Tran Truong

Tran Truong

Auto-generated profile, based on publicly available information

Tran Truong

Techna Health Informatics Research, University Health Network, Canada

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
4 November 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
ASAmir H Safavi
Amir H Safavi
MLMike Lovas
Mike Lovas
ZLZhihui Liu
Zhihui Liu
SMSheena Melwani
Sheena Melwani
TTTran Truong
Tran Truong
ABAlejandro Berlin
Alejandro Berlin
Background: Virtual care (VC) visits (telephone or video) and email-based patient communication have been rapidly adopted to facilitate cancer care during the COVID-19 pandemic. Inequities in access and patient experience may arise as these digital health tools become prevalent. Objective: We aimed to characterize inequities in access and patient-reported experience following adoption of digital health tools at a tertiary cancer center during the COVID-19 pandemic. Methods: We designed a cross-sectional study of outpatients with visits from September to December 2020. Patient characteristics and responses to an email-based patient-experience survey were collated. Inequities in access were assessed across three pairs of comparison groups: (1) patients with VC and in-person visits, (2) patients with and without documented email addresses, and (3) responders and nonresponders to the survey. Inequities in patient-reported experience were assessed among survey responders. Demographics were mapped to area-level averages from national census data. Socioeconomic status was mapped to area-level dimensions of the Canadian Index of Multiple Deprivation. Covariate balance between comparison groups was assessed using standardized mean differences (SMDs), with SMD≥0.2 indicating differences between groups. Associations between patient experience satisfaction scores and covariates were assessed using multivariable analyses, with P<.05 indicating statistical significance. Results: Among the 42,194 patients who had outpatient visits, 62.65% (n=26,435) had at least one VC visit and 31.15% (n=13,144) were emailable. Access to VC and email was similar across demographic and socioeconomic indices (SMD<0.2). Among emailable patients, 21.84% (2870/13,144) responded to the survey. Survey responsiveness was similar across indices, aside from a small difference by age (SMD=0.24). Among responders, 24.4% received VC and were similar to in-person responders across indices (SMD.05). Regardless of visit type, patients had variable satisfaction with care domains across demographic and socioeconomic indices. Patients with higher ethnocultural composition scores were less satisfied with the cultural appropriateness of their care (odds ratio [OR] 0.70, 95% CI 0.57-0.86). Patients with higher situational vulnerability scores were less satisfied with discussion of physical symptoms (OR 0.67, 95% CI 0.48-0.93). Patients with higher residential instability scores were less satisfied with discussion of both physical (OR 0.81, 95% CI 0.68-0.97) and emotional (OR 0.86, 95% CI 0.77-0.96) symptoms, and also with the duration of their visit (OR 0.85, 95% CI 0.74-0.98; P=.02). Male patients were more satisfied with how their health care provider had listened to them (OR 1.64, 95% CI 1.11-2.44; P=.01). Conclusions: Adoption of VC and email can equitably maintain access and patient-reported experience in cancer care across demographics and socioeconomic indices. Existing health inequities among structurally marginalized patients must continue to be addressed to improve their care experience.

2 March 2025 in Current Oncology
Verified
Journal Article
Open access
PDF file
YLYvonne W Leung
Yvonne W Leung
JSJeremiah So
Jeremiah So
ASAvneet Sidhu
Avneet Sidhu
VAVeenaajaa Asokan
Veenaajaa Asokan
MGMathew Gancarz
Mathew Gancarz
JWJiahui Wong
Jiahui Wong
The Artificial Intelligence Patient Librarian (AIPL) was designed to meet the psychosocial and supportive care needs of Metastatic Breast Cancer (MBC) patients with HR+/HER2− subtypes. AIPL provides conversational patient education, answers user questions, and offers tailored online resource recommendations. This study, conducted in three phases, assessed AIPL’s impact on patients’ ability to manage their advanced disease. In Phase 1, educational content was adapted for chatbot delivery, and over 100 credible online resources were annotated using a Convolutional Neural Network (CNN) to drive recommendations. Phase 2 involved 42 participants who completed pre- and post-surveys after using AIPL for two weeks. The surveys measured patient activation using the Patient Activation Measure (PAM) tool and evaluated user experience with the System Usability Scale (SUS). Phase 3 included focus groups to explore user experiences in depth. Of the 42 participants, 36 completed the study, with 10 participating in focus groups. Most participants were aged 40–64. PAM scores showed no significant differences between pre-survey (mean = 59.33, SD = 5.19) and post-survey (mean = 59.22, SD = 6.16), while SUS scores indicated good usability. Thematic analysis revealed four key themes: AIPL offers basic wellness and health guidance, provides limited support for managing relationships, offers limited condition-specific medical information, and is unable to offer hope to patients. Despite showing no impact on the PAM, possibly due to high baseline activation, AIPL demonstrated good usability and met basic information needs, particularly for newly diagnosed MBC patients. Future iterations will incorporate a large language model (LLM) to provide more comprehensive and personalized assistance.

1 May 2023 in JCO Oncology Practice
Verified
Journal Article
Closed access
ASAdam Suleman
Adam Suleman
AVAbi Vijenthira
Abi Vijenthira
ZLZhihui Amy Liu
Zhihui Amy Liu
TTTran Truong
Tran Truong
ABAlejandro Berlin
Alejandro Berlin
DRDanielle Rodin
Danielle Rodin
PURPOSE:The use of virtual care rapidly increased during the COVID-19 pandemic and has persisted as a routine method of care delivery. Much of the literature on virtual care in oncology has focused on solid tumors, and little is known about its application in malignant hematology.METHODS:We performed a retrospective review of patients with hematologic malignancies at Princess Margaret Cancer Centre from October 2019 to March 2021 to determine the use of virtual care during this period, cost-savings associated with virtual visits, and patient satisfaction. Patient satisfaction was assessed using the Your Voice Matters survey, a provincially administered survey to evaluate patient experience.RESULTS:Overall, 12.1% (1,122/9,295) of patients had a virtual visit during the study period (0% from October 2019 to February 2020, 36% from March to August 2020, and 30% from September 2020 to March 2021), of which 36% were in the lymphoma clinic and 46% were in the myeloma clinic. The mean two-way opportunity cost for an in-person visit was $168.00 CAD per person with public transit, and $120.40 CAD per person driving. Responses to the Your Voice Matters survey indicated that patients with a virtual visit reported that physical symptoms were discussed appropriately (mean 4.73/5), and were more likely to ask for a follow-up virtual visit compared with patients with in-person visits (mean 4.50/5 v 3.02/5, respectively; P < .01).CONCLUSION:These findings suggest that virtual care may be a feasible and well-received tool for delivering care to a substantial proportion of patients with hematologic malignancies, while enabling substantial cost-savings to patients.

20 February 2020 in Journal of Clinical Oncology
Verified
Journal Article
Closed access
RHRobert James Hamilton
Robert James Hamilton
LLLauren Landoni
Lauren Landoni
KKKopika Kuhathaas
Kopika Kuhathaas
PCPeter Chung
Peter Chung
PBPhilippe L. Bedard
Philippe L. Bedard
MJMichael A.S. Jewett
Michael A.S. Jewett
396 Background: Most guidelines recommend active surveillance (AS) as initial management for stage I testis cancer (TC). AS entails blood work and imaging at regular intervals requiring multiple clinic visits spanning 5 years. This can be time-consuming, difficult to adhere to, dissatisfying and costly for patients and health care systems. We innovated a secure online platform, WATChmAN (Web-based virtuAl Testicular CANcer clinic) allowing asynchronous communication between patients, results, and physician team. Methods: We are conducting an RCT (NCT03360994) where patients with stage I TC on AS are randomized to virtual care (WATChmAN), or standard in-person care. Primary endpoint is safety: examining loss-to-follow-up and compliance with AS schedules, incidence of relapse, delays in detection of relapse, and burden of relapse. Non-compliance represents a) patient-derived delay in visit; or b) follow-up visit with incomplete testing. Secondary endpoints include: patient/physician satisfaction and cost savings. Results: At present, 102 of a planned 144 patients are enrolled: 51 to virtual care, and 51 to standard in-person care. More patients in the virtual arm have been compliant with AS schedules (89% vs 73%) with shorter median compliance delays (12 vs. 14 days). To date, 10 patients have relapsed: 6 virtual (11.8%) and 4 standard (7.8%). Median time to relapse was shorter for the virtual arm (8 vs. 9.5 months), with no difference in burden of disease at relapse. Response rates to 6-month surveys were 90% and 59% for virtual and standard arms respectively. When asked if satisfied with their care, on the virtual arm 67% reported “extremely satisfied”, and 33% “satisfied” compared to 50% and 45% for the standard arm. When WATChmAN patients were asked if the application is able to provide the same excellence of care as in-person appointments, 82% reported “strongly agree” or “agree”. Conclusions: Interim results suggest virtual care in stage I TC is feasible and safe with improvements in patient satisfaction. Through semi-structured interviews and cost-effectiveness analyses, we anticipate more insight into virtual care. This may serve as a potential model for virtual care for other cancers. Clinical trial information: NCT03360994.

1 September 2025 in JCO Clinical Cancer Informatics
Verified
Journal Article
Open access
BYBaijiang Yuan
Baijiang Yuan
MKMuammar Kabir
Muammar Kabir
JHJiang Chen He
Jiang Chen He
YLYuchen Li
Yuchen Li
BGBenjamin Grant
Benjamin Grant
RGRobert C. Grant
Robert C. Grant
PURPOSE: Cancer and its treatment cause symptoms. In this study, we aimed to develop machine learning (ML) systems that predict future symptom deterioration among people receiving treatment for cancer and then validate the systems in a simulated deployment across an entire health care system. METHODS: We trained and tested ML systems that predict a deterioration in nine patient-reported symptoms within 30 days after treatments for aerodigestive cancers, using internal electronic health record (EHR) data at Princess Margaret Cancer Centre (3,229 patients; 20,267 treatments). The primary performance metric was the area under the receiver operating characteristic curve (AUROC). The best-performing systems in the held-out internal test set were then externally validated across 82 cancer centers in Ontario (12,079 patients; 77,003 treatments) by adapting techniques from meta-analysis. RESULTS: The best ML systems predicted symptom deterioration with AUROCs ranging from 0.66 (95% CI, 0.63 to 0.69) for dyspnea to 0.73 (95% CI, 0.71 to 0.75) for drowsiness in the internal test cohort. Treatments flagged as high-risk were significantly associated with future symptom deterioration (odds ratios [ORs], 2.53-6.56; all P < .001) and emergency department visits for dyspnea (OR, 1.85; P = .008), depression (OR, 1.84; P = .04), and anxiety (OR, 2.66; P < .001). In the external validation cohort, the AUROCs for different symptoms meta-analyzed across centers ranged from 0.67 (95% CI, 0.66 to 0.68) to 0.73 (95% CI, 0.72 to 0.74). Performance across centers displayed significant heterogeneity for six of nine symptoms (I 2 , 46.4%-66.9%; P = .004 for dyspnea, P < .001 for the rest). CONCLUSION: ML can predict future symptoms among people with cancer from routine EHR data, which could guide personalized interventions. Heterogeneous performance across centers must be considered when systems are deployed across a health care system.

21 March 2025 in International Journal of Gynecological Cancer
Verified
Journal Article
Closed access
MKMelissa Kozak
Melissa Kozak
AMAinhoa Madariaga
Ainhoa Madariaga
YGYuliya Gavrylyuk
Yuliya Gavrylyuk
GBGenevieve Bouchard-Fortier
Genevieve Bouchard-Fortier
VBValerie Bowering
Valerie Bowering
ABAlejandro Berlin
Alejandro Berlin