Jennifer Yin Yee Kwan

Jennifer Yin Yee Kwan

Auto-generated profile, based on publicly available information

Jennifer Yin Yee Kwan

Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Ontario, Canada

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
23 September 2019 in Nature Reviews Drug Discovery
Verified
Journal Article
Closed access
PDF file
XZXiao Zhao
Xiao Zhao
JKJennifer Yin Yee Kwan
Jennifer Yin Yee Kwan
KYKenneth Yip
Kenneth Yip
PLPeter P. Liu
Peter P. Liu
FLFei-Fei Liu
Fei-Fei Liu

5 April 2024 in EBioMedicine
Verified
Journal Article
Open access
MFMackenzie Fijardo
Mackenzie Fijardo
JKJennifer Yin Yee Kwan
Jennifer Yin Yee Kwan
PBPierre-Antoine Bissey
Pierre-Antoine Bissey
DCDeborah E. Citrin
Deborah E. Citrin
KYKenneth W. Yip
Kenneth W. Yip
FLFei-Fei Liu
Fei-Fei Liu
Advances in radiation techniques have enabled the precise delivery of higher doses of radiotherapy to tumours, while sparing surrounding healthy tissues. Consequently, the incidence of radiation toxicities has declined, and will likely continue to improve as radiotherapy further evolves. Nonetheless, ionizing radiation elicits tissue-specific toxicities that gradually develop into radiation-induced fibrosis, a common long-term side-effect of radiotherapy. Radiation fibrosis is characterized by an aberrant wound repair process, which promotes the deposition of extensive scar tissue, clinically manifesting as a loss of elasticity, tissue thickening, and organ-specific functional consequences. In addition to improving the existing technologies and guidelines directing the administration of radiotherapy, understanding the pathogenesis underlying radiation fibrosis is essential for the success of cancer treatments. This review integrates the principles for radiotherapy dosimetry to minimize off-target effects, the tissue-specific clinical manifestations, the key cellular and molecular drivers of radiation fibrosis, and emerging therapeutic opportunities for both prevention and treatment.

1 June 2021 in Computers in Biology and Medicine
Verified
Journal Article
Open access
RRReza Reiazi
Reza Reiazi
EAEngy Abbas
Engy Abbas
PFPetra Famiyeh
Petra Famiyeh
ARAria Rezaie
Aria Rezaie
JKJennifer Y.Y. Kwan
Jennifer Y.Y. Kwan
BHBenjamin Haibe-Kains
Benjamin Haibe-Kains
The field of radiomics is at the forefront of personalized medicine. However, there is concern that high variation in imaging parameters will impact robustness of radiomic features and subsequently the performance of the predictive models built upon them. Therefore, our review aims to evaluate the impact of imaging parameters on the robustness of radiomic features. We also provide insights into the validity and discrepancy of different methodologies applied to investigate the robustness of radiomic features. We selected 47 papers based on our predefined inclusion criteria and grouped these papers by the imaging parameter under investigation: (i) scanner parameters, (ii) acquisition parameters and (iii) reconstruction parameters. Our review highlighted that most of the imaging parameters are disruptive parameters, and shape along with First order statistics were reported as the most robust radiomic features against variation in imaging parameters. This review identified inconsistencies related to the methodology of the reviewed studies such as the metrics used for robustness, the feature extraction techniques, the reporting style, and their outcome inclusion. We hope this review will aid the scientific community in conducting research in a way that is more reproducible and avoids the pitfalls of previous analyses.

1 December 2024 in JCO Clinical Cancer Informatics
Verified
Journal Article
Closed access
SVSanam Tabataba Vakili
Sanam Tabataba Vakili
DHDarren Haywood
Darren Haywood
DKDeborah Kirk
Deborah Kirk
AAAalaa M. Abdou
Aalaa M. Abdou
RGRagisha Gopalakrishnan
Ragisha Gopalakrishnan
OGon behalf of the Multinational Association of Supportive Care in Cancer (MASCC) Survivorship Study Group
on behalf of the Multinational Association of Supportive Care in Cancer (MASCC) Survivorship Study Group
PURPOSE: The adoption of artificial intelligence (AI) in health care may afford new avenues for personalized and patient-centered care. This systematic review explored the role of AI in symptom monitoring for adult cancer survivors. METHODS: A comprehensive search was performed from inception to November 2023 in seven bibliographic databases and three clinical trial registries. This PROSPERO registered review (ID: CRD42023476027) assessed reports of empirical research studies of AI use in symptom monitoring (physical and psychological symptoms) across all cancer types in adults. RESULTS: A total of 18,530 reports were identified, of which 41 met review criteria and were analyzed. Included studies were predominantly published between 2021 and 2023, originated in the United States (39.0%) and Japan (14.6%), and primarily used cohort designs (80.5%), followed by cross-sectional designs (12.2%). The mean sample size was 617.14 (standard deviation = 1,401.37), with most studies primarily including multiple tumor types (31.7%) or breast cancer survivors (26.8%). Machine learning algorithms (43.9%) was the most used AI method, followed by natural language processing (29.3%), AI-driven chatbots (17.1%), and decision support tools (9.8%). The most common inputs to the AI algorithms were textual data, patient-reported symptoms, and physiologic measurements. The most examined symptom was pain (34.2% of studies), followed by fatigue and nausea (17.1% of studies each). Overall, the review showed increasing AI technology use in the prediction and monitoring of cancer symptoms. CONCLUSION: AI is being used to enhance symptom monitoring in various cancer settings. When considering integration into clinical practice, standardization of data capture, the use of analytics, investing in infrastructure, and the end-user experience should be considered for successful implementation and monitoring the improvement of patient outcomes.

5 March 2025 in Clinical Breast Cancer
Verified
Journal Article
Open access
NLNeil Lin
Neil Lin
FAFarnoosh Abbas-Aghababazadeh
Farnoosh Abbas-Aghababazadeh
JSJie Su
Jie Su
AWAlison J. Wu
Alison J. Wu
CLCherie Lin
Cherie Lin
JKJennifer Y.Y. Kwan
Jennifer Y.Y. Kwan
Radiation dermatitis (RD) is a significant side effect of radiotherapy experienced by breast cancer patients. Severe symptoms include desquamation or ulceration of irradiated skin, which impacts quality of life and increases healthcare costs. Early identification of patients at risk for severe RD can facilitate preventive management and reduce severe symptoms. This study evaluated the utility of subjective and objective factors, such as patient-reported outcomes (PROs) and serum cytokines, for predicting RD in breast cancer patients. The performance of machine learning (ML) and logistic regression-based models were compared. Data from 147 breast cancer patients who underwent radiotherapy was analyzed to develop prognostic models. ML algorithms, including neural networks, random forest, XGBoost, and logistic regression, were employed to predict clinically significant Grade 2+ RD. Clinical factors, PROs, and cytokine biomarkers were incorporated into the risk models. Model performance was evaluated using nested cross-validation with separate loops for hyperparameter tuning and calculating performance metrics. Feature selection identified 18 predictors of Grade 2+ RD including smoking, radiotherapy boost, reduced motivation, and the cytokines interleukin-4, interleukin-17, interleukin-1RA, interferon-gamma, and stromal cell-derived factor-1a. Incorporating these predictors, the XGBoost model achieved the highest performance with an area under the curve (AUC) of 0.780 (95% CI: 0.701-0.854). This was not significantly improved over the logistic regression model, which demonstrated an AUC of 0.714 (95% CI: 0.629-0.798). Clinical risk factors, PROs, and serum cytokine levels provide complementary prognostic information for predicting severe RD in breast cancer patients undergoing radiotherapy. ML and logistic regression models demonstrated comparable performance for predicting clinically significant RD with AUC>0.70.

2 January 2025 in JAMA Network Open
Verified
Journal Article
Open access
CLCherie Lin
Cherie Lin
JSJie Su
Jie Su
AWAlison J. Wu
Alison J. Wu
NLNeil Lin
Neil Lin
MHMadison-Shira Hossack
Madison-Shira Hossack
JKJennifer Y. Y. Kwan
Jennifer Y. Y. Kwan
Importance: Secondary lymphedema is a common, harmful side effect of breast cancer treatment. Robust risk models that are externally validated are needed to facilitate clinical translation. A published risk model used 5 accessible clinical factors to predict the development of breast cancer–related lymphedema; this model included a patient’s mammographic breast density as a novel predictive factor.Objective: To investigate the external validity of a previously reported 5-factor model by applying it to an independent cohort of patients with breast cancer.Design, Setting, and Participants: This prognostic study collected data on a longitudinal cohort of patients with predominantly early-stage breast cancer treated with curative intent at the Princess Margaret Cancer Centre in Toronto, Canada between February 1, 2010, and July 31, 2014, with a median (IQR) follow-up of 4.3 (2.4-7.6) years. The 5 factors (age, body mass index, breast density, nodal burden, and use of axillary lymph node dissection [ALND]) were used as input into the established regression-based model. The analysis was performed from July 2 through August 29, 2024.Exposure: Lymphedema after breast cancer treatment.Main Outcomes and Measures: Lymphedema-free survival (LFS) was analyzed using Kaplan-Meier analysis, and sensitivity, specificity, and accuracy performance metrics of predicting breast cancer–related lymphedema were calculated.Results: A total of 101 female patients (median [IQR] age, 54.8 [48.8-62.3] years) were included in the analysis. These patients had localized or locoregional breast cancer treated with primary lumpectomy (90 [89%]) or mastectomy (11 [11%]); 75 (74%) had no axillary biopsy or sentinel lymph node biopsy; 26 (26%) had undergone ALND; and 38 (38%) had received chemotherapy, 101 (100%) received radiotherapy, and 64 (63%) received hormone therapy. Kaplan-Meier analysis showed a 2-year LFS of 97.5% (95% CI, 94.0%-100.0%) vs 65.0% (95% CI, 47.1%-89.7%) for the low- vs high-risk groups as defined by the 5-factor model (P < .001). The model sensitivity was 0.83 (95% CI, 0.52-0.98), specificity was 0.89 (95% CI, 0.80-0.94), and accuracy was 0.88 (95% CI, 0.80-0.94) for predicting breast cancer–related lymphedema.Conclusions and Relevance: These findings validate the performance of a 5-factor risk model for its prediction of 2-year LFS. Future clinical translation of this model can help with identifying patients at the highest risk of breast cancer–related lymphedema to facilitate closer surveillance and/or preventive management to improve health outcomes and quality of life.