Reza
Basiri
Clinical AI engineer and medical device founder
I build machine learning that reads wounds, scans and patient records, and I take health products through regulation and clinical trials to the people who need them.
Now
Kanjin HealthCo-founder and Director of Operations, since 2026Regulatory, import and market-entry partner for medical device manufacturers entering Canada.
MedProactiveFounder and CEO, since 2024Clinical trial services company that runs studies for sponsors under ICH-GCP.
Own HealthStrategic Consultant, since 2025Care-navigation platform connecting patients with interdisciplinary care teams.- Zivot Limb Preservation CentreSenior Research Coordinator, since 2018Multidisciplinary clinic in Calgary that works to save the limbs of people with diabetes.
Research
- Clinical AI for wound care7 worksDetecting, measuring and forecasting diabetic foot ulcers from images, thermal and depth maps, and routine clinical records.
- Generative and language models5 worksDiffusion models that synthesize medical images, and vision-language models that describe what a clinician would see.
- Health systems and outcomes2 worksPopulation-level evidence that multidisciplinary limb-preservation care prevents amputations and hospital stays.
- Quantitative MRI and epilepsy5 worksSharper T2 relaxometry for spotting subtle brain abnormalities, and what scalp EEG misses in focal epilepsy.
Cited 215 times on Google Scholar, h-index 7, with $235K+ in competitive scholarships and research funding.
Selected publications
-
Temporal machine learning framework for diabetic foot ulcer healing trajectory prediction
Journal article. BioMedical Engineering OnLine, 25(1), 41, 2026 Open access
Wound care is mostly reactive: treatment changes after a wound has already stalled. This framework looks one appointment ahead. Using only the clinical notes clinics already record, with no imaging, it predicts whether a diabetic foot ulcer will move in a favourable, acceptable or unfavourable direction by the next visit, and pairs that forecast with treatment suggestions.
-
Accessible healing phase classification of diabetic foot ulcer
Journal article. Computers in Biology and Medicine, 197, 111066, 2025
Knowing whether a wound is in the inflammatory, proliferative or remodelling phase steers treatment, but judging it takes specialist experience. This study shows a machine learning model can make that call from routine patient and wound information, and uses explainable AI to show which clinical features drive the decision.
-
UlcerGPT: A Multimodal Approach Leveraging Large Language and Vision Models for Diabetic Foot Ulcer Image Transcription
Conference paper. ICPR 2024 workshops (PRHA), Lecture Notes in Computer Science (Springer), 221-232, 2024
UlcerGPT pairs a vision-language model (LLaVA) with a large language model (ChatGPT) to turn a photo of a diabetic foot ulcer into a written clinical description: what is in the image, where the regions of concern are, and how they should be classified. Expert clinicians rated its output on a public dataset.
-
Protocol for metadata and image collection at diabetic foot ulcer clinics: enabling research in wound analytics and deep learning
Journal article. BioMedical Engineering OnLine, 23(1), 12, 2024 Open access
Good wound AI starts with good data. This paper sets out a standard way to collect diabetic foot ulcer data at the clinic, including a dedicated case report form, and introduces the resulting Zivot dataset: colour photos with matching thermal and depth maps and full clinical metadata. A baseline detector trained on it shows the data is clean enough to learn from.
-
Synthesizing Diabetic Foot Ulcer Images with Diffusion Model
Conference paper. ECML PKDD 2023 workshops (ARIAL), Communications in Computer and Information Science (Springer), 353-360, 2023
Medical AI is starved of data, and wound images are especially scarce. A diffusion model trained on 2,000 diabetic foot ulcer photos produced synthetic wounds realistic enough that clinicians took them for real 70% of the time. The study also shows that the standard image-quality scores, FID and KID, do not agree with clinicians, so better ways to judge synthetic medical images are needed.