Mariana Ramirez Posada

All Publications

• Patient-Centered Research Through Artificial Intelligence to Identify Priorities in Cancer Care. JAMA oncology Kim, J., Chen, M. L., Rezaei, S. J., Ramirez-Posada, M., Caswell-Jin, J. L., Kurian, A. W., Riaz, F., Sarin, K. Y., Tang, J. Y., Asch, S. M., Linos, E. 2025

  Abstract

  Patient-centered research is essential for bridging the gap between research and patient care, yet patient perspectives are often inadequately represented in health research.To leverage artificial intelligence (AI) and natural language processing (NLP) to analyze a large dataset of patient messages, defining patient concerns and generating relevant research topics, and to quantify the quality of these AI-generated topics.This case series was conducted using an automated framework involving a 2-staged unsupervised NLP topic model and AI-generated research topic suggestions. The study was based on deidentified patient portal message data from individuals with breast or skin cancer at Stanford Health Care and 22 affiliated centers over July 2013 to April 2024.A widely used large language model (ChatGPT-4o [OpenAI]; April 2024) was used and guided through multiple prompt-engineering strategies to perform multilevel tasks, including knowledge interpretation and summarization (eg, interpreting and summarizing the NLP-defined topics), knowledge generation (eg, generating research ideas corresponding to patients' issues), self-reflection and correction (eg, ensuring and revising the research ideas after searching for scientific articles), and self-reassurance (eg, confirming and finalizing the research ideas).Three breast oncologists (J.L.C., A.W.K., F.R) and 3 dermatologists (K.Y.S, J.Y.T., E.L.) evaluated the meaningfulness and novelty of the AI-generated research topics using a 5-point Likert scale (1 representing exceptional to 5 representing poor). Mean (SD) scores for meaningfulness and novelty were computed for each topic.A total of 614 464 patient messages were analyzed from 25 549 individuals, 10 665 with breast cancer (98.6% female) and 14 884 had skin cancer (49.0% female). The overall mean (SD) scores for meaningfulness and novelty were 3.00 (0.50) and 3.29 (0.74), respectively, for breast cancer topics and 2.67 (0.45) and 3.09 (0.68), respectively, for skin cancer topics. One-third of the AI-suggested research topics were highly meaningful and novel when both scores were lower than the average (5 of 15 for breast cancer and 6 of 15 for skin cancer). Notably, two-thirds of the AI-suggested topics were novel (10 of 15 for breast cancer and 11 of 15 for skin cancer).This case series demonstrates that AI/NLP-driven analysis of large volumes of patient messages can generate quality research topics in cancer care that reflect patient perspectives, providing valuable guidance for future patient-centered health research endeavors.

  View details for DOI 10.1001/jamaoncol.2025.0694

  View details for PubMedID 40272833

• Fine-tuning Large Language Models in Behavioral Psychology for Scalable Physical Activity Coaching. medRxiv : the preprint server for health sciences Mantena, S., Johnson, A., Oppezzo, M., Schuetz, N., Tolas, A., Doijad, R., Mattson, C. M., Lawrie, A., Ramirez-Posada, M., Linos, E., King, A. C., Rodriguez, F., Kim, D. S., Ashley, E. A. 2025

  Abstract

  Personalized, smartphone-based coaching improves physical activity but relies on static, human-crafted messages. We introduce My Heart Counts (MHC)-Coach, a large language model fine-tuned on the Transtheoretical Model of Change. MHC-Coach generates messages tailored to an individual's psychology (their "stage of change"), providing personalized support to foster long-term physical activity behavior change. To evaluate MHC-Coach's efficacy, 632 participants compared human-expert and MHC-Coach text-based interventions encouraging physical activity. Among messages matched to an individual's stage of change, 68.0% (N=430) preferred MHC-Coach-generated messages (P < 0.001). Blinded behavioral science experts (N=2) rated MHC-Coach messages higher than human-expert messages for perceived effectiveness (4.4 vs. 2.8) and Transtheoretical Model alignment (4.1 vs. 3.5) on a 5-point Likert scale. This work demonstrates how language models can operationalize behavioral science frameworks for personalized health coaching, promoting long-term physical activity and potentially reducing cardiovascular disease risk at scale.

  View details for DOI 10.1101/2025.02.19.25322559

  View details for PubMedID 40034753

• Major Depressive Disorder in Long COVID and Exposure to Pro‐Inflammatory Cytokines During Infection by SARS‐CoV‐2 Psychiatric Research and Clinical Practice Guillen‐Burgo, H. F., Gálvez‐Flórez, . F., Moreno‐López, S., Wong, S., Kwan, A. T., Ramirez‐Posada, M., Anaya, ., McIntyre, R. S. 2025
• Determining the medical Spanish translation capabilities of three artificial intelligence translation models for Mohs micrographic surgical instructions. Journal of the American Academy of Dermatology Scheinkman, R., Montoya, S., Náder, M., Ramírez, M., Barbato, K., Jean-Pierre, P., Vignau, A., Nouri, K. 2024

  View details for DOI 10.1016/j.jaad.2024.09.070

  View details for PubMedID 39447753

• Immunofluorescence findings in a reactivating lichenoid photoallergic chronic dermatitis (actinic reticuloid). Photodermatology, photoimmunology & photomedicine Abreu Velez, A. M., Ramírez-Posada, M., Howard, M. S. 2024; 40 (5): e12995

  Abstract

  Chronic photosensitivity dermatitis (CPD) (also named actinic reticuloid) is an unusual disease classically referred often in elderly men. Affected patients have severely itchy, thickened dry skin in areas exposed to the sun throughout the years.A Caucasian female patient who worked most of her life outside who had "chronic dermatitis" in her neck started planting chrysanthemum in her garden on a sunny day. Later, she presented edema, erythema, papules, and a few vesicles in her neck with severe pruritus.A skin biopsy revealed the diagnosis of CPD, along with positive testing for ultraviolet B (UVB), minimal erythema doses (MED) for UVB (MEDB) UVA (MEDA) and PhotoPath.Direct immunofluorescence (DIF) stains using anti-human antibodies against fibrinogen, albumin, IgG, IgM, lambda, kappa, and C3c and C1q were positive at the base membrane area of the dermal epidermal junction, in the papillary dermis, as well as the neurovascular bundles in all the dermis and the extracellular matrix, especially those under the blisters.With this case, we suggest not forgetting the importance of using DIF in reactivated CPD cases in addition to the photo patch testing.

  View details for DOI 10.1111/phpp.12995

  View details for PubMedID 39145412