XCXi Chen

Xi Chen

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xi Chen has a total of 99 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Faculty Diversity Associated With Decreased Orthopaedic Surgery Resident Attrition

    by Xi Chen, Hiroko Matsumoto, Lee S. Haruno, Melodie F. Metzger, Carol A. Lin, Milton T.M. Little, Selina C. Poon

    Introduction: Underrepresented minority (URM) and female orthopaedic surgical residents have an increased risk of attrition. The purpose of this study was to investigate the relationship between orthopaedic faculty demographic diversity and resident attrition. Methods: Demographic data for full-time faculty in departments or divisions of Orthopaedic Surgery at accredited medical schools in the United States and demographic and attrition data for 13,785 affiliated orthopaedic residents were sourced from the Association of American Medical Colleges. Faculty diversity was defined by the number of female and/or URM faculty at medical school affiliated with residency. The faculty per year (FPY) was calculated by dividing the total number of female and URM faculty by the number of years in residency for each resident. The average FPY across all programs was calculated to assess whether programs had above-average FPY (greater faculty diversity) or below-average FPY. This stratification was used to investigate the relationship between faculty diversity and resident attrition. Diverse faculty was defined as the aggregate of URM and female faculty. A p-value of <0.05 was considered statistically significant. Results: Overall resident attrition was 3.2%. Female and URM residents had attrition rates of 6.2% and 6.3%, respectively. The average URM FPY for all orthopaedic surgery departments was 2.0; the average female FPY was 5.8; and the average diverse FPY was 7.5. Residents in programs with above-average female and URM FPY had a decreased risk of attrition (relative risk [RR] = 0.25, p < 0.001; RR = 0.23, p < 0.001, respectively). Programs with below-average female, URM, and diverse FPY significantly increased the risk of all resident attrition by 82% (RR = 1.82, p < 0.001), 47% (RR = 1.47, p < 0.001), and 88% (RR = 1.88, p < 0.001), respectively. Conclusions: Programs with increased racial and gender faculty diversity are associated with lower resident attrition, regardless of resident race or sex. Below-average faculty diversity is associated with the greatest risk of attrition among female and URM residents.


  • Open Access

    Racial and Sex Disparities in Resident Attrition in Orthopaedic Surgery

    by Lee S. Haruno, Xi Chen, Melodie Metzger, Carol A. Lin, Milton T.M. Little, Linda E.A. Kanim, Selina C. Poon

    Background: Studies have suggested that female individuals and individuals from backgrounds under-represented in medicine (URiM) are at increased risk of attrition during residency. This likely exacerbates the lack of diversity in our field. The aims of this study were to (1) characterize demographic composition in orthopaedic residency from 2001 to 2018 and (2) determine the race/ethnicity and identify any disparities. Methods: Demographic and attrition data from 2001 to 2018 were obtained from the Association of American Medical Colleges. Attrition data comprised the following categories: withdrawals, dismissals, and transfers to another specialty. Analysis compared demographic composition and determined attrition rates with subgroup analysis by race/ethnicity and sex. Results: From 2001 to 2018, female orthopaedic residents increased from 8.77% to 15.54% and URiM residents from 9.49% to 11.32%. The overall and unintended attrition rates in orthopaedic surgery were 3.20% and 1.15%, respectively. Among female residents, the overall and unintended attrition rates were 5.96% and 2.09% compared with 2.79% and 1.01%, respectively, in male residents. URiM residents had overall and unintended attrition rates of 6.16% and 3.11% compared with 2.71% and 0.83%, respectively, for their White counterparts. Black/African American residents had an attrition rate of nearly 10%. Female residents averaged 12.9% of all residents but 24% of those leaving orthopaedics. URiM residents were 10.14% of all residents but 19.51% of those experiencing attrition. In logistic regression models, female residents had a relative risk (RR) of 2.20 (p < 0.001) for experiencing all-cause attrition and 2.09 (p < 0.001) for unintended attrition compared with male residents. Compared with their White male counterparts, URiM residents had a RR for overall and unintended attrition of 2.36 and 3.84 (p < 0.001), respectively; Black/African American residents had a RR for the same of 3.80 and 7.20 (p < 0.001), respectively. Conclusion: Although female resident percentage has increased, orthopaedics continues to train fewer female surgeons than all other fields. Female and URiM residents in orthopaedic surgery are disproportionately affected by attrition. While recruitment has been the primary focus of diversity, equity, and inclusion efforts, this study suggests that resident retention through appropriately supporting residents during training is equally critical.


  • Machine learning integration of circulating and imaging biomarkers for explainable patient-specific prediction of cardiac events: A prospective study

    by Balaji K. Tamarappoo, Andrew Lin, Frederic Commandeur, Priscilla A. McElhinney, Sebastien Cadet, Markus Goeller, Aryabod Razipour, Xi Chen, Heidi Gransar, Stephanie Cantu, et al.


  • LONG-TERM PREDICTION OF CARDIAC EVENTS IN ASYMPTOMATIC SUBJECTS BY INTEGRATING NOVEL CIRCULATING AND IMAGING BIOMARKERS USING MACHINE LEARNING

    by Andrew Lin, Balaji Tamarappoo, Frederic Commandeur, Priscilla McElhinney, Sebastien Cadet, Markus Goeller, Xi Chen, Aryabod Razipour, Heidi Gransar, Stephanie Cantu, et al.

  • METABOLIC SYNDROME AND AUTOMATED EPICARDIAL ADIPOSE TISSUE MEASURES PREDICT LONG-TERM RISK OF CARDIAC EVENTS IN ASYMPTOMATIC SUBJECTS

    by Andrew Lin, Nathan D. Wong, Frederic Commandeur, Sebastien Cadet, Heidi Gransar, Xi Chen, Stephanie Cantu, Robert Miller, Priscilla McElhinney, Nitesh Nerlekar, et al.

  • Deep Learning–Based Quantification of Epicardial Adipose Tissue Volume and Attenuation Predicts Major Adverse Cardiovascular Events in Asymptomatic Subjects

    by Evann Eisenberg, Priscilla A. McElhinney, Frederic Commandeur, Xi Chen, Sebastien Cadet, Markus Goeller, Aryabod Razipour, Heidi Gransar, Stephanie Cantu, Robert J.H. Miller, et al.

    Background: Epicardial adipose tissue (EAT) volume (cm 3 ) and attenuation (Hounsfield units) may predict major adverse cardiovascular events (MACE). We aimed to evaluate the prognostic value of fully automated deep learning-based EAT volume and attenuation measurements quantified from noncontrast cardiac computed tomography. Methods: Our study included 2068 asymptomatic subjects (56±9 years, 59% male) from the EISNER trial (Early Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) with long-term follow-up after coronary artery calcium measurement. EAT volume and mean attenuation were quantified using automated deep learning software from noncontrast cardiac computed tomography. MACE was defined as myocardial infarction, late (>180 days) revascularization, and cardiac death. EAT measures were compared to coronary artery calcium score and atherosclerotic cardiovascular disease risk score for MACE prediction. Results: At 14±3 years, 223 subjects suffered MACE. Increased EAT volume and decreased EAT attenuation were both independently associated with MACE. Atherosclerotic cardiovascular disease risk score, coronary artery calcium, and EAT volume were associated with increased risk of MACE (hazard ratio [95%CI]: 1.03 [1.01–1.04]; 1.25 [1.19–1.30]; and 1.35 [1.07–1.68], P P =0.01), with corresponding Harrell C statistic of 0.76. MACE risk progressively increased with EAT volume ≥113 cm 3 and coronary artery calcium ≥100 AU and was highest in subjects with both ( P <0.02 for all). In 1317 subjects, EAT volume was correlated with inflammatory biomarkers C-reactive protein, myeloperoxidase, and adiponectin reduction; EAT attenuation was inversely related to these biomarkers. Conclusions: Fully automated EAT volume and attenuation quantification by deep learning from noncontrast cardiac computed tomography can provide prognostic value for the asymptomatic patient, without additional imaging or physician interaction.


  • Open Access

    Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium, and epicardial adipose tissue: a prospective study

    by Frederic Commandeur, Piotr J Slomka, Markus Goeller, Xi Chen, Sebastien Cadet, Aryabod Razipour, Priscilla McElhinney, Heidi Gransar, Stephanie Cantu, Robert J H Miller, et al.

    Our aim was to evaluate the performance of machine learning (ML), integrating clinical parameters with coronary artery calcium (CAC), and automated epicardial adipose tissue (EAT) quantification, for the prediction of long-term risk of myocardial infarction (MI) and cardiac death in asymptomatic subjects. Our study included 1912 asymptomatic subjects [1117 (58.4%) male, age: 55.8 ± 9.1 years] from the prospective EISNER trial with long-term follow-up after CAC scoring. EAT volume and density were quantified using a fully automated deep learning method. ML extreme gradient boosting was trained using clinical co-variates, plasma lipid panel measurements, risk factors, CAC, aortic calcium, and automated EAT measures, and validated using repeated 10-fold cross validation. During mean follow-up of 14.5 ± 2 years, 76 events of MI and/or cardiac death occurred. ML obtained a significantly higher AUC than atherosclerotic cardiovascular disease (ASCVD) risk and CAC score for predicting events (ML: 0.82; ASCVD: 0.77; CAC: 0.77, P < 0.05 for all). Subjects with a higher ML score (by Youden’s index) had high hazard of suffering events (HR: 10.38, P < 0.001); the relationships persisted in multivariable analysis including ASCVD-risk and CAC measures (HR: 2.94, P = 0.005). Age, ASCVD-risk, and CAC were prognostically important for both genders. Systolic blood pressure was more important than cholesterol in women, and the opposite in men. In this prospective study, machine learning used to integrate clinical and quantitative imaging-based variables significantly improves prediction of MI and cardiac death compared with standard clinical risk assessment. Following further validation, such a personalized paradigm could potentially be used to improve cardiovascular risk assessment.


  • Fully Automated CT Quantification of Epicardial Adipose Tissue by Deep Learning: A Multicenter Study

    by Frederic Commandeur, Markus Goeller, Aryabod Razipour, Sebastien Cadet, Michaela M. Hell, Jacek Kwiecinski, Xi Chen, Hyuk-Jae Chang, Mohamed Marwan, Stephan Achenbach, et al.

    Deep learning allows for fast, robust, and fully automated quantification of epicardial adipose tissue from non–contrast material–enhanced calcium-scoring CT. Purpose To evaluate the performance of deep learning for robust and fully automated quantification of epicardial adipose tissue (EAT) from multicenter cardiac CT data. Materials and Methods In this...


  • Open Access

    Mycobacterium abscessus cutaneous infection secondary to botulinum toxin injection: A report of 2 cases

    by Xi Chen, Yan Jin, Kara Melissa T. Torres, Bo Li, Fenglin Zhuo, Xiaolan Ding, Lin Cai, Jianzhong Zhang, Cheng Zhou


  • 5963Automated quantification of epicardial adipose tissue from non-contrast CT on multi-center and multi-vendor data using deep learning

    by F Commandeur, M Goeller, A Razipour, S Cadet, M M Hell, J Kwiecinski, X Chen, H J Chang, M Marwan, S Achenbach, et al.

    Background: Epicardial adipose tissue (EAT), a metabolically active visceral fat depot surrounding the coronary arteries, has been shown to promote the development of atherosclerosis in underlying coronary vasculature. Purpose: We evaluate the performance of deep learning (DL), a sub-group of machine learning algorithms, for robust and fully automated quantification of EAT on multi-center cardiac CT data. Methods: In this study, 850 non-contrast calcium scoring CT scans, from multiple cohorts, scanners and protocols, with manual measurements of EAT from 3 different readers were considered. The DL method was based on a convolutional neural network trained to reproduce the expert measurement. DL global performance was first assessed using all the scans, and then compared to inter-observer variability on a subset of 141 scans. Finally, automated EAT progression was compared to manual measurement using baseline and follow-up serial scans available for 70 subjects. The proposed model was validated using 10-fold cross validation. Results: Automated quantification was performed in 1.57±0.49 seconds compared to 15 minutes for manual measurement. DL provided high agreement with expert manual quantification for all scans (R=0.974, p<0.001) with no significant bias (0.53 cm3, p=0.13). EAT volume was higher in patients with hypertension (+18.02 cm3, p<0.001, N=442), with diabetes (+18.33 cm3, p<0.001, N=75) and with hypercholesterolemia (+7.33 cm3, p=0.039, N=508). Manual EAT volumes measured by two experienced readers on 141 scans were highly correlated (R=0.984, p<0.001) but presented a significant difference of 4.35 cm3 (p<0.001). On these 141 scans, DL quantifications were highly correlated to both experts' measurements (R=0.973, p<0.001; R=0.979, p<0.001) with significant and non-significant bias for readers 1 and 2 (5.19 cm3, p<0.001; 0.84 cm3, p=0.26), respectively. In 70 subjects, EAT progression quantified by DL correlated strongly with EAT progression measured by the expert reader (R=0.905, p<0.001) with no significant bias (0.64 cm3, p=0.43), and was related to increased non-calcified plaque burden quantified from coronary CT angiography (5.7% vs 1.8%, p=0.026). Automated vs. manual EAT volume Conclusion: Deep learning allows rapid, robust and fully automated quantification of EAT from calcium scoring CT. It performs as an expert reader and can be implemented for routine cardiovascular risk assessment. Acknowledgement/Funding: 1R01HL133616/01EX1012B/Adelson Medical Research Foundation