Psykisk ohälsa ökar bland ungdomar och unga vuxna, både i Sverige och globalt. Trots detta får många inte det stöd de behöver, eller så når hjälpen fram för sent. Här kan artificiell intelligens (AI) spela en avgörande roll. Inom PadAI-projektet ser vi potentialen i AI-genererad information för att förbättra och göra vården mer träffsäker. För att uppnå detta krävs dock förändringar i såväl arbetssätt som vårdprocesser. Syftet är att använda AI för att identifiera individer med förhöjd risk för psykisk ohälsa och utveckla effektiva, förebyggande insatser som möter dessa utmaningar.

Inom projektet har vi redan gjort flera betydande upptäckter. Bland annat har vi kartlagt vårdresorna för unga vuxna som söker hjälp för psykisk ohälsa. Vi har även identifierat hinder och möjligheter som vårdpersonal ser i samband med implementeringen av AI inom vården för psykisk ohälsa. En central aspekt är hur patienter uppfattar användningen av AI. Vi kommer att presentera nya resultat som visar att unga vuxna med erfarenhet av att söka vård för psykisk ohälsa upplever att AI kan förbättra och effektivisera vårdprocesser samt fungera som stöd i egenvård, men också vilka risker och utmaningar som förknippas med användning av AI i vården.

Vi kommer också att redovisa resultat från vår unika kohortstudie baserad på retrospektiva data från Region Hallands vårdinformationssystem mellan 2010 och 2021. Kohorten omfattar totalt 43 520 patienter i åldern 18–30 år, varav 13 136 har fått diagnoser relaterade till ångest eller depression. Med hjälp av maskininlärningsmodeller har vi analyserat strukturerad data från vårdinformationssystemet och kan bland annat presentera mängden vårdbesök, var patienter söker vård, vilka vårdgivare de träffar, de vanligaste diagnoskoderna samt förskrivningen av läkemedel för dessa patienter.

Vi hoppas att presentationen ska bidra med värdefulla insikter som kan göra en verklig skillnad i vården och fungera som en betydelsefull pusselbit i förståelsen av möjligheter och utmaningar kopplade till användningen av AI i tidiga insatser mot psykisk ohälsa hos unga vuxna. Denna kunskap är av stor relevans för aktörer som arbetar med att utveckla detta område på nationell, regional och lokal nivå.

Aims: The aim of this study was to explore healthcare leaders' perceptions of the contribution of artificial intelligence (AI) to person-centred care (PCC). Methods: The study had an explorative qualitative approach. Individual interviews were conducted from October 2020 to May 2021 with 26 healthcare leaders in a county council in Sweden. An abductive qualitative content analysis was conducted based on McCormack and McCance's framework of PCC. The four constructs (i.e. prerequisites, care environment, person-centred processes and expected outcomes) constituted the four categories for the deductive analysis. The inductive analysis generated 11 subcategories to the four constructs, representing how AI could contribute to PCC. Results: Healthcare leaders perceived that AI applications could contribute to the four PCC constructs through (a) supporting professional competence and establishing trust among healthcare professionals and patients (prerequisites); (b) including AI's ability to facilitate patient safety, enable proactive care, provide treatment recommendations and prioritise healthcare resources (the care environment); (c) including AI's ability to tailor information and promote the process of shared decision making and self-management (person-centred processes); and (d) including improving care quality and promoting health outcomes (expected outcomes). Conclusions: The healthcare leaders perceived that AI applications could contribute to PCC at different levels of healthcare, thereby enhancing the quality of care and patients' health. © Author(s) 2025.

Background: Mental healthcare faces growing challenges due to rising mental health issues, particularly among young adults. AI-based systems show promise in supporting prevention, diagnosis, and treatment through personalized care but raise concerns about trust, inclusivity, and workflow integration. Limited research exists on aligning AI functionalities with healthcare professionals’ needs or incorporating shared decision-making (SDM) into AI-supported mental health services, emphasizing the need for further exploration. Objective: This study aims to explore how AI-based decision support systems can be used in mental healthcare from the perspective of healthcare professionals and in the light of a SDM framework. Methods: A qualitative approach using deductive content analysis was employed. Sixteen healthcare professionals working with young adults participated in semi-structured interviews. The analysis was guided by elements of SDM to identify key needs and concerns related to AI. Results: Healthcare professionals acknowledged both the potential benefits and challenges of integrating AI-based decision support systems into SDM for mental healthcare. Fifteen of 23 SDM elements were identified as relevant. AI was valued for its potential in early detection, holistic assessments, and personalized treatment recommendations. However, concerns were raised about inaccuracies in interpreting non-verbal cues, risks of overdiagnosis, reduced clinician autonomy, and weakened trust and therapeutic relationships. Conclusions: AI holds promise for enhancing triage, patient participation, and information exchange in mental healthcare. However, concerns about trust, safety, and overreliance on technology must be addressed. Future efforts should prioritize human-centric SDM, ensuring AI implementation mitigates risks related to equity, data privacy, and the preservation of therapeutic relationships. © 2025 Auf, Nygren, Lundgren, Petersson and Svedberg.

Background: Globally, young adults with mental health problems struggle to access appropriate and timely care, which may lead to a poorer future prognosis. Artificial intelligence (AI) is suggested to improve the quality of mental health care through increased capacities in diagnostics, monitoring, access, advanced decision-making, and digital consultations. Within mental health care, the design and application of AI solutions should elucidate the patient perspective on AI. Objective: The aim was to explore the perceptions of AI in mental health care from the viewpoint of young adults with experience of seeking help for common mental health problems. Methods: This was an interview study with 25 young adults aged between 18 and 30 years that applied a qualitative inductive design, with content analysis, to explore how AI-based technology can be used in mental health care. Results: Three categories were derived from the analysis, representing the participants’ perceptions of how AI-based technology can be used in care for mental health problems. The first category entailed perceptions of AI-based technology as a digital companion, supporting individuals at difficult times, reminding and suggesting self-care activities, suggesting sources of information, and generally being receptive to changes in behavior or mood. The second category revolved around AI enabling more effective care and functioning as a tool, both for the patient and health care professionals (HCPs). Young adults expressed confidence in AI to improve triage, screening, identification, and diagnosis. The third category concerned risks and skepticism toward AI as a product developed by humans with limitations. Young adults voiced concerns about security and integrity, and about AI being autonomous, incapable of human empathy but with strong predictive capabilities. Conclusions: Young adults recognize the potential of AI to serve as personalized support and its function as a digital guide and companion between mental health care consultations. It was believed that AI would function as a support in navigating the help-seeking process, ensuring that they avoid the “missing middle” service gap. They also voiced that AI will improve efficiency in health care, through monitoring, diagnostic accuracy, and reduction of the workload of HCPs, while simultaneously reducing the need for young adults to repeatedly tell their stories. Young adults express an ambivalence toward the use of AI in health care and voice risks of data integrity and bias. They consider AI to be more rational and objective than HCPs but do not want to forsake personal interaction with humans. Based on the results of this study and young adults’ perceptions of the monitoring capabilities of AI, future studies should define the boundaries regarding information collection responsibilities of the health care system versus the individuals’ responsibility for self-care. © Lena Petersson, Mikael G Ahlborg, Katrin Häggström Westberg.

Background: Artificial intelligence (AI) is increasingly introduced into healthcare, promising improved efficiency and clinical decision-making. While research has mainly focused on AI in hospital settings and physician perspectives, less is known about how AI may challenge the values that guide nursing practices. This study explores nurses’ perceptions of wound care in municipal home healthcare and the opportunities and challenges with the integration of AI technologies into their practices.

Methods: An exploratory qualitative study using semi-structured interviews was conducted with 14 registered nurses from two municipalities in Sweden. Participants were recruited through purposive sampling, and data were collected through individual interviews, either in person or via video call. Interviews were transcribed verbatim and analyzed inductively, inspired by the Gioia methodology. This approach allowed themes to emerge from the data while maintaining close alignment with participants’ perspectives. In a subsequent phase, the data were interpreted through the lens of Mol’s Logic of Care to deepen understanding of the relational, embodied, and adaptive nature of wound care. Ethical approval was obtained, and the study adhered to the Consolidated Criteria for Reporting Qualitative Research (COREQ).

Results: Three interconnected dimensions emerged from the data: relational, embodied, and adaptive practices. Nurses emphasized the importance of relational work in wound care, highlighting the trust and continuity necessary for effective wound care, which AI-driven automation might overlook. Embodied practices, such as sensory engagement through touch, sight, and smell, were central to wound care, raising nurses’ concerns about AI’s ability to replicate these nuanced judgments. Adaptive practices, including improvisation and situational awareness in non-standardized home environments, were presented as challenges for AI integration, as existing digital systems were perceived as rigid and often increased administrative burdens rather than streamlining care.

Conclusions: Home healthcare nurses’ perspectives highlight the complex interplay between technology and caregiving. While AI could support documentation and diagnostic processes, its current limitations in relational, sensory, and adaptive aspects raised the nurses’ concerns about its suitability for wound care in home settings. Successful AI integration should account for the realities of nursing practice, ensuring that technological tools enhance the embodied, relational, and adaptive dimensions of wound care. Applying Mol’s Logic of Care helps illuminate how good care emerges through ongoing, situated practices that resist full automation. Future research could further explore how AI aligns with professional nursing values and decision-making in real-world care settings.

 © The Author(s) 2025.

BACKGROUND: Help-seeking for mental health problems is a complex process that involves handling both personal challenges and dealing with the organizational structure of the healthcare system. The healthcare system is siloed and fragmented, but it is unclear how the challenges are experienced by the young adults and what their healthcare journeys look like. Therefore, the aim of this study was to explore experiences of young adults' healthcare journeys in the context of help-seeking for common mental health problems.

METHODS: In total, 25 young adults (16 women and 9 men) from a student healthcare centre at a Swedish university seeking help for common mental health problems, such as anxiety and depression, were interviewed. A qualitative thematic analysis with an inductive approach was done, and results were abstracted and presented in terms of journey-related metaphors.

RESULTS: The healthcare journeys of young adults were described as Taxi Riding, Commuting, Sightseeing, and Backpacking. Taxi riding and Commuting are defined by going in a straightforward and smooth way in the healthcare system, without major obstacles to care. In contrast, Sightseeing and Backpacking are characterized by more diffuse and negative experiences, where the young adults are not satisfied with the help received from healthcare providers. Help-seeking is not conformant with the design of the healthcare system but steered by a range of factors, including individual experiences and young adults' agency, the available resources at the various healthcare providers, and interaction with healthcare professionals.

CONCLUSIONS: Young adults' healthcare journeys in the context of help-seeking for common mental health problems are related to individual, relational, and organizational factors. Some journeys run smoothly, epitomizing a functioning healthcare system that accommodates a rational help-seeker. Other journeys depict a rigid healthcare system, where the success and nature of the journey primarily depend on individual agency and on not becoming discouraged by obstacles. There is a need for more knowledge on how to support young adults' mental health help-seeking. However, we also need more insights into how the healthcare system can become more receptive and accommodating toward the needs of young adults with common mental health problems. © The Author(s) 2025.

This manuscript delineates the pathway from in-house research on Artificial Intelligence (AI) to the development of a medical device, addressing critical phases including conceptualization, development, validation, and regulatory compliance. Key stages in the transformation process involve identifying clinical needs, data management, model training, and rigorous validation to ensure AI models are both robust and clinically relevant. Continuous post-deployment surveillance is essential to maintain performance and adapt to changes in clinical practice. The regulatory landscape is complex, encompassing stringent certification processes under the EU Medical Device Regulation (MDR) and the upcoming EU AI Act, which imposes additional compliance requirements aimed at mitigating AI-specific risks. Ethical considerations such as, emphasizing transparency, patient privacy, and equitable access to AI technologies, are paramount. The manuscript underscores the importance of interdisciplinary collaboration, between healthcare institutions and industry partners, and navigation of commercialization and market entry of AI devices. This overview provides a strategic framework for radiologists and healthcare leaders to effectively integrate AI into clinical practice, while adhering to regulatory and ethical standards, ultimately enhancing patient care and operational efficiency. © 2024 Elsevier B.V.

Recent advancements in connectivity and automation driven by artificial intelligence (AI) is leading to trans-formative changes in the healthcare sector. This study investigates physicians' experience of AI-based technologies in healthcare. To achieve this objective, we gathered responses through open-ended essays from 326 physicians working in Swedish healthcare. These respondents have experience in using AI technologies for distinct tasks, which include prediction, diagnosis, medical image analysis, text generation, analysis, chatbots, wearable devices, telemedicine and robot assistance. The data was analyzed by thematic coding. The findings show that the physicians' perception towards use of AI in healthcare is influenced by drivers and barriers that are present at macro, organizational, system and personal level. The identified drivers include work task changes, functional aspects, organizational aspects, system characteristics and personal motivators. The barriers include legal and ethical dilemma, organizational readiness, system limitations and personal demotivators. This study leverages paradox theory as a framework to deepen the understanding of the complexities and interconnections between perceived barriers and potential solutions related to AI in healthcare as a contribution to the literature. © 2025 The Authors. Published by Elsevier Ltd.

Background: The electronic medication administration record (eMAR) is an eHealth system that has replaced the traditional paper-based medication administration used in many healthcare settings. Research has highlighted that eHealth technologies can change working methods and professional roles in both expected and unexpected ways. To date, there is sparse research that has explored how nurses and nurse assistants (NA) in home healthcare experience eMAR in relation to their work environment. Aim: The aim was to explore how nurses and nurse assistants experienced their work environment, in terms of job-demand, control, and support in a Swedish home healthcare setting where an electronic medication administration record had been implemented to facilitate delegation of medical administration. Method: We took a qualitative approach, where focus groups were used as data collection method. The focus groups included 16 nurses and nine NAs employed in a Swedish municipality where an eMAR had been implemented 6 months before the first focus groups were performed. The analysis adapted the job-demand-control-support model, by condensing the professionals' experiences into the three categories of demand, control, and support, in alignment with the model. Results: NAs experienced high levels of job demand and low levels of job control. The use of the eMAR limited NAs' ability to control their work, in terms of priorities, content, and timing. In contrast, the nurses described demands as high but manageable, and described having a high level of control. Both professions found the eMar supportive. Conclusion: Nurses and NAs in home healthcare experienced changes in their work environment regarding demand, control, and support when an eMAR was implemented to facilitate delegation of medical administration. In general, nurses were satisfied with the eMAR. However, NAs felt that the eMAR did not cover all aspects of their daily work. Healthcare organisations should be aware of the changes that digitalisation processes entail in the work environment of nurses and NAs in home healthcare. © 2024 The Authors. Scandinavian Journal of Caring Sciences published by John Wiley & Sons Ltd on behalf of Nordic College of Caring Science.

A digital transformation of Swedish healthcare is currently taking place, and artificial intelligence (AI) is meant to solve many of the healthcare sector's challenges. The objective of this paper is to describe and analyze how the boundaries around the physicians' work could change when AI is implemented in healthcare and what boundary work actors on different levels in a healthcare system conduct. We conducted 26 semi-structured interviews with healthcare leaders and 18 with healthcare managers and professionals. The result shows that the leaders, healthcare managers, and healthcare professionals describe different types of boundary work in regard to the implementation of AI. The implementation of AI in healthcare could change the boundaries around the healthcare professionals’ work and generate new kinds of boundary work that could affect the implementation. These findings can inform both practice and policy.