AMAreti Manataki

Areti Manataki

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Areti Manataki has a total of 76 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Longitudinal physical-mental multimorbidity trajectories by sociodemographic factors: a cohort study using electronic health records in Scotland (2000–2021)

    by Thu Nguyen, Katherine Keenan, Colin McCowan, Michail Papathomas, Areti Manataki

    Multimorbidity, the co-occurrence of two or more chronic conditions, is a pressing global health challenge. However, research capturing the dynamic, longitudinal nature of health trajectories, particularly the intersection of physical and mental domains, remains scarce compared to traditional cross-sectional “snapshots.” Leveraging up to 21 years of electronic health records data from 858,789 Scottish patients in the University of Dundee Health Informatics Centre, we used multistate modelling to explore how individuals transition from a disease-free baseline into multimorbidity, evaluating how age, sex, and socioeconomic status shape these pathways. Overall transition estimates were driven by the younger demographic of our baseline disease-free cohort. The findings highlight the critical role of severe, hospital-contacting mental health conditions in driving early-onset multimorbidity, particularly in young men and socioeconomically disadvantaged groups. These findings underscore the urgent need to prioritise integrated physical-mental care and address upstream structural determinants of health. This temporal approach identifies high-risk populations for targeted early interventions and informs policy initiatives aimed at reducing health disparities.

  • Open Access

    The use of machine learning to predict pharmacological therapy in gestational diabetes: A scoping review

    by Jasmine R. Kirkwood, Natasha Galloway, Robert S. Lindsay, Areti Manataki, Deborah J. Wake, Rebecca M. Reynolds

    Aims: Early identification of pharmacological therapy for gestational diabetes mellitus (GDM), a common pregnancy complication, through machine learning could allow for better therapeutic strategies and improved treatment efficiency. This scoping review aimed to comprehensively review the machine learning models used to predict the need for pharmacological therapy in GDM. Methods: Four electronic databases—Embase, Medline, IEEE Xplore and Web of Science—were searched for publications between 1 July 2007 and 31 August 2024. Studies predicting pharmacological therapy for GDM using machine learning were included. The Joanna Briggs Institute and PRISMA‐ScR checklist was followed, and the Prediction model Risk Of Bias ASsessment Tool (PROBAST) was used to assess quality. Results: Included were 17 studies presenting 44 models, 61.4% (27/44) predicted any pharmacological therapy use and 38.6% (17/44) predicted insulin use alone. All were binary classifiers, and logistic regression was typically used. The overall area under the receiver operating curve had a median of 0.75. Common clinical variables were found to be predictors, such as history of GDM, gestational week at GDM diagnosis, pregestational body mass index, maternal age, HbA1c, fasting and 1 h glucose from 75 g oral glucose tolerance test. Though 65.9% of models were validated, there was a lack of external validation. There was no evidence of clinical application of the models. Conclusion: Logistic regression with common clinical variables was often used to predict pharmacological therapy for GDM. Few models were externally validated or clinically applicable.


  • Open Access

    Visualising Uncertainty of Vaccine Data

    by Qianhui Lin, Peter D. Donnelly, Areti Manataki

    As healthcare data grows more complex, effectively conveying the inherent uncertainties in medical research and clinical decision-making is crucial to avoid misinterpretation. This study explores visualising the effectiveness and safety of the herpes zoster vaccine, focusing on conveying associated uncertainties to the general public. Two visualisation formats (static and interactive) were developed. A questionnaire-based evaluation assessed their effectiveness and impact on vaccination intentions. Both formats effectively conveyed data, with most participants accurately interpreting the information. Vaccination intentions generally declined after viewing the visualisations, indicating that presenting comprehensive information informs decision-making. This study offers a design approach for visualising vaccine data uncertainties, which has the potential to enhance healthcare decision quality regarding vaccination.

  • Open Access

    Analysing Disease Trajectories of Multimorbidity Through Process Mining Techniques: A Case Study

    by Daniel Petrov, Thu Nguyen, Areti Manataki, Colin McCowan

    Multimorbidity is a global public health challenge, where an individual has two or more chronic conditions, making it difficult to treat and manage illnesses. Understanding the disease trajectories of multimorbidity is crucial for providing patient-centred care. Previous research has primarily employed regression-based approaches, which don’t consider the specific diseases involved and the order in which they occur. Process mining was recently proposed to address this gap, showing promising results in modelling disease trajectories across the entire spectrum of diseases. However, that study involved admissions to a single hospital, and hence the size of the dataset was much smaller than what is typically used in population-level studies on multimorbidity. In this paper, we present a case study where process mining techniques are applied to a much larger dataset of patients in Scotland. We present the disease trajectories discovered for the entire population, as well as stratified by sex. We also describe temporal patterns of disease trajectories, including trajectories with rapid progression. Finally, we discuss the experience of employing process mining within a trusted research environment, and we reflect on challenges that we faced when mining disease trajectories based on a large and complex dataset. Our main contribution involves providing additional evidence around the feasibility of disease trajectory modelling through process mining techniques, in particular when a much larger health dataset is involved.

  • Open Access

    The User-Centered Design of a Clinical Dashboard and Patient-Facing App for Gestational Diabetes

    by Jasmine R. Kirkwood, Jane Dickson, Marryat Stevens, Areti Manataki, Robert S. Lindsay, Deborah J. Wake, Rebecca M. Reynolds

    Background: The number of pregnancies affected by gestational diabetes mellitus (GDM) is growing. With the increased use of smartphones and predictive modeling, a mobile health (mHealth) solution could be developed to improve care and management of GDM while streamlining care through risk stratification. Methods: A user-centered mHealth tool was designed from ethnographic observations and 11 semi-structured interviews (six health care professionals [HCPs] and five women with GDM), followed by iterative changes and evaluation from three feedback groups with 31 participants (17 HCPs, 14 researchers) and 13 questionnaires with women with GDM. Results: “MyGDM” includes a clinical dashboard that centralizes the clinic’s patients, highlighting off-target blood glucose and predicting the need for pharmacological intervention. It is linked with a patient-facing app that includes structured education, culturally inclusive language options, and meal ideas. Through the feedback sessions, iterative changes were made around visualization and patient safety, and participants were positive toward the potential user experience. In the 13 questionnaires with women with GDM, 100% said it would fit into their lifestyle and help them manage GDM. Educational resources and the “request a call” functions were well received with 61.5% (8/13) and 69.2% (9/13) saying they were very likely or likely to use these, respectively. Conclusion: A user-centered mHealth tool consisting of a clinical dashboard linked with a patient-facing app for GDM care and management has been designed. Evaluation of the interactive design by end users was positive and showed that it met their needs.


  • Open Access

    Insights into Health Data Science Education: A Qualitative Content Analysis

    by Narjes Rohani, Michael Gallagher, Kobi Gal, Areti Manataki

    Background: Early career researchers in Health Data Science (HDS) struggle to effectively manage their learning process due to the novel and interdisciplinary nature of this field. To date, there is limited understanding about learning strategies in health data science. Therefore, we aim to uncover learning strategies that early career researchers employ to address their educational challenges, as well as shed light on their preferences regarding HDS teaching approach and course design. Method: In this study, we conducted a qualitative content analysis through semistructured interviews with ten early career researchers, including individuals pursuing master’s, PhD, and postdoctoral research programmes in HDS, across two higher education institutions in the United Kingdom. Interviews were carried out in person from June 2023 to August 2023. Data were analysed qualitatively using NVivo software. Descriptive statistics were employed for quantitative analysis. Results: Regarding learning strategies, we identified ten main categories with 22 codes, including collaboration, information seeking, active learning, focus granularity, elaboration, organisation, order granularity, goal orientation, reviewing, and deep learning strategies. Regarding course design and teaching, we discovered four categories with 14 codes, including course materials, duration and complexity, online discussion, and teaching approaches. Conclusions: Early career researchers used a range of learning strategies aligned with well-established learning theories, such as peer learning, information seeking, and active learning. It is also evident that learners in HDS favour interactive courses that provide them with hands-on experience and interactive discussion. The insights derived from our findings can enhance the quality of education in HDS.

  • Open Access

    Feasibility of forecasting future critical care bed availability using bed management data

    by John Palmer, Areti Manataki, Laura Moss, Aileen Neilson, Tsz-Yan Milly Lo

    Objectives: This project aims to determine the feasibility of predicting future critical care bed availability using data-driven computational forecast modelling and routinely collected hospital bed management data.Methods: In this proof-of-concept, single-centre data informatics feasibility study, regression-based and classification data science techniques were applied retrospectively to prospectively collect routine hospital-wide bed management data to forecast critical care bed capacity. The availability of at least one critical care bed was forecasted using a forecast horizon of 1, 7 and 14 days in advance.Results: We demonstrated for the first time the feasibility of forecasting critical care bed capacity without requiring detailed patient-level data using only routinely collected hospital bed management data and interpretable models. Predictive performance for bed availability 1 day in the future was better than 14 days (mean absolute error 1.33 vs 1.61 and area under the curve 0.78 vs 0.73, respectively). By analysing feature importance, we demonstrated that the models relied mainly on critical care and temporal data rather than data from other wards in the hospital.Discussion: Our data-driven forecasting tool only required hospital bed management data to forecast critical care bed availability. This novel approach means no patient-sensitive data are required in the modelling and warrants further work to refine this approach in future bed availability forecast in other hospital wards.Conclusions: Data-driven critical care bed availability prediction was possible. Further investigations into its utility in multicentre critical care settings or in other clinical settings are warranted.