Ruchi Thanawala
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ruchi Thanawala has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Phillip D. Jenkins
Surgical Data and Decision Sciences Lab, Department of Surgery, Oregon Health & Science University, Portland, Oregon
7 shared publications - Jonathan Jesneck
Firefly Foundation, Lake Oswego, Oregon
6 shared publications - Julie Doberne
Division of Cardiothoracic Surgery, Department of Surgery, Oregon Health & Science University, Portland, USA
6 shared publications Emily Lee
Biostatistics and Design Program, Oregon Health & Science University (OHSU) Portland, Oregon
3 shared publications- Mackenzie R. Cook
Department of Surgery, Oregon Health & Science University, Portland, Oregon
3 shared publications - Rebecca Rhee
Department of Surgery, Maimonides Medical Center, Brooklyn, New York
3 shared publications
Latest Publications
- 26 June 2026
- Published by Elsevier in Journal of Surgical Education
- Vol. 83 (9) , 104057
Surgical Education as a Complex Adaptive System: The Need for Pedagogical Competence
- 26 June 2026
- Published by Elsevier in Journal of Surgical Education
- Vol. 83 (9) , 104057
Surgical Education as a Complex Adaptive System: The Need for Pedagogical Competence
- 16 June 2026
- Published by Elsevier in Journal of Surgical Education
- Vol. 83 (9) , 104022
Leveraging Natural Language Processing and Structured Scoring to Evaluate Operative Note Quality in Surgical Training
- 16 June 2026
- Published by Elsevier in Journal of Surgical Education
- Vol. 83 (9) , 104022
Leveraging Natural Language Processing and Structured Scoring to Evaluate Operative Note Quality in Surgical Training
- Open Access
- 1 January 2026
- Published by The Pacific Northwest Journal of Surgery in The Pacific Northwest Journal of Surgery
- Vol. 3 (1) , 13-17
Case Report: Feasibility of Video-Assisted Thoracoscopic Thymectomy in Giant Thymoma
Background: Thymomas are slow-growing mediastinal masses, usually resectable through minimally invasive approaches. However, some thymomas, referred to as 'giant thymomas', can exceed 10 cm and are thought to require open resection. There are few reports of successful removal via video assisted thoracoscopic surgery (VATS) in adults. We present the first case of a giant thymoma resected via VATS in the pediatric population. Case Presentation: A 17-year-old female presented with a bilobed, anterior mediastinal mass. Three family members had history of thymoma resected via median sternotomy. Adult thoracic surgery and pediatric surgery collaborated on a bilateral VATS approach with left mini thoracotomy for mass extraction. On gross pathology, the specimen measured 16 cm in maximum dimension and the margins were negative. Epidural analgesia was utilized with minimal postoperative opioid needs. The patient was discharged to home on post-operative day 3. Conclusion: Bilateral VATS with mini-thoracotomy for extraction is a feasible approach for the resection of a pediatric, giant thymoma. Comprehensive pain management, including a thoracic epidural, allowed for excellent pain control and facilitated rapid discharge. Collaboration between adult thoracic surgery and pediatric general surgery was fundamental to the success of this approach.
- 1 January 2026
- Published by The Pacific Northwest Journal of Surgery in The Pacific Northwest Journal of Surgery
- Vol. 3 (1) , 13-17
Open AccessCase Report: Feasibility of Video-Assisted Thoracoscopic Thymectomy in Giant Thymoma
Background: Thymomas are slow-growing mediastinal masses, usually resectable through minimally invasive approaches. However, some thymomas, referred to as 'giant thymomas', can exceed 10 cm and are thought to require open resection. There are few reports of successful removal via video assisted thoracoscopic surgery (VATS) in adults. We present the first case of a giant thymoma resected via VATS in the pediatric population. Case Presentation: A 17-year-old female presented with a bilobed, anterior mediastinal mass. Three family members had history of thymoma resected via median sternotomy. Adult thoracic surgery and pediatric surgery collaborated on a bilateral VATS approach with left mini thoracotomy for mass extraction. On gross pathology, the specimen measured 16 cm in maximum dimension and the margins were negative. Epidural analgesia was utilized with minimal postoperative opioid needs. The patient was discharged to home on post-operative day 3. Conclusion: Bilateral VATS with mini-thoracotomy for extraction is a feasible approach for the resection of a pediatric, giant thymoma. Comprehensive pain management, including a thoracic epidural, allowed for excellent pain control and facilitated rapid discharge. Collaboration between adult thoracic surgery and pediatric general surgery was fundamental to the success of this approach.
- Open Access
- 1 January 2026
- Published by The Pacific Northwest Journal of Surgery in The Pacific Northwest Journal of Surgery
- Vol. 3 (1) , 4-12
Comparative Performance of Logistic Regression, XGBoost, and Multilayer Perceptron for Mortality and Treatment Strategy Prediction in Blunt Thoracic Aortic Injury
Introduction: Blunt thoracic aortic injury (BTAI) is a rare but lethal trauma mechanism. Mortality prediction has traditionally relied on logistic regression (LR), yet machine learning (ML) methods may better capture complex nonlinear relationships. Methods: Using the Aortic Trauma Foundation registry, we compared LR, extreme gradient boosting (XGB), and multilayer perceptron (MLP) for two tasks: (1) in-hospital mortality prediction and (2) classification of management strategy, open surgical repair (OSR), thoracic endovascular aortic repair (TEVAR), or medical management alone (MMA). Explanatory LR models identified independent predictors; predictive models targeted ~80% sensitivity in test sets. Performance metrics included area under the receiver operating characteristic curve (AUC), average precision, accuracy, F1 score, precision, recall, and Brier score. Results: Explanatory LR for mortality achieved excellent discrimination (AUC = 0.961), with higher Injury Severity Score, age, and ICU length of stay predicting increased mortality, and conversely, higher Glasgow Coma Scale, pH, and hospital stay protective. Predictive LR and XGB performed similarly (AUCs = 0.849 and 0.855; Brier = 0.083 and 0.101), both outperforming MLP (AUC = 0.757). For management strategy, explanatory LR identified limited predictors (e.g., ISS for OSR; age, heart rate, platelet count, and ISS for TEVAR). Predictive performance was modest: XGB (accuracy = 0.690; macro-AUC = 0.648) slightly outperformed MLP (accuracy = 0.667; macro-AUC = 0.565). Conclusions: Well-specified LR matched XGB for mortality prediction in BTAI, offering interpretability with high accuracy. Management strategy prediction remained limited across models, likely reflecting unmeasured institutional and procedural factors. Enriching datasets with imaging and practice-pattern variables may improve operative decision modeling.
- 1 January 2026
- Published by The Pacific Northwest Journal of Surgery in The Pacific Northwest Journal of Surgery
- Vol. 3 (1) , 4-12
Open AccessComparative Performance of Logistic Regression, XGBoost, and Multilayer Perceptron for Mortality and Treatment Strategy Prediction in Blunt Thoracic Aortic Injury
Introduction: Blunt thoracic aortic injury (BTAI) is a rare but lethal trauma mechanism. Mortality prediction has traditionally relied on logistic regression (LR), yet machine learning (ML) methods may better capture complex nonlinear relationships. Methods: Using the Aortic Trauma Foundation registry, we compared LR, extreme gradient boosting (XGB), and multilayer perceptron (MLP) for two tasks: (1) in-hospital mortality prediction and (2) classification of management strategy, open surgical repair (OSR), thoracic endovascular aortic repair (TEVAR), or medical management alone (MMA). Explanatory LR models identified independent predictors; predictive models targeted ~80% sensitivity in test sets. Performance metrics included area under the receiver operating characteristic curve (AUC), average precision, accuracy, F1 score, precision, recall, and Brier score. Results: Explanatory LR for mortality achieved excellent discrimination (AUC = 0.961), with higher Injury Severity Score, age, and ICU length of stay predicting increased mortality, and conversely, higher Glasgow Coma Scale, pH, and hospital stay protective. Predictive LR and XGB performed similarly (AUCs = 0.849 and 0.855; Brier = 0.083 and 0.101), both outperforming MLP (AUC = 0.757). For management strategy, explanatory LR identified limited predictors (e.g., ISS for OSR; age, heart rate, platelet count, and ISS for TEVAR). Predictive performance was modest: XGB (accuracy = 0.690; macro-AUC = 0.648) slightly outperformed MLP (accuracy = 0.667; macro-AUC = 0.565). Conclusions: Well-specified LR matched XGB for mortality prediction in BTAI, offering interpretability with high accuracy. Management strategy prediction remained limited across models, likely reflecting unmeasured institutional and procedural factors. Enriching datasets with imaging and practice-pattern variables may improve operative decision modeling.
- 9 October 2025
- Published by Elsevier in Journal of Surgical Education
- Vol. 82 (11) , 103737
Profiling and Predicting Faculty Assessment Behavior in Surgical Education
- 9 October 2025
- Published by Elsevier in Journal of Surgical Education
- Vol. 82 (11) , 103737
Profiling and Predicting Faculty Assessment Behavior in Surgical Education
- 27 September 2025
- Published by Elsevier in Journal of Surgical Education
- Vol. 82 (12) , 103708
Not All EPAs Are Created Equal: Fixing Sampling Bias With Utility Modeling
- 27 September 2025
- Published by Elsevier in Journal of Surgical Education
- Vol. 82 (12) , 103708
Not All EPAs Are Created Equal: Fixing Sampling Bias With Utility Modeling
- Open Access
- 3 May 2025
- Published by Elsevier in Annals of Thoracic Surgery Short Reports
- Vol. 3 (4) , 1166-1170
Extending the Reach of Thoracic Surgical Oncology With Telehealth
- 3 May 2025
- Published by Elsevier in Annals of Thoracic Surgery Short Reports
- Vol. 3 (4) , 1166-1170
Open AccessExtending the Reach of Thoracic Surgical Oncology With Telehealth
- Open Access
Profiling and Predicting Faculty Assessment Behavior in Surgical Education
Objective To study and profile the digital assessment behaviors of surgical faculty and residents, and to build a classifier to predict assessment completion, enhancing formative feedback initiatives. Background As competency-based paradigms are integrated into surgical training, developing digital education tools for measuring competency and providing rapid feedback is crucial. Simply making assessments available is inadequate and results in disappointingly low user participation. To optimize engagement and efficacy of these tools, user assessment behaviors need to be studied. Methods User data was aggregated from a HIPAA-compliant electronic health record (EHR)-integrated medical education platform. Faculty and resident behaviors were analyzed with respect to factors, such as time, day, device type, automated reminders, and EHR integration. A graphical convolutional neural network (GCN) model was trained to predict faculty participation in completing assessments. Results 10,729 assessments were completed by 254 attendings for 428 residents across 22 institutions, from 2022 to 2024. 86% of assessments were completed by faculty on weekdays, were significantly influenced by automated platform triggers and EHR integration, and distinct faculty behavior profiles contingent upon time to completion and comment length were established. Residents opened assessments at a median of 1.5 hours of faculty assessment completion, with 96% of assessments viewed by 24 hours. The GCN model successfully predicted faculty assessment completion with 93.5% accuracy and an area under the ROC curve of 0.97. Conclusions Faculty assessment behaviors represent an actionable bottleneck which can be leveraged to optimize and tailor the design of digital education tools, to enhance formative feedback.
Open AccessProfiling and Predicting Faculty Assessment Behavior in Surgical Education
Objective To study and profile the digital assessment behaviors of surgical faculty and residents, and to build a classifier to predict assessment completion, enhancing formative feedback initiatives. Background As competency-based paradigms are integrated into surgical training, developing digital education tools for measuring competency and providing rapid feedback is crucial. Simply making assessments available is inadequate and results in disappointingly low user participation. To optimize engagement and efficacy of these tools, user assessment behaviors need to be studied. Methods User data was aggregated from a HIPAA-compliant electronic health record (EHR)-integrated medical education platform. Faculty and resident behaviors were analyzed with respect to factors, such as time, day, device type, automated reminders, and EHR integration. A graphical convolutional neural network (GCN) model was trained to predict faculty participation in completing assessments. Results 10,729 assessments were completed by 254 attendings for 428 residents across 22 institutions, from 2022 to 2024. 86% of assessments were completed by faculty on weekdays, were significantly influenced by automated platform triggers and EHR integration, and distinct faculty behavior profiles contingent upon time to completion and comment length were established. Residents opened assessments at a median of 1.5 hours of faculty assessment completion, with 96% of assessments viewed by 24 hours. The GCN model successfully predicted faculty assessment completion with 93.5% accuracy and an area under the ROC curve of 0.97. Conclusions Faculty assessment behaviors represent an actionable bottleneck which can be leveraged to optimize and tailor the design of digital education tools, to enhance formative feedback.