Introduction Internet-based interactive behavioral intervention (IBIBI) has the potential to optimize insulin adherence and improve diabetes outcomes.Objectives This study aims to identify the factors and strategies to facilitate the design and clinical adoption of IBIBI by healthcare professionals (HCPs) and organizations in Qatar and other Gulf Cooperation Council countries.Methodology A three-round Delphi study was conducted using mixed purposive, database-based, and snowball sampling strategy was employed to recruit senior experts in diabetes care, eHealth, social and behavioral sciences, health policy, and decision-making. A total of 42, 450, and 46 experts invited to participate in rounds one, two, and three, respectively. The Integrated Change Model, a well-established behavioral theory, was incorporated to guide the intervention design, thereby strengthening its development, implementation, and evaluation.Results Findings indicate that both intervention content and adoption strategies must be tailored to the needs of individuals and organizations involved in the design and implementation processes. Practical implications The study offers practical guidance for HCPs and program developers to design tailored, internet-based behavioral interventions. It addresses barriers to clinical adoption, including usability, accessibility, and integration with existing healthcare systems. The study also identifies actionable strategies to promote eHealth adoption and highlights interactive design elements that support active patient engagement across diverse clinical practice settings.
IntroductionImproving reproductive health (RH) remains a central priority in health policy agendas and sustainable development goals, particularly in sub-Saharan Africa. Despite growing policy interest, the interrelationships among RH service utilization, household-level determinants, and child health outcomes remain insufficiently understood in the West African context.ObjectivesThis study examines the demand for reproductive health services in selected West African countries, with a specific focus on the complementarity hypothesis. It analyses the associations between a mother's demand for tetanus immunization, her child's birth weight, parental education, and women's decision-making autonomy.MethodologyDrawing on pooled data from the 2018 Demographic and Health Survey (DHS), the study employs a control function model to address potential econometric issues, including endogeneity. The empirical strategy allows for a causal examination of the relationship between antenatal care uptake and birth outcomes, with subgroup analyses conducted to uncover heterogeneous effects.ResultsFindings indicate a positive and statistically significant association between maternal tetanus immunization during pregnancy and child birth weight, supporting the complementarity of antenatal care services with broader reproductive health outcomes. Subgroup analyses reveal distinct effects across specific population groups. Healthcare service demand is found to be significantly enhanced by empowering social factors such as parental education and women's decision-making autonomy, while access-related constraints and persistent patriarchal norms exert adverse effects. Urban-rural disparities in service utilization are rooted in cultural, behavioral, and psychosocial dimensions.Practical implicationsThese findings underscore the need for integrated reproductive health strategies that are equity-focused and behaviorally informed. Policies should prioritize women's empowerment, address structural access barriers, and tailor interventions to account for urban-rural and sociocultural heterogeneity in order to sustainably improve maternal and child health outcomes.
Introduction Mathematical and optimisation models are frequently used to improve hospital planning and capacity management. However, the resulting model-derived solutions are rarely evaluated for their adoption within the real-world context of a hospital. Objectives In this study, we share our experience of an interdisciplinary collaboration between operations research/management science and implementation science, as one way of bridging the gap between technically sound solutions and their practical, sustainable use in healthcare. Methodology We applied implementation science prospectively to anticipate adoption implications at the design stage of a scheduling tool. Specifically, we used the Consolidated Framework for Implementation Research (CFIR) to identify anticipated barriers and facilitators for adopting a mathematically optimised surgery blueprint schedule within a children's hospital. Results Identified anticipated facilitators included strong staff motivation to improve schedules, as well as positive perceptions of an objectively designed mathematical scheduling tool. Barriers included resistance to change among some staff and the demand for more evidence of the schedule's benefits prior to implementation. We identified a strong culture of retaining autonomy in scheduling decisions, as well as operational adjustments made to current scheduling tools. Practical implications Applying CFIR prospectively demonstrated how implementation science frameworks could provide a structured way to anticipate adoption challenges and align technical solutions with organisational realities.
IntroductionIntensive-Care-Units (ICUs) play a vital role in healthcare systems to deliver life-saving care to critical-patients, emergency-patients, and elective-surgical-patients who require specialized post-surgery facilities. Arrivals to this unit and Length-of-Stays(LOS) are both stochastic and affect the occupied capacity of the unit. Because of limited ICU resources, capacity management has paramount importance, involving optimal utilization of available resources.ObjectivesThis paper proposes a stochastic model for capacity management aimed at reducing congestion in ICU through a two-step approach.MethodologyA Multilayer-Perceptron Artificial Neural Network(MLP-ANN) model is employed based on time-series data to address the uncertainty associated with the admission of various patient types and the daily-occupied capacity of the ICU. Then, a stochastic model is developed to determine the ICU occupancy level over the study period. The first stage predictive models' outputs are utilized along with appropriate probability distribution functions for LOSs to account for the uncertainty inherent in serving patients.ResultsWe recommend policies to control the arrival of the elective-surgical-patients who require admission to ICU, to manage bed capacity. The results indicate a reduction (at least 1.6% per day) in congestion within the unit.Practical ImplicationsWe provide guidelines (e.g. protocol-driven OR-ICU-coordination) for decision-makers to more efficiently manage the ICU.
IntroductionElectronic Health Records and claims data are increasingly used for research, though not designed for this purpose. These data result from complex interactions between healthcare professionals and Information Technology (IT), but the impact of these interactions on data quality remains insufficiently conceptualized.ObjectivesWe address this gap by analysing how data are recorded and integrated within Clinical Information Systems. (CISs).MethodologyInformed by Failure Modes and Effects Analysis, we decomposed the data recording process, identified components involved at each step, and analysed potential failures through focused literature searches. Failures were classified using an established framework to assess their effect on data quality.ResultsWe identified four steps: administrative enrolment, data acquisition during care, data assembly into stay records, and aggregation into a patient record. Risks included IT failures, confusing software settings (e.g. values carried forward by default), human-computer interaction issues and system-level factors such as database management or IT system updates. While the literature provided practical examples of these failures, few studies quantified their impact.Practical ImplicationsThrough this study, we elucidate the mechanisms by which CISs influence healthcare data quality and highlight their broader sociotechnical implications of the reuse of real-world data in research.
IntroductionHeart disease remains one of the leading causes of mortality worldwide, necessitating accurate and early prediction systems. Traditional methods often fail to effectively integrate diverse clinical data sources, creating a need for advanced, scalable solutions.ObjectivesThis study aims to develop a High-Performance Computing (HPC)-based Clinical Decision Support System (CDSS) for improved heart disease prediction using multi-modal healthcare data.MethodologyThe proposed system utilizes the Symile MIMIC dataset, which includes Electronic Health Records (EHR), time-series ECG signals, and medical imaging data. Categorical variables are encoded using label encoding techniques. Feature extraction is performed using specialized models: AlexNet for medical images, Gated Recurrent Units (GRUs) for ECG time-series data, and a Feedforward Neural Network (FNN) for EHR data. The extracted features are integrated through a weighted feature fusion approach to enhance predictive performance. The model is implemented in Python and evaluated using standard performance metrics.ResultsExperimental findings demonstrate high predictive performance, achieving accuracy values of 0.987 and 0.988 for 70/30 and 80/20 training-testing splits, respectively, along with strong sensitivity, specificity, and precision.Practical ImplicationsThe proposed system offers a reliable and scalable solution for clinical decision-making, enabling early detection and improved management of heart disease in real-world healthcare settings.
Patient satisfaction has been highlighted as an important indicator of healthcare delivery quality and a direct predictor of patient revisiting intentions. The present study aims to provide insight concerning the interaction between service quality, patient satisfaction and revisiting intentions, in the setting of hospital Emergency Departments (EDs). More specifically it (a) compares two public EDs, one urban and one rural; (b) identifies the quality dimensions that are perceived as valuable from patients and highlights their relative importance, (c) investigates the reasons behind poor service quality. A newly-developed conceptual framework is proposed and empirically tested, using primary data collected from 169 ED patients of two different hospitals. Empirical results provide valuable insight into the relationship between perceived service quality and patient revisiting intentions, by examining the mediating effects of patient satisfaction.
The rapid evolution of artificial intelligence (AI) is reshaping healthcare by improving diagnostics, patient outcomes, and operational efficiency. Yet, many frameworks for AI adoption overlook the complex and iterative nature of healthcare systems. This study introduces the AI Healthcare Symbiosis Cycle (AI-HSC), a novel framework based on Dynamic Capabilities Theory, Systems Theory, and Kotter's 8-Step Change Model, conceptualising AI adoption as a continuous and adaptive process. Dynamic Capabilities Theory highlights the need for organisations to sense opportunities, seize resources, and change processes in response to AI advancements. Systems Theory focuses on optimising interdependencies within healthcare organisations, while Kotter's model ensures a structured approach to managing change. The AI-HSC aligns phases of AI integration - initiation, integration, evolution, and revolution - with Kotter's steps, promoting a systematic and scalable adoption strategy. Key recommendations include implementing pilot programs, fostering interdisciplinary coalitions, embedding AI literacy into organisational culture, and developing robust ethics and compliance frameworks. By bridging theory with practice, the AI-HSC provides actionable strategies for sustainable AI integration, addressing critical barriers and fostering continuous innovation. This research contributes to the digital change discourse, offering valuable insights for academia and healthcare practitioners.
This paper presents a community pharmacy information system to assist with medication dispensing and monitoring medication adherence. The proposed prototype uses artificial intelligence (AI), cloud, and mobile technology to support patient medication records, reduce medication errors when preparing pillboxes, and provide personalized information to end-users. Action design research was selected to understand how innovative dispensing processes can be deployed in community pharmacies. The results include design guidelines for AI-enabled medicine dispensing and an evaluation of digital transformation success factors in this vital healthcare sector. AI-enabled systems can contribute to (1) prevent errors in filling pillbox compartments, (2) provide an additional cross-check in medication dispensing, and (3) identify medication adherence problems in more demanding scenarios of institutions with multiple patients. However, there are also relevant challenges, making the replacement of non-critical manual tasks, complementary checkpoints, and pre-validation stages of medicine dispensing the most promising use cases for artificial intelligence adoption.
This study investigates social metrics and features of mental health mobile applications (mHealth apps), a growing digital health tool used by individuals often facing social stigma, barriers to care, and the need for privacy-preserving support. Drawing on an app-derived dataset of 434 mental mHealth apps, we developed a conceptual framework to examine a comprehensive set of 35 app metrics and feature characteristics relevant to mHealth apps' user ratings, functionality, ease-of-use, credibility, privacy assurance, and monetization and test whether these app attributes can explain the patients' intention-to-use (download) these apps. Data collection provides a detailed map of these apps current state-of-the-art. Results indicate that app downloads positively relate to stars rating and user evaluations, app's description length, number of screenshots and readability in the app store, app's age, recent updates and developer information. Interestingly, features related to functional support, privacy, monetization and expert endorsement are not found significant. These findings offer preliminary guidance for developers and organizations aiming to create effective mental mHealth apps, while also advancing the dialogue on assessment criteria to support informed choices by patients and clinicians. By emphasizing objective app data and design features, we highlight how digital health tools shape help-seeking behaviours, particularly among vulnerable populations.
Outpatient chemotherapy is experiencing increased demand while available resources are limited and costly. It is important to have efficient planning for outpatient chemotherapy to optimize the utilization of resources while maintaining the optimal quality of care services. This paper provides a comprehensive review of research studies on outpatient chemotherapy planning (OCP) and decision making. A total of 1,262 articles were retrieved from the most prominent databases (Scopus, PubMed, Web of Science, and Science Direct) and other resources, 99 of which passed the inclusion criteria and were included in this study for analysis. A bibliometric analysis was subsequently conducted with a comprehensive classification of studies based on several predefined criteria that included decision level, problem scope, performance metrics and objectives, complexity factors, methodology, and solution methods. The papers are reviewed in structured categories to provide a detailed overview of this field and highlight the areas that need to be focused on, and the gaps and limitations are summarized. Finally, future research trends on OCP and several promising lines of research that are worthy of study in the future are identified and discussed.
Recent research has revealed how operational research (OR) models and methods have been successfully applied to model alcohol consumption and its consequences (ACC). However, to date, there is no systematic review of OR methods to model ACC that can provide a broad overview of the utilisation of OR methods in this field. In this paper, we contribute to the OR literature as follows. Firstly, we provide a structured taxonomy which helps categorising the literature. Secondly, we conduct a systematic and reproducible search to identify publications that have utilised OR methods to model ACC. Thirdly, we categorise the relevant publications using the taxonomy and provide a dataset of the classification. Our findings highlight that recent research has focused on modelling consumption behaviours, particularly by utilising graph and network methods. Moreover, previous research has been predominantly led by the social sciences and public health fields and less so by the OR domain. Our results reveal gaps in the literature, including limited whole systems modelling and scarce interdisciplinary collaboration across research domains. The development of a future research agenda using our taxonomy and literature review may help closing these gaps and, ultimately, improve planning decisions to improve health, social care, and crime systems.
Polycystic ovary syndrome (PCOS) is a common endocrine disorder that affects women of reproductive age and often leads to complications such as infertility, metabolic disorders, and hormonal imbalance. Early and accurate diagnosis of PCOS is crucial for effective treatment and control. In this study, we propose a novel hybrid deep learning model that integrates TabNet and BiLSTM with an attention mechanism for PCOS detection. The proposed model effectively captures both tabular data dependencies and sequential patterns and achieves an accuracy of 93.45%. To verify its effectiveness, we compare our model with several traditional machine learning and deep learning approaches, including Random Forest, XGBoost, CatBoost, CNN, RNN, and BERT. The experimental results show that our model outperforms these baselines in terms of accuracy, precision, recall, and F1-score. Integrating the interpretability of TabNet with the sequential learning capability of BiLSTM improves the representation of features.
The World Population Prospects (2022) report by the United Nations highlights a decline in global population growth, underscoring the critical role of healthcare systems in reducing maternal and infant mortality rates. While birth rates vary across high-income and low- and middle-income countries, ensuring safe childbirth remains a fundamental healthcare objective. Despite the known risks associated with unnecessary caesarean sections, their prevalence continues to rise in developing countries. This study examines the underlying factors contributing to this trend, using Iran as a case study. A systems approach is employed, incorporating Causal Loop Diagrams (CLDs) and the Decision Making Trial and Evaluation Laboratory (DEMATEL) to identify and prioritise key influencing factors. The findings suggest that societal and cultural dynamics play a more significant role in the increasing rates of unnecessary caesarean sections than technical medical considerations and individual preferences. Notably, the influence of word-of-mouth and support from reference groups underscores the importance of a community-focused approach in addressing this challenge.
PurposeThis research investigates ChatGPT-4o reliability in analyzing medical data for diabetic patients at risk of limb loss. It evaluates whether a generative AI tool can serve as a viable alternative to traditional statistical methods for predictive medical analysis. The research question is: How does ChatGPT-4o perform in answering predictive questions about patient outcomes compared with a professional statistician using conventional tools?MethodsData were drawn from Sheba Medical Center's diabetic foot clinic, focusing on mortality and amputation risk. ChatGPT-4o's predictive responses were compared with those produced by a professional statistician. The study emphasized the importance of prompt design and required substantial human involvement in data cleaning to ensure accuracy.ResultsChatGPT-4o produced accuracy comparable to traditional statistical methods when prompts were well-designed. Findings highlight the central role of prompt engineering in obtaining reliable outputs. Human intervention in preparing the dataset remained necessary, underscoring current limitations in fully automating the process.ConclusionThe study demonstrates the potential of generative AI-specifically ChatGPT-4o-as a tool enabling clinicians to analyse medical data without advanced technical training. With proper instruction and careful prompt engineering, generative AI can help democratize access to predictive medical analysis as a user-friendly alternative to conventional methods.
