Michael C. Tjong

Michael C. Tjong

Auto-generated profile, based on publicly available information

Michael C. Tjong

Department of Radiation Oncology, Dana-Farber Cancer Institute and Brigham and Women's Hospital, Boston, MA, United States

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
3 July 2021 in The Oncologist
Verified
Journal Article
Open access
PDF file
MTMichael C. Tjong
Michael C. Tjong
MDMark Doherty
Mark Doherty
HTHendrick Tan
Hendrick Tan
WCWing C. Chan
Wing C. Chan
HZHaoyu Zhao
Haoyu Zhao
ALAlexander Louie
Alexander Louie
Background: In Ontario, Canada, patient-reported outcome (PRO) evaluation through the Edmonton Symptom Assessment System (ESAS) has been integrated into clinical workflow since 2007. As stage IV non-small cell lung cancer (NSCLC) is associated with substantial disease and treatment-related morbidity, this province-wide study investigated moderate to severe symptom burden in this population. Materials and Methods: ESAS collected from patients with stage IV NSCLC diagnosed between 2007 and 2018 linked to the Ontario provincial health care system database were studied. ESAS acquired within 12 months following diagnosis were analyzed and the proportion reporting moderate to severe scores (ESAS ≥4) in each domain was calculated. Predictors of moderate to severe scores were identified using multivariable Poisson regression models with robust error variance. Results: Of 22,799 patients, 13,289 (58.3%) completed ESAS (84,373 assessments) in the year following diagnosis. Patients with older age, with high comorbidity, and not receiving active cancer therapy had lower ESAS completion. The majority (94.4%) reported at least one moderate to severe symptom. The most prevalent were tiredness (84.1%), low well-being (80.7%), low appetite (71.7%), and shortness of breath (67.8%). Most symptoms peaked at diagnosis and, while declining, remained high in the following year. On multivariable analyses, comorbidity, low income, nonimmigrants, and urban residency were associated with moderate to severe symptoms. Moderate to severe scores in all ESAS domains aside from anxiety were associated with radiotherapy within 2 weeks prior, whereas drowsiness, low appetite and well-being, nausea, and tiredness were associated with systemic therapy within 2 weeks prior. Conclusion: This province-wide PRO analysis showed moderate to severe symptoms were prevalent and persistent among patients with metastatic NSCLC, underscoring the need to address supportive measures in this population especially around treatments. Implications for Practice: In this largest study of lung cancer patient-reported outcomes (PROs), stage IV non-small cell lung cancer patients had worse moderate-to-severe symptoms than other metastatic malignancies such as breast or gastrointestinal cancers when assessed with similar methodology. Prevalence of moderate-to-severe symptoms peaked early and remained high during the first year of follow-up. Symptom burden was associated with recent radiation and systemic treatments. Early and sustained PRO collection is important to detect actionable symptom progression, especially around treatments. Vulnerable patients (e.g., older, high comorbidity) who face barriers in attending in-person clinic visits had lower PRO completion. Virtual PRO collection may improve completion.

1 July 2024 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
ABAidan Boyd
Aidan Boyd
ZYZezhong Ye
Zezhong Ye
SPSanjay P Prabhu
Sanjay P Prabhu
MTMichael C. Tjong
Michael C. Tjong
YZYining Zha
Yining Zha
BKBenjamin H. Kann
Benjamin H. Kann
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop, externally test, and evaluate clinical acceptability of a deep learning (DL) pediatric brain tumor segmentation model using stepwise transfer learning. Materials and Methods In this retrospective study, the authors leveraged two T2-weighted MRI datasets (May 2001-December 2015) from a national brain tumor consortium (n = 184; median age, 7 years (range: 1-23 years); 94 male) and a pediatric cancer center (n = 100; median age, 8 years (range: 1-19 years); 47 male) to develop and evaluate DL neural networks for pediatric low-grade glioma segmentation using a novel stepwise transfer learning approach to maximize performance in a limited data scenario. The best model was externally-tested on an independent test set and subjected to randomized, blinded evaluation by three clinicians, wherein they assessed clinical acceptability of expert- and artificial intelligence (AI)-generated segmentations via 10-point Likert scales and Turing tests. Results The best AI model used in-domain, stepwise transfer learning (median DSC: 0.88 [IQR 0.72-0.91] versus 0.812 [0.56-0.89] for baseline model; P = .049). On external testing, AI model yielded excellent accuracy using reference standards from three clinical experts (Expert-1: 0.83 [0.75-0.90]; Expert-2: 0.81 [0.70-0.89]; Expert-3: 0.81 [0.68-0.88]; mean accuracy: 0.82)). On clinical benchmarking (n = 100 scans), experts rated AI-based segmentations higher on average compared with other experts (median Likert score: median 9 [IQR 7-9]) versus 7 [IQR 7-9]) and rated more AI segmentations as clinically acceptable (80.2% versus 65.4%). Experts correctly predicted the origin of AI segmentations in an average of 26.0% of cases. Conclusion Stepwise transfer learning enabled expert-level, automated pediatric brain tumor auto-segmentation and volumetric measurement with a high level of clinical acceptability. ©RSNA, 2024.

24 July 2023 in Clinical and Translational Radiation Oncology
Verified
Journal Article
Open access
MTM.C. Tjong
M.C. Tjong
SZS.C. Zhang
S.C. Zhang
JGJ.O. Gasho
J.O. Gasho
KSK.D. Silos
K.D. Silos
CGC. Gay
C. Gay
KAKatelyn M. Atkins
Katelyn M. Atkins
Major adverse cardiac events(MACE) are prevalent in patients with locally advanced-non-small cell lung cancer(LA-NSCLC) following radiotherapy(RT). The CHyLL model, incorporating coronary heart disease(CHD),Hypertension(HTN),Logarithmic LADV15 was developed and internally-validated to predict MACE among LA-NSCLC patients. We sought to externally validate CHyLL to predict MACE in an independent LA-NSCLC cohort. Patients with LA-NSCLC treated with RT were included. CHyLL score was calculated:5.51CHD + 1.28HTN + 1.48ln(LADV15 + 1)-1.36CHD*ln(LADV15 + 1). CHyLL performance in predicting MACE was assessed and compared to mean heart dose(MHD) using Cox-proportional hazard(PH) analyses and Harrel’s concordance(C)-indices. MACE and overall survival(OS) among low-vs high-risk groups(CHyLL < 5 vs ≥ 5) were compared. In the external validation cohort(N = 102), the median age was 71 years and 55% were females. Most(n = 74,73%), had clinical Stage III disease and 35(34%) underwent surgery. CHyLL demonstrated good MACE prediction with C-index of 0.73(95% Confidence Interval(CI):0.58–0.89), while MHD did not (C-index = 0.46 (95% CI:0.30–0.62)). Per CHyLL, 32(31%) and 70(69%) patients were considered low-and high-risk for MACE, respectively. CHyLL consistently identified lower MACE rates in the low-vs high-risk group(log-rank p = 0.108):0 vs 8%(12 months),5 vs 16%(24 months),5 vs 16%(36 months),and 5 vs 19%(48 months) post-RT. In the pooled internal and external validation cohort(N = 303), MACE rates in low-vs high-risk groups were statistically significantly different(log-rank p = 0.01):1 vs 6%(12 months),3 vs 12%(24 months),6 vs 19%(36 months),and 6 vs 21%(48 months). CHyLL was externally validated and superior to MHD in predicting MACE. CHyLL has the potential to identify high-risk patients who may benefit from cardio-oncology optimization and to estimate personalized LADV15 constraints based on cardiac risk factors and acceptable MACE thresholds.

15 March 2019 in European Urology Supplements
Verified
Journal Article
Closed access
KAKhaled Ajib
Khaled Ajib
MTM. Tjong
M. Tjong
ILI. Lunsky
I. Lunsky
GTG.H. Tan
G.H. Tan
GNG. Nason
G. Nason
GKG. Kulkarni
G. Kulkarni