JSJulie E. M. Swillens

Julie E. M. Swillens

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Julie E. M. Swillens has a total of 56 co-authors. Here are the top co-authors by number of shared publications:

  • Iris D. Nagtegaal

    Department of Pathology, Radboud Institute for Molecular Life Sciences (RIMLS), Radboud University Medical Centre, Nijmegen, the Netherlands

    3 shared publications
  • Iris D. Nagtegaal

    Department of Pathology Radboud university medical center Nijmegen The Netherlands

    3 shared publications
  • Rosella P. M. G. Hermens

    Scientific Center for Quality of Healthcare (IQ Healthcare), Radboud Institute for Health Sciences (RIHS), Radboud University Medical Centre, Nijmegen, The Netherlands

    3 shared publications
  • Aura Timen

    Department of Primary and Community Care, Radboud University Medical Center, Geert Grooteplein Noord 21, Nijmegen, 6525EZ, The Netherlands, 31 0243618181

    2 shared publications
  • Babette van Deursen

    Department of Primary and Community Care, Research Institute for Medical Innovation, Radboud University Medical Center, Nijmegen, the Netherlands

    2 shared publications
  • Cornelia H. M. van Jaarsveld

    Department of Primary and Community Care, Research Institute for Medical Innovation, Radboud University Medical Center, Nijmegen, the Netherlands

    2 shared publications

Latest Publications

  • Open Access

    Consensus-Based Minimum Requirements for the Adoption of a Computational Pathology Algorithm for Tumor Budding in Colorectal Cancer: An Early Health Technology Assessment

    by Julie E.M. Swillens, Iris D. Nagtegaal, Alessandro Lugli, Jeroen A.W.M. Van der Laak, Marcia Tummers

    PURPOSE: Tumor budding (TB) is an independent prognostic biomarker for colorectal cancer (CRC), yet its clinical adoption is limited by labor-intensive and subjective visual scoring. Computational pathology (CPath) algorithms using deep learning offer potential to improve efficiency and reproducibility. Using an international Delphi study, we established consensus requirements to guide validation and clinical adoption of CPath algorithms, aiming to enhance diagnostic accuracy and patient care. METHODS: A two-round international Delphi process was conducted, involving international experts, to reach consensus on predefined statements. In round 1, baseline characteristics were collected and participants were asked to rank statements representing the minimal requirements for the implementation of a CPath algorithm for TB assessment. After completion of this round, participants received a personalized feedback report summarizing interim results for items that lacked consensus. In round 2, participants re-evaluated their initial responses to statements without consensus, in the light of anonymized group feedback provided in their personalized report. RESULTS: Fifty-nine pathologists participated in round 1, with a 90% response rate in round 2. Consensus was reached for 21 of 29 (72%) minimal requirements. All reached consensus by agreement. Eight statements (28%) remained without consensus after round 2. CONCLUSION: Agreement was reached on the technical, organizational, ethical, and legal aspects, although some requirements were not agreed upon. This highlights the importance of evaluations that take specific contexts into account, as well as the need for continuous stakeholder engagement throughout the development and implementation phases.

  • Open Access

    The process of implementing AI in healthcare: a scoping review of facilitators, barriers, and future directions (Preprint)

    by Daniel Gyllenhammar, Julie Swillens, Jens Nygren, Ingrid Larsson, Victoria Sandholm, Kitty Balazadeh, Sofia Johansson, Petra Svedberg

    BACKGROUND Artificial intelligence (AI) is rapidly reshaping healthcare, offering tools to enhance diagnostic accuracy, streamline clinical workflows, and personalize care delivery. However, real-world AI implementation remains limited, hindered by organizational, technical, and sociocultural barriers that implementation science has only begun to address systematically. OBJECTIVE This scoping review maps the intersection of AI and implementation science in healthcare, examining the types of AI technologies deployed, their intended use, and the processes by which these tools are implemented into practice. METHODS Following PRISMA-ScR guidelines, we synthesized empirical evidence from 65 studies published between December 2011 and March 2025. Searches were performed across the databases CINAHL, PubMed, PsycINFO, Scopus, and Web of Science using the terms Artificial Intelligence, Healthcare, implementation, and empirical, combined with relevant synonyms. RESULTS AI implementation research has expanded rapidly, predominantly in high-income countries, raising important questions about global equity. The most common application areas were automation and optimization (40%), computer vision (34%), and human language technologies (20%), primarily targeting clinical care (68%) and health systems management (25%). Most systems were designed for low-action autonomy (62%), emphasizing human-in-the-loop decision-making. Intended users were physicians (43%), nurses (26%), and radiologists (25%), while patients appeared as intended users in only 11% of implementations. Across the 65 studies, 40 barriers and 55 facilitators were identified across five themes: the AI system itself, healthcare professionals, patients, organizational context, and the macro level. Organizational factors and multidisciplinary stakeholder engagement emerged as the most critical enablers of successful adoption. Key barriers included insufficient AI performance, lack of transparency and explainability, limited IT infrastructure, and inadequate workflow integration. Patient-level and governance-level barriers, including data privacy and regulatory uncertainty, remained underexplored. Only 20% of studies applied theoretical implementation frameworks, and most analyses were conducted retrospectively. Mapping via the AIGENT framework revealed a disproportionate focus on workflow alignment and outcome evaluation, with comparatively little attention to early-phase activities such as needs assessment, adaptation planning, and stakeholder approvals. CONCLUSIONS The current literature predominantly focuses on implementation evaluation and workflow alignment, while patient perspectives, governance conditions, and early implementation activities are underexplored. The finding that only 20% applied theoretical implementation frameworks, mostly retrospectively, reflects a gap between theory and practice and points to a need to apply them prospectively across the full implementation process. From a practitioner perspective, AI implementation should be seen as a sociotechnical and governance process that requires technical, contextual, and system knowledge, rather than merely a technical deployment.


  • Open Access

    Feasibility and Implementation of an eHealth Dashboard for the Remote Monitoring of Dutch Patients With Chronic Myeloid Leukemia: Multimethods Approach

    by Lynn Verweij, Julie E M Swillens, Sanne J J P M Metsemakers, Yolba Smit, Esri Wener, Geneviève I C G Ector, Rosella P M G Hermens, Nicole M A Blijlevens

    Background: Chronic myeloid leukemia (CML) has evolved into a chronic condition as a consequence of effective tyrosine kinase inhibitor (TKI) therapy, leading to an expanding demographic of patients necessitating lifelong monitoring. The use of eHealth solutions has the potential to facilitate sustainable and patient-centered care by enabling remote monitoring and enhancing guideline adherence. The Dutch CMyLife digital care platform incorporates a CML Dashboard intended for health care professionals (HCPs). This dashboard is designed to provide insight into real-world CML care and enable remote monitoring. Objective: This study aimed to evaluate the feasibility of the CML Dashboard for remote monitoring of CML care, to assess the usefulness of dashboard-derived data, and to identify barriers and facilitators for its implementation in routine clinical practice. Methods: We conducted a multimethods early-stage evaluation, determining the feasibility of the CML Dashboard and its barriers and facilitators. Quantitative data were generated through the CMyLife app and displayed in the CML Dashboard. These data were collected over a 2.5-year period and analyzed descriptively. Concurrently, semistructured interviews were conducted with HCPs treating patients with CML to explore barriers and facilitators for implementation. The analysis of interview transcripts was conducted using framework analysis, using established implementation models. Results: Of the 199 patients who were registered, 177 provided data to the dashboard. The dashboard provided insight into patient characteristics, TKI treatment, BCR::ABL1 values, and monitoring intervals. However, the completeness and reliability of the data were limited, as the majority of the data were manually entered by the patients. The absence of complete data and the presence of inconsistencies in monitoring time points reduced the immediate usability of the dashboard for clinical decision-making and quality monitoring. A total of 8 HCPs participated in the interviews. The facilitators included an enhanced overview of patient data, support for consultation preparation, and the potential for remote monitoring and quality improvement. Key barriers identified were the lack of integration with electronic medical records, the necessity for additional log-in procedures, the limited adoption of the app by patients, and the perception of its added value as being inferior to existing systems. Conclusions: The prospect of implementing a remote monitoring system for CML care holds promise. Such a system, using a digital dashboard, has the potential to enhance oversight and contribute to the enhancement of quality assurance. Nonetheless, the implementation of automated data exchange with electronic medical records, enhanced data completeness, and the augmentation of integration into clinical workflows are imperative prior to the large-scale implementation and the transition toward home-based CML care.

  • Open Access

    AI-Generated Responses to Patient's Messages: Effectiveness, Feasibility and Implementation

    by Kim J.M. Bladder, Arie C. Verburg, Milou Arts-Tenhagen, Rene Willemsen, Guido B. van Den Broek, Chantal M.L. Driessen, Rieke J.B. Driessen, Bas Robberts, Arthur R.T. Scheffer, Arjen P. de Vries, et al.

    Background Generative artificial intelligence (GenAI) in healthcare may reduce administrative burden and enhance quality of care. Large language models (LLMs) can generate draft responses to patient messages using electronic health record (EHR) data. This could mitigate increased workload related to high message volumes. While effectiveness and feasibility of these GenAI tools have been studied in the United States, evidence from non-English contexts is scarce, particularly regarding user experience. Objective This study evaluated the effectiveness, feasibility and barriers and facilitators of implementing Epic's Augmented Response Technology (Art) GenAI tool (Epic Systems Corporation, Verona, WI, USA) in a Dutch academic healthcare setting among a broad range of end users. It explored healthcare professionals' (HCP) usage metrics, expectations, and early user experiences. Methods We conducted a hybrid type 1 effectiveness-implementation design. HCPs of four clinical departments (dermatology, medical oncology, otorhinolaryngology, and pulmonology) participated in a six-month study. Effectiveness of Art was assessed using efficiency indicators from Epic (including all InBasket users in the hospital) and survey scales measuring well-being and clinical efficiency at three time points: PRE, POST-1 (1 month), and POST-2 (4 months). Feasibility of Art was evaluated through adoption indicators from Epic and survey scales on use and usability. Barriers and facilitators of Art implementation were collected through the survey and thematized using the NASSS framework (Nonadoption, Abandonment, Scale-up, Spread and Sustainability). Results 237 unique HCPs generated a total of 8,410 drafts. Review and drafting times were similar for users with and without Art, indicating minimal differences. Perceived clinical efficiency declined significantly from PRE to POST-2, while well-being remained unchanged. Adoption was initially high but decreased over time, averaging 16.7% across departments. Usability and intention-to-use scores also declined significantly. Qualitative findings highlighted time savings, well-structured drafts, and patient-centered language as facilitators. Reported barriers included limited impact on time, low practical utility, content inaccuracies, and style misalignment. Conclusions This evaluation of a GenAI tool for patient-provider communication in a non-English academic hospital revealed mixed perceptions of effectiveness and feasibility. High initial expectations contrasted with limited perceived impact on time-savings, well-being and clinical efficiency, alongside declining adoption and usability. Barriers and facilitators revealed contrasting views. These findings underscore the need for a workflow for the handling of user feedback, guidance on clinical responsibilities, along with clear communication about the tool's purpose and limitations to manage expectations. Additionally, establishing consensus on a set of quality indicators and their thresholds that indicate when a GenAI tool is sufficiently robust will be critical for responsible scaling of GenAI in clinical practice.


  • Open Access

    Data-Driven Infectious Disease Control: Qualitative Study of Professionals’ Attitudes, Barriers, and Needs

    by Babette van Deursen, Cornelia H M van Jaarsveld, Tessa van der Bruggen, Stijn Raven, Julie E M Swillens, Aura Timen

    Background: Data-driven strategies are increasingly integrated into infectious disease control (IDC), enabling professionals to act in a timely and proactive manner; however, their implementation requires alignment with professionals’ needs. Little is known about professionals’ views on data-driven IDC. Objective: This study aims to assess IDC professionals’ knowledge, attitudes, and perceptions toward working in a data-driven manner, as well as their needs, facilitators, and barriers. Methods: We conducted exploratory online focus group discussions (FGDs) with IDC professionals from the Public Health Services (PHSs) in the Netherlands. FGDs were organized by profession, followed by a final mixed-group session that included medical doctors, nurses, infection preventionists, epidemiologists, policy advisors, project leaders, and managers working in IDC. The topic guide was based on the Attitude-Social Influence-Efficacy model and the Consolidated Framework for Implementation Research, complemented with questions on current practices within the PHS related to data-driven work (DDW). Framework and thematic analyses were performed. Results: Between September 2024 and January 2025, nine FGDs were conducted with 36 IDC professionals. Five main themes emerged: (1) context of the work environment, (2) interpretation of DDW in the context of IDC, (3) added value of DDW, (4) views on team participation, and (5) perspectives on development and implementation. While participants mentioned that some data-driven strategies were already implemented within the PHS, they observed that data were not often translated into action. Attitudes toward DDW varied across participants, particularly regarding its definition, application in daily practice, the importance of data interpretation by professionals, results, implementation, and added value. Participation in DDW varied within teams and was influenced by role, interest, workload, time, knowledge, and willingness to change. Participants also identified various facilitators, barriers, and needs at the individual, process, and organizational levels, such as a national approach of data-driven IDC guided by a shared vision, defined role assignments, and clear protocols for data registration. Conclusions: In this study, IDC professionals generally expressed a positive attitude toward DDW but also identified several barriers and needs for future implementation. The limited translation of data into action was viewed as untapped potential. To support effective data-driven IDC, we recommend investing in a supportive work environment that promotes a clear, shared definition of DDW, including defined roles and responsibilities. By doing so, IDC professionals can shift from reactive to strategic, data-informed action and be better equipped future public health threats.

  • Open Access

    Data-Driven Infectious Disease Control: Qualitative Study of Professionals’ Attitudes, Barriers, and Needs (Preprint)

    by Babette van Deursen, Cornelia H M van Jaarsveld, Tessa van der Bruggen, Stijn Raven, Julie E M Swillens, Aura Timen

    BACKGROUND Data-driven strategies are increasingly integrated into infectious disease control (IDC), enabling professionals to act in a timely and proactive manner; however, their implementation requires alignment with professionals’ needs. Little is known about professionals’ views on data-driven IDC. OBJECTIVE This study aims to assess IDC professionals’ knowledge, attitudes, and perceptions toward working in a data-driven manner, as well as their needs, facilitators, and barriers. METHODS We conducted exploratory online focus group discussions (FGDs) with IDC professionals from the Public Health Services (PHSs) in the Netherlands. FGDs were organized by profession, followed by a final mixed-group session that included medical doctors, nurses, infection preventionists, epidemiologists, policy advisors, project leaders, and managers working in IDC. The topic guide was based on the Attitude-Social Influence-Efficacy model and the Consolidated Framework for Implementation Research, complemented with questions on current practices within the PHS related to data-driven work (DDW). Framework and thematic analyses were performed. RESULTS Between September 2024 and January 2025, nine FGDs were conducted with 36 IDC professionals. Five main themes emerged: (1) context of the work environment, (2) interpretation of DDW in the context of IDC, (3) added value of DDW, (4) views on team participation, and (5) perspectives on development and implementation. While participants mentioned that some data-driven strategies were already implemented within the PHS, they observed that data were not often translated into action. Attitudes toward DDW varied across participants, particularly regarding its definition, application in daily practice, the importance of data interpretation by professionals, results, implementation, and added value. Participation in DDW varied within teams and was influenced by role, interest, workload, time, knowledge, and willingness to change. Participants also identified various facilitators, barriers, and needs at the individual, process, and organizational levels, such as a national approach of data-driven IDC guided by a shared vision, defined role assignments, and clear protocols for data registration. CONCLUSIONS In this study, IDC professionals generally expressed a positive attitude toward DDW but also identified several barriers and needs for future implementation. The limited translation of data into action was viewed as untapped potential. To support effective data-driven IDC, we recommend investing in a supportive work environment that promotes a clear, shared definition of DDW, including defined roles and responsibilities. By doing so, IDC professionals can shift from reactive to strategic, data-informed action and be better equipped future public health threats.

  • Open Access

    Nationwide implementation and evaluation of the Tumor‐First workflow for genetic testing in ovarian carcinoma

    by Vera M. Witjes, Joanne A. de Hullu, Dorien M. A. Hermkens, Yvonne H. C. M. Smolders, Julie E. M. Swillens, Sarah‐Lotte Slob, Tjalling Bosse, Marian J. E. Mourits, Margreet G. E. M. Ausems, Tumor‐First Implementation Group, et al.

    Despite international agreement on the importance of tumor DNA testing and germline testing for determining PARP inhibitor treatment eligibility in patients with ovarian carcinoma (OC) and for cancer prevention in their relatives, the optimal strategy remains under debate. In the Netherlands, the “Tumor‐First workflow” was initiated and implemented nationwide: a well‐validated tumor DNA test is the primary test for detecting tumor pathogenic variants (PVs) in OC risk genes (BRCA1/2, RAD51C/D, BRIP1, PALB2). The detection of tumor PVs is subsequently used to stratify germline testing and determine treatment eligibility. The Tumor‐First workflow is efficient and saves costs. The aim of this study was to evaluate the nationwide implementation of the Tumor‐First workflow. We analyzed real‐time genetic testing practices, including tumor DNA and germline testing, in patients diagnosed with OC from 2019 to 2023, as identified through the Dutch Pathology Registry (Palga). Testing data were collected from diagnostic pathology and genetic reports. Out of the 3926 OC patients, 2778 (71%) received OC tumor DNA testing as the primary test. Between 2019 and 2023, this percentage increased from 50% to 85%. Of these tumor DNA tests, 2703 (97%) were successful, with 398 (15%) resulting in the identification of a PV in an OC risk gene. Most of these patients (291; 73%) underwent germline testing, and 147 (51%) were found to have a germline PV. We conclude that the nationwide implementation of the Tumor‐First workflow for OC was effective. Multidisciplinary efforts contributed to a more efficient detection of germline and somatic PVs in OC risk genes.


  • Open Access

    Pathologists’ first opinions on barriers and facilitators of computational pathology adoption in oncological pathology: an international study

    by Julie E. M. Swillens, Iris D. Nagtegaal, Sam Engels, Alessandro Lugli, Rosella P. M. G. Hermens, Jeroen A. W. M. van der Laak

    Computational pathology (CPath) algorithms detect, segment or classify cancer in whole slide images, approaching or even exceeding the accuracy of pathologists. Challenges have to be overcome before these algorithms can be used in practice. We therefore aim to explore international perspectives on the future role of CPath in oncological pathology by focusing on opinions and first experiences regarding barriers and facilitators. We conducted an international explorative eSurvey and semi-structured interviews with pathologists utilizing an implementation framework to classify potential influencing factors. The eSurvey results showed remarkable variation in opinions regarding attitude, understandability and validation of CPath. Interview results showed that barriers focused on the quality of available evidence, while most facilitators concerned strengths of CPath. A lack of consensus was present for multiple factors, such as the determination of sufficient validation using CPath, the preferred function of CPath within the digital workflow and the timing of CPath introduction in pathology education. The diversity in opinions illustrates variety in influencing factors in CPath adoption. A next step would be to quantitatively determine important factors for adoption and initiate validation studies. Both should include clear case descriptions and be conducted among a more homogenous panel of pathologists based on sub specialization.


  • Open Access

    Nationwide implementation of a multifaceted tailored strategy to improve uptake of standardized structured reporting in pathology: an effect and process evaluation

    by Julie E. M. Swillens, Quirinus J. M. Voorham, Reinier P. Akkermans, Iris D. Nagtegaal, Rosella P. M. G. Hermens

    Background: Implementation strategies are aimed at improving guideline adherence. Both effect and process evaluations are conducted to provide insights into the success or failure of these strategies. In our study, we evaluate the nationwide implementation of standardized structured reporting (SSR) in pathology. Methods: An interrupted time series analysis was conducted to evaluate the effect of a previously developed implementation strategy, which consisted of various digitally available elements, on SSR in pathology laboratories. A segmented regression analysis was performed to analyze the change in mean SSR percentages directly after the strategy introduction for pathology reporting and specific subcategories. In addition, we analyzed the change in trend in the weekly percentages after strategy introduction, also for subgroups of tumor groups, retrieval methods, and type of laboratory. The change in SSR use after the strategy introduction was determined for all pathology laboratories. We further conducted a process evaluation in which the exposure to the strategy elements was determined. Experiences of the users with all strategy elements and the remaining barriers and potential strategy elements were evaluated through an eSurvey. We also tested whether exposure to a specific element and a combination of elements resulted in a higher uptake of SSR after strategy introduction. Results: There was a significant increase in an average use of SSR after the strategy introduction for reporting of gastrointestinal (p=.018) and urological (p=.003) oncological diagnoses. A significant increase was present for all oncological resections as a group (p=.007). Thirty-three out of 42 pathology laboratories increased SSR use after the strategy introduction. The “Feedback button”, an option within the templates for SSR to provide feedback to the provider and one of the elements of the implementation strategy, was most frequently used by the SSR users, and effectiveness results showed that it increased average SSR use after the strategy introduction. Barriers were still present for SSR implementation. Conclusions: Nationwide SSR implementation improved for specific tumor groups and retrieval methods. The next step will be to further improve the use of SSR and, simultaneously, to further develop potential benefits of high SSR use, focusing on re-using discrete pathology data. In this way, we can facilitate proper treatment decisions in oncology.


  • Open Access

    Evidence-Based Selection, Development, and Testing of a Tailored Strategy to Improve Standardized Structured Reporting in Pathology: A Multicenter Study

    by Julie E. M. Swillens, Quirinus J. M. Voorham, Iris D. Nagtegaal, Rosella P. M. G. Hermens

    Context.—: Standardized structured reporting (SSR) among pathologists results in more complete diagnoses and, subsequently, improved treatment decisions and patient outcomes. Therefore, SSR templates' usage is advocated in oncology guidelines. However, actual SSR usage varies widely. Previous studies have shown multiple impeding and facilitating factors regarding SSR implementation. Objective.—: To select, develop, and test an evidence-based multifaceted strategy, tailored to the impeding and facilitating factors to improve SSR implementation in oncologic pathology. Design.—: Six strategy elements to increase the use of SSR were selected on the basis of a barrier and facilitator analysis, literature review, and consecutive discussions with a nationwide expert panel and project team. In collaboration with a professional organization for developing SSR templates (PALGA), we developed elements and combined them in 1 multifaceted strategy and subsequently tested effectiveness and feasibility. Results.—: The 6 strategy elements were as follows: (1) renewed Web site including SSR information; (2) e-learning including SSR instructions; (3) communication manual describing communication about SSR; (4) improved feedback process, including use of the “Feedback Button” within SSR templates and “Frequently Asked Questions” on the Web site; (5) information sheet on SSR updates within SSR templates; and (6) monthly telephone conversations to discuss audit and feedback information regarding local SSR usage. A significant change (12.4%) in SSR usage among test laboratories was noticed. After the first test, e-learning and the “Feedback Button” were deemed most feasible and effective. However, awareness of all elements could be increased. Conclusions.—: Next steps will be to optimize the tailored strategy, to distribute it to all Dutch pathology laboratories, and to evaluate effectiveness and feasibility in a nationwide setting.