Andreas Balaskas

Andreas Balaskas

Auto-generated profile, based on publicly available information

Andreas Balaskas

School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2022 in Frontiers in Digital Health
Verified
Journal Article
Open access
ABAndreas Balaskas
Andreas Balaskas
SSStephen M. Schueller
Stephen M. Schueller
ACAnna L. Cox
Anna L. Cox
GDGavin Doherty
Gavin Doherty
Anxiety disorders are the most common type of mental health problem. The potential of apps to improve mental health has led to an increase in the number of anxiety apps available. Even though anxiety apps hold the potential to enhance mental health care for individuals, there is relatively little knowledge concerning users’ perspectives. This mixed-methods study aims to understand the nature of user burden and engagement with mental health apps (MHapps) targeting anxiety management, in order to identify ways to improve the design of these apps. Users’ perspectives on these apps were gathered by analyzing 600 reviews from 5 apps on the app stores (Study 1), and conducting 15 interviews with app users (Study 2). The results shed light on several barriers to adoption and sustained use. Users appreciate apps that offer content variation, customizability, and good interface design, and often requested an enhanced, personalized experience to improve engagement. We propose addressing the specific app quality issues identified through human-centered design, more personalized content delivery, and by improving features for social and therapeutic support.

6 October 2021 in JMIR mHealth and uHealth
Verified
Journal Article
Open access
ABAndreas Balaskas
Andreas Balaskas
SSStephen M Schueller
Stephen M Schueller
ACAnna Cox
Anna Cox
GDGavin Doherty
Gavin Doherty
Background: A range of mobile apps for anxiety have been developed in response to the high prevalence of anxiety disorders. Although the number of publicly available apps for anxiety is increasing, attrition rates among mobile apps are high. These apps must be engaging and relevant to end users to be effective; thus, engagement features and the ability to tailor delivery to the needs of individual users are key. However, our understanding of the functionality of these apps concerning engagement and tailoring features is limited. Objective: The aim of this study is to review how cognitive behavioral elements are delivered by anxiety apps and their functionalities to support user engagement and tailoring based on user needs. Methods: A systematic search for anxiety apps described as being based on cognitive behavioral therapy (CBT) was conducted on Android and iPhone marketplaces. Apps were included if they mentioned the use of CBT for anxiety-related disorders. We identified 597 apps, of which 36 met the inclusion criteria and were reviewed through direct use. Results: Cognitive behavioral apps for anxiety incorporate a variety of functionalities, offer several engagement features, and integrate low-intensity CBT exercises. However, the provision of features to support engagement is highly uneven, and support is provided only for low-intensity CBT treatment. Cognitive behavioral elements combine various modalities to deliver intervention content and support the interactive delivery of these elements. Options for personalization are limited and restricted to goal selection upon beginning use or based on self-monitoring entries. Apps do not appear to provide individualized content to users based on their input. Conclusions: Engagement and tailoring features can be significantly expanded in existing apps, which make limited use of social features and clinical support and do not use sophisticated features such as personalization based on sensor data. To guide the evolution of these interventions, further research is needed to explore the effectiveness of different types of engagement features and approaches to tailoring therapeutic content.

26 January 2023 in PLOS Digital Health
Verified
Journal Article
Open access
PDF file
ABAndreas Balaskas
Andreas Balaskas
SSStephen M Schueller
Stephen M Schueller
ACAnna L Cox
Anna L Cox
CRChuck Rashleigh
Chuck Rashleigh
GDGavin Doherty
Gavin Doherty
The growing number of mental health smartphone applications has led to increased interest in how these tools might support users in different models of care. However, research on the use of these interventions in real-world settings has been scarce. It is important to understand how apps are used in a deployment setting, especially among populations where such tools might add value to current models of care. The objective of this study is to explore the daily use of commercially-available mobile apps for anxiety that integrate CBT, with a focus on understanding reasons for and barriers for app use and engagement. This study recruited 17 young adults (age M = 24.17 years) while on a waiting list to receive therapy in a Student Counselling Service. Participants were asked to select up to two of a list of three selected apps (Wysa, Woebot, and Sanvello) and instructed to use the apps for two weeks. Apps were selected because they used techniques from cognitive behavioral therapy, and offer diverse functionality for anxiety management. Qualitative and quantitative data were gathered through daily questionnaires to capture participants’ experiences with the mobile apps. In addition, eleven semi-structured interviews were conducted at the end of the study. We used descriptive statistics to analyze participants’ interaction with different app features and used a general inductive approach to analyze the collected qualitative data. The results highlight that users form opinions about the apps during the first days of app use. A number of barriers to sustained use are identified including cost-related issues, inadequate content to support long-term use, and a lack of customization options for different app functions. The app features used differ among participants with self-monitoring and treatment elements being the most used features.

1 September 2026 in JMIR Mental Health
Verified
Journal Article
Open access
SBSylvie Bernaerts
Sylvie Bernaerts
FBFien Buelens
Fien Buelens
NWNele A J De Witte
Nele A J De Witte
ABAndreas Balaskas
Andreas Balaskas
TCToon Colman
Toon Colman
TDTom Van Daele
Tom Van Daele
Background: In recent years, innovations in generative AI, in particular large language models (LLMs) in the form of AI chatbots, have found their way to the general public. First studies indicate a growing prevalence of individuals talking to AI chatbots about mental health–related topics; yet, knowledge of how, why, and which individuals are using these AI chatbots for their mental health is limited. Objective: This study aimed to provide insights into the use of AI chatbot–delivered mental health support. Methods: To do so, an online survey in 2 Belgian samples was conducted. A student sample was collected, and individuals who used AI chatbots for mental health support were included (approximately 40% of the student sample were eligible users). Second, a recruitment call for users of AI chatbots for mental health support was launched in the general public. Data from 349 participants, 276 members of the general public, and 73 students were included in the analyses. Results: Descriptive analyses were used to report the use of AI chatbot–delivered mental health support. Most respondents in the present samples were women and indicated having received or receiving professional mental health support. The most common conversation topics across both samples focused on personal and interpersonal issues. Freely accessible AI chatbots, mainly ChatGPT, were the predominant choice in both samples and were mainly chosen for their constant availability and accessibility. Respondents in the student sample also preferred their anonymity, and those in the general sample also used them because they felt supported by them. The preliminary associations found between digital working alliance and engagement factors in the student sample and in the general sample suggest that relational factors might play a role in sustained AI chatbot use but warrant further investigation. Conclusions: To conclude, this study confirms that general-purpose AI chatbots that are not designed or regulated for mental health support, specifically ChatGPT, are being used to obtain social and emotional support, often by individuals already familiar with professional mental health support.

21 November 2025 in JMIR Preprints
Verified
Preprint
Open access
Oluwadara AdedejiOluwadara Adedeji
Oluwadara Adedeji
ABAndreas Balaskas
Andreas Balaskas
DCDavid Coyle
David Coyle
KGKeith Gaynor
Keith Gaynor
MMMark Matthews
Mark Matthews
BACKGROUND The bidirectional relationship between financial circumstances and mental health is well-established but complex. However, the diverse modeling approaches and financial data sources used to examine this relationship have not been systematically reviewed. Understanding these methodological approaches is critical for informing future research studies and developing integrated interventions that improve both financial and mental health outcomes. OBJECTIVE This scoping review synthesizes existing literature on the relationship between money and mental health, with a particular focus on the analytical and modelling methods employed. METHODS We used the PRISMA Extension for Scoping Reviews (PRISMA-ScR) to systematically map literature on money and mental health. Databases searched included PubMed, PsycINFO, IEEE Xplore, ACM Digital Library, and Scopus. Papers were screened against predefined inclusion/exclusion criteria, and data were extracted using a standardized spreadsheet. Synthesis employed deductive analysis guided by our research questions. RESULTS Of 45 papers included, most (n=36, 80%) assessed mental health alongside financial variables such as financial difficulty and strain, while fewer focused on predictive modelling using financial behavioral data (n=5, 11%), macroeconomic factors (n=2, 4%), or intergenerational support (n=2, 4%). Depression was most commonly assessed (n=27, 60%), followed by anxiety, psychological distress, and bipolar disorder. Ground truths were predominantly self-reported questionnaires, with limited use of objective financial data: three papers used gambling site data and only one used bank transaction data. Statistical analysis predominated (78%) (primarily logistic and linear regression) for assessing the relationship between mental health and finance, while 18% employed machine learning or deep learning approaches for prediction. CONCLUSIONS This review confirms the bidirectional money-mental health relationship, identifying associations between financial difficulty, financial behaviours, and mental health outcomes through modelling approaches such as classical statistical analysis and machine learning. The majority of studies focused on the effect of financial difficulty on mental health, with fewer (5) focusing on the manifestations of mental illness on financial behaviour, highlighting a research gap. Significant opportunity exists to leverage objective financial data and diverse analytical approaches, particularly machine learning methods, to better understand this relationship and inform targeted interventions.

22 May 2026 in JMIR Preprints
Verified
Preprint
Open access
CPClaudette Pretorius
Claudette Pretorius
ACAlba Madrid Cagigal
Alba Madrid Cagigal
TCTiago Casaleiro
Tiago Casaleiro
KDKaterina Drakos
Katerina Drakos
EDEglantina Dervishi
Eglantina Dervishi
IBIne Beyens
Ine Beyens
BACKGROUND Digital mental health tools (DMHTs) are increasingly used by young people as first points of contact for mental health support, yet evidence on how their design and implementation collectively shape help-seeking outcomes remains fragmented. OBJECTIVE This umbrella review aimed to synthesise findings from systematic, scoping, and narrative reviews to identify best practices and minimum standards for promoting help-seeking through DMHTs targeting young people aged 12–25. METHODS Following PRISMA guidelines, a comprehensive search of six electronic databases was conducted covering the period 2015–2025, supplemented by grey literature. Methodological quality of included reviews was assessed using AMSTAR 2. RESULTS Twenty-six reviews met the eligibility criteria. Findings indicate that DMHTs improve help-seeking intentions, primarily through enhanced mental health literacy and reduced stigma; however, these improvements do not reliably translate into observable help-seeking behaviour. Key facilitators for engagement included anonymity, privacy, and social connectedness. Best practices identified included co-design with young people, personalisation of content, and clinical moderation. DMHTs were most effective when integrated into established referral pathways, such as school systems or primary healthcare. CONCLUSIONS While DMHTs are effective in improving help-seeking intentions, their real-world impact remains limited, highlighting the need for integrated approaches to design, implementation, and behavioural outcomes. These findings provide actionable guidance for policymakers and practitioners integrating DMHTs into youth mental health systems.