Shadi Momtahen
Postdoctoral Scholar, Anesthesiology, Perioperative and Pain Medicine
Web page: https://profiles.stanford.edu/shadi-momtahen
Bio
Shadi Momtahen is an AI researcher and Postdoctoral Scholar in the Aghaeepour Lab at Stanford School of Medicine, working across Anesthesiology, Perioperative and Pain Medicine and Pathology, in collaboration with Stanford Blood Center. Her work spans multimodal deep learning, medical image reconstruction, and physiological time-series analysis, turning biomedical data into predictive models and research tools.
At Stanford, she works with clinicians at Stanford Blood Center to develop models that integrate clinical, laboratory, donor, and HLA-antibody data to predict platelet transfusion response and support platelet selection. The model is deployed as a real-time application connected to a blood-center server. She also developed DonorPulse, a smartwatch application for physiological monitoring during blood donation and fainting-detection research, along with signal-processing pipelines for PPG and heart rate variability analysis.
She earned her PhD in Engineering (machine learning concentration) from Simon Fraser University. Working with BC Cancer, she developed deep-learning methods for near-infrared breast image reconstruction and treatment-response assessment. She was previously a Postdoctoral Research Fellow at UBC ICORD, developing machine-learning methods for biosensor-based health monitoring. She holds BSc and MSc degrees in computer science, has contributed to more than 20 publications and presentations, and is a co-inventor on a published US patent application.
Honors & Awards
-
The Young Investigator Award, BC Cancer Agency (2023)
-
Research and Innovation Award, BC Cancer Agency (2023)
Professional Education
-
Doctor of Philosophy, Simon Fraser University (2024)
-
BSc, Simon Fraser University, Computer Science (2015)
-
PhD, Simon Fraser University, Engineering (machine learning concentration) (2023)
Patents
-
"United States Patent US 2026/0053369 A1 (Application No. 19/308,126) Handheld Probe and System for Imaging Human Tissue", Optican Systems Inc., Feb 26, 2026
Current Research and Scholarly Interests
My research develops and deploys multimodal machine-learning models for clinical decision support. At Stanford, I work with Pathology and Stanford Blood Center on models that link donor–recipient HLA interactions, clinical features, and patient history to transfusion outcomes, and on tools that rank platelet products in real time. I also build wearable-sensing pipelines, including a smartwatch app and signal-processing methods for PPG-based heart rate variability, to study physiological responses during blood donation. My earlier work applied deep learning and optical sensing to breast cancer assessment and tissue perfusion monitoring.
All Publications
-
Diffuse optical breast (DOB) scanner as a non-invasive approach for predicting pathologic response to neoadjuvant chemotherapy (NAC) in locally advanced breast cancer (LABC)
ELSEVIER. 2025
View details for DOI 10.1016/j.annonc.2025.10.905
View details for Web of Science ID 001656822100060
-
Prediction of pathologic response to neoadjuvant chemotherapy (NAC) using diffuse optical breast scanner (DOB-Scan) in patients with locally advanced breast cancer (LABC)
ELSEVIER. 2023: S326
View details for DOI 10.1016/j.annonc.2023.09.536
View details for Web of Science ID 001087480200347
-
Near-Infrared Handheld Probe and Imaging System for Breast Tumor Localization
IEEE CANADIAN JOURNAL OF ELECTRICAL AND COMPUTER ENGINEERING
2023; 46 (4): 246-255
View details for DOI 10.1109/ICJECE.2023.3259239
View details for Web of Science ID 001085347400001
-
An Optical Sensory System for Assessment of Residual Cancer Burden in Breast Cancer Patients Undergoing Neoadjuvant Chemotherapy.
Sensors (Basel, Switzerland)
2023; 23 (12)
Abstract
Breast cancer patients undergoing neoadjuvant chemotherapy (NAC) require precise and accurate evaluation of treatment response. Residual cancer burden (RCB) is a prognostic tool widely used to estimate survival outcomes in breast cancer. In this study, we introduced a machine-learning-based optical biosensor called the Opti-scan probe to assess residual cancer burden in breast cancer patients undergoing NAC. The Opti-scan probe data were acquired from 15 patients (mean age: 61.8 years) before and after each cycle of NAC. Using regression analysis with k-fold cross-validation, we calculated the optical properties of healthy and unhealthy breast tissues. The ML predictive model was trained on the optical parameter values and breast cancer imaging features obtained from the Opti-scan probe data to calculate RCB values. The results show that the ML model achieved a high accuracy of 0.98 in predicting RCB number/class based on the changes in optical properties measured by the Opti-scan probe. These findings suggest that our ML-based Opti-scan probe has considerable potential as a valuable tool for the assessment of breast cancer response after NAC and to guide treatment decisions. Therefore, it could be a promising, non-invasive, and accurate method for monitoring breast cancer patient's response to NAC.
View details for DOI 10.3390/s23125761
View details for PubMedID 37420927
View details for PubMedCentralID PMC10303311
-
Early Detection of Breast Cancer using Diffuse Optical Probe and Ensemble Learning Method
IEEE. 2023: 139-142
View details for DOI 10.1109/NEMO56117.2023.10202520
View details for Web of Science ID 001050927700039
https://orcid.org/0000-0002-1610-0204