Anna Hermansen

Anna Hermansen

Auto-generated profile, based on publicly available information

Anna Hermansen

BC Cancer Research Institute, Vancouver, BC, Canada

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications

17 December 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
AHAnna Hermansen
Anna Hermansen
SPSamantha Pollard
Samantha Pollard
KMKimberlyn McGrail
Kimberlyn McGrail
NBNick Bansback
Nick Bansback
DRDean Regier
Dean Regier
Background: Evaluating precision oncology outcomes requires access to real-world and clinical trial data. Access is based on consent, and consent is based on patients’ informed preferences when deciding to share their data. Decision-making is often modeled using utility theory, but a complex decision context calls for a consideration of how heuristic, intuitive thought processes interact with rational utility maximization. Data-sharing decision-making has been studied using heuristic theory, but almost no heuristic research exists in the health data context. This study explores this evidence gap, applying a qualitative approach to probe for evidence of heuristic mechanisms behind the health data-sharing preferences of those who have experienced cancer. Exploring qualitative decision-making reveals the types of heuristics used and how they are related to the process of decision-making to better understand whether consent mechanisms should consider nonrational processes to better serve patient decision-making. Objective: This study aimed to explore how patients with cancer use heuristics when deciding whether to share their data for research. Methods: The researchers conducted a focus group study of Canadians who have experienced cancer. We recruited participants through an online advertisement, screening individuals based on their ability to increase demographic diversity in the sample. We reviewed the literature on data-sharing platforms to develop a semistructured topic guide on concerns about data sharing, incentives to share, and consent and control. Focus group facilitators led the open-ended discussions about data-sharing preferences that revealed underlying heuristics. Two qualitative analysts coded transcripts using a heuristic framework developed from a review of the literature. Transcripts were analyzed for heuristic instances which were grouped according to sociocultural categories. Using thematic analysis, the analysts generated reflexive themes through norming sessions and consultations. Results: A total of 3 focus groups were held with 19 participants in total. The analysis identified 12 heuristics underlying intentions to share data. From the thematic analysis, we identified how the heuristics of social norms and community building were expressed through altruism; the recognition, reputation, and authority heuristics led to (dis)trust in certain institutions; the need for security prompted the illusion of control and transparency heuristics; and the availability and affect heuristics influenced attitudes around risk and benefit. These thematic relationships all had impacts on the participants’ intentions to share their health data. Conclusions: The findings provide a novel qualitative understanding of how health data–sharing decisions and preferences may be based on heuristic processing. As patients consider the extent of risks and benefits, heuristic processes influence their assessment of anticipated outcomes, which may not result in rational, truly informed consent. This study shows how considering heuristic processing when designing current consent mechanisms opens up the opportunity for more meaningful and realistic interactions with the complex decision-making context.

1 August 2025
Verified
Report
Closed access
MGMarco Gerosa
Marco Gerosa
AHAnna Hermansen
Anna Hermansen
ALAnni Lai
Anni Lai
ALAdrienn Lawson
Adrienn Lawson
In 2025, Futurewei, LF AI & Data, and LF Research partnered to explore the state of sovereign AI around the world. Based on a global survey and a webinar series, this report captures expert perspectives on and organizational practices in this trend. The data shows that sovereignty is seen as strategically important by the vast majority of organizations and governments worldwide, driven by goals such as data control, national security, economic competitiveness, and regulatory alignment. Open source was identified as the foundation for achieving sovereignty, due to its flexibility, transparency, and control. Importantly, the research concludes that sovereign AI is not about isolation but about maintaining autonomy while engaging in open, community-driven innovation networks. Read the full report for an analysis of what sovereign AI is, how organizations are adopting it, and why global collaboration is essential to its growth.

1 August 2024 in JCO Precision Oncology
Verified
Journal Article
Open access
SPSamantha Pollard
Samantha Pollard
MEMorgan Ehman
Morgan Ehman
AHAnna Hermansen
Anna Hermansen
DWDeirdre Weymann
Deirdre Weymann
EKEmanuel Krebs
Emanuel Krebs
DRDean Regier
Dean Regier
PURPOSE: In Canada, health data are siloed, slowing bioinnovation and evidence generation for personalized cancer care. Secured data-sharing platforms (SDSPs) can enable data analysis across silos through rapid concatenation across trial and real-world settings and timely researcher access. To motivate patient participation and trust in research, it is critical to ensure that SDSP design and oversight align with patients' values and address their concerns. We sought to qualitatively characterize patient preferences for the design of a pan-Canadian SDSP. METHODS: Between January 2022 and July 2023, we conducted pan-Canadian virtual focus groups with individuals who had a personal history of cancer. Following each focus group, participants were invited to provide feedback on early-phase analysis results via a member-checking survey. Three trained qualitative researchers analyzed data using thematic analysis. RESULTS: Twenty-eight individuals participated across five focus groups. Four focus groups were conducted in English and one in French. Thematic analysis generated two major and five minor themes. Analytic themes spanned personal and population implications of data sharing and willingness to manage perceived risks. Participants were supportive of increasing access to health data for precision oncology research, while voicing concerns about unintended data use, reidentification, and inequitable access to costly therapeutics. To mitigate perceived risks, participants highlighted the value of data access oversight and governance and informational transparency. CONCLUSION: Strategies for secured data sharing should anticipate and mitigate the risks that patients perceive. Participants supported enhancing timely research capability while ensuring safeguards to protect patient autonomy and privacy. Our study informs the development of data-governance and data-sharing frameworks that integrate real-world and trial data, informed by evidence from direct patient input.

1 May 2025
Verified
Report
Closed access
AHAnna Hermansen
Anna Hermansen
COCailean Osborne
Cailean Osborne
In a literature review commissioned by Meta, LF Research found that open source AI (OSAI) is widely adopted, cost effective, highly performing, and leads to faster and higher-quality development of tools and models. The study included a comprehensive analysis of academic and industry literature as well as empirical data from previous LF Research surveys to determine existing evidence of the economic and workforce impacts of OSAI. The study assessed these impacts in four areas: Adoption rates: a significant majority (89%) of organizations are using some form of open source in their AI stack and almost two-thirds (63%) of companies are using an open model Economic benefits: OSAI is considered a cost-effective choice as compared to proprietary solutions while increasing productivity and accelerating collaborative innovation Workforce impacts: AI has nuanced impacts on the workforce and is poised to be more of a complement for jobs than a tool to replace jobs Sector-specific insights: AI has unique impacts on healthcare, agriculture, construction, manufacturing, and energy

1 September 2025
Verified
Report
Closed access
AHAnna Hermansen
Anna Hermansen
MGMarco Gerosa
Marco Gerosa
In our series on the value of open source AI, the Linux Foundation partnered with Meta on an analysis of AI in Africa, the Middle East, and Türkiye (AMET). From a literature review of over 100 sources, the analysis provides a picture into the impacts and value of open source AI unique to this region, including: Countries across the region are showing good investment and adoption signals Open source AI benefits both large infrastructure projects in the Middle East and nimble grassroots AI projects in Africa Africa’s young population positions the continent for intense growth Open models are widely used across key sectors to solve issues Read the full report for an overview of open source AI adoption in AMET, the technology’s impacts across the workforce and within sectors, and how the region is currently positioned to embrace AI to solve economic and societal challenges.