1228: Assessing the Surgical Decision-Making Ability of Novice and Proficient Urologists

2007 ◽  
Vol 177 (4S) ◽  
pp. 405-405
Author(s):  
Suman Chatterjee ◽  
Jonathon Ng ◽  
Edward D. Matsumoto
Keyword(s):  
Decision Making ◽  
Surgical Decision ◽  
Surgical Decision Making

Myocardial infarction – An important factor for surgical decision-making?

2008 ◽  
Vol 56 (S 1) ◽  
Author(s):  
B Osswald ◽  
U Tochtermann ◽  
S Keller ◽  
D Badowski-Zyla ◽  
V Gegouskov ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Decision Making ◽  
Surgical Decision ◽  
Surgical Decision Making

scholarly journals 3132 Machine Learning for Prediction of Pathologic Pneumatosis Intestinalis Using CT Scans

2019 ◽  
Vol 3 (s1) ◽  
pp. 60-61
Author(s):  
Kadie Clancy ◽  
Esmaeel Dadashzadeh ◽  
Christof Kaltenmeier ◽  
JB Moses ◽  
Shandong Wu
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Pneumatosis Intestinalis ◽  
Learning Models ◽  
Surgical Decision ◽  
Prediction Task ◽  
Svm Model ◽  
Surgical Decision Making ◽  
Intraoperative Visualization ◽  
Machine Learning Models

OBJECTIVES/SPECIFIC AIMS: This retrospective study aims to create and train machine learning models using a radiomic-based feature extraction method for two classification tasks: benign vs. pathologic PI and operation of benefit vs. operation not needed. The long-term goal of our study is to build a computerized model that incorporates both radiomic features and critical non-imaging clinical factors to improve current surgical decision-making when managing PI patients. METHODS/STUDY POPULATION: Searched radiology reports from 2010-2012 via the UPMC MARS Database for reports containing the term “pneumatosis” (subsequently accounting for negations and age restrictions). Our inclusion criteria included: patient age 18 or older, clinical data available at time of CT diagnosis, and PI visualized on manual review of imaging. Cases with intra-abdominal free air were excluded. Collected CT imaging data and an additional 149 clinical data elements per patient for a total of 75 PI cases. Data collection of an additional 225 patients is ongoing. We trained models for two clinically-relevant prediction tasks. The first (referred to as prediction task 1) classifies between benign and pathologic PI. Benign PI is defined as either lack of intraoperative visualization of transmural intestinal necrosis or successful non-operative management until discharge. Pathologic PI is defined as either intraoperative visualization of transmural PI or withdrawal of care and subsequent death during hospitalization. The distribution of data samples for prediction task 1 is 47 benign cases and 38 pathologic cases. The second (referred to as prediction task 2) classifies between whether the patient benefitted from an operation or not. “Operation of benefit” is defined as patients with PI, be it transmural or simply mucosal, who benefited from an operation. “Operation not needed” is defined as patients who were safely discharged without an operation or patients who had an operation, but nothing was found. The distribution of data samples for prediction task 2 is 37 operation not needed cases and 38 operation of benefit cases. An experienced surgical resident from UPMC manually segmented 3D PI ROIs from the CT scans (5 mm Axial cut) for each case. The most concerning ~10-15 cm segment of bowel for necrosis with a 1 cm margin was selected. A total of 7 slices per patient were segmented for consistency. For both prediction task 1 and prediction task 2, we independently completed the following procedure for testing and training: 1.) Extracted radiomic features from the 3D PI ROIs that resulted in 99 total features. 2.) Used LASSO feature selection to determine the subset of the original 99 features that are most significant for performance of the prediction task. 3.) Used leave-one-out cross-validation for testing and training to account for the small dataset size in our preliminary analysis. Implemented and trained several machine learning models (AdaBoost, SVM, and Naive Bayes). 4.) Evaluated the trained models in terms of AUC and Accuracy and determined the ideal model structure based on these performance metrics. RESULTS/ANTICIPATED RESULTS: Prediction Task 1: The top-performing model for this task was an SVM model trained using 19 features. This model had an AUC of 0.79 and an accuracy of 75%. Prediction Task 2: The top-performing model for this task was an SVM model trained using 28 features. This model had an AUC of 0.74 and an accuracy of 64%. DISCUSSION/SIGNIFICANCE OF IMPACT: To the best of our knowledge, this is the first study to use radiomic-based machine learning models for the prediction of tissue ischemia, specifically intestinal ischemia in the setting of PI. In this preliminary study, which serves as a proof of concept, the performance of our models has demonstrated the potential of machine learning based only on radiomic imaging features to have discriminative power for surgical decision-making problems. While many non-imaging-related clinical factors play a role in the gestalt of clinical decision making when PI presents, we have presented radiomic-based models that may augment this decision-making process, especially for more difficult cases when clinical features indicating acute abdomen are absent. It should be noted that prediction task 2, whether or not a patient presenting with PI would benefit from an operation, has lower performance than prediction task 1 and is also a more challenging task for physicians in real clinical environments. While our results are promising and demonstrate potential, we are currently working to increase our dataset to 300 patients to further train and assess our models. References DuBose, Joseph J., et al. “Pneumatosis Intestinalis Predictive Evaluation Study (PIPES): a multicenter epidemiologic study of the Eastern Association for the Surgery of Trauma.” Journal of Trauma and Acute Care Surgery 75.1 (2013): 15-23. Knechtle, Stuart J., Andrew M. Davidoff, and Reed P. Rice. “Pneumatosis intestinalis. Surgical management and clinical outcome.” Annals of Surgery 212.2 (1990): 160.

scholarly journals Understanding Surgical Decision Making in Early Hepatocellular Carcinoma

2011 ◽  
Vol 29 (6) ◽  
pp. 619-625 ◽  
Author(s):  
Hari Nathan ◽  
John F.P. Bridges ◽  
Richard D. Schulick ◽  
Andrew M. Cameron ◽  
Kenzo Hirose ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Decision Making ◽  
Independent Effect ◽  
Clinical Factors ◽  
Surgical Decision ◽  
Early Hepatocellular Carcinoma ◽  
Early Hcc ◽  
The Impact ◽  
Surgical Decision Making ◽  
Choice Of Therapy

Purpose The choice between liver transplantation (LT), liver resection (LR), and radiofrequency ablation (RFA) as initial therapy for early hepatocellular carcinoma (HCC) is controversial, yet little is known about how surgeons choose therapy for individual patients. We sought to quantify the impact of both clinical factors and surgeon specialty on surgical decision making in early HCC by using conjoint analysis. Methods Surgeons with an interest in liver surgery were invited to complete a Web-based survey including 10 case scenarios. Choice of therapy was then analyzed by using regression models that included both clinical factors and surgeon specialty (non-LT v LT). Results When assessing early HCC occurrences, non-LT surgeons (50% LR; 41% LT; 9% RFA) made significantly different recommendations compared with LT surgeons (63% LT; 31% LR; 6% RFA; P < .001). Clinical factors, including tumor number and size, type of resection required, and platelet count, had significant effects on the choice between LR, LT, and RFA. After adjusting for clinical factors, non-LT surgeons remained more likely than LT surgeons to choose LR compared with LT (relative risk ratio [RRR], 2.67). When the weight of each clinical factor was allowed to vary by surgeon specialty, the residual independent effect of surgeon specialty on the decision between LR and LT was negligible (RRR, 0.93). Conclusion The impact of surgeon specialty on choice of therapy for early HCC is stronger than that of some clinical factors. However, the influence of surgeon specialty does not merely reflect an across-the-board preference for one therapy over another. Rather, certain clinical factors are weighed differently by surgeons in different specialties.

Surgical Decision Making for Unstable Thoracolumbar Spine Injuries

2006 ◽  
Vol 19 (1) ◽  
pp. 1-10 ◽  
Author(s):  
Alexander R Vaccaro ◽  
Moe R Lim ◽  
R John Hurlbert ◽  
Ronald A Lehman ◽  
James Harrop ◽  
...  
Keyword(s):  
Decision Making ◽  
Thoracolumbar Spine ◽  
Surgical Decision ◽  
Spine Injuries ◽  
Surgical Decision Making

119. Indications conference for surgical decision-making in complex spine surgery: creating consensus when the stakes are high

2021 ◽  
Vol 21 (9) ◽  
pp. S58-S59
Author(s):  
Theresa Williamson ◽  
Kelly Murphy ◽  
Isaac O. Karikari ◽  
Clifford L. Crutcher ◽  
Tara Dalton ◽  
...  
Keyword(s):  
Decision Making ◽  
Spine Surgery ◽  
Surgical Decision ◽  
Surgical Decision Making

scholarly journals P2.16-014 Deconstructing Surgical Decision Making

2017 ◽  
Vol 12 (11) ◽  
pp. S2193-S2194
Author(s):  
R. Yip ◽  
K. Li ◽  
C. Henschke ◽  
D. Yankelevitz
Keyword(s):  
Decision Making ◽  
Surgical Decision ◽  
Surgical Decision Making

On-line Flow Cytometry for Real-time Surgical Guidance

Neurosurgery ◽  
2004 ◽  
Vol 55 (3) ◽  
pp. 551-561 ◽  
Author(s):  
Ali H. Mesiwala ◽  
Louis D. Scampavia ◽  
Peter S. Rabinovitch ◽  
Jaromir Ruzicka ◽  
Robert C. Rostomily
Keyword(s):  
Decision Making ◽  
Real Time ◽  
Dna Content ◽  
Time Frame ◽  
Tissue Samples ◽  
Surgical Decision ◽  
Surgical Guidance ◽  
On Line ◽  
Surgical Decision Making ◽  
Line Analysis

Abstract OBJECTIVE: This study tests the feasibility of using on-line analysis of tissue during surgical resection of brain tumors to provide biologically relevant information in a clinically relevant time frame to augment surgical decision making. For the purposes of establishing feasibility, we used measurement of deoxyribonucleic acid (DNA) content as the end point for analysis. METHODS: We investigated the feasibility of interfacing an ultrasonic aspiration (USA) system with a flow cytometer (FC) capable of analyzing DNA content (DNA-FC). The sampling system design, tissue preparation requirements, and time requirements for each step of the on-line analysis system were determined using fresh beef brain tissue samples. We also compared DNA-FC measurements in 28 nonneoplastic human brain samples with DNA-FC measurements in specimens of 11 glioma patients obtained from central tumor regions and surgical margins after macroscopically gross total tumor removal to estimate the potential for analysis of a biological marker to influence surgical decision making. RESULTS: With minimal modification, modern FC systems are fully capable of real-time, intraoperative analysis of USA specimens. The total time required for on-line analysis of USA specimens varies between 36 and 63 seconds; this time includes delivery from the tip of the USA to complete analysis of the specimen. Approximately 60% of this time is required for equilibration of the DNA stain. When compared with values for nonneoplastic human brain samples, 50% of samples (10 of 20) from macroscopically normal glioma surgical margins contained DNA-FC abnormalities potentially indicating residual tumor. CONCLUSION: With an interface of existing technologies, DNA content of brain tissue samples can be analyzed in a meaningful time frame that has the potential to provide real-time information for surgical guidance. The identification of DNA content abnormalities in macroscopically normal tumor resection margins by DNA-FC supports the practical potential for on-line analysis of a tumor marker to guide surgical resections. The development of such a device would provide neurosurgeons with an objective method for intraoperative analysis of a clinically relevant biological parameter that can be measured in real time.

Sign in / Sign up

Export Citation Format

Share Document