years) who tested positive for COVID-19 while hospitalized, comprising 960 (60.8%) female patients with a mean (SD) age of 51.86 (18.49) years and 618 (39.2%) male patients with a mean (SD) age of 54.35 (18.48) years. Machine learning (ML) model training involved cross-validation to assess their performance in predicting patient disposition. We developed and validated six supervised ML-based prediction models (logistic regression, Gaussian Naïve Bayes, k-nearest neighbors, decision trees, random forest, and support vector machine classifier) to predict patient discharge status. The models were evaluated based on the area under the receiver operating characteristic curve (ROC-AUC), precision, accuracy, F1 score, and Brier score. The random forest classifier exhibited the highest performance, achieving an accuracy of 0.84 and an AUC of 0.72. Logistic regression (accuracy: 0.85, AUC: 0.71), k-nearest neighbor (accuracy: 0.84, AUC: 0.63), decision tree (accuracy: 0.84, AUC: 0.61), Gaussian Naïve Bayes (accuracy: 0.84, AUC: 0.66), and support vector machine classifier (accuracy: 0.84, AUC: 0.67) also demonstrated valuable predictive capabilities. This study's findings are crucial for efficiently allocating healthcare resources during pandemics like COVID-19. By harnessing ML techniques and EHR data, we can create predictive tools to identify patients at greater risk of severe symptoms based on their medical histories. The models developed here serve as a foundation for expanding the toolkit available to healthcare professionals and organizations. Additionally, explainable ML methods, such as Shapley Additive Explanations, aid in uncovering underlying data features that inform healthcare decision-making processes.

Budgetary impact of new label indications after initial drug registration in Brazil: A case study of pembrolizumab and trastuzumab deruxtecan

The pharmaceutical landscape has undergone a transformative shift due to emerging technologies, leading to a projected value of USD 405.52 billion for the global pharmaceutical manufacturing market in 2020. Brazil, representing 2% of the global pharmaceutical market, boasts a comprehensive public health system called Sistema Único de Saúde (SUS), ensuring universal health coverage. However, the public and private health sectors in Brazil operate independently, with 23% of Brazilians possessing private health insurance plans. Regulated by the Brazilian Drug Market Regulation Chamber (CMED), which controls drug prices based on international retail prices and other factors, the pharmaceutical market in Brazil faces significant challenges in maintaining the sustainability of the Brazilian health-care system, particularly due to the high costs of cancer medications, such as pembrolizumab and trastuzumab deruxtecan. This study aims to assess the budgetary impact of expanding indications for pembrolizumab and trastuzumab deruxtecan in Brazil after their initial registration by the Brazilian Health Regulatory Agency. Utilizing epidemiological data from the National Cancer Institute (INCA) and clinical trial data, we estimated the eligible patient populations and associated costs for these medications. Trastuzumab deruxtecan’s eligible patient population increased from 383 to 23,000 across various indications, resulting in a total cost increase from USD 90.6 million to USD 5.0 billion. Similarly, pembrolizumab’s eligible patient population expanded from 1796 to 99,544 for multiple indications, causing the total cost increase from USD 121.1 million to USD 6.7 billion. The study highlights the substantial expansions in indications and patient eligibility for trastuzumab deruxtecan and pembrolizumab in Brazil, with significant budgetary implications potentially jeopardizing the health-care system’s sustainability. To ensure the long-term sustainability of health-care systems and to provide equitable access to optimal treatments, it is crucial for policymakers to monitor and adjust drug prices following their initial registration. Policymakers must be aware of these challenges and consider them in health-care policy development and decision-making processes.

Assessing medical doctors' knowledge about medical ethics in health practices

Background: When it comes to protecting patients' rights and ensuring the quality of healthcare, medical ethics are of the utmost importance. Clinical specialists need a solid understanding of clinical morals to adhere to moral guidelines in the delivery of medical care. Objective: The study aims to determine, how well doctors in Lahore, Pakistan, are aware of medical ethics in health practices and their comprehension of healthcare ethical principles, guidelines, and decision-making processes knowledge and contribution. Methods: A cross-sectional review was conducted in Lahore with 350 health professionals from various medical services settings. The survey had unconditional and different decision inquiries to evaluate the comprehension specialists might interpret clinical morals using Medical Ethics Attitude Scale (MEAS). Results The findings of this analysis suggest that the opinions of medical professionals regarding how they adhere to medical ethics vary significantly. The professional respondents' mean score of 2.01 indicates a moderate level of agreement regarding medical ethics. To determine the significance of the differences in the assessment scores, an analysis of variance (ANOVA) was conducted. The ANOVA test resulted in an F-value of 69.87, indicating a highly significant association between the assessment scores and the variables related to knowledge of medical ethics practice.

Patient engagement in decision making and associated factors among outpatients with selected non-communicable chronic diseases in public hospitals of West Shoa, Ethiopia.

Despite the importance of patient engagement in health care decision-making in the care of patients with chronic diseases, there is limited information about it and the factors affecting it in Ethiopia and in the Public Hospitals of West Shoa in particular. Thus, this study was designed to assess the engagement of patients with selected chronic non-communicable diseases in health care decision-making and associated factors in public hospitals of West Shoa Zone, Oromia, Ethiopia. We used an institution -based cross-sectional study design. We used systematic sampling for the selection of study participants from June 7-July 26, 2020. Standardized, pretested, and structured Patient Activation Measure was used to measure patient engagement in healthcare decision-making. We did descriptive analysis to determine the magnitude of patient engagement in health care decision-making. Multivariate logistic regression analysis was used to determine factors associated with patients' engagement in the health care decision-making process. Adjusted odds ratio with a 95% confidence interval was calculated to measure the strength of association. We declared statistical significance at p<0.05. we presented the results in tables and graphs. 406 patients with chronic diseases took part in the study, yielding a response rate of 96.2%. Less than a fifth [19.5% (95% CI: 15.5, 23.6)] of participants in the study area had a high engagement in their health care decision-making. Educational level (college or above) [AOR = 5.2, 95% CI (1.76-15.46)], duration of diagnosis >5 years [AOR = 1.8, 95% CI (1.03-3.2)], health literacy [AOR = 1.15, 95% CI (1.06-1.24)], autonomy preference in decision making [AOR = 1.35, 95% CI (1.03-1.96)] were factors significantly associated with participants' engagement in health care decision making among patients with chronic diseases. A high number of respondents had a low engagement in their health care decision-making. Preference for autonomy in decision making, educational level, health literacy, duration of diagnosis with the disease were factors associated with patient engagement in health care decision making among patients with chronic diseases in the study area. Thus, patients should be empowered to be involved in decision making to increase their engagement in the care.

A novel approach for assessing bias during team-based clinical decision-making.

Many clinical processes include multidisciplinary group decision-making, yet few methods exist to evaluate the presence of implicit bias during this collective process. Implicit bias negatively impacts the equitable delivery of evidence-based interventions and ultimately patient outcomes. Since implicit bias can be difficult to assess, novel approaches are required to detect and analyze this elusive phenomenon. In this paper, we describe how the de Groot Critically Reflective Diagnoses Protocol (DCRDP) can be used as a data analysis tool to evaluate group dynamics as an essential foundation for exploring how interactions can bias collective clinical decision-making. The DCRDP includes 6 distinct criteria: challenging groupthink, critical opinion sharing, research utilization, openness to mistakes, asking and giving feedback, and experimentation. Based on the strength and frequency of codes in the form of exemplar quotes, each criterion was given a numerical score of 1-4 with 1 representing teams that are interactive, reflective, higher functioning, and more equitable. When applied as a coding scheme to transcripts of recorded decision-making meetings, the DCRDP was revealed as a practical tool for examining group decision-making bias. It can be adapted to a variety of clinical, educational, and other professional settings as an impetus for recognizing the presence of team-based bias, engaging in reflexivity, informing the design and testing of implementation strategies, and monitoring long-term outcomes to promote more equitable decision-making processes in healthcare.

Patient preferences for anti-hyperglycaemic medication for type 2 diabetes mellitus in China: findings from a national survey

ObjectiveThis study aimed to investigate the preferences regarding risks, benefits and other treatment attributes of patients with type 2 diabetes mellitus (T2DM) in China when selecting a second-line anti-hyperglycaemic medicine.MethodsA...

On the building of efficient self-adaptable health data science services by using dynamic patterns

Health data science systems are becoming key for supporting healthcare decision-making processes. However, these systems should achieve continuous data processing and adapt their behavior to changes arising in real scenarios. Nevertheless, building this type of self-adaptable systems is not trivial, as it requires integrating data analytics and artificial intelligence with cloud computing tools and security and fault tolerance applications. This produces delays in the processing of data, affecting the information delivery in decision-making processes. In this paper, we present the design and implementation of a method to build self-adaptable data science services by using dynamic patterns. This method includes two models: a construction model and a coupling model. The construction model is based on dynamic parallel patterns to create, at design time, in-memory processing structures including as many applications as needed to meet the non-functional requirements (NFRs), such as security and fault tolerance, established by healthcare organizations without affecting the efficiency of a data science system. In turn, the coupling model converts the in-memory processing structures into software blocks that are coupled with the I/O interfaces of data science systems to support the automatic and transparent continuous management of data for facing changes in the incoming workload during execution time. A prototype was implemented to create self-adaptable health data science systems including in-memory processing structures for managing spirometry studies, tomography images, and electrocardiograms. The performance evaluation showed that the dynamic patterns significantly reduced the response time required to prepare contents with NFR characteristics in comparison with solutions from the state-of-the-art such as Nextflow and Makeflow.

Assessment of quality and reliability of YouTube videos for patient and physician education on inflammatory myositis

IntroductionYouTube is the second most popular search website worldwide to access health information online. This study was undertaken to assess the reliability and quality of information about myositis on YouTube and delineate attributes of useful videos using standard metrics.MethodsWe conducted a thorough search on YouTube using 9 search terms related to myositis. The inclusion criteria were content related to myositis, English language and acceptable audio–video quality. Duplicates and advertisements were excluded from the analysis. Videos were classified as useful, not very useful or misleading and patient narratives. Reliability was determined using the mDISCERN criteria, quality using the Global Quality Scale (GQS) and JAMA system, using appropriate cut-offs (mDISCERN > 4, GQS > 4, JAMA > 3).ResultsOut of a total of 900 videos, 453 were included for the analysis. Seventy-four per cent and 2% provided useful and not very useful information respectively, while 24% were patient narratives. Seventy-one per cent were intended specifically for patients while 69% were for healthcare providers and students.Noteworthily, useful and not very useful videos had similar total views though the number of likes and daily viewership were higher for useful videos (p = 0.024, p = 0.046).Nearly half (47%) of useful videos were by professional medical societies/patient support groups (PSGs) while not very useful ones were by nonmedical media (38%). Physician-predicted usefulness was discordant with score-based usefulness (κ = 0.129). However, GQS emerged as a significant (p = 0.008) predictor of video usefulness in multivariate analysis.ConclusionA large majority of English YouTube videos on myositis provide useful information for patients. Physicians could signpost patients to high-quality useful videos as determined by GQS and sources like professional medical societies and PSGs.Key Points•This study highlights the importance of regulating health information posted online, accessed by millions of people, to gauge the quality of information and to identify and curb misinformation.•It also identifies recommendations for the future for uploading such content on the Internet.•The implications lie in our patients being better informed about their disease as they are important stakeholders in the healthcare decision-making process.

HTA CAPACITY BUILDING IN ASIA: TOWARDS ONE GOAL.

The aim of the 2022 Health Technology Assessment International (HTAi) Asia Policy Forum (APF) was to discuss experiences and challenges around health technology assessment (HTA) capacity building for both HTA agencies and companies in the Asia region and to identify possible solutions as part of a capacity building roadmap. Discussions during the 2022 APF, informed by a pre-meeting survey of HTA agencies and industry attendees from the region, form the basis of this paper. HTA is an essential element of priority-setting in healthcare; however, the scarcity of skilled technical HTA practitioners is a rate-limiting step in the conduct of HTA. The lack of investment in HTA and the political will to mandate the use of HTA in decision-making may be due to a lack of understanding of the value of the HTA process, and how HTA is interpreted and used in the healthcare decision-making process. Increased demand for HTA is created when the value of HTA is recognized. HTA capacity-building challenges may be mitigated by educating stakeholders, particularly policymakers, on the value of, and the need to invest in, HTA as a transparent process to ensure equitable access to health care for all. Investigating a means of funding and implementing an HTA intern program between agencies, in partnership with industry, to facilitate a supportive environment to foster HTA skills and knowledge, build capacity or strengthen existing capacity should be a priority.

METHOD OF PERFORMING THE TRANSACTIONS ON MEDICAL DATA BASED ON BLOCKCHAIN TECHNOLOGIES

Today, healthcare decision-making processes are time consuming and complex. The productivity of health workers can be increased through the use of information technology. It is information technology that can reduce medical errors, provide more reliable solutions, and reduce health care costs. Today, medical information technology must meet 4 requirements: efficiency, safety, novelty and economic benefits. The healthcare sector in Ukraine has long been in need of change, and the many opportunities blockchain technology can help it lead the transformation of this area and meet these 4 requirements. Thus, increased attention to the technology of distributed registries has led to an understanding of the potential of blockchain technology in the health care system. Thus, the current challenge is the need to manage medical data based on blockchain technologies. The conducted state-of-the-art on known decisions on the use of blockchain technologies in the construction of information technology for medical data management showed that, despite a large number of different solutions, effective methods and solutions for medical data management based on blockchain technologies are currently lacking. Thus, improving the efficiency of medical data management by developing methods of medical data management based on blockchain technologies is currently an urgent problem. The aim of this study is to increase the efficiency of medical data management by developing a method of performing transactions on medical data based on blockchain technologies. A method of performing the transactions on medical data based on blockchain technologies has been developed, which consists of the stages of entering information into the blockchain and obtaining information from the blockchain. The developed method of performing the transactions on medical data provides: the ability to decide on the addition of transactions and medical data from the patient to the blockchain; the ability to decide on the issuance of data from the blockchain on request from a doctor

Application of Terror Management Theory to End-Of-Life Care Decision-Making: A Narrative Literature Review.

Patients with serious illnesses often do not engage in discussions about end-of-life care decision-making, or do so reluctantly. These discussions can be useful in facilitating advance care planning and connecting patients to services such as palliative care that improve quality of life. Terror Management Theory, a social psychology theory stating that humans are motivated to resolve the discomfort surrounding their inevitable death, has been discussed in the psychology literature as an underlying basis of human decision-making and behavior. This paper explores how Terror Management Theory could be extended to seriously ill populations and applied to their healthcare decision-making processes and quality of care received.

Financial Health Literacy and the Shared Decision-Making Process in Healthcare

Patient-centered care is the delivery of care that is unique to each patient, individualized to their needs, and established through a shared patient-clinician decision-making process [...].

Federated Learning for Healthcare: Systematic Review and Architecture Proposal

The use of machine learning (ML) with electronic health records (EHR) is growing in popularity as a means to extract knowledge that can improve the decision-making process in healthcare. Such methods require training of high-quality learning models based on diverse and comprehensive datasets, which are hard to obtain due to the sensitive nature of medical data from patients. In this context, federated learning (FL) is a methodology that enables the distributed training of machine learning models with remotely hosted datasets without the need to accumulate data and, therefore, compromise it. FL is a promising solution to improve ML-based systems, better aligning them to regulatory requirements, improving trustworthiness and data sovereignty. However, many open questions must be addressed before the use of FL becomes widespread. This article aims at presenting a systematic literature review on current research about FL in the context of EHR data for healthcare applications. Our analysis highlights the main research topics, proposed solutions, case studies, and respective ML methods. Furthermore, the article discusses a general architecture for FL applied to healthcare data based on the main insights obtained from the literature review. The collected literature corpus indicates that there is extensive research on the privacy and confidentiality aspects of training data and model sharing, which is expected given the sensitive nature of medical data. Studies also explore improvements to the aggregation mechanisms required to generate the learning model from distributed contributions and case studies with different types of medical data.