RTRyan Shea Ying Cong Tan

Ryan Shea Ying Cong Tan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ryan Shea Ying Cong Tan has a total of 87 co-authors. Here are the top co-authors by number of shared publications:

  • Choon Hua Thng

    Singapore Duke-NUS Medical School, Singapore, Singapore

    2 shared publications
  • Fuh Yong Wong

    Division of Radiation Oncology, National Cancer Centre Singapore, Singapore Health Services, Singapore, Singapore

    2 shared publications
  • Han Jieh Tey

    Division of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore

    2 shared publications
  • Hong Qi Tan

    Division of Radiation Oncology, National Cancer Centre Singapore, Singapore Health Services, Singapore, Singapore

    2 shared publications
  • Iain Bee Huat Tan

    Division of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore

    2 shared publications
  • Irene Teo

    Lien Centre for Palliative Care Duke‐NUS Medical School Singapore

    2 shared publications

Latest Publications

  • Open Access

    Graded Exercise Therapy and Cognitive Behavioral Therapy for Fatigue in Patients With Breast Cancer: Protocol for a Randomized Controlled Pilot Study

    by Joanna Rui En Fong, Pei Ling Tan, Michelle Tian Nee Chow, Whee Sze Ong, Irene Teo, Ryan Shea Ying Cong Tan, Mothi Babu Ramalingam

    Background: Fatigue is a common debilitating symptom of breast cancer (BC), and its treatment may result in a significant symptom burden and affect adherence to treatment. Graded exercise therapy (GET) and cognitive behavioral therapy (CBT) have separately been shown in previous studies to be beneficial for the management of cancer-related fatigue. Objective: This study’s coprimary aims are to assess the feasibility and acceptability of combining GET and CBT for the treatment of fatigue in patients with BC in Singapore. The secondary aims are to generate preliminary efficacy estimates of the combination therapy. Methods: In this randomized controlled pilot study, a total of 100 female patients with BC, with a self-reported rating of at least moderate fatigue (One-Item Fatigue Scale score ≥4), will be recruited and randomized in a 1:1 ratio to undergo a combination of GET and CBT vs GET alone (standard of care). This will include a primary cohort of 90 patients with stage I to III BC who have completed surgery and adjuvant chemotherapy (if indicated), and an exploratory cohort of 10 patients with stage IV BC undergoing systemic therapy. Acceptability will be measured using the Client Satisfaction Questionnaire, including items on cultural sensitivity. Feasibility will be measured by participant uptake, adherence to sessions, and willingness to pay for therapy sessions. Efficacy will be assessed based on quantitative measures of fatigue, treatment adherence, quality of life, and physical and functional outcomes. Results: Recruitment of participants commenced on July 14, 2025, and is projected to be completed by December 31, 2026. The primary completion date is expected to be April 30, 2027, and publication of the final results is expected by the end of 2027. Conclusions: This study will provide evidence on whether a combination of GET and CBT is feasible and acceptable for the treatment of fatigue in patients with BC in Singapore. It supports the refinement of evidence-based fatigue management guidelines and improvements in BC survivorship care.

  • Open Access

    Graded Exercise Therapy and Cognitive Behavioral Therapy for fatigue in breast cancer patients (GET-CBT): protocol for a randomized controlled pilot study (Preprint)

    by Joanna Rui En Fong, Pei Ling Tan, Michelle Tian Nee Chow, Whee Sze Ong, Irene Teo, Ryan Shea Ying Cong Tan, Mothi Babu Ramalingam

    BACKGROUND Fatigue is a common debilitating symptom of breast cancer, and its treatment may result in significant symptom burden and affect adherence to treatment. Graded Exercise Therapy (GET) and Cognitive Behavioral Therapy (CBT) have separately been shown in previous studies to be beneficial for the management of cancer-related fatigue (CRF). OBJECTIVE This study aims to assess the feasibility, acceptability and potential efficacy of combining GET and CBT for treatment of fatigue in breast cancer patients on treatment in Singapore. METHODS In this randomized controlled pilot study, a total of 100 female breast cancer patients, with self-reported rating of at least moderate fatigue (One-item fatigue scale score ≥4) will be recruited and randomized in a 1:1 ratio to undergo a combination of GET and CBT versus GET alone (standard of care). This will include a primary cohort of 90 patients with Stage I to III breast cancer who have completed surgery and adjuvant chemotherapy (if indicated), and an exploratory cohort of 10 patients with Stage IV breast cancer undergoing systemic therapy. Acceptability is measured using client satisfaction questionnaire including items on cultural sensitivity. Feasibility is measured by participant uptake, adherence to sessions and willingness to pay for therapy sessions. Efficacy is assessed based on quantitative measures of fatigue, quality of life, and physical and functional outcomes. RESULTS The recruitment of participants commenced on 14 July 2025 and is projected to be completed by 31 July 2026. Potential extension to this project would be the subsequent expansion of the current exploratory cohort of patients with metastatic breast cancer. CONCLUSIONS The present study compares the use of a combination of GET and CBT against GET alone for management of fatigue in breast cancer survivors, applied to the Singaporean context. The primary aim is to establish feasibility and acceptability of GET and CBT interventions in the local context, with a secondary aim of evaluating efficacy in terms of fatigue, quality of life and functional outcomes. CLINICALTRIAL ClinicalTrials.gov ID: NCT07116161

  • Using Machine Learning Models to Predict Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer

    by Rayhan Erlangga Rahadian, Hong Qi Tan, Bryan Shihan Ho, Arjunan Kumaran, Andre Villanueva, Joy Sng, Ryan Shea Ying Cong Tan, Tira Jing Ying Tan, Veronique Kiak Mien Tan, Benita Kiat Tee Tan, et al.

    PURPOSE: Neoadjuvant chemotherapy (NAC) is increasingly used in breast cancer. Predictive modeling is useful in predicting pathologic complete response (pCR) to NAC. We test machine learning (ML) models to predict pCR in breast cancer and explore methods of handling missing data. METHODS: Four hundred and ninety-nine patients with breast cancer treated with NAC in two centers in Singapore (National Cancer Centre Singapore [NCCS] and KK Hospital) between January 2014 and December 2017 were included. Eleven clinical features were used to train five different ML models. Listwise deletion and imputation were evaluated on handling missing data. Model performance was evaluated by AUC and calibration (Brier score). Feature importance from the best performing model in the external testing data set was calculated using Shapley additive explanations. RESULTS: Seventy-two (24.6%), 18 (24.7%), and 31 (24.8%) patients attained pCR in NCCS training, NCCS testing, and KK Women's and Children's Hospital (KKH) testing data sets, respectively. The random forest (RF) base and imputed models have the highest AUCs in the KKH cohort of 0.794 (95% CI, 0.709 to 0.873) and 0.795 (95% CI, 0.706 to 0.871), respectively, and were the best calibrated with the lowest Brier score. No statistically significant difference was noted between AUCs of the base and imputed models in all data sets. The imputed model had a larger positive predictive value (PPV; 98.2% v 95.1%) and negative predictive value (NPV; 96.7% v 90.0%) than the base model in the KKH data set. Estrogen receptor intensity, human epidermal growth factor 2 intensity, and age at diagnosis were the three most important predictors. CONCLUSION: ML, particularly RF, demonstrates reasonable accuracy in pCR prediction after NAC. Imputing missing fields in the data can improve the PPV and NPV of the pCR prediction model.


  • Open Access

    Use of Natural Language Processing to Infer Sites of Metastatic Disease From Radiology Reports at Scale

    by See Boon Tay, Guat Hwa Low, Gillian Jing En Wong, Han Jieh Tey, Fun Loon Leong, Constance Li, Melvin Lee Kiang Chua, Daniel Shao Weng Tan, Choon Hua Thng, Iain Bee Huat Tan, et al.

    PURPOSE: To evaluate natural language processing (NLP) methods to infer metastatic sites from radiology reports. METHODS: A set of 4,522 computed tomography (CT) reports of 550 patients with 14 types of cancer was used to fine-tune four clinical large language models (LLMs) for multilabel classification of metastatic sites. We also developed an NLP information extraction (IE) system (on the basis of named entity recognition, assertion status detection, and relation extraction) for comparison. Model performances were measured by F1 scores on test and three external validation sets. The best model was used to facilitate analysis of metastatic frequencies in a cohort study of 6,555 patients with 53,838 CT reports. RESULTS: The RadBERT, BioBERT, GatorTron-base, and GatorTron-medium LLMs achieved F1 scores of 0.84, 0.87, 0.89, and 0.91, respectively, on the test set. The IE system performed best, achieving an F1 score of 0.93. F1 scores of the IE system by individual cancer type ranged from 0.89 to 0.96. The IE system attained F1 scores of 0.89, 0.83, and 0.81, respectively, on external validation sets including additional cancer types, positron emission tomography-CT ,and magnetic resonance imaging scans, respectively. In our cohort study, we found that for colorectal cancer, liver-only metastases were higher in de novo stage IV versus recurrent patients (29.7% v 12.2%; P < .001). Conversely, lung-only metastases were more frequent in recurrent versus de novo stage IV patients (17.2% v 7.3%; P < .001). CONCLUSION: We developed an IE system that accurately infers metastatic sites in multiple primary cancers from radiology reports. It has explainable methods and performs better than some clinical LLMs. The inferred metastatic phenotypes could enhance cancer research databases and clinical trial matching, and identify potential patients for oligometastatic interventions.


  • Open Access

    Inferring cancer disease response from radiology reports using large language models with data augmentation and prompting

    by Ryan Shea Ying Cong Tan, Qian Lin, Guat Hwa Low, Ruixi Lin, Tzer Chew Goh, Christopher Chu En Chang, Fung Fung Lee, Wei Yin Chan, Wei Chong Tan, Han Jieh Tey, et al.

    Objective: To assess large language models on their ability to accurately infer cancer disease response from free-text radiology reports. Materials and Methods: We assembled 10 602 computed tomography reports from cancer patients seen at a single institution. All reports were classified into: no evidence of disease, partial response, stable disease, or progressive disease. We applied transformer models, a bidirectional long short-term memory model, a convolutional neural network model, and conventional machine learning methods to this task. Data augmentation using sentence permutation with consistency loss as well as prompt-based fine-tuning were used on the best-performing models. Models were validated on a hold-out test set and an external validation set based on Response Evaluation Criteria in Solid Tumors (RECIST) classifications. Results: The best-performing model was the GatorTron transformer which achieved an accuracy of 0.8916 on the test set and 0.8919 on the RECIST validation set. Data augmentation further improved the accuracy to 0.8976. Prompt-based fine-tuning did not further improve accuracy but was able to reduce the number of training reports to 500 while still achieving good performance. Discussion: These models could be used by researchers to derive progression-free survival in large datasets. It may also serve as a decision support tool by providing clinicians an automated second opinion of disease response. Conclusions: Large clinical language models demonstrate potential to infer cancer disease response from radiology reports at scale. Data augmentation techniques are useful to further improve performance. Prompt-based fine-tuning can significantly reduce the size of the training dataset.


  • Multi-center evaluation of artificial intelligent imaging and clinical models for predicting neoadjuvant chemotherapy response in breast cancer

    by Tan Hong Qi, Ong Hiok Hian, Arjunan Muthu Kumaran, Tira J. Tan, Tan Ryan Ying Cong, Ghislaine Lee Su-Xin, Elaine Hsuen Lim, Raymond Ng, Ming Chert Richard Yeo, Faye Lynette Lim Wei Tching, et al.

    Background Neoadjuvant chemotherapy (NAC) plays an important role in the management of locally advanced breast cancer. It allows for downstaging of tumors, potentially allowing for breast conservation. NAC also allows for in-vivo testing of the tumors’ response to chemotherapy and provides important prognostic information. There are currently no clearly defined clinical models that incorporate imaging with clinical data to predict response to NAC. Thus, the aim of this work is to develop a predictive AI model based on routine CT imaging and clinical parameters to predict response to NAC. Methods The CT scans of 324 patients with NAC from multiple centers in Singapore were used in this study. Four different radiomics models were built for predicting pathological complete response (pCR): first two were based on textural features extracted from peri-tumoral and tumoral regions, the third model based on novel space-resolved radiomics which extract feature maps using voxel-based radiomics and the fourth model based on deep learning (DL). Clinical parameters were included to build a final prognostic model. Results The best performing models were based on space-resolved and DL approaches. Space-resolved radiomics improves the clinical AUCs of pCR prediction from 0.743 (0.650 to 0.831) to 0.775 (0.685 to 0.860) and our DL model improved it from 0.743 (0.650 to 0.831) to 0.772 (0.685 to 0.853). The tumoral radiomics model performs the worst with no improvement of the AUC from the clinical model. The peri-tumoral combined model gives moderate performance with an AUC of 0.765 (0.671 to 0.855). Conclusions Radiomics features extracted from diagnostic CT augment the predictive ability of pCR when combined with clinical features. The novel space-resolved radiomics and DL radiomics approaches outperformed conventional radiomics techniques.


  • Open Access

    Human epidermal growth factor receptor 2 positive rates in invasive lobular breast carcinoma: The Singapore experience

    by Ga-Jing Kee, Ryan Ying-Cong Tan, Sultana Rehena, Joycelyn Jie-Xin Lee, Ma Wai-Wai Zaw, Wei-Xiang Lian, Joe Yeong, Su-Ming Tan, Swee-Ho Lim, Benita Kiat-Tee Tan, et al.

    Human epidermal growth factor receptor 2 positive rates in invasive lobular breast carcinoma: The Singapore experience


  • HER2 positive rates are enriched amongst colorectal cancer brain metastases: a study amongst 1920 consecutive patients

    by R.Y.C. Tan, M D Camat, M. Ng, T.H. Lim, A.S.T. Lim, K.H. Lim, I.B.H. Tan

    Brain metastases from colorectal cancer (CRC) are a rare but increasing event as patients survive longer. While HER2 gene amplification in breast cancer is well described and known to increase risk of brain metastases [1], information in CRC patients with brain metastases is lacking. A multi-centre phase II trial has shown that HER2-directed therapies are efficacious in HER2 positive (HER2+) stage IV CRC without brain metastases [2]. If HER2 is enriched in CRC patients with brain metastases, it may provide a possible therapeutic target.