Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures
Objective: Osteoporosis is a common skeletal disease that greatly increases the risk of pathologic fractures and accounts for approximately 700,000 vertebral compression fractures (VCFs) annually in the United States. Cement augmentation procedures such as balloon kyphoplasty (KP) and percutaneous v...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-07-01
|
| Series: | World Neurosurgery: X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590139724000693 |
| _version_ | 1827184150475440128 |
|---|---|
| author | Andrew Cabrera Alexander Bouterse Michael Nelson Luke Thomas Omar Ramos Wayne Cheng Olumide Danisa |
| author_facet | Andrew Cabrera Alexander Bouterse Michael Nelson Luke Thomas Omar Ramos Wayne Cheng Olumide Danisa |
| author_sort | Andrew Cabrera |
| collection | DOAJ |
| description | Objective: Osteoporosis is a common skeletal disease that greatly increases the risk of pathologic fractures and accounts for approximately 700,000 vertebral compression fractures (VCFs) annually in the United States. Cement augmentation procedures such as balloon kyphoplasty (KP) and percutaneous vertebroplasty (VP) have demonstrated efficacy in the treatment of VCFs, however, some studies report rates of readmission as high as 10.8% following such procedures. The purpose of this study was to employ Machine Learning (ML) algorithms to predict 30-day hospital readmission following cement augmentation procedures for the treatment of VCFs using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. Methods: ACS-NSQIP was queried to identify patients undergoing either KP or VP from 2011 to 2014. Three ML algorithms were constructed and tasked with predicting post-operative readmissions within this cohort of patients. Results: Postoperative pneumonia, ASA Class 2 designation, age, partially-dependent functional status, and a history of smoking were independently identified as highly predictive of readmission by all ML algorithms. Among these variables postoperative pneumonia (p < 0.01), ASA Class 2 designation (p < 0.01), age (p = 0.002), and partially-dependent functional status (p < 0.01) were found to be statistically significant. Predictions were generated with an average AUC value of 0.757 and an average accuracy of 80.5%. Conclusions: Postoperative pneumonia, ASA Class 2 designation, partially-dependent functional status, and age are perioperative variables associated with 30-day readmission following cement augmentation procedures. The use of ML allows for quantification of the relative contributions of these variables toward producing readmission. |
| first_indexed | 2024-04-25T00:46:49Z |
| format | Article |
| id | doaj.art-d6cc39859c6d42fbaa74dab3852db529 |
| institution | Directory Open Access Journal |
| issn | 2590-1397 |
| language | English |
| last_indexed | 2025-03-21T06:29:55Z |
| publishDate | 2024-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | World Neurosurgery: X |
| spelling | doaj.art-d6cc39859c6d42fbaa74dab3852db5292024-07-21T05:26:16ZengElsevierWorld Neurosurgery: X2590-13972024-07-0123100338Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fracturesAndrew Cabrera0Alexander Bouterse1Michael Nelson2Luke Thomas3Omar Ramos4Wayne Cheng5Olumide Danisa6School of Medicine, Loma Linda University, Loma Linda, CA, 92354, USASchool of Medicine, Loma Linda University, Loma Linda, CA, 92354, USASchool of Medicine, Loma Linda University, Loma Linda, CA, 92354, USASchool of Medicine, Loma Linda University, Loma Linda, CA, 92354, USATwin Cities Spine Center, Minneapolis, MN 55404, USAJerry L Pettis Memorial Veterans Hospital, Loma Linda, CA, 92354, USADepartment of Orthopedics, Loma Linda University, Loma Linda, CA, 92354, USA; Corresponding author. 25805 Barton Road Suite A106, Loma Linda, CA, 92354, USA.Objective: Osteoporosis is a common skeletal disease that greatly increases the risk of pathologic fractures and accounts for approximately 700,000 vertebral compression fractures (VCFs) annually in the United States. Cement augmentation procedures such as balloon kyphoplasty (KP) and percutaneous vertebroplasty (VP) have demonstrated efficacy in the treatment of VCFs, however, some studies report rates of readmission as high as 10.8% following such procedures. The purpose of this study was to employ Machine Learning (ML) algorithms to predict 30-day hospital readmission following cement augmentation procedures for the treatment of VCFs using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. Methods: ACS-NSQIP was queried to identify patients undergoing either KP or VP from 2011 to 2014. Three ML algorithms were constructed and tasked with predicting post-operative readmissions within this cohort of patients. Results: Postoperative pneumonia, ASA Class 2 designation, age, partially-dependent functional status, and a history of smoking were independently identified as highly predictive of readmission by all ML algorithms. Among these variables postoperative pneumonia (p < 0.01), ASA Class 2 designation (p < 0.01), age (p = 0.002), and partially-dependent functional status (p < 0.01) were found to be statistically significant. Predictions were generated with an average AUC value of 0.757 and an average accuracy of 80.5%. Conclusions: Postoperative pneumonia, ASA Class 2 designation, partially-dependent functional status, and age are perioperative variables associated with 30-day readmission following cement augmentation procedures. The use of ML allows for quantification of the relative contributions of these variables toward producing readmission.http://www.sciencedirect.com/science/article/pii/S2590139724000693Cement augmentationKyphoplastyMachine learningReadmissionVertebroplasty |
| spellingShingle | Andrew Cabrera Alexander Bouterse Michael Nelson Luke Thomas Omar Ramos Wayne Cheng Olumide Danisa Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures World Neurosurgery: X Cement augmentation Kyphoplasty Machine learning Readmission Vertebroplasty |
| title | Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures |
| title_full | Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures |
| title_fullStr | Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures |
| title_full_unstemmed | Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures |
| title_short | Application of machine learning algorithms to predict 30-day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures |
| title_sort | application of machine learning algorithms to predict 30 day hospital readmission following cement augmentation for osteoporotic vertebral compression fractures |
| topic | Cement augmentation Kyphoplasty Machine learning Readmission Vertebroplasty |
| url | http://www.sciencedirect.com/science/article/pii/S2590139724000693 |
| work_keys_str_mv | AT andrewcabrera applicationofmachinelearningalgorithmstopredict30dayhospitalreadmissionfollowingcementaugmentationforosteoporoticvertebralcompressionfractures AT alexanderbouterse applicationofmachinelearningalgorithmstopredict30dayhospitalreadmissionfollowingcementaugmentationforosteoporoticvertebralcompressionfractures AT michaelnelson applicationofmachinelearningalgorithmstopredict30dayhospitalreadmissionfollowingcementaugmentationforosteoporoticvertebralcompressionfractures AT lukethomas applicationofmachinelearningalgorithmstopredict30dayhospitalreadmissionfollowingcementaugmentationforosteoporoticvertebralcompressionfractures AT omarramos applicationofmachinelearningalgorithmstopredict30dayhospitalreadmissionfollowingcementaugmentationforosteoporoticvertebralcompressionfractures AT waynecheng applicationofmachinelearningalgorithmstopredict30dayhospitalreadmissionfollowingcementaugmentationforosteoporoticvertebralcompressionfractures AT olumidedanisa applicationofmachinelearningalgorithmstopredict30dayhospitalreadmissionfollowingcementaugmentationforosteoporoticvertebralcompressionfractures |