Alex Maurice Dussaq
Affiliate, Department Funds
Fellow in Graduate Medical Education
Bio
Alex Maurice Dussaq, M.D., Ph.D., is a fellow in both the Clinical Informatics Fellowship Program and the Breast Pathology Fellowship. Dr. Dussaq holds a B.S. in Mathematics and Biochemistry from University of Nevada, Reno and an M.D./Ph.D. from University at Alabama, Birmingham. His Ph.D. focused on novel platform informatics and statistical analysis. He completed a Pathology residency at Stanford. Dr. Dussaq's research interests include the implementation and creation of workflow tools for surgical pathology and lab. He is particularly interested in API implementation and use in reporting and whole slide image management systems.
Clinical Focus
- Clinical Informatics
- Breast Pathology
- Fellow
All Publications
-
A pathologist-AI collaboration framework for enhancing diagnostic accuracies and efficiencies.
Nature biomedical engineering
2024
Abstract
In pathology, the deployment of artificial intelligence (AI) in clinical settings is constrained by limitations in data collection and in model transparency and interpretability. Here we describe a digital pathology framework, nuclei.io, that incorporates active learning and human-in-the-loop real-time feedback for the rapid creation of diverse datasets and models. We validate the effectiveness of the framework via two crossover user studies that leveraged collaboration between the AI and the pathologist, including the identification of plasma cells in endometrial biopsies and the detection of colorectal cancer metastasis in lymph nodes. In both studies, nuclei.io yielded considerable diagnostic performance improvements. Collaboration between clinicians and AI will aid digital pathology by enhancing accuracies and efficiencies.
View details for DOI 10.1038/s41551-024-01223-5
View details for PubMedID 38898173
View details for PubMedCentralID 6345440
-
Comparison of the solid-phase red cell adherence assay and tube method for detection and identification of red blood cell antibodies.
American journal of clinical pathology
2024
Abstract
Identifying antibodies to red blood cell antigens is one of transfusion medicine's critical responsibilities. The International Society of Blood Transfusion recognizes 354 red blood cell antigens. Accurate identification of clinically significant alloantibodies is imperative for preventing hemolytic transfusion reactions and hemolytic disease of the fetus and newborn. We compared the performance of the tube (polyethylene glycol-indirect antiglobulin test [PEG-IAT]) and solid-phase red cell adherence assay techniques.We performed a retrospective study on all antibody screens performed between 2007 and 2021 at Stanford Transfusion Services. Initially, 631,535 antibody screens were performed using a solid-phase technique. Subsequent antibody identifications were performed using a combination of tube testing and solid-phase techniques.Antibody screening resulted in 28,316 (4.5%) positive samples. Antibody identification performed on both platforms identified 50 discordant samples. The anti-E antibody had the lowest sensitivity (98.99%) in the automated solid-phase technique, while anti-Jkb had the lowest sensitivity (98.78%) with the PEG-IAT method.To our knowledge, this is the first robust, 15-year study comparing methodologic sensitivity to detect clinically significant alloantibodies. The incidence of discordant results between PEG-IAT and the solid-phase technique was low. Among discordant samples, anti-Jka was commonly detected using the solid-phase method but not with the PEG-IAT. In contrast, anti-E was commonly detected by PEG-IAT but not by the solid-phase method.
View details for DOI 10.1093/ajcp/aqae035
View details for PubMedID 38607807
-
Rapid Deployment of Whole Slide Imaging for Primary Diagnosis in Surgical Pathology at Stanford Medicine Responding to Challenges of the COVID-19 Pandemic
ARCHIVES OF PATHOLOGY & LABORATORY MEDICINE
2023; 147 (3): 359-367
View details for DOI 10.5858/arpa.2021-0438-OA)
View details for Web of Science ID 000958483400012
-
Rapid Deployment of Whole Slide Imaging for Primary Diagnosis in Surgical Pathology at Stanford Medicine.
Archives of pathology & laboratory medicine
2022
Abstract
Stanford Pathology began stepwise subspecialty implementation of whole slide imaging (WSI) in 2018 soon after the first US Food and Drug Administration approval. In 2020, during the COVID-19 pandemic, the Centers for Medicare & Medicaid Services waived the requirement for pathologists to perform diagnostic tests in Clinical Laboratory Improvement Amendments (CLIA)-licensed facilities. This encouraged rapid implementation of WSI across all surgical pathology subspecialties.To present our experience with validation and implementation of WSI at a large academic medical center encompassing a caseload of more than 50 000 cases per year.Validation was performed independently for 3 subspecialty services with a diagnostic concordance threshold above 95%. Analysis of user experience, staffing, infrastructure, and information technology was performed after department-wide expansion.Diagnostic concordance was achieved in 96% of neuropathology cases, 100% of gynecologic pathology cases, and 98% of immunohistochemistry cases. After full implementation, 8 high-capacity scanners were operational, with whole slide images generated on greater than 2000 slides per weekday, accounting for approximately 80% of histologic slides at Stanford Medicine. Multiple modifications in workflow and information technology were needed to improve performance. Within months of full implementation, most attending pathologists and trainees had adopted WSI for primary diagnosis.WSI across all surgical subspecialities is achievable at scale at an academic medical center; however, adoption required flexibility to adjust workflows and develop tailored solutions. WSI at scale supported the health and safety of medical staff while facilitating high-quality patient care and education during COVID-19 restrictions.
View details for DOI 10.5858/arpa.2021-0438-OA
View details for PubMedID 35802938