Alexander Lupi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Alexander Lupi has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Kotz
Institute of Photonics and Quantum Electronics (IPQ), Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
2 shared publications - Anna M. Maw
Department of Emergency Medicine, University of Colorado Anschutz Medical Campus, Aurora, US
2 shared publications - Benjamin Li
Department of Emergency Medicine, University of Colorado Anschutz Medical Campus, Aurora, US
2 shared publications - Foster R. Goss
Department of Emergency Medicine, University of Colorado Anschutz Medical Campus, Aurora, US
2 shared publications - Heather Coats
Department of Emergency Medicine, University of Colorado Anschutz Medical Campus, Aurora, US
2 shared publications - Joseph M. Plasek
Brigham and Women’s Hospital, Division of General Internal Medicine, Boston, MA, USA
2 shared publications
Latest Publications
- Open Access
- 7 August 2026
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 10, e89837
Iterative Multidisciplinary Development and Evaluation of a Patient-Facing Social Determinants of Health Chatbot Using Synthetic Data Simulation: Mixed Methods Study
Background: Systematic collection of social determinants of health (SDoH) data remains inconsistent across health care settings, despite its critical impact on patient outcomes. Large language model–powered chatbots offer promise for scalable SDoH data collection, but rigorous, feasible evaluation methods for patient-facing applications are lacking. Objective: This study aimed to describe an efficient, iterative, multidisciplinary approach for developing and evaluating a patient-facing SDoH chatbot using synthetic data and case simulation, with the goal of optimizing both chatbot performance and the evaluation rubric prior to clinical deployment. Methods: A 10-criterion evaluation rubric was adapted from established health care AI frameworks and applied to 27 synthetic clinical scenarios representing diverse SDoH profiles. Scenarios were role-played by a licensed clinical social worker, and chatbot-patient interactions were rated by 3 members of the research team that were multidisciplinary experts: a social worker, a nurse practitioner, and a physician. Quantitative analysis used percent agreement and Fleiss κ to characterize chatbot performance and rater consensus, with percent agreement selected due to the high prevalence of ceiling effects in several domains. Qualitative analysis synthesized rater feedback to guide iterative refinement of both chatbot prompts and rubric domains. Results: Across 27 simulated cases, the chatbot received high proportions of positive ratings for accurate interpretation (agreement=0.98%, 95% CI 0.91‐0.99), communication quality, and cultural sensitivity (agreement=0.99%, 95% CI 0.93‐1.00), and appropriately adaptive questioning (agreement=0.99%, 95% CI 0.93‐1.00). Lower performance was observed in domain focus and completeness (agreement=0.51%, 95% CI 0.40‐0.61), completeness of data capture (agreement=0.59%, 95% CI 0.48‐0.69; Fleiss κ=0.18), and safety (agreement=0.69%, 95% CI 0.58‐0.78; Fleiss κ=−0.04), prompting targeted adaptations. Qualitative feedback highlighted the importance of distinguishing screening from clinical interviewing capabilities and informed the refinement of the rubric, including clarifying the definition of safety to focus on recognition of physical and mental health emergencies. Conclusions: This study describes a formative feasibility approach for iterative refinement of a patient-facing SDoH chatbot and its evaluation rubric using synthetic case simulation. Future work will include independent external raters, patient stakeholders, repeated scenario testing, and prospective clinical evaluation.
- 7 August 2026
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 10, e89837
Open AccessIterative Multidisciplinary Development and Evaluation of a Patient-Facing Social Determinants of Health Chatbot Using Synthetic Data Simulation: Mixed Methods Study
Background: Systematic collection of social determinants of health (SDoH) data remains inconsistent across health care settings, despite its critical impact on patient outcomes. Large language model–powered chatbots offer promise for scalable SDoH data collection, but rigorous, feasible evaluation methods for patient-facing applications are lacking. Objective: This study aimed to describe an efficient, iterative, multidisciplinary approach for developing and evaluating a patient-facing SDoH chatbot using synthetic data and case simulation, with the goal of optimizing both chatbot performance and the evaluation rubric prior to clinical deployment. Methods: A 10-criterion evaluation rubric was adapted from established health care AI frameworks and applied to 27 synthetic clinical scenarios representing diverse SDoH profiles. Scenarios were role-played by a licensed clinical social worker, and chatbot-patient interactions were rated by 3 members of the research team that were multidisciplinary experts: a social worker, a nurse practitioner, and a physician. Quantitative analysis used percent agreement and Fleiss κ to characterize chatbot performance and rater consensus, with percent agreement selected due to the high prevalence of ceiling effects in several domains. Qualitative analysis synthesized rater feedback to guide iterative refinement of both chatbot prompts and rubric domains. Results: Across 27 simulated cases, the chatbot received high proportions of positive ratings for accurate interpretation (agreement=0.98%, 95% CI 0.91‐0.99), communication quality, and cultural sensitivity (agreement=0.99%, 95% CI 0.93‐1.00), and appropriately adaptive questioning (agreement=0.99%, 95% CI 0.93‐1.00). Lower performance was observed in domain focus and completeness (agreement=0.51%, 95% CI 0.40‐0.61), completeness of data capture (agreement=0.59%, 95% CI 0.48‐0.69; Fleiss κ=0.18), and safety (agreement=0.69%, 95% CI 0.58‐0.78; Fleiss κ=−0.04), prompting targeted adaptations. Qualitative feedback highlighted the importance of distinguishing screening from clinical interviewing capabilities and informed the refinement of the rubric, including clarifying the definition of safety to focus on recognition of physical and mental health emergencies. Conclusions: This study describes a formative feasibility approach for iterative refinement of a patient-facing SDoH chatbot and its evaluation rubric using synthetic case simulation. Future work will include independent external raters, patient stakeholders, repeated scenario testing, and prospective clinical evaluation.
- Open Access
- 27 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Iterative Multidisciplinary Development and Evaluation a Patient-Facing SDoH Chatbot Using Synthetic Data Simulation (Preprint)
BACKGROUND Systematic collection of social determinants of health (SDoH) data remains inconsistent across healthcare settings, despite its critical impact on patient outcomes. Large language model (LLM)-powered chatbots offer promise for scalable SDoH data collection, but rigorous, feasible evaluation methods for patient-facing applications are lacking. OBJECTIVE To describe an efficient, iterative, multidisciplinary approach for developing and evaluating a patient-facing SDoH chatbot using synthetic data and case simulation, with the goal of optimizing both chatbot performance and the evaluation rubric prior to clinical deployment. METHODS A 10-criterion evaluation rubric was adapted from established healthcare artificial intelligence (AI) frameworks and applied to 27 synthetic clinical scenarios representing diverse SDoH profiles. Scenarios were role-played by a licensed clinical social worker, and chatbot-patient interactions were independently rated by three multidisciplinary experts (social worker, nurse practitioner, physician). Quantitative analysis used descriptive statistics and percent agreement to characterize chatbot performance and rater consensus, with percent agreement selected due to high prevalence of ceiling effects in several domains. Qualitative analysis synthesized rater feedback to guide iterative refinement of both chatbot prompts and rubric domains. RESULTS The chatbot demonstrated robust performance in domains such as accurate interpretation (mean = 0.98, SD = 0.09), communication quality and cultural sensitivity (mean = 0.99, SD = 0.06), and adaptive questioning (mean = 0.99, SD = 0.06), with near-perfect rater agreement. Lower scores and greater variability were observed in completeness of data collection, systematic domain exploration, and safety, prompting targeted adaptations. Qualitative feedback highlighted the importance of distinguishing screening from clinical interviewing capabilities and informed the refinement of the rubric, including clarifying the definition of safety to focus on recognition of physical and mental health emergencies. CONCLUSIONS This study provides a practical, replicable blueprint for pre-deployment evaluation of patient-facing SDoH chatbots, balancing rigor with feasibility. The iterative, multidisciplinary approach enabled rapid identification and remediation of performance gaps, supporting responsible integration of AI into SDoH data collection. Explicit performance thresholds and rubric refinement are essential for protecting patient trust and safety, particularly in vulnerable populations. Future work will validate findings with real patient interactions and expand stakeholder involvement. CLINICALTRIAL N/A
- 27 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessIterative Multidisciplinary Development and Evaluation a Patient-Facing SDoH Chatbot Using Synthetic Data Simulation (Preprint)
BACKGROUND Systematic collection of social determinants of health (SDoH) data remains inconsistent across healthcare settings, despite its critical impact on patient outcomes. Large language model (LLM)-powered chatbots offer promise for scalable SDoH data collection, but rigorous, feasible evaluation methods for patient-facing applications are lacking. OBJECTIVE To describe an efficient, iterative, multidisciplinary approach for developing and evaluating a patient-facing SDoH chatbot using synthetic data and case simulation, with the goal of optimizing both chatbot performance and the evaluation rubric prior to clinical deployment. METHODS A 10-criterion evaluation rubric was adapted from established healthcare artificial intelligence (AI) frameworks and applied to 27 synthetic clinical scenarios representing diverse SDoH profiles. Scenarios were role-played by a licensed clinical social worker, and chatbot-patient interactions were independently rated by three multidisciplinary experts (social worker, nurse practitioner, physician). Quantitative analysis used descriptive statistics and percent agreement to characterize chatbot performance and rater consensus, with percent agreement selected due to high prevalence of ceiling effects in several domains. Qualitative analysis synthesized rater feedback to guide iterative refinement of both chatbot prompts and rubric domains. RESULTS The chatbot demonstrated robust performance in domains such as accurate interpretation (mean = 0.98, SD = 0.09), communication quality and cultural sensitivity (mean = 0.99, SD = 0.06), and adaptive questioning (mean = 0.99, SD = 0.06), with near-perfect rater agreement. Lower scores and greater variability were observed in completeness of data collection, systematic domain exploration, and safety, prompting targeted adaptations. Qualitative feedback highlighted the importance of distinguishing screening from clinical interviewing capabilities and informed the refinement of the rubric, including clarifying the definition of safety to focus on recognition of physical and mental health emergencies. CONCLUSIONS This study provides a practical, replicable blueprint for pre-deployment evaluation of patient-facing SDoH chatbots, balancing rigor with feasibility. The iterative, multidisciplinary approach enabled rapid identification and remediation of performance gaps, supporting responsible integration of AI into SDoH data collection. Explicit performance thresholds and rubric refinement are essential for protecting patient trust and safety, particularly in vulnerable populations. Future work will validate findings with real patient interactions and expand stakeholder involvement. CLINICALTRIAL N/A
- 26 August 2022
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 97 (9) , 1257-1258
Policy and Curricular Changes Support Service Learning Across the Medical Education Continuum
- 26 August 2022
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 97 (9) , 1257-1258
Policy and Curricular Changes Support Service Learning Across the Medical Education Continuum
- 5 October 2021
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 97 (6) , 779-780
Local Mentoring as a Strategy to Recruit a More Diverse Physician Workforce
An abstract is unavailable. This article is available as a PDF only.
- 5 October 2021
- Published by Oxford University Press (OUP) in Academic Medicine
- Vol. 97 (6) , 779-780
Local Mentoring as a Strategy to Recruit a More Diverse Physician Workforce
An abstract is unavailable. This article is available as a PDF only.
- Top Cited Papers
- 17 September 2018
- Published by Springer Nature in Nature Neuroscience
- Vol. 21 (10) , 1380-1391
CNS lymphatic drainage and neuroinflammation are regulated by meningeal lymphatic vasculature
Neuroinflammatory diseases, such as multiple sclerosis, are characterized by invasion of the brain by autoreactive T cells. The mechanism for how T cells acquire their encephalitogenic phenotype and trigger disease remains, however, unclear. The existence of lymphatic vessels in the meninges indicates a relevant link between the CNS and peripheral immune system, perhaps affecting autoimmunity. Here we demonstrate that meningeal lymphatics fulfill two critical criteria: they assist in the drainage of cerebrospinal fluid components and enable immune cells to enter draining lymph nodes in a CCR7-dependent manner. Unlike other tissues, meningeal lymphatic endothelial cells do not undergo expansion during inflammation, and they express a unique transcriptional signature. Notably, the ablation of meningeal lymphatics diminishes pathology and reduces the inflammatory response of brain-reactive T cells during an animal model of multiple sclerosis. Our findings demonstrate that meningeal lymphatics govern inflammatory processes and immune surveillance of the CNS and pose a valuable target for therapeutic intervention.
- 17 September 2018
- Published by Springer Nature in Nature Neuroscience
- Vol. 21 (10) , 1380-1391
Top Cited PapersCNS lymphatic drainage and neuroinflammation are regulated by meningeal lymphatic vasculature
Neuroinflammatory diseases, such as multiple sclerosis, are characterized by invasion of the brain by autoreactive T cells. The mechanism for how T cells acquire their encephalitogenic phenotype and trigger disease remains, however, unclear. The existence of lymphatic vessels in the meninges indicates a relevant link between the CNS and peripheral immune system, perhaps affecting autoimmunity. Here we demonstrate that meningeal lymphatics fulfill two critical criteria: they assist in the drainage of cerebrospinal fluid components and enable immune cells to enter draining lymph nodes in a CCR7-dependent manner. Unlike other tissues, meningeal lymphatic endothelial cells do not undergo expansion during inflammation, and they express a unique transcriptional signature. Notably, the ablation of meningeal lymphatics diminishes pathology and reduces the inflammatory response of brain-reactive T cells during an animal model of multiple sclerosis. Our findings demonstrate that meningeal lymphatics govern inflammatory processes and immune surveillance of the CNS and pose a valuable target for therapeutic intervention.