{"id":1215,"date":"2023-10-19T19:06:06","date_gmt":"2023-10-19T19:06:06","guid":{"rendered":"https:\/\/bcchrmicro.wpengine.com\/?page_id=1215"},"modified":"2026-05-26T18:47:45","modified_gmt":"2026-05-26T18:47:45","slug":"projects","status":"publish","type":"page","link":"https:\/\/www.bcchr.ca\/adsu\/projects\/","title":{"rendered":"ADSU Projects"},"content":{"rendered":"
\n\t
\n\t
\n\t
\n\t
\n\t<\/span>\n\tAI and Data Science Unit<\/span><\/a><\/span><\/div>\n

ADSU Projects<\/h1><\/div>\n
\n\t
\n\t<\/figure>\n<\/div>\n<\/div><\/div>\n<\/div>\n\n\n
\n\t
\n
\n\t\t
\n \n \n \n\t\t\t\t

Pediatric Epilepsy: AI-Assisted Surgical Decision Support<\/h3> <\/span>\n\t\t\t \n \n <\/svg>\n\t\t\t <\/button>\n \n
\n\t\t\t\t
\n\t
\n\t
\n\t

Led by Dr. Mandeep Tamber (Neurosurgeon, BCCH), the broader aim of this project is to improve both patient selection and surgical decision-making in pediatric epilepsy, using AI assisted methods.<\/p>

To do this, a multimodal approach combining low- and high-dimensional pre-surgical data to predict seizure freedom at 1-year postoperatively is being tried. As part of this, we validated using LLMs to automatically extract clinically relevant features from MRI reports that is then feed into the predictive model \u2014 helping clinicians identify the right candidates for surgery and anticipate results.<\/p>

\n\t
\n\t
\n\t
\n\t<\/figure>\n

B. King presenting a poster at Canadian League Against Epilepsy 2025 ASM at Calgary<\/em><\/p><\/div>\n

\n\t
\n\t<\/figure>\n

V. Bahel presenting a poster at American Association of Neurosurgeons 2025 ASM at Boston<\/em><\/p><\/div>\n<\/div><\/div>\n\n

\n

Posters\/Papers:<\/strong><\/p>\n

PO1- Feature extraction from MRI clinical reports in Pediatric Epilepsy: Rule-based, Open-weight LLMs and Hybrid Methods.<\/strong><\/em><\/em><\/summary>

King B, Bahel VR, Paul S, Abraham AP, Kim D, G\u00f6rges M, Bjornson BH, Sujan J, van Rooij T, Tamber MS. In: Proceedings of CLAE 2025 Annual Scientific Meeting. Calgary, AB: Canadian League Against Epilepsy; 2025.<\/em><\/p>\n\n

\n\t<\/figure>\n\n\n
    \n\tKey epilepsy surgery details like lesion type, which side of the brain is affected, and whether it\u2019s focal or not can be automatically pulled out of MRI reports using a mix of simple rules and AI language models.<\/li>\n\n\tRule-based systems, especially those that can spot phrases like \u201cno atrophy,\u201d are easier to understand and are better at capturing specific lesion types that depend on detailed medical wording.<\/li>\n\n\tAI language models are better at details that depend on context (such as figuring out the correct side of the brain), and using them together with rule-based tools gives the best overall results.<\/li>\n<\/ul><\/details>\n\n
    PO2 – Predictive Models for Postoperative Seizure Freedom in Pediatric Epilepsy: Merging MRI Saliency Features to Enhance Model Parsimony.<\/strong><\/em><\/summary>

    Bahel VR, Phung TAT, Sujan J, G\u00f6rges M, van Rooij T, Kim D, Bjornson B, Go C, Connoly M, Tamber M. In: Proceedings of the 2025 AANS Annual Scientific Meeting, Boston, MA: American Association of Neurological Surgeons AANS; 2025. P104.<\/em><\/p>\n\n

    \n\t<\/figure>\n\n\n
      \n\tWhen using detailed MRI measurements in a small group of kids, the model \u201cmemorizes\u201d those patients and then poorly predicts results for new kids<\/li>\n\n\tIf we combine many smaller brain areas into a few larger brain areas, we end up with fewer inputs, and the model becomes simpler and tends to work better overall<\/li>\n\n\tAfter combining regions, the model is less \u201cover\u2011tuned\u201d to the original data (its performance on training and test sets is more similar), which means it\u2019s more likely to work well on future patients.<\/li>\n<\/ul><\/details>\n\n
      PO3 – Comparing the performance of automated feature extraction from medical imaging reports using large language models and rule-based algorithms \u2013 a retrospective feasibility study<\/em>.<\/strong><\/em><\/em><\/summary>

      Bahel VR, Kim D, G\u00f6rges M, Bjornson BH, Sujan J, van Rooij T, Tamber MS. [poster]. Presented at: 3rd International Conference on Artificial Intelligence in Epilepsy and Neurological Disorders; 2025 Mar; Colorado, USA.<\/em><\/em><\/p>\n\n

      \n\t<\/figure>\n\n\n
        \n\tComputers can reliably grab key epilepsy surgery details (like whether there is a lesion on the MRI and where it is) directly from radiology reports, without someone having to read and code them manually.<\/li>\n\n\tSimple keyword rules pick up almost every MRI that looks abnormal (they are very good at not missing positives) but can make mistakes when the wording is more complex, such as misinterpreting phrases like \u201cno atrophy.\u201d<\/li>\n\n\tAI language models work best when they read the short summary section of the report and can achieve both high sensitivity and high accuracy, so the best choice depends on whether to prioritize not missing cases, being very precise, or keeping the system easy to set up.<\/li>\n<\/ul><\/details>\n<\/div>\n<\/div><\/div>\n <\/div>\n <\/div>\n <\/div>\n<\/div>\n
        \n \n \n \n\t\t\t\t

        Developmental Dysplasia of the Hip: Predicting Treatment Trajectories<\/h3> <\/span>\n\t\t\t \n \n <\/svg>\n\t\t\t <\/button>\n \n
        \n\t\t\t\t
        \n\t
        \n\t
        \n\t

        In collaboration with Hippy Lab (Dr. Kishore Mulpuri and Dr. Emily Schaeffer) this project utilizes predictive modeling to forecast how long children with Developmental Dysplasia of Hip (DDH) will require follow-up care, supporting more personalized and proactive clinical decision-making.<\/p>

        Using advanced interpretable model on data from the Global Hip Dysplasia Registry, a database spanning across 32 centers on 6 continents with over 10,000 patients, we are trying to develop AI-supported decision making system for DDH.<\/p>

        \n\t
        \n\t
        \n\t
        \n\t<\/figure>\n

        T. Amin presents at UBC Transforming Health Symposium Vancouver, 2026<\/em><\/p><\/div>\n<\/div><\/div>\n

        \n\t
        \n\t
        \n\t<\/div>\n<\/div><\/div>\n\n
        PO1- Prediction of longitudinal outcomes and follow-up duration in developmental dysplasia of the hip using joint modeling techniques and the Global Hip Dysplasia Registry<\/em>.<\/strong><\/em><\/summary>

        Amin T, Ujlain G, Sujan J, van Rooij T, Bahel V, Sloan J, Mulpuri K, Global Hip Dysplasia Study Group, Schaeffer E. [poster]. Presented at: Evidence2Innovation Symposium, BC Children\u2019s Hospital Research Institute; 2024 Nov 21; Vancouver (BC), Canada.<\/em><\/em><\/p>\n\n

        \n\t<\/figure>\n\n\n