Tirth Patel

Tirth Patel

Auto-generated profile, based on publicly available information

Tirth Patel

Techna Institute, University Health Network, Toronto, Ontario, Canada

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 May 2024 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
CLCathy Ong Ly
Cathy Ong Ly
BUBalagopal Unnikrishnan
Balagopal Unnikrishnan
TTTony Tadic
Tony Tadic
TPTirth Patel
Tirth Patel
JDJoe Duhamel
Joe Duhamel
CMChris McIntosh
Chris McIntosh
Healthcare datasets are becoming larger and more complex, necessitating the development of accurate and generalizable AI models for medical applications. Unstructured datasets, including medical imaging, electrocardiograms, and natural language data, are gaining attention with advancements in deep convolutional neural networks and large language models. However, estimating the generalizability of these models to new healthcare settings without extensive validation on external data remains challenging. In experiments across 13 datasets including X-rays, CTs, ECGs, clinical discharge summaries, and lung auscultation data, our results demonstrate that model performance is frequently overestimated by up to 20% on average due to shortcut learning of hidden data acquisition biases (DAB). Shortcut learning refers to a phenomenon in which an AI model learns to solve a task based on spurious correlations present in the data as opposed to features directly related to the task itself. We propose an open source, bias-corrected external accuracy estimate, PEst, that better estimates external accuracy to within 4% on average by measuring and calibrating for DAB-induced shortcut learning.

29 June 2023 in Cancer Research Communications
Verified
Journal Article
Open access
PDF file
MKMichal Kazmierski
Michal Kazmierski
MWMattea Welch
Mattea Welch
SKSejin Kim
Sejin Kim
CMChris McIntosh
Chris McIntosh
KRKatrina Rey-McIntyre
Katrina Rey-McIntyre
BHBenjamin Haibe-Kains
Benjamin Haibe-Kains
Artificial intelligence (AI) and machine learning (ML) are becoming critical in developing and deploying personalized medicine and targeted clinical trials. Recent advances in ML have enabled the integration of wider ranges of data including both medical records and imaging (radiomics). However, the development of prognostic models is complex as no modeling strategy is universally superior to others and validation of developed models requires large and diverse datasets to demonstrate that prognostic models developed (regardless of method) from one dataset are applicable to other datasets both internally and externally. Using a retrospective dataset of 2,552 patients from a single institution and a strict evaluation framework that included external validation on three external patient cohorts (873 patients), we crowdsourced the development of ML models to predict overall survival in head and neck cancer (HNC) using electronic medical records (EMR) and pretreatment radiological images. To assess the relative contributions of radiomics in predicting HNC prognosis, we compared 12 different models using imaging and/or EMR data. The model with the highest accuracy used multitask learning on clinical data and tumor volume, achieving high prognostic accuracy for 2-year and lifetime survival prediction, outperforming models relying on clinical data only, engineered radiomics, or complex deep neural network architecture. However, when we attempted to extend the best performing models from this large training dataset to other institutions, we observed significant reductions in the performance of the model in those datasets, highlighting the importance of detailed population-based reporting for AI/ML model utility and stronger validation frameworks. We have developed highly prognostic models for overall survival in HNC using EMRs and pretreatment radiological images based on a large, retrospective dataset of 2,552 patients from our institution.Diverse ML approaches were used by independent investigators. The model with the highest accuracy used multitask learning on clinical data and tumor volume.External validation of the top three performing models on three datasets (873 patients) with significant differences in the distributions of clinical and demographic variables demonstrated significant decreases in model performance. Significance: ML combined with simple prognostic factors outperformed multiple advanced CT radiomics and deep learning methods. ML models provided diverse solutions for prognosis of patients with HNC but their prognostic value is affected by differences in patient populations and require extensive validation.

13 September 2025 in Radiotherapy and Oncology
Verified
Journal Article
Closed access
HBHannah Bacon
Hannah Bacon
NMNicholas McNeil
Nicholas McNeil
TPTirth Patel
Tirth Patel
MWMattea Welch
Mattea Welch
XYXiang Y Ye
Xiang Y Ye
AHAndrew J. Hope
Andrew J. Hope

25 January 2022 in medRxiv
Verified
Preprint
Open access
PDF file
JMJoseph Marsilla
Joseph Marsilla
JKJun Won Kim
Jun Won Kim
DTDenis Tkachuck
Denis Tkachuck
AHAli Hosni
Ali Hosni
SKSejin Kim
Sejin Kim
BHBenjamin Haibe-Kains
Benjamin Haibe-Kains
Background and Purpose: Auto-segmentation of organs at risk (OAR) in cancer patients is essential for enhancing radiotherapy planning efficacy and reducing inter-observer variability. Deep learning auto-segmentation models have shown promise, but their lack of transparency and reproducibility hinders their generalizability and clinical acceptability, limiting their use in clinical settings. Materials and Methods: This study introduces SCARF (auto-Segmentation Clinical Acceptability & Reproducibility Framework), a comprehensive six-stage reproducible framework designed to benchmark open-source convolutional neural networks for auto-segmentation of 19 essential OARs in head and neck cancer (HNC). Results: SCARF offers an easily implementable framework for designing and reproducibly benchmarking auto-segmentation tools, along with thorough expert assessment capabilities. Expert assessment labelled 16/19 AI-generated OAR categories as acceptable with minor revisions. Boundary distance metrics, such as 95th Percentile Hausdorff Distance (95HD), were found to be 2x more correlated to Mean Acceptability Rating (MAR) than volumetric overlap metrics (DICE). Conclusions: The introduction of SCARF, our auto-Segmentation Clinical Acceptability & Reproducibility Framework, represents a significant step forward in systematically assessing the performance of AI models for auto-segmentation in radiation therapy planning. By providing a comprehensive and reproducible framework, SCARF facilitates benchmarking and expert assessment of AI-driven auto-segmentation tools, addressing the need for transparency and reproducibility in this domain. The robust foundation laid by SCARF enables the progression towards the creation of usable AI tools in the field of radiation therapy. Through its emphasis on clinical acceptability and expert assessment, SCARF fosters the integration of AI models into clinical environments, paving the way for more randomised clinical trials to evaluate their real-world impact.

22 April 2026 in Radiotherapy and Oncology
Verified
Journal Article
Closed access
OIOded Icht
Oded Icht
IAInbar Nardi Agmon
Inbar Nardi Agmon
JMJ.M. Miro
J.M. Miro
Omar BadranOmar Badran
Omar Badran
SKS. Keshavjee
S. Keshavjee
AHA. Hope
A. Hope

29 June 2023
Verified
Other
Open access
MKMichal Kazmierski
Michal Kazmierski
MWMattea Welch
Mattea Welch
SKSejin Kim
Sejin Kim
CMChris McIntosh
Chris McIntosh
KRKatrina Rey-McIntyre
Katrina Rey-McIntyre
BHBenjamin Haibe-Kains
Benjamin Haibe-Kains
Artificial intelligence (AI) and machine learning (ML) are becoming critical in developing and deploying personalized medicine and targeted clinical trials. Recent advances in ML have enabled the integration of wider ranges of data including both medical records and imaging (radiomics). However, the development of prognostic models is complex as no modeling strategy is universally superior to others and validation of developed models requires large and diverse datasets to demonstrate that prognostic models developed (regardless of method) from one dataset are applicable to other datasets both internally and externally. Using a retrospective dataset of 2,552 patients from a single institution and a strict evaluation framework that included external validation on three external patient cohorts (873 patients), we crowdsourced the development of ML models to predict overall survival in head and neck cancer (HNC) using electronic medical records (EMR) and pretreatment radiological images. To assess the relative contributions of radiomics in predicting HNC prognosis, we compared 12 different models using imaging and/or EMR data. The model with the highest accuracy used multitask learning on clinical data and tumor volume, achieving high prognostic accuracy for 2-year and lifetime survival prediction, outperforming models relying on clinical data only, engineered radiomics, or complex deep neural network architecture. However, when we attempted to extend the best performing models from this large training dataset to other institutions, we observed significant reductions in the performance of the model in those datasets, highlighting the importance of detailed population-based reporting for AI/ML model utility and stronger validation frameworks. We have developed highly prognostic models for overall survival in HNC using EMRs and pretreatment radiological images based on a large, retrospective dataset of 2,552 patients from our institution.Diverse ML approaches were used by independent investigators. The model with the highest accuracy used multitask learning on clinical data and tumor volume.External validation of the top three performing models on three datasets (873 patients) with significant differences in the distributions of clinical and demographic variables demonstrated significant decreases in model performance.Significance:ML combined with simple prognostic factors outperformed multiple advanced CT radiomics and deep learning methods. ML models provided diverse solutions for prognosis of patients with HNC but their prognostic value is affected by differences in patient populations and require extensive validation.