Author: network

  • Bias Discovery in Machine Learning Models for Mental Health

    Bias Discovery in Machine Learning Models for Mental Health

    This article examined how AI can unintentionally reproduce social and demographic biases when applied to mental health prediction. Using benzodiazepine prescriptions as a proxy for conditions such as depression and anxiety, a study analyzed machine learning models trained on patient data to identify systematic disparities.

    It found that women are more frequently predicted to receive such treatments, reflecting gender bias, while the models perform less accurately for minority ethnic groups, indicating representation and evaluation bias. The AI models here are not used to prescribe drugs but rather to predict treatment likelihoods, revealing how bias in healthcare data can lead to inequitable AI performance in the context of depression-related care.

    Learn more about the article here: https://doi.org/10.3390/info13050237


    Reference

    Mosteiro, P.J., Kuiper, J., Masthoff, J., Scheepers, F., & Spruit, M. (2022). Bias Discovery in Machine Learning Models for Mental Health. Inf., 13, 237.

  • Increased risk of short-term depressive disorder after Helicobacter pylori eradication: A population-based nested cohort study

    Increased risk of short-term depressive disorder after Helicobacter pylori eradication: A population-based nested cohort study

    A study using Taiwan’s National Health Insurance data found that antibiotic therapy for H. pylori in patients with peptic ulcer disease was linked to a short-term increase in psychiatrist-diagnosed depression within 30 days. Women and patients treated with clarithromycin were particularly at higher risk.

    The researchers reported that the increased risk of depression after H. pylori eradication therapy may involve alterations in the brain-gut-microbiome axis induced by antibiotic treatment, as is it well known that antibiotics can change the gut microbial composition, metabolism, and function, thereby affecting human health and possibly contributing to the pathophysiology of depression.

    Based on these findings, the authors recommend that clinicians should monitor mental health shortly after H. pylori eradication, as short-term depressive symptoms may occur and be easily overlooked.

    Learn more about this study here: https://doi.org/10.1111/hel.12824


    Reference

    Tsai C-F, Chen M-H, Wang Y-P, et al. Increased risk of short-term depressive disorder after Helicobacter pylori eradication: A population-based nested cohort study. Helicobacter. 2021; 26:e12824.

  • GWAS of peptic ulcer disease implicates Helicobacter pylori infection, other gastrointestinal disorders and depression

    GWAS of peptic ulcer disease implicates Helicobacter pylori infection, other gastrointestinal disorders and depression

    A study of over 450,000 people in the UK Biobank identified 8 independent genes that affect stomach acid, gut movement, and the body’s response to infection, including susceptibility to Helicobacter pylori infection.

    The study also explored connections between these gut conditions and depression, which often occurs alongside digestive problems, providing new insights into the complex interplay between gut health and mental well-being.

    Learn more about this study here: https://doi.org/10.1038/s41467-021-21280-7


    Reference

    Wu, Y., Murray, G.K., Byrne, E.M. et al. GWAS of peptic ulcer disease implicates Helicobacter pylori infection, other gastrointestinal disorders and depression. Nat Commun 12, 1146 (2021)

  • Helicobacter pylori Infection Is Associated with Long-Term Cognitive Decline in Older Adults: A Two-Year Follow-Up Study

    Helicobacter pylori Infection Is Associated with Long-Term Cognitive Decline in Older Adults: A Two-Year Follow-Up Study

    Helicobacter pylori infection is usually known for causing stomach problems, but it may also affect brain health. This research study published in 2023 followed 268 older adults with memory complaints for two years to see whether H. pylori infection was linked to cognitive decline.

    While at the beginning of the study, people with and without H. pylori performed similarly on memory tests, over the two-year follow-up, those with a history of infection showed greater declines in their Mini-Mental State Examination (MMSE) scores. After taking into account age, sex, education, genetic risk factors and common medical conditions, H. pylori infection was still associated with a significantly higher risk of cognitive decline, with infected participants more likely to lose three or more MMSE points and showing a faster rate of decline over time.

    These findings suggest that H. pylori infection may contribute to progressive cognitive deterioration in older adults with memory complaints and may be relevant in understanding pathways linking infection and dementia.

    Learn more about this study here: https://doi.org/10.3233/JAD-221112


    Reference

    Wang J, Yu N-W, Wang D-Z, et al. Helicobacter pylori Infection Is Associated with Long-Term Cognitive Decline in Older Adults: A Two-Year Follow-Up Study. Journal of Alzheimer’s Disease. 2023;91(4):1351-1358.

  • Mental Health, AI & Learning

    Mental Health, AI & Learning

    Proposal: Using Artificial Intelligence tools to support and mediate learning for students with math related difficulties, preventing and minimizing mental health issues.

    Proposed Implementation: 2026 to 2028

    Call: HORIZON-CL2-2025-01 – Culture, Creativity and Inclusive Society – 2025

    Proposed Budget: 3 850 702,80€

    Keywords: Population dynamics, aging, health and society, Social sciences, interdisciplinary, Sociology

    Objective: This interdisciplinary project brings together experts in AI, psychology, education, and policy across eight countries to understand how the timing and availability of support during digital learning influences mathematics anxiety, and to develop scalable, ethical solutions to address it.

    The project will co-design, deploy, and evaluate AI model, a generative LM interactive system and will integrate foundational research, multi-country piloting, psychological analysis, and socio-economic modelling, supported by robust ethics, governance, and dissemination strategies. FAIR-aligned datasets and AI explainability tools will ensure transparency, privacy, and reuse.

    Aligned with Horizon Europe Cluster 2 goals on educational resilience, mental health, and the Digital Education Action Plan, this project delivers new scientific insights, evidence-based policy recommendations, and an ethically grounded digital intervention with EU-wide relevance.

    Partners:

    • Liverpool John Moores University
    • Health Citizens – European Institute
    • Wageningen University
    • Università Degli Studi Di Siena
    • Finnovaregio
    • SYNYO
    • Kepez İlce Milli Egitim Mudurlugu
    • Ibonis European Research Projects
    • Fundación Cibervoluntarios
  • The association between psychological status and the development of early gastric cancer from atrophic gastritis

    The association between psychological status and the development of early gastric cancer from atrophic gastritis

    A recent hospital-based, cross-sectional observational study, was conducted in the Chinese population to explore the potential relationship between psychological state and the progression of atrophic gastritis (AG; caused by H. pylori or not) to early stage gastric cancer (EGC).

    The study included 258 individuals receiving care in the Department of Gastroenterology at The Affiliated Hospital of Xuzhou Medical University between March 2020 and November 2024, and included 173 patients diagnosed with AG and 85 with EGC. Clinical profiles, demographic characteristics, and laboratory indices were initially recorded, and then comparative analyses were conducted between groups.

    Results showed that, compared to the AG group, patients with EGC exhibited significantly higher psychological distress and depressive tendencies. These findings, while not conclusive, imply a possible association between psychological state and the presence of early gastric cancer (EGC) in patients with atrophic gastritis, thus suggesting that they could function as independent indicators and contribute to the malignant progression of EGC in patients.

    Incorporating mental health screening tools could, therefore, offer supplementary value in the broader context of evaluating patients who might carry an increased likelihood of disease progression.

    Learn more about this study here: http://dx.doi.org/10.1097/MD.0000000000045653


    Reference

    Liang, Mengmeng BD; Wang, Juan MD; Li, Rui MD; Yang, Jun MD; Liu, Yuping BD; Zhao, Lian BD. The association between psychological status and the development of early gastric cancer from atrophic gastritis. Medicine 104(45):p e45653, November 07, 2025

  • Scalable Soil Health Restoration

    Scalable Soil Health Restoration

    Proposal: Scalable Soil Health Restoration and Climate Resilience through Biostimulants, Modelling, and Community Networks

    Proposed Implementation: 2026 to 2030

    Call: HORIZON-MISS-2025-05 – Supporting the implementation of the Soil Deal for Europe Mission

    Proposed Budget:    3 688 792,50€

    Keywords: Soil improvement, Soil management, Soil science, ecological capsule system, Soil restoration, Salinity mitigation, Aridity resilience, Biochar engineering, Capsule material science, Digital ecological modelling.

    Objective: The overarching objective is to develop, validate, and demonstrate the ecological capsules system, an integrated soil restoration technology addressing salinity, aridity, and land degradation challenges. The project combines advances in biochar engineering, capsule material science, digital ecological modelling, and socio-economic assessment into a coherent pathway that bridges laboratory innovation with field-scale demonstration and long-term exploitation. 

    Pilot trials will be implemented in three countries, in an area of around 100 000m2, supported by harmonised monitoring protocols and FAIR-compliant data infrastructure. A predictive ecological Digital Twin will integrate field and laboratory data with socio-economic modelling to support decision-making and scaling. Outcomes include measurable improvements in soil organic carbon, salinity reduction, and biodiversity, as well as evidence-based adoption pathways aligned with EU Mission Soil KPIs. By linking technological innovation with policy-relevant impact assessment, the project directly contributes to the Mission Soil ambition of transitioning 75% of EU soils to health by 2030.

    Partners:

    • Panepistimio Dytikis Attikis
    • Scyring, Inc
    • Health Citizens – European Institute
    • University of Glasgow
    • Evenor Tech Sl
    • Agrinewtech Srl
    • Association Green Development and Innovation
    • Cyens Centre of Excellence
    • Periopsis Ltd
    • Cerca Trova
    • Circular Research Foundation Srl Impresa Social
    • Minds & Sparks Gmbh
    • Synyo Gmbh
    • Tech2market Spolka Z Ograniczona Odpowiedzial
    • Cluster for the Development of Start-Ups, Deep Tebg
  • Family Well-Being & Key Gender Drivers on Labour Market

    Family Well-Being & Key Gender Drivers on Labour Market

    Proposal: Advancing Labour Market Accessibility in the Mediterranean

    Proposed Implementation: 2026 to 2029

    Call: HORIZON-CL2-2025-02-TWO-STAGE – Culture, Creativity and Inclusive Society – 2025 – Two-stage

    Proposed Budget:    3 200 000,00

    Keywords: Gender in economics, Social economics, Women and gender studies, key gender drivers, labour market, parenthood, work-life balance, career opportunities, discrimination, capacity building actions, SMEs, key drivers, family well-being, qualitative research, EEN, SDG5

    Objective: The ambition of the project is to provide evidence-based data, through a scientific and comparative in-depth study identifying key gender drivers on career outcomes among parents, analyzing how parenthood affects job opportunities, career growth and well-being and observing how these dynamics vary across countries and social groups, equipping policymakers at local, national, and EU levels with actionable insights and policy recommendations and practical tools.

    Persistent gender inequalities in the labour market will be investigated in Mediterranean regions within specific target countries of the project, Italy, Spain, Portugal, Malta, Turkey and Cyprus, where domestic welfare models, cultural norms and labour market segmentation reinforce gender gaps. The impact of gender asymmetries on relational and psychological well-being in the private and family sphere will also be analysed.

    The project adopts a multi-level approach: the analysis of existing EU data sources and national datasets, followed by a cross-country survey targeting working parents, a qualitative research phase showcasing case studies and capacity-building schemes addressed to SMEs.

    Recent EU data show that the EU had 32.3 million enterprises, employing 160 million persons: micro and small enterprises account for 99%, employing 77.5 million persons, i.e. almost half of the total number of all employed. The EEN Network partners involved in the project have the unique position to reach these actors, whose voice cannot be ignored.

    The project aligns with the EU Gender Equality Strategy 2020-25 and contributes to SDG5 and the European Pillar of Social Rights by promoting equal opportunities, work-life balance, and family well-being across Europe.

    Partners:

    • Consiglio Nazionale Delle Ricerche
    • Health Citizens – European Institute
    • Unione Per la Difesa dei Consumatori APS
    • Federazione Trentina Della Cooperazione SC
    • The Malta Chamber of Commerce and Enterprise AMT
    • Csi Center for Social Innovation Ltd
    • Passport 2 Employability International Foundation
    • INESC TEC – Instituto de Engenharia de Sistemas e Comunicação
    • Federación de Cooperativas y de la Economía Social
    • EGE University
  • The association between H. pylori infection and cognitive deterioration: a systematic review and meta-analysis

    The association between H. pylori infection and cognitive deterioration: a systematic review and meta-analysis

    The association between cognitive decline and H. pylori infection remains controversial, with some evidence suggesting that H. pylori eradication may slow the progression of the disease.

    A new meta-analysis reviewed 16 studies to explore whether H. pylori affects cognitive function and whether cognitive decline is linked to higher rates of infection.

    The analysis found that people with H. pylori infection had a higher risk of cognitive decline, especially when cognitive dysfunction and dementia were combined. However, the infection was not clearly linked to Alzheimer’s disease. Conversely, people with Alzheimer’s disease were more likely to have H. pylori infection than those without, though the association was weaker for other forms of dementia.

    These findings suggest a bidirectional relationship in which H. pylori may contribute to cognitive decline, and certain cognitive conditions may increase susceptibility to infection. The study also highlights the need for more well-designed research to fully understand this complex interaction.

    Learn more about this study here: https://doi.org/10.1186/s40001-025-03160-8


    Reference

    Elhady, M.M., Zidan, A., Rabea, E.M. et al. The association between H. pylori infection and cognitive deterioration: a systematic review and meta-analysis. Eur J Med Res 30, 846 (2025)

  • Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches

    Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches

    A study found that large language models (LLMs) outperform traditional deep neural network (DNN) embeddings in automated depression detection and show reduced gender bias, through racial disparities remain. Among DNN fairness-mitigation techniques, the worst-group loss provided the best balance between overall accuracy and demographic fairness, while fairness-regularized loss underperformed.

    The identified biases affect the fairness and diagnostic reliability of AI systems for mental health assessment, particularly by disadvantaging underrepresented racial and gender groups, mainly Hispanic participants in the case of this research. Such disparities risk perpetuating inequities in automated mental health screening and could undermine trust and validity in clinical or public health applications.

    Learn more about the study here: https://doi.org/10.48550/arXiv.2509.25795


    Reference

    Junias, O., Kini, P., & Chaspari, T. (2025). Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches. 2025 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), 1-7.