{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T11:22:32Z","timestamp":1758280952776,"version":"3.40.5"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>By predicting short-term postoperative outcomes before surgery, patients who undergo posterior cervical fusion (PCF) surgery may benefit from more precise patient care plans that reduce the likelihood of unfavorable outcomes. We developed machine learning models for predicting short-term postoperative outcomes and incorporate these models into an open-source web application in this study. The American College of Surgeons National Surgical Quality Improvement Program database was used to identify patients who underwent PCF surgery. Prolonged length of stay, non-home discharges, and readmissions were the three outcomes that were investigated. To predict these three outcomes, machine learning models were developed and incorporated into an open access web application. A total of 6277 patients that underwent PCF surgery were included in the analysis. The most accurately predicted outcome in terms of the area under the receiver operating characteristic curve (AUROC) was the non-home discharges with a mean AUROC of 0.812, and the most accurately predicting algorithm in terms of AUROC was the LightGBM algorithm with a mean AUROC of 0.766. The following URL will take users to the open access web application created to provide predictions for individual patients based on their characteristics: <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/huggingface.co\/spaces\/MSHS-Neurosurgery-Research\/NSQIP-PCF\" xlink:type=\"simple\">https:\/\/huggingface.co\/spaces\/MSHS-Neurosurgery-Research\/NSQIP-PCF<\/jats:ext-link>. Machine learning techniques have a significant potential for predicting postoperative outcomes following PCF surgery. The development of predictive models as clinically useful decision-making tools may significantly improve risk assessment and prognosis as the amount of data in spinal surgery keeps growing. Here, we present predictive models for PCF surgery that are meant to accomplish the aforementioned goals and make them publicly available.<\/jats:p>","DOI":"10.1371\/journal.pone.0288939","type":"journal-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T17:35:05Z","timestamp":1689960905000},"page":"e0288939","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["Interpretable machine learning models to predict short-term postoperative outcomes following posterior cervical fusion"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9263-9893","authenticated-orcid":true,"given":"Mert","family":"Karabacak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3715-8093","authenticated-orcid":true,"given":"Konstantinos","family":"Margetis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2023,7,21]]},"reference":[{"key":"pone.0288939.ref001","doi-asserted-by":"crossref","first-page":"225","DOI":"10.4103\/2152-7806.98581","article-title":"Is posterior fusion necessary with laminectomy in the cervical spine?","volume":"3","author":"B McAllister","year":"2012","journal-title":"Surg Neurol Int"},{"key":"pone.0288939.ref002","doi-asserted-by":"crossref","first-page":"E906","DOI":"10.1097\/BRS.0000000000001999","article-title":"Trends in Utilization and Cost of Cervical Spine Surgery Using the National Inpatient Sample Database, 2001 to 2013","volume":"42","author":"CY Liu","year":"2017","journal-title":"Spine"},{"key":"pone.0288939.ref003","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1177\/2192568217722562","article-title":"National Trends in Demographics and Outcomes Following Cervical Fusion for Cervical Spondylotic Myelopathy","volume":"8","author":"CE Vonck","year":"2018","journal-title":"Global Spine J"},{"key":"pone.0288939.ref004","doi-asserted-by":"crossref","first-page":"e280","DOI":"10.1016\/j.wneu.2018.02.004","article-title":"Cervical Spinal Fusion: 16-Year Trends in Epidemiology, Indications, and In-Hospital Outcomes by Surgical Approach","volume":"113","author":"SN Salzmann","year":"2018","journal-title":"World Neurosurg"},{"key":"pone.0288939.ref005","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1056\/NEJMp1702071","article-title":"Machine Learning and Prediction in Medicine\u2014Beyond the Peak of Inflated Expectations","volume":"376","author":"JH Chen","year":"2017","journal-title":"N Engl J Med"},{"key":"pone.0288939.ref006","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1186\/1471-2288-12-82","article-title":"Interpreting the concordance statistic of a logistic regression model: relation to the variance and odds ratio of a continuous explanatory variable","volume":"12","author":"PC Austin","year":"2012","journal-title":"BMC Med Res Methodol"},{"key":"pone.0288939.ref007","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big Data and Machine Learning in Health Care","volume":"319","author":"AL Beam","year":"2018","journal-title":"JAMA"},{"key":"pone.0288939.ref008","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine Learning in Medicine","volume":"380","author":"A Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"key":"pone.0288939.ref009","doi-asserted-by":"crossref","first-page":"812","DOI":"10.3390\/cancers15030812","article-title":"A Machine Learning-Based Online Prediction Tool for Predicting Short-Term Postoperative Outcomes Following Spinal Tumor Resections","volume":"15","author":"M Karabacak","year":"2023","journal-title":"Cancers"},{"key":"pone.0288939.ref010","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1016\/j.jamcollsurg.2007.03.028","article-title":"The Patient Safety in Surgery Study: Background, Study Design, and Patient Populations","volume":"204","author":"SF Khuri","year":"2007","journal-title":"J Am Coll Surg"},{"key":"pone.0288939.ref011","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1097\/SLA.0b013e3181b4148f","article-title":"Does surgical quality improve in the American College of Surgeons National Surgical Quality Improvement Program: an evaluation of all participating hospitals","volume":"250","author":"BL Hall","year":"2009","journal-title":"Ann Surg"},{"key":"pone.0288939.ref012","unstructured":"About ACS NSQIP. In: ACS [Internet]. [cited 29 Sep 2022]. Available: https:\/\/www.facs.org\/quality-programs\/data-and-registries\/acs-nsqip\/about-acs-nsqip\/"},{"key":"pone.0288939.ref013","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12916-014-0241-z","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement","volume":"13","author":"GS Collins","year":"2015","journal-title":"BMC Med"},{"key":"pone.0288939.ref014","doi-asserted-by":"crossref","first-page":"e323","DOI":"10.2196\/jmir.5870","article-title":"Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary View","volume":"18","author":"W Luo","year":"2016","journal-title":"J Med Internet Res"},{"key":"pone.0288939.ref015","unstructured":"sklearn.impute.KNNImputer. In: scikit-learn [Internet]. [cited 29 Sep 2022]. Available: https:\/\/scikit-learn\/stable\/modules\/generated\/sklearn.impute.KNNImputer.html"},{"key":"pone.0288939.ref016","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s12911-016-0318-z","article-title":"Nearest neighbor imputation algorithms: a critical evaluation","volume":"16","author":"L Beretta","year":"2016","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"pone.0288939.ref017","unstructured":"sklearn.preprocessing.RobustScaler. In: scikit-learn [Internet]. [cited 29 Sep 2022]. Available: https:\/\/scikit-learn\/stable\/modules\/generated\/sklearn.preprocessing.RobustScaler.html"},{"key":"pone.0288939.ref018","unstructured":"sklearn.preprocessing.MinMaxScaler. In: scikit-learn [Internet]. [cited 29 Sep 2022]. Available: https:\/\/scikit-learn\/stable\/modules\/generated\/sklearn.preprocessing.MinMaxScaler.html"},{"key":"pone.0288939.ref019","unstructured":"sklearn.preprocessing.OrdinalEncoder. In: scikit-learn [Internet]. [cited 29 Sep 2022]. Available: https:\/\/scikit-learn\/stable\/modules\/generated\/sklearn.preprocessing.OrdinalEncoder.html"},{"key":"pone.0288939.ref020","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"jair"},{"key":"pone.0288939.ref021","doi-asserted-by":"crossref","DOI":"10.1002\/9781118646106","volume-title":"Imbalanced learning: foundations, algorithms, and applications","author":"H He","year":"2013"},{"key":"pone.0288939.ref022","article-title":"Optuna: A Next-generation Hyperparameter Optimization Framework","author":"T Akiba","year":"2019","journal-title":"arXiv"},{"key":"pone.0288939.ref023","unstructured":"Prediction Tools | Memorial Sloan Kettering Cancer Center. [cited 2 Jan 2023]. Available: https:\/\/www.mskcc.org\/nomograms"},{"key":"pone.0288939.ref024","doi-asserted-by":"crossref","first-page":"e1044","DOI":"10.1002\/jsp2.1044","article-title":"Artificial intelligence and machine learning in spine research","volume":"2","author":"F Galbusera","year":"2019","journal-title":"JOR Spine"},{"key":"pone.0288939.ref025","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"JA Hanley","year":"1982","journal-title":"Radiology"},{"key":"pone.0288939.ref026","article-title":"Use of random forest machine learning algorithm to predict short term outcomes following posterior cervical decompression with instrumented fusion","author":"A Cabrera","year":"2022","journal-title":"Journal of Clinical Neuroscience"},{"key":"pone.0288939.ref027","doi-asserted-by":"crossref","first-page":"450","DOI":"10.5152\/dir.2022.211297","article-title":"Key concepts, common pitfalls, and best practices in artificial intelligence and machine learning: focus on radiomics","volume":"28","author":"B. Kocak","year":"2022","journal-title":"Diagn Interv Radiol"},{"key":"pone.0288939.ref028","doi-asserted-by":"crossref","first-page":"1952","DOI":"10.1007\/s00586-021-06961-7","article-title":"Machine learning-driven identification of novel patient factors for prediction of major complications after posterior cervical spinal fusion","volume":"31","author":"AA Shah","year":"2022","journal-title":"Eur Spine J"},{"key":"pone.0288939.ref029","doi-asserted-by":"crossref","first-page":"E55","DOI":"10.1097\/BSD.0000000000000512","article-title":"Patient Factors Contributing to Prolonged Postoperative Length of Stay and Increased Rate of Readmission After Elective Posterior Cervical Fusion","volume":"31","author":"JI Shin","year":"2018","journal-title":"Clinical Spine Surgery: A Spine Publication"},{"key":"pone.0288939.ref030","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1177\/2192568217705654","article-title":"Impact of Preoperative Anemia on Outcomes in Adults Undergoing Elective Posterior Cervical Fusion","volume":"7","author":"K Phan","year":"2017","journal-title":"Global Spine Journal"},{"key":"pone.0288939.ref031","doi-asserted-by":"crossref","first-page":"e789","DOI":"10.1016\/j.wneu.2019.10.011","article-title":"Does Increasing Body Mass Index Correlate with Adverse Outcomes Following Posterior Cervical Fusions?","volume":"133","author":"M Sridharan","year":"2020","journal-title":"World Neurosurgery"},{"key":"pone.0288939.ref032","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.jocn.2016.10.045","article-title":"Systemic inaccuracies in the National Surgical Quality Improvement Program database: Implications for accuracy and validity for neurosurgery outcomes research","volume":"37","author":"JD Rolston","year":"2017","journal-title":"Journal of Clinical Neuroscience"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0288939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T17:35:28Z","timestamp":1689960928000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0288939"}},"subtitle":[],"editor":[{"given":"Mohamed El-Sayed","family":"Abdel-Wanis","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,7,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0288939","relation":{},"ISSN":["1932-6203"],"issn-type":[{"type":"electronic","value":"1932-6203"}],"subject":[],"published":{"date-parts":[[2023,7,21]]}}}