Rodrigo Rosa Gameiro

Rodrigo Rosa Gameiro

Auto-generated profile, based on publicly available information

Rodrigo Rosa Gameiro

Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, Mass

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
3 March 2025 in medRxiv
Verified
Preprint
Open access
PDF file
YKYubin Kim
Yubin Kim
HJHyewon Jeong
Hyewon Jeong
SCShen Chen
Shen Chen
SLShuyue Stella Li
Shuyue Stella Li
CPChanwoo Park
Chanwoo Park
CBCynthia Breazeal
Cynthia Breazeal
Foundation Models that are capable of processing and generating multi-modal data have transformed AI’s role in medicine. However, a key limitation of their reliability is hallucination, where inaccurate or fabricated information can impact clinical decisions and patient safety. We define medical hallucination as any instance in which a model generates misleading medical content. This paper examines the unique characteristics, causes, and implications of medical hallucinations, with a particular focus on how these errors manifest themselves in real-world clinical scenarios. Our contributions include (1) a taxonomy for understanding and addressing medical hallucinations, (2) benchmarking models using medical hallucination dataset and physician-annotated LLM responses to real medical cases, providing direct insight into the clinical impact of hallucinations, and (3) a multi-national clinician survey on their experiences with medical hallucinations. Our results reveal that inference techniques such as Chain-of-Thought (CoT) and Search Augmented Generation can effectively reduce hallucination rates. However, despite these improvements, non-trivial levels of hallucination persist. These findings underscore the ethical and practical imperative for robust detection and mitigation strategies, establishing a foundation for regulatory policies that prioritize patient safety and maintain clinical integrity as AI becomes more integrated into healthcare. The feedback from clinicians highlights the urgent need for not only technical advances but also for clearer ethical and regulatory guidelines to ensure patient safety. A repository organizing the paper resources, summaries, and additional information is available at https://github.com/mitmedialab/medical_hallucination.

1 December 2020 in American Journal of Ophthalmology Case Reports
Verified
Journal Article
Open access
AFAluisio Rosa Gameiro Filho
Aluisio Rosa Gameiro Filho
CECarolina Tagliari Estacia
Carolina Tagliari Estacia
RGRodrigo Rosa Gameiro
Rodrigo Rosa Gameiro
LVLeandro de Mattos Fonseca Vieira
Leandro de Mattos Fonseca Vieira
DCDaniella Socci da Costa
Daniella Socci da Costa
Sporotrichosis is the most common subcutaneous mycosis in the world and it is presented usually in the lymphocutaneous form. When the eye is involved, it typically includes the conjunctival and periorbital tissues or even the intraocular tissues. We present a case of a 13-year-old girl complaining about nodules in the left malar region and in both the outer nasal corner and the lower eyelid of the left eye, which had appeared one month earlier. and significance: Sporotrichosis is a hyperendemic disease in Brazil and its diagnosis is based on clinical aspects, epidemiological history, and culture. Ophthalmologists and other professionals should be aware of this condition.

31 July 2025 in Critical Care Science
Verified
Journal Article
Open access
PDF file
NWNaira Link Woite
Naira Link Woite
RGRodrigo R. Gameiro
Rodrigo R. Gameiro
MLMarianna Leite
Marianna Leite
AHAlessandro Hammond
Alessandro Hammond
MCMarisa Cobanaj
Marisa Cobanaj
LCLeo Anthony Celi
Leo Anthony Celi
Artificial intelligence technologies are rapidly advancing and significantly impacting healthcare, particularly in critical care environments where rapid, precise decision-making is crucial. They promise reductions in clinical errors, enhanced diagnostic accuracy, optimized treatment plans, and better resource allocation. Artificial intelligence applications are widespread across medical fields, with numerous artificial intelligence/machine learning-enabled medical devices approved by […] ABSTRACT Artificial intelligence technologies are rapidly advancing and significantly impacting healthcare, particularly in critical care environments where rapid, precise decision-making is crucial. They promise reductions in clinical errors, enhanced diagnostic accuracy, optimized treatment plans, and better resource allocation. Artificial intelligence applications are widespread across medical fields, with numerous artificial intelligence/machine learning-enabled medical devices approved by […]

22 December 2025 in Research Involvement and Engagement
Verified
Journal Article
Open access
PDF file
NJNikhil Jaiswal
Nikhil Jaiswal
BLBertrand Lebouche
Bertrand Lebouche
Bertrand LebouchéBertrand Lebouché
Bertrand Lebouché
DPDan Poenaru
Dan Poenaru
MPMarie-Pascale Pomey
Marie-Pascale Pomey
EOEsli Osmanlliu
Esli Osmanlliu
Uses of large language models (LLMs) in health chatbots are expanding into high-stakes clinical contexts, heightening the need for tools that are evidence-based, accountable, accurate, and patient-centred. This conceptual, practice-informed Perspective reflects on engaging patients and non-academic partners for the responsible integration of LLMs, grounded in the co-construction of MARVIN (for people living with HIV) and in an emerging collaboration with MIT Critical Data. Organised by the Software Development Life Cycle, we describe: conception/needs assessment with patient partners to identify use cases, acceptable trade-offs, and privacy expectations; development that prioritises grounding via vetted sources, structured human feedback, and data-validation committees including patient partners; testing and evaluation using patient-reported outcome measures (PROMs) and patient-reported experience measures (PREMs) chosen in collaboration with patients to capture usability, acceptability, trust, and perceived safety, alongside task performance and harmful-output monitoring; and implementation via diverse governance boards, knowledge-mobilisation materials to set expectations, and risk-management pathways for potentially unsafe outputs. Based on our experience with MARVIN, we recommend early and continuous engagement of patients and non-academic partners, fair compensation, shared decision-making power, transparent decision logging, and inclusive, adaptable governance that can evolve with changing models and standards. These lessons highlight how patient partnership can directly shape chatbot design and oversight, helping teams align LLM-enabled tools with patient-centred goals while building accountable, safe, and equitable systems.

24 June 2026 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
HSHan-Jay Shu
Han-Jay Shu
SCShun-Ting Chang
Shun-Ting Chang
RGRodrigo Rosa Gameiro
Rodrigo Rosa Gameiro
Judy Wawira GichoyaJudy Wawira Gichoya
Judy Wawira Gichoya
LCLeo Anthony Celi
Leo Anthony Celi
PKPo-Chih Kuo
Po-Chih Kuo
Purpose To investigate whether deep learning models trained on chest radiographs (CXRs) rely on radiographic exposure parameters as shortcut features and to quantify the resulting biases under controlled confounding and natural exposure regimes. Materials and Methods In this retrospective study, CXRs from MIMIC-CXR (January 2011–December 2016), the Medical Imaging and Data Resource Center (MIDRC; August 2020–May 2022), and EmoryCXR (September 2008–February 2023) were analyzed for pneumothorax detection, coronavirus disease 2019 (COVID-19) diagnosis, and race classification. Dataset-provided labels served as the reference standard. Three exposure parameters (ExposureTime, XRayTubeCurrent, ExposureInuAs) were extracted from Digital Imaging and Communications in Medicine (DICOM) metadata. Models were trained under biased and balanced exposure–label alignments and evaluated on matched and reversed distributions. A priori screening additionally identified high-risk exposure regimes. Area under the receiver operating characteristic curve (AUC) was compared using the DeLong test. Results A total of 727,604 CXRs from 240,681 patients (mean age, 60 years ± 17 [SD]; 126,432 men, 114,128 women) were analyzed. For pneumothorax detection, AUC decreased from 0.94 (95% CI: 0.94, 0.95) to 0.56 (95% CI: 0.55, 0.58) on mismatched exposure distributions (ΔAUC = –0.38; P < .001). Similar declines were observed for COVID-19 (ΔAUC = –0.33; P < .001) and race classification (ΔAUC = –0.09; P < .001). The priori exposure-regimen screening revealed high-risk regimes within the natural distribution that were associated with reduced model performance compared with typical exposures. Conclusion Deep learning models trained on CXRs may exploit exposure parameters as shortcut features; exposure-regimen audits may flag high-risk conditions before clinical deployment. ©RSNA, 2026

7 April 2026 in medRxiv
Verified
Preprint
Open access
PDF file
CVConstanza Vasquez-Venegas
Constanza Vasquez-Venegas
ACApi Chewcharat
Api Chewcharat
RKRichard Kimera
Richard Kimera
NKNicholas Kurtzman
Nicholas Kurtzman
MLMarianna Leite
Marianna Leite
LCLeo Anthony Celi
Leo Anthony Celi
Computer vision models for chest X-ray interpretation hold significant promise for global healthcare, but their clinical value depends on equitable development across diverse populations. We conducted a scientometric analysis to examine authorship patterns, geographic distribution, and dataset origins to assess potential disparities that could affect clinical applicability. We systematically reviewed literature on computer vision applications for chest X-rays published between 2017-2025 across multiple databases, including PubMed, Embase and SciELO databases. Using Dimensions API and manual extraction, we analyzed 928 eligible studies, examining first and senior author affiliations, institutional contributions, dataset provenance, and collaboration patterns across different income classifications based on World Bank categories. High-income countries dominated research leadership, representing 55.6% of first authors and 59.7% of senior authors; no first authors were affiliated with low-income countries. China (16.93%) and the United States (16.72%) led in first authorship positions. Most datasets (73.6%) originated from high-income settings, with the United States being the largest contributor (40.45%). Private datasets were most frequently used (20.52%). Cross-income collaborations were rare, with only 3.9% of publications involving partnerships between high-income and lower-middle-income countries. Findings reveal substantial disparities in who shapes computer vision research on chest X-rays and which populations are represented in training data. These imbalances risk developing AI systems that perform inconsistently across diverse healthcare settings, potentially exacerbating healthcare inequities. Addressing these disparities requires coordinated efforts to develop globally representative datasets, establish equitable international collaborations, and implement policies that promote inclusive research practices. Author Summary: In this study, we examined the global landscape of research involving computer vision applied to chest X-rays. While these technologies have the potential to significantly improve healthcare worldwide, their effectiveness depends on being developed and tested using data from diverse populations. We analyzed nearly one thousand scientific articles and found that research leadership and data sources are heavily concentrated in high-income countries, particularly the United States and China. Our findings reveal a concerning gap because people in low-income regions, who often face the highest burden of respiratory diseases, are almost entirely absent from the research process as both authors and data contributors. This imbalance creates a risk that medical artificial intelligence may not perform reliably when used in different parts of the world, which could accidentally worsen existing health inequalities. We argue that the scientific community must prioritize international partnerships that treat researchers from developing nations as equal leaders. By making medical data more diverse and accessible, we can ensure that these powerful diagnostic tools benefit patients everywhere, regardless of their location or economic status.