2026 ASH®
Annual Meeting & Exposition December 12-15, 2026 ▪ New Orleans, Louisiana

Paper Details

Abstracts, authors, affiliations, and disclosures.

Saturday, December 12, 2026
05:30 p.m. - 07:30 p.m.
MCCNO - Hall F
Access, Representation, Population Health, Technology and Procedures, Imaging, Molecular Testing, Omics Technologies, Pathology, Bioinformatics, Blood Banking, Computational Biology, Emerging Technologies, Profiling, Treatment Considerations, Drug Development, Supportive Care, Therapy Sequence, Biological Therapies, Chimeric Antigen Receptor, (CAR)-T Cell Therapies, Women’s Health, Workforce, Adverse Events, Artificial Intelligence (AI), Computer Vision, Deep Learning, Generative AI, Machine Learning, Natural Language Processing, Biological Processes, Apoptosis, Genomics, Hematopoiesis, Molecular Biology, Clinical Practice (Health Services and Quality), Clinical Guidelines, Quality Improvement, Quality of Care, Systems-Based Hematology, Diseases, Bleeding and Clotting, Thromboembolism, Bone Marrow Failure Syndromes, Inherited Marrow Failure Syndromes, Paroxysmal Nocturnal Hemoglobinuria, Lymphoid Malignancies, Lymphoid Leukemias, Lymphomas, Plasma Cell Disorders, Myeloid Malignancies, Acute Myeloid Malignancies, Chronic Myeloid Malignancies, Metabolic Disorders, Iron Deficiency, Measurable Residual Disease, Non-Hodgkin Lymphoma, B Cell Lymphoma, Aggressive Lymphoma, Research, Fundamental Science, AML, APL, Translational Research, MDS, MPN, Clinical Research, Clinical Trials, Real-World Evidence, Study Population, Human, Adult, Pediatric
PAPER

2589 Development of a novel wearable for at-home detection of heavy menstrual bleeding

Asish Koruprolu, PhD, Parker Abramson2, Parmis Shahim3, Hou Dren Yen4, Ina A. Stelzer, PhD5, Jenny Y Zhou, MD6, Benjamin Smarr, PhD7, H. Irene Su, MD8, Drew A. Hall, PhD9
1 University of California San Diego, San Diego, California, United States
2 University of California San Diego, San Diego, California, United States
3 University of California San Diego, San Diego, California, United States
4 University of California San Diego, San Diego, California, United States
5 University of California San Diego, San Diego, California, United States
6 University of California San Diego, San Diego, California, United States
7 University of California San Diego, San Diego, California, United States
8 University of California San Diego, San Diego, California, United States
9 University of California San Diego, San Diego, California, United States
Introduction
Heavy menstrual bleeding (HMB) affects 1 in 4 reproductive-aged women and up to 90% of women with bleeding disorders and is a leading cause of iron deficiency anemia, resulting in substantial physical, cognitive, and psychosocial morbidity. Despite its prevalence, HMB is frequently underrecognized because existing methods to quantify menstrual blood loss (MBL) are either labor-intensive and confined to research settings (e.g., gold-standard modified alkaline hematin method) or rely on subjective or semi-quantitative assessments with variable accuracy. Moreover, total menstrual effluent volume is an unreliable surrogate for MBL because blood content varies. To address this unmet need, we developed SmartPad, a wearable smart-textile platform integrating bioimpedance (BioZ), electrical impedance spectroscopy (EIS), and machine learning (ML) for objective, real-time MBL quantification.

Methods
SmartPad comprises a flexible interdigitated BioZ sensor integrated beneath the absorbent core of a menstrual pad and connected to a reusable wireless readout module containing the BioZ circuitry and rechargeable battery. Benchtop studies characterized volume-dependent BioZ conductance using phosphate-buffered saline (PBS) and expired human whole blood (100–500 µL). Multi-frequency EIS was performed on blood-PBS mixtures and blood-0.5% xanthan gum mixtures, using a previously described approach to mimic menstrual effluent viscosity. Human menstrual effluent collected under an IRB-approved protocol underwent EIS characterization. A physics-based synthetic data generator was developed to create synthetic BioZ conductance data for training an XGBoost ML model estimating menstrual effluent volume from dynamic conductance features. ML-derived fluid-volume estimates were combined with EIS-derived blood fraction to calculate cumulative MBL, displayed in a smartphone application with longitudinal blood-loss tracking and alerts when cumulative MBL exceeds the HMB threshold (≥80 mL). ML performance was evaluated by prediction accuracy and cumulative volume error.

Results
Benchtop proof-of-concept studies established the feasibility of BioZ-based quantification of menstrual effluent volume. Sequential 100-µL PBS additions on the electrode produced reproducible impedance step responses. Controlled applications of saline and whole blood on the electrode with an absorbent core generated reproducible conductance peaks and decay profiles that tracked applied volumes. Conductance traces generated by the synthetic data generator closely reproduced experimental BioZ measurements, supporting ML-based fluid-volume estimation. The XGBoost model achieved 91.0% per-drop fluid-volume prediction accuracy (within ±100 µL) with <10% cumulative trial-level volume error in benchtop testing. Multi-frequency EIS identified spectral features distinguishing blood concentration within mixed-fluid environments. Impedance magnitude (|Z|) at 100 kHz demonstrated a strong linear relationship with blood concentration in blood-PBS mixtures (R²=0.96), whereas blood-xanthan mixtures demonstrated a strong inverse relationship (R²=0.95); phase angle at 3 kHz provided an additional discriminative feature. Human menstrual effluent demonstrated EIS spectra similar to those of blood-containing synthetic simulants, supporting the use of simulants for benchtop SmartPad development.

An integrated SmartPad prototype featuring a compact, coin-sized wearable readout module (33.2 mm diameter, 9.4 mm height) and smartphone interface was successfully developed. The system supported continuous BioZ acquisition, real-time MBL visualization, Bluetooth Low Energy communication, and >1-week battery life.

Conclusion
SmartPad is a novel wearable platform that combines continuous BioZ-based measurement of menstrual effluent volume with EIS-based estimation of blood fraction in a mixed-fluid environment. Preliminary studies demonstrate dynamic fluid-volume sensing, ML-based fluid-volume estimation, discrimination of blood content, and successful integration into an end-to-end prototype. By enabling objective, home-based MBL quantification through a scalable technology, SmartPad has the potential to address a major unmet need for HMB assessment, particularly for individuals with bleeding disorders. Future work will optimize the SmartPad prototype and prospectively validate it against the modified alkaline hematin method while assessing real-world usability in menstruating individuals.

Jenny Y Zhou, MD: Sanofi - Honoraria; Takeda - Honoraria; Pharmacosmos - Honoraria