Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306177812> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4306177812 endingPage "S51" @default.
- W4306177812 startingPage "S51" @default.
- W4306177812 abstract "INTRODUCTION: Studies comparing conversion from laparoscopic to open approach to colectomy have found an association between conversion and morbidity, mortality, and length of stay, suggesting that certain patients may benefit from an open approach “up-front”. The objective of this study was to use machine learning algorithms to develop a model enabling the prediction of which patients are likely to require conversion. METHODS: We used American College of Surgeons NSQIP data to identify patients undergoing colectomy (2014-2019). We included patients undergoing elective colectomy for colorectal neoplasm via a minimally invasive approach or a converted approach. The outcome of interest was conversion. Variables were included in the model based on their correlation with conversion by logistic regression (p < 0.05). Two models were used: weighted logistic regression with regularization, and Random Forest classifier. The data was randomly split into training (70%) and test (30%) cohorts, and prediction performance was calculated. RESULTS: A total of 24,327 cases were included (17,028 training, 7,299 test). When applied to the test cohort, the models had an accuracy of 0.675 (range 0.65-0.70) in predicting conversion; c-index ranged from 0.62-0.63 (Table). This machine learning model achieved a moderate AUC and a high negative predictive value, but a low positive predictive value; therefore, this model can predict (with 95% accuracy) whether a colectomy for neoplasm can be successfully completed using a minimally invasive approach. CONCLUSION: This model can be used to reassure surgeons of the appropriateness of a minimally invasive approach when planning for an elective colectomy. Table. - Predictive Model Performance Metrics Model C-index Accuracy PPV NPV Logistic regression 0.633 0.70 0.11 0.95 Random forest classifier 0.616 0.65 0.10 0.95" @default.
- W4306177812 created "2022-10-14" @default.
- W4306177812 creator A5000064291 @default.
- W4306177812 creator A5001636245 @default.
- W4306177812 creator A5048713481 @default.
- W4306177812 creator A5068964738 @default.
- W4306177812 creator A5081736204 @default.
- W4306177812 date "2022-10-17" @default.
- W4306177812 modified "2023-09-27" @default.
- W4306177812 title "Predicting the Need for Conversion of Operative Approach in Patients Undergoing Colectomy for Neoplasm: A Machine-Learning Model" @default.
- W4306177812 doi "https://doi.org/10.1097/01.xcs.0000893304.27005.55" @default.
- W4306177812 hasPublicationYear "2022" @default.
- W4306177812 type Work @default.
- W4306177812 citedByCount "0" @default.
- W4306177812 crossrefType "journal-article" @default.
- W4306177812 hasAuthorship W4306177812A5000064291 @default.
- W4306177812 hasAuthorship W4306177812A5001636245 @default.
- W4306177812 hasAuthorship W4306177812A5048713481 @default.
- W4306177812 hasAuthorship W4306177812A5068964738 @default.
- W4306177812 hasAuthorship W4306177812A5081736204 @default.
- W4306177812 hasBestOaLocation W43061778121 @default.
- W4306177812 hasConcept C105795698 @default.
- W4306177812 hasConcept C119857082 @default.
- W4306177812 hasConcept C121608353 @default.
- W4306177812 hasConcept C126322002 @default.
- W4306177812 hasConcept C141071460 @default.
- W4306177812 hasConcept C151956035 @default.
- W4306177812 hasConcept C154945302 @default.
- W4306177812 hasConcept C169258074 @default.
- W4306177812 hasConcept C2776667177 @default.
- W4306177812 hasConcept C33923547 @default.
- W4306177812 hasConcept C41008148 @default.
- W4306177812 hasConcept C526805850 @default.
- W4306177812 hasConcept C58471807 @default.
- W4306177812 hasConcept C71924100 @default.
- W4306177812 hasConcept C72563966 @default.
- W4306177812 hasConcept C83546350 @default.
- W4306177812 hasConceptScore W4306177812C105795698 @default.
- W4306177812 hasConceptScore W4306177812C119857082 @default.
- W4306177812 hasConceptScore W4306177812C121608353 @default.
- W4306177812 hasConceptScore W4306177812C126322002 @default.
- W4306177812 hasConceptScore W4306177812C141071460 @default.
- W4306177812 hasConceptScore W4306177812C151956035 @default.
- W4306177812 hasConceptScore W4306177812C154945302 @default.
- W4306177812 hasConceptScore W4306177812C169258074 @default.
- W4306177812 hasConceptScore W4306177812C2776667177 @default.
- W4306177812 hasConceptScore W4306177812C33923547 @default.
- W4306177812 hasConceptScore W4306177812C41008148 @default.
- W4306177812 hasConceptScore W4306177812C526805850 @default.
- W4306177812 hasConceptScore W4306177812C58471807 @default.
- W4306177812 hasConceptScore W4306177812C71924100 @default.
- W4306177812 hasConceptScore W4306177812C72563966 @default.
- W4306177812 hasConceptScore W4306177812C83546350 @default.
- W4306177812 hasIssue "5" @default.
- W4306177812 hasLocation W43061778121 @default.
- W4306177812 hasLocation W43061778122 @default.
- W4306177812 hasOpenAccess W4306177812 @default.
- W4306177812 hasPrimaryLocation W43061778121 @default.
- W4306177812 hasRelatedWork W2799952019 @default.
- W4306177812 hasRelatedWork W2899909823 @default.
- W4306177812 hasRelatedWork W3099386970 @default.
- W4306177812 hasRelatedWork W3116896278 @default.
- W4306177812 hasRelatedWork W3174196512 @default.
- W4306177812 hasRelatedWork W3176645224 @default.
- W4306177812 hasRelatedWork W4205415703 @default.
- W4306177812 hasRelatedWork W4225984265 @default.
- W4306177812 hasRelatedWork W4308993660 @default.
- W4306177812 hasRelatedWork W4367596031 @default.
- W4306177812 hasVolume "235" @default.
- W4306177812 isParatext "false" @default.
- W4306177812 isRetracted "false" @default.
- W4306177812 workType "article" @default.