Healthcare Decision Support Research Articles

Effectiveness of EHR systems on decision support in primary healthcare: a technology acceptance model 3 perspective.

This study aims to evaluate healthcare practitioners' perceptions of electronic health record (EHR) systems and their effectiveness in supporting clinical decision-making in Tanzanian Primary Healthcare (PHC) facilities. A mixed-methods approach was employed, combining quantitative data from structured questionnaires and qualitative insights from open-ended responses. The study was conducted in the Dodoma region of Tanzania, focusing on a diverse representation of PHC facilities, including district hospitals, health centres and dispensaries. Data were analysed using multiple linear regression for quantitative data, and thematic analysis was applied to qualitative responses. The results revealed that while EHR systems are widely used in Tanzanian PHC facilities, their impact on clinical decision-making remains limited. Only a moderate portion of practitioners perceived EHR systems as effective in decision support, and frequent system use was negatively correlated with user satisfaction. Challenges such as inadequate training and support, system crashes, slow performance and poor usability and integration into clinical workflows were significant barriers to effectively utilising EHR systems. This study contributes to the limited literature on EHR system implementation in low-resource settings, specifically Tanzania, by focusing on decision-support features within EHR systems. The findings offer valuable insights for healthcare policymakers, system designers and practitioners to optimise EHR implementation and improve healthcare outcomes in resource-constrained environments.

Flipping healthcare by including the patient perspective in integrated care pathway design: A scoping review

BackgroundDespite the recognized benefits of integrating patient perspectives into healthcare design and clinical decision support, theoretical approaches and standardized methods are lacking. Various strategies, such as developing pathways, have evolved to address these challenges. Previous research emphasized the need for a framework for care pathways that includes theoretical principles, extensive user involvement, and data from electronic health records to bridge the gap between different fields and disciplines. Standardizing the representation of the patient perspective could facilitate its sharing across healthcare organizations and domains and its integration into journal systems, shifting the balance of power from the provider to the patient. ObjectivesThis study aims to 1) Identify research approaches taken to develop patient-centred, integrated, care pathways supported by electronic health records 2) Propose a socio-technical framework for designing patient-centred care pathways across multiple healthcare levels that integrates the voice of the patient with the knowledge of the care provider and technological perspectives. MethodsThis study conducted a scoping review following the Joanna Briggs Institute guidelines and PRISMA-ScR protocol. The databases PubMed, Scopus, Web of Science, ProQuest, IEEE, and Google Scholar were searched using a key term search strategy including variations of patient-centred, integrated care, pathway, framework and model to identify relevant studies. Eligible articles included peer-reviewed literature documenting methodologies for mapping patient-centred, integrated care pathways in healthcare service design. ResultsThis review summarizes the application of care pathway modelling practices across various areas of healthcare innovation. The search resulted in 410 studies, with 16 articles included after the full review and grey literature search. ConclusionsOur research illustrated incorporating patient perspectives into modelling care pathways and healthcare service design. Regardless of the medical domain, our methodology proposes an approach for modelling patient-centred, integrated care pathways across the care continuum, including using electronic health records to support the pathways.

Optimized Tiny Machine Learning and Explainable AI for Trustable and Energy-Efficient Fog-Enabled Healthcare Decision Support System

The Internet of things (IoT)-based healthcare decision support system plays a crucial role in modern medicine, especially with the rise in chronic illnesses and an aging population necessitating continuous remote health monitoring. Current healthcare decision support systems struggle to deliver timely and accurate decisions with minimal latency due to limited real-time healthcare data and inefficient computational resources. There is a critical need for an optimized, energy-efficient machine learning model that reliably supports remote health monitoring within IoT and fog computing environments. Our study proposes an Optimized Tiny Machine Learning (TinyML) and Explainable AI (XAI) binary classification model for a trustable and energy-efficient healthcare decision support system, leveraging fog computing to optimize performance. The fog-based approach improves response times and enhances bandwidth usage, addressing critical needs such as reduced latency, higher bandwidth utilization, and decreased packet loss. To further improve efficiency, we incorporate the innovative mLZW data compression technique, significantly enhancing data communication efficiency and reducing response time to critical health alerts. However, limited real-time healthcare data records challenge machine learning classification performance. By implementing a TinyML algorithm, our system demonstrates superior performance to other machine learning models. The proposed optimized TinyML model achieves an impressive F1 score of 0.93 for health abnormalities detection, emphasizing its robustness and effectiveness. This paper highlights the potential of TinyML and XAI in delivering robust, trustworthy, and energy-aware healthcare solutions, making significant contributions toward effective remote health monitoring and decision support in fog-enabled IoT networks.Graphical abstract

A novel healthcare decision support system using IoT and ANFIS

A novel healthcare decision support system using IoT and ANFIS

Secure app-based secondary healthcare clinical decision support to deployed forces in the UK Defence Medical Services

BackgroundModern instant messaging systems facilitate reach-back medical support for Defence Medical Services (DMS) by connecting deployed clinicians to remote specialists. The mobile app Pando (Forward Clinical, UK) has been used...

A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis

Proactive analysis of patient pathways helps healthcare providers anticipate treatment-related risks, identify outcomes, and allocate resources. Machine learning (ML) can leverage a patient’s complete health history to make informed decisions about future events. However, previous work has mostly relied on so-called black-box models, which are unintelligible to humans, making it difficult for clinicians to apply such models. Our work introduces PatWay-Net, an ML framework designed for interpretable predictions of admission to the intensive care unit (ICU) for patients with symptoms of sepsis. We propose a novel type of recurrent neural network and combine it with multi-layer perceptrons to process the patient pathways and produce predictive yet interpretable results. We demonstrate its utility through a comprehensive dashboard that visualizes patient health trajectories, predictive outcomes, and associated risks. Our evaluation includes both predictive performance – where PatWay-Net outperforms standard models such as decision trees, random forests, and gradient-boosted decision trees – and clinical utility, validated through structured interviews with clinicians. By providing improved predictive accuracy along with interpretable and actionable insights, PatWay-Net serves as a valuable tool for healthcare decision support in the critical case of patients with symptoms of sepsis.

A predictive algorithm for the analysis of AMR trends and healthcare decision support

Background Translating available AMR surveillance data to observe evolving patterns of microbial resistance to antimicrobial agents while identifying regions at high risk of resistant cases and serving as a decision-support tool is an aspect of AMR surveillance that is rarely explored nationwide and uncommon globally. Therefore, we developed a two-tier dashboard algorithm (PATHFINDER) that can analyse antimicrobial surveillance datasets, observe evolving global spatiotemporal patterns of AMR, and integrate local AMR gene resources to identify functional AMR determinant genes and antibiotic classes from the query organism genome. Methods The Python-based plotly library was used to develop the interactive variables of the Antimicrobial Testing Leadership Surveillance (ATLAS) dataset in an adjustable spatiotemporal environment. A lightweight database containing multiple known resistant genes from the ResFinder database was used as a prototype to identify unique AMR determinant genes from query nucleotide sequences. In R, a function was created to accept query genome sequences and generate Kmers of length 250 using the blaster package. The GPT-4 API plug-in was embedded with adequate prompt parsing for it as an interpretation LLM function. Results AMR trendline plots were designed for invasive infections and customised based on the class of antibiotics and infection types on the surveillance dashboard. The decision-support tool correctly predicted resistant genes with a sensitivity of 75% on pre-confirmed organisms. The observed specificity score (51.5%) was due to the need for more filtering and optimisation and not to PATHFINDER performance. When run against the reference gene dataset containing pre-identified AMR genes, the support tool generated a BLAST table with identified AMR gene determinants in a nucleotide sequence. Conclusions The PATHFINDER algorithm has the potential to revolutionise healthcare decision-making. It can inform targeted interventions, guide antimicrobial stewardship efforts at a national level, promote appropriate antibiotic use, and significantly reduce the risk of resistance development.

Application of artificial intelligence for the classification of the clinical outcome and therapy in patients with viral infections: The case of COVID-19.

With the end of the coronavirus disease 2019 (COVID-19) pandemic, it becomes intriguing to observe the impact of innovative digital technologies on the diagnosis and management of diseases, in order to improve clinical outcomes for patients. The research aims to enhance diagnostics, prediction, and personalized treatment for patients across three classes of clinical severity (mild, moderate, and severe). What sets this study apart is its innovative approach, wherein classification extends beyond mere disease presence, encompassing the classification of disease severity. This novel perspective lays the foundation for a crucial decision support system during patient triage. An artificial neural network, as a deep learning technique, enabled the development of a complex model based on the analysis of data collected during the process of diagnosing and treating 1000 patients at the Tešanj General Hospital, Bosnia and Herzegovina. The final model achieved a classification accuracy of 82.4% on the validation data set, which testifies to the successful application of the artificial neural network in the classification of clinical outcomes and therapy in patients infected with viral infections. The results obtained show that expert systems are valuable tools for decision support in healthcare in communities with limited resources and increased demands. The research has the potential to improve patient care for future epidemics and pandemics.

BRCA mutations and decision regret: a comprehensive analysis of existing research through a scoping review and reflections from a nursing perspective.

Given the significance of healthcare decisions in women with BRCA1 and BRCA2 mutations and their impact on patients' lives, this study aims to map the existing literature on decision regret in women with BRCA1 and BRCA2 mutations. A scoping review was conducted in the following databases: PubMed, Embase, Scopus, CINAHL, Cochrane, and Google Scholar. Inclusion criteria focused on decision regret in the female population with BRCA1 and/or BRCA2 mutations, with no restrictions on the methodologies of the included studies, but only in the English language. The selection process led to the inclusion of 13 studies. The analysis revealed a significant trend toward decision regret among patients facing complex medical choices. The quality of healthcare communication, decision support, and genetic counselling emerged as key factors influencing patients' perceptions and experiences, with direct implications for their quality of life and psychological well-being. The results suggest that these decisions considerably impact patients, both in terms of clinical outcomes and emotional experiences. The investigation highlights the vital importance of a personalized care approach, emphasizing the critical role of managing patients' emotional and psychological complexity. Managing decision regret requires acute attention to individual needs and effective communication to mitigate emotional impact and improve patient outcomes. Insights from a nursing perspective in the analysis of results indicate the need for informed, empathetic, and integrated care that considers the emotional complexity of women with BRCA1 and/or BRCA2 mutations in their lives and health choices.

Enhancing healthcare decision support through explainable AI models for risk prediction

Electronic health records (EHRs) are a valuable source of information that can aid in understanding a patient’s health condition and making informed healthcare decisions. However, modelling longitudinal EHRs with heterogeneous information is a challenging task. Although recurrent neural networks (RNNs) are frequently utilized in artificial intelligence (AI) models for capturing longitudinal data, their explanatory capabilities are limited. Predictive clustering stands as the most recent advancement within this domain, offering interpretable indications at the cluster level for predicting disease risk. Nonetheless, the challenge of determining the optimal number of clusters has put a brake on the widespread application of predictive clustering for disease risk prediction. In this paper, we introduce a novel non-parametric predictive clustering-based risk prediction model that integrates the Dirichlet Process Mixture Model (DPMM) with predictive clustering via neural networks. To enhance the model’s interpretability, we integrate attention mechanisms that enable the capture of local-level evidence in addition to the cluster-level evidence provided by predictive clustering. The outcome of this research is the development of a multi-level explainable artificial intelligence (AI) model. We evaluated the proposed model on two real-world datasets and demonstrated its effectiveness in capturing longitudinal EHR information for disease risk prediction. Moreover, the model successfully produced interpretable evidence to bolster its predictions.

Designing interpretable ML system to enhance trust in healthcare: A systematic review to proposed responsible clinician-AI-collaboration framework

BackgroundArtificial intelligence (AI)-based medical devices and digital health technologies, including medical sensors, wearable health trackers, telemedicine, mobile health (mHealth), large language models (LLMs), and digital care twins (DCTs), significantly influence the process of clinical decision support systems (CDSS) in healthcare and medical applications. However, given the complexity of medical decisions, it is crucial that results generated by AI tools not only be correct but also carefully evaluated, understandable, and explainable to end-users, especially clinicians. The lack of interpretability in communicating AI clinical decisions can lead to mistrust among decision-makers and a reluctance to use these technologies. ObjectiveThis paper systematically reviews the processes and challenges associated with interpretable machine learning (IML) and explainable artificial intelligence (XAI) within the healthcare and medical domains. Its main goals are to examine the processes of IML and XAI, their related methods, applications, and the implementation challenges they pose in digital health interventions (DHIs), particularly from a quality control perspective, to help understand and improve communication between AI systems and clinicians. The IML process is categorized into pre-processing interpretability, interpretable modeling, and post-processing interpretability. This paper aims to foster a comprehensive understanding of the significance of a robust interpretability approach in clinical decision support systems (CDSS) by reviewing related experimental results. The goal is to provide future researchers with insights for creating clinician-AI tools that are more communicable in healthcare decision support systems and offer a deeper understanding of their challenges. MethodsOur research questions, eligibility criteria, and primary goals were proved using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline and the PICO (population, intervention, control, and outcomes) method. We systematically searched PubMed, Scopus, and Web of Science databases using sensitive and specific search strings. Subsequently, duplicate papers were removed using EndNote and Covidence. A two-phase selection process was then carried out on Covidence, starting with screening by title and abstract, followed by a full-text appraisal. The Meta Quality Appraisal Tool (MetaQAT) was used to assess the quality and risk of bias. Finally, a standardized data extraction tool was employed for reliable data mining. ResultsThe searches yielded 2,241 records, from which 555 duplicate papers were removed. During the title and abstract screening step, 958 papers were excluded, and the full-text review step excluded 482 studies. Subsequently, in quality and risk of bias assessment, 172 papers were removed. 74 publications were selected for data extraction, which formed 10 insightful reviews and 64 related experimental studies. ConclusionThe paper provides general definitions of explainable artificial intelligence (XAI) in the medical domain and introduces a framework for interpretability in clinical decision support systems structured across three levels. It explores XAI-related health applications within each tier of this framework, underpinned by a review of related experimental findings. Furthermore, the paper engages in a detailed discussion of quality assessment tools for evaluating XAI in intelligent health systems. It also presents a step-by-step roadmap for implementing XAI in clinical settings. To direct future research toward bridging current gaps, the paper examines the importance of XAI models from various angles and acknowledges their limitations.

Subjective Rationalities of Nonadherence to Treatment and Vaccination in Healthcare Decision-Making.

In this short report contributing to the literature on treatment and vaccination adherence, nonadherence was examined from the perspective of decision-making (DM) practice in healthcare. The objective of this study was to survey the rationalities given for treatment nonadherence and their association with DM practice. The Ottawa decision Support Framework was used as a theoretical background for the study. Multiple choice and open-text responses indicating nonadherence were drawn from vignette survey data. The results have been analyzed and reported as descriptive statistics and findings of data-driven content analysis. The number of observatory units was 1032 in the within-subject study design. DM practice was predominantly associated with nonadherence to vaccination, whereas nonadherence to treatment was consistently associated with attitudinal reasons independent of DM practice. Nonadherence to vaccination was most often rationalized by prior negative experiences in simple DM scenarios. After other DM practices, nonadherence was rationalized by uncertainty and criticism about the benefits of the recommended vaccine. Mistrust toward healthcare providers stood out, first in treatment nonadherence generally and, second, in vaccination nonadherence after simple DM where the final decision was left to the patient. In medical DM, adherence to treatment and vaccination may be achieved through a recognition of patients' previous healthcare encounters and potential trust-related concerns, which could pose a risk for nonadherence. To be able to observe these risks, patient engagement and mutual trust should be priorities in decision support in healthcare.

AI for decision support: What are possible futures, social impacts, regulatory options, ethical conundrums and agency constellations?

Although artificial intelligence (AI) and automated decision-making systems have been around for some time, they have only recently gained in importance as they are now actually being used and are no longer just the subject of research. AI to support decision-making is thus affecting ever larger parts of society, creating technical, but above all ethical, legal, and societal challenges, as decisions can now be made by machines that were previously the responsibility of humans. This introduction provides an overview of attempts to regulate AI and addresses key challenges that arise when integrating AI systems into human decision-making. The Special topic brings together research articles that present societal challenges, ethical issues, stakeholders, and possible futures of AI use for decision support in healthcare, the legal system, and border control.

AI‑based decision support systems and society: An opening statement

Although artificial intelligence (AI) and automated decision-making systems have been around for some time, they have only recently gained in importance as they are now actually being used and are no longer just the subject of research. AI to support decision-making is thus affecting ever larger parts of society, creating technical, but above all ethical, legal, and societal challenges, as decisions can now be made by machines that were previously the responsibility of humans. This introduction provides an overview of attempts to regulate AI and addresses key challenges that arise when integrating AI systems into human decision-making. The Special topic brings together research articles that present societal challenges, ethical issues, stakeholders, and possible futures of AI use for decision support in healthcare, the legal system, and border control.

Deep convolutional neural network and IoT technology for healthcare.

Deep convolutional neural network and IoT technology for healthcare.

Interpretable Model For Decision Support In Healthcare

"In thе rapidly еvolving landscapе of hеalthcarе, thе intеgration of machinе lеarning modеls into dеcision-making procеssеs has shown grеat promisе. Howеvеr, thе black-box naturе of complеx algorithms oftеn impеdеs thеir adoption in critical hеalthcarе scеnarios. This rеsеarch dеlvеs into thе rеalm of intеrprеtablе modеls for dеcision support in hеalthcarе, addrеssing thе pivotal nееd for transparеncy and comprеhеnsion in mеdical dеcision-making. By еxamining divеrsе datasеts and еmploying intеrprеtablе machinе lеarning tеchniquеs such as dеcision trееs, logistic rеgrеssion, and rulе-basеd modеls, this study shеds light on modеls' intеrprеtability without compromising thеir prеdictivе accuracy. Thе findings not only dеmonstratе thе viability of intеrprеtablе modеls in hеalthcarе contеxts but also undеrscorе thеir еssеntial rolе in еnhancing trust bеtwееn hеalthcarе providеrs and artificial intеlligеncе systеms. This rеsеarch advocatеs for a paradigm shift towards thе widеsprеad adoption of intеrprеtablе modеls, thеrеby paving thе way for informеd, rеliablе, and accountablе dеcision support in hеalthcarе practicеs."
 This rеsеarch papеr focusеs on addrеssing this challеngе by еxploring thе rеalm of intеrprеtablе modеls for dеcision support in hеalthcarе. Rеcognizing that mеdical profеssionals and stakеholdеrs rеquirе not only accuratе prеdictions but also clеar еxplanations for thosе prеdictions, intеrprеtablе machinе lеarning modеls such as dеcision trееs, logistic rеgrеssion, and rulе-basеd modеls havе gainеd prominеncе. Thеsе modеls offеr a uniquе advantagе: thеy providе insights into thе factors that influеncе prеdictions, allowing hеalthcarе providеrs to validatе thе rеcommеndations and makе wеll-informеd dеcisions collaborativеly with artificial intеlligеncе systеms.

An Alzheimer’s disease classification model using transfer learning Densenet with embedded healthcare decision support system

Training a Convolutional Neural Network (CNN) from scratch is time-consuming and expensive. In this study, we propose implementing the DenseNet architecture for classification of AD in three classes. Our approach leverages transfer learning architectures as the base model and showcases superior performance on the MRI dataset compared to other techniques. We use a variety of methodologies to provide a thorough study of our model. We first create a performance baseline without data augmentation, addressing the difficulties in classifying Alzheimer’s disease (AD) caused by high-dimensional MRI brain scans. The improved model performance obtained through data augmentation is then highlighted, demonstrating its effectiveness in handling sparse data and assisting in generalization. We also investigate the impact of omitting particular transformations and modifying dataset split ratios, providing more insights into the behavior of the model. Through comprehensive evaluation, we demonstrate that our proposed system model achieves an accuracy of 96.5% and an impressive AUC of 99%, surpassing previous methods. This study mainly highlights the effectiveness of DenseNet architecture, current study limitations and future recommendation. Moreover, incorporating a healthcare decision support system further aid in providing valuable insights for AD diagnosis and decision-making in clinical settings.

How Can Transformer Models Shape Future Healthcare: A Qualitative Study.

Transformer models have been successfully applied to various natural language processing and machine translation tasks in recent years, e.g. automatic language understanding. With the advent of more efficient and reliable models (e.g. GPT-3), there is a growing potential for automating time-consuming tasks that could be of particular benefit in healthcare to improve clinical outcomes. This paper aims at summarizing potential use cases of transformer models for future healthcare applications. Precisely, we conducted a survey asking experts on their ideas and reflections for future use cases. We received 28 responses, analyzed using an adapted thematic analysis. Overall, 8 use case categories were identified including documentation and clinical coding, workflow and healthcare services, decision support, knowledge management, interaction support, patient education, health management, and public health monitoring. Future research should consider developing and testing the application of transformer models for such use cases.

Explainable Deep Learning Models for Healthcare Decision Support

Deep learning has recently become a potent tool in healthcare, excelling at tasks like analyzing medical images, diagnosing diseases, and predicting patient outcomes. The Second Chapter's Literature Review explained Deep Learning in Healthcare: Current Applications and Challenges or Interpretable Techniques in Deep Learning along with Performance Evaluation of Deep Learning Models in Healthcare. It has also done Clinical Standards and Decision Support Systems. The Third Chapter Methodology discusses comprehending the subjective perceptions and interpretations of healthcare professionals regarding Explainable Deep Learning Models (EDLMs) in clinical decision-making, this study employs an interpretive research philosophy

Bayesian monitoring of COVID-19 in Sweden

In an effort to provide regional decision support for the public healthcare, we design a data-driven compartment-based model of COVID-19 in Sweden. From national hospital statistics we derive parameter priors, and we develop linear filtering techniques to drive the simulations given data in the form of daily healthcare demands. We additionally propose a posterior marginal estimator which provides for an improved temporal resolution of the reproduction number estimate as well as supports robustness checks via a parametric bootstrap procedure.From our computational approach we obtain a Bayesian model of predictive value which provides important insight into the progression of the disease, including estimates of the effective reproduction number, the infection fatality rate, and the regional-level immunity. We successfully validate our posterior model against several different sources, including outputs from extensive screening programs. Since our required data in comparison is easy and non-sensitive to collect, we argue that our approach is particularly promising as a tool to support monitoring and decisions within public health.Significance: Using public data from Swedish patient registries we develop a national-scale computational model of COVID-19. The parametrized model produces valuable weekly predictions of healthcare demands at the regional level and validates well against several different sources. We also obtain critical epidemiological insights into the disease progression, including, e.g., reproduction number, immunity and disease fatality estimates. The success of the model hinges on our novel use of filtering techniques which allows us to design an accurate data-driven procedure using data exclusively from healthcare demands, i.e., our approach does not rely on public testing and is therefore very cost-effective.