{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T03:40:48Z","timestamp":1790566848227,"version":"4.1.0"},"reference-count":22,"publisher":"Journal of Neurosurgery Publishing Group (JNSPG)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"abstract":"<jats:sec><jats:title>OBJECTIVE<\/jats:title><jats:p>Unplanned preventable hospital readmissions within 30 days are a great burden to patients and the healthcare system. With an estimated $41.3 billion spent yearly, reducing such readmission rates is of the utmost importance. With the widespread adoption of big data and machine learning, clinicians can use these analytical tools to understand these complex relationships and find predictive factors that can be generalized to future patients. The object of this study was to assess the efficacy of a machine learning algorithm in the prediction of 30-day hospital readmission after posterior spinal fusion surgery.<\/jats:p><\/jats:sec><jats:sec><jats:title>METHODS<\/jats:title><jats:p>The authors analyzed the distribution of National Surgical Quality Improvement Program (NSQIP) posterior lumbar fusions from 2011 to 2016 by using machine learning techniques to create a model predictive of hospital readmissions. A deep neural network was trained using 177 unique input variables. The model was trained and tested using cross-validation, in which the data were randomly partitioned into training (n = 17,448 [75%]) and testing (n = 5816 [25%]) data sets. In training, the 17,448 training cases were fed through a series of 7 layers, each with varying degrees of forward and backward communicating nodes (neurons).<\/jats:p><\/jats:sec><jats:sec><jats:title>RESULTS<\/jats:title><jats:p>Mean and median positive predictive values were 78.5% and 78.0%, respectively. Mean and median negative predictive values were both 97%, respectively. Mean and median areas under the curve for the model were 0.812 and 0.810, respectively. The five most heavily weighted inputs were (in order of importance) return to the operating room, septic shock, superficial surgical site infection, sepsis, and being on a ventilator for &gt; 48 hours.<\/jats:p><\/jats:sec><jats:sec><jats:title>CONCLUSIONS<\/jats:title><jats:p>Machine learning and artificial intelligence are powerful tools with the ability to improve understanding of predictive metrics in clinical spine surgery. The authors\u2019 model was able to predict those patients who would not require readmission. Similarly, the majority of predicted readmissions (up to 60%) were predicted by the model while retaining a 0% false-positive rate. Such findings suggest a possible need for reevaluation of the current Hospital Readmissions Reduction Program penalties in spine surgery.<\/jats:p><\/jats:sec>","DOI":"10.3171\/2019.9.spine19860","type":"journal-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T22:53:36Z","timestamp":1575068016000},"page":"399-406","source":"Crossref","is-referenced-by-count":52,"title":["Using machine learning to predict 30-day readmissions after posterior lumbar fusion: an NSQIP study involving 23,264 patients"],"prefix":"10.3171","volume":"32","author":[{"given":"Benjamin S.","family":"Hopkins","sequence":"first","affiliation":[{"name":"Northwestern University, Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan T.","family":"Yamaguchi","sequence":"additional","affiliation":[{"name":"Northwestern University, Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roxanna","family":"Garcia","sequence":"additional","affiliation":[{"name":"Departments of Neurological Surgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kartik","family":"Kesavabhotla","sequence":"additional","affiliation":[{"name":"Departments of Neurological Surgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah","family":"Weiss","sequence":"additional","affiliation":[{"name":"Northwestern University, Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wellington K.","family":"Hsu","sequence":"additional","affiliation":[{"name":"Orthopedic Surgery,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zachary A.","family":"Smith","sequence":"additional","affiliation":[{"name":"Departments of Neurological Surgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nader S.","family":"Dahdaleh","sequence":"additional","affiliation":[{"name":"Departments of Neurological Surgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1754","reference":[{"key":"b1","series-title":"AHRQ.gov","article-title":"Preventing avoidable readmissions","author":"Agency for Healthcare Research and Quality","unstructured":"Agency for Healthcare Research and Quality: Preventing avoidable readmissions. AHRQ.gov (https:\/\/www.ahrq.gov\/patient-safety\/resources\/improve-discharge\/index.html) [Accessed September 27, 2019]"},{"key":"b2","series-title":"Ann Surg","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1097\/SLA.0b013e318265ef0b","article-title":"Factors influencing readmission after pancreaticoduodenectomy: a multi-institutional study of 1302 patients","volume":"256","author":"Ahmad SA","year":"2012","unstructured":"Ahmad SA, Edwards MJ, Sutton JM, Grewal SS, Hanseman DJ, Maithel SK, : Factors influencing readmission after pancreaticoduodenectomy: a multi-institutional study of 1302 patients. Ann Surg 256:529\u2013537, 20122286837310.1097\/SLA.0b013e318265ef0b"},{"key":"b3","series-title":"Injury","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.injury.2017.01.005","article-title":"Predictors of 30-day hospital readmission after hip fracture: a systematic review","volume":"48","author":"Ali AM","year":"2017","unstructured":"Ali AM, Gibbons CE: Predictors of 30-day hospital readmission after hip fracture: a systematic review. Injury 48:243\u2013252, 201710.1016\/j.injury.2017.01.00528063674"},{"key":"b4","series-title":"Orthopedics","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.3928\/01477447-20160915-06","article-title":"Predictors of hospital readmission after total shoulder arthroplasty","volume":"40","author":"Belmont PJ Jr","year":"2017","unstructured":"Belmont PJ Jr, Kusnezov NA, Dunn JC, Bader JO, Kilcoyne K, Waterman BR: Predictors of hospital readmission after total shoulder arthroplasty. Orthopedics 40:e1\u2013e10, 20172764857610.3928\/01477447-20160915-06"},{"key":"b5","series-title":"arXiv","first-page":"1802.09941","article-title":"Demystifying parallel and distributed deep learning: an in-depth concurrency analysis","author":"Ben-Nun T","year":"2018","unstructured":"Ben-Nun T, Hoefler T: Demystifying parallel and distributed deep learning: an in-depth concurrency analysis. arXiv:1802.09941, 2018"},{"issue":"4","key":"b6","series-title":"Neurosurg Focus","doi-asserted-by":"publisher","first-page":"E7","DOI":"10.3171\/2015.7.FOCUS1534","article-title":"Thirty-day readmission rates in spine surgery: systematic review and meta-analysis","volume":"39","author":"Bernatz JT","year":"2015","unstructured":"Bernatz JT, Anderson PA: Thirty-day readmission rates in spine surgery: systematic review and meta-analysis. Neurosurg Focus 39(4):E7, 20152642434710.3171\/2015.7.FOCUS1534"},{"key":"b7","series-title":"Spine (Phila Pa 1976)","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1097\/BRS.0000000000001450","article-title":"Predictors of 30-day hospital readmission after posterior cervical fusion in 3401 patients","volume":"43","author":"Choy W","year":"2018","unstructured":"Choy W, Lam SK, Smith ZA, Dahdaleh NS: Predictors of 30-day hospital readmission after posterior cervical fusion in 3401 patients. Spine (Phila Pa 1976) 43:356\u2013363, 201810.1097\/BRS.0000000000001450"},{"key":"b8","series-title":"Health Serv Res","first-page":"81","article-title":"Identification of factors associated with hospital readmission and development of a predictive model","volume":"27","author":"Corrigan JM","year":"1992","unstructured":"Corrigan JM, Martin JB: Identification of factors associated with hospital readmission and development of a predictive model. Health Serv Res 27:81\u2013101, 19921563955"},{"key":"b9","series-title":"Healthcare Cost and Utilization Project (HCUP) Statistical Briefs","article-title":"Conditions with the largest number of adult hospital readmissions by payer, 2011. Statistical brief #172","author":"Hines AL","unstructured":"Hines AL, Barrett ML, Jiang HJ, Steiner CA: Conditions with the largest number of adult hospital readmissions by payer, 2011. Statistical brief #172. Healthcare Cost and Utilization Project (HCUP) Statistical Briefs. April 2014 (https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK206781\/) [Accessed September 27, 2019]"},{"key":"b10","series-title":"Towards Data Science","article-title":"Interpreting machine learning models","author":"Hulstaert L","unstructured":"Hulstaert L: Interpreting machine learning models. Towards Data Science. February 20, 2018 (https:\/\/towardsdatascience.com\/interpretability-in-machine-learning-70c30694a05f) [Accessed September 27, 2019]"},{"key":"b11","series-title":"J Neurosurg Spine","doi-asserted-by":"publisher","first-page":"344","DOI":"10.3171\/2018.8.SPINE1869","article-title":"Machine learning modeling for predicting hospital readmission following lumbar laminectomy","volume":"30","author":"Kalagara S","year":"2018","unstructured":"Kalagara S, Eltorai AEM, Durand WM, DePasse JM, Daniels AH: Machine learning modeling for predicting hospital readmission following lumbar laminectomy. J Neurosurg Spine 30:344\u2013352, 201810.3171\/2018.8.SPINE186930544346"},{"key":"b12","series-title":"J Am Coll Surg","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1016\/j.jamcollsurg.2012.05.024","article-title":"Risk factors for 30-day hospital readmission among general surgery patients","volume":"215","author":"Kassin MT","year":"2012","unstructured":"Kassin MT, Owen RM, Perez SD, Leeds I, Cox JC, Schnier K, : Risk factors for 30-day hospital readmission among general surgery patients. J Am Coll Surg 215:322\u2013330, 201210.1016\/j.jamcollsurg.2012.05.02422726893"},{"key":"b13","series-title":"Surgery","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1016\/j.surg.2005.08.016","article-title":"The NSQIP: a new frontier in surgery","volume":"138","author":"Khuri SF","year":"2005","unstructured":"Khuri SF: The NSQIP: a new frontier in surgery. Surgery 138:837\u2013843, 200510.1016\/j.surg.2005.08.016"},{"key":"b14","series-title":"Ann Surg","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1097\/00000658-199810000-00006","article-title":"The Department of Veterans Affairs\u2019 NSQIP: the first national, validated, outcome-based, risk-adjusted, and peer-controlled program for the measurement and enhancement of the quality of surgical care","volume":"228","author":"Khuri SF","year":"1998","unstructured":"Khuri SF, Daley J, Henderson W, Hur K, Demakis J, Aust JB, : The Department of Veterans Affairs\u2019 NSQIP: the first national, validated, outcome-based, risk-adjusted, and peer-controlled program for the measurement and enhancement of the quality of surgical care. Ann Surg 228:491\u2013507, 199810.1097\/00000658-199810000-000069790339"},{"key":"b15","series-title":"Ann Surg","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1097\/SLA.0b013e3181823485","article-title":"Successful implementation of the Department of Veterans Affairs\u2019 National Surgical Quality Improvement Program in the private sector: the Patient Safety in Surgery study","volume":"248","author":"Khuri SF","year":"2008","unstructured":"Khuri SF, Henderson WG, Daley J, Jonasson O, Jones RS, Campbell DA Jr, : Successful implementation of the Department of Veterans Affairs\u2019 National Surgical Quality Improvement Program in the private sector: the Patient Safety in Surgery study. Ann Surg 248:329\u2013336, 200810.1097\/SLA.0b013e3181823485"},{"key":"b16","series-title":"Spine (Phila Pa 1976)","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1097\/BRS.0000000000001586","article-title":"Incidence and risk factors for 30-day unplanned readmissions after elective posterior lumbar fusion","volume":"43","author":"Lee NJ","year":"2018","unstructured":"Lee NJ, Kothari P, Phan K, Shin JI, Cutler HS, Lakomkin N, : Incidence and risk factors for 30-day unplanned readmissions after elective posterior lumbar fusion. Spine (Phila Pa 1976) 43:41\u201348, 201810.1097\/BRS.0000000000001586"},{"key":"b17","series-title":"Circulation","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.1161\/CIRCULATIONAHA.114.010270","article-title":"Hospital readmissions reduction program","volume":"131","author":"McIlvennan CKEZ","year":"2015","unstructured":"McIlvennan CKEZ, Eapen ZJ, Allen LA: Hospital readmissions reduction program. Circulation 131:1796\u20131803, 201510.1161\/CIRCULATIONAHA.114.01027025986448"},{"key":"b18","series-title":"Forbes. December","article-title":"How fast is artificial intelligence growing? Look at the key bellwethers","volume":"19","author":"McKendrick J","year":"2018","unstructured":"McKendrick J: How fast is artificial intelligence growing? Look at the key bellwethers. Forbes. December 19, 2018 (https:\/\/www.forbes.com\/sites\/joemckendrick\/2018\/12\/19\/how-fast-is-artificial-intelligence-growing-look-at-the-key-bellwethers\/#4d41baa6474a) [Accessed September 27, 2019]"},{"key":"b19","series-title":"Healthcare IT News","article-title":"A realistic look at the hype of machine learning and AI","author":"Muoio D","unstructured":"Muoio D: A realistic look at the hype of machine learning and AI. Healthcare IT News. March 27, 2018 (https:\/\/www.healthcareitnews.com\/news\/realistic-look-hype-machine-learning-and-ai) [Accessed September 27, 2019] 2018"},{"key":"b20","series-title":"Spine (Phila Pa 1976)","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.1097\/BRS.0000000000000489","article-title":"Surgeon specialty and outcomes after elective spine surgery","volume":"39","author":"Seicean A","year":"2014","unstructured":"Seicean A, Alan N, Seicean S, Neuhauser D, Benzel EC, Weil RJ: Surgeon specialty and outcomes after elective spine surgery. Spine (Phila Pa 1976) 39:1605\u20131613, 201410.1097\/BRS.0000000000000489"},{"key":"b21","series-title":"Spine J","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.spinee.2018.11.009","article-title":"Deep learning-based preoperative predictive analytics for patient-reported outcomes following lumbar diskectomy: feasibility of center-specific modeling","volume":"19","author":"Staartjes VE","year":"2019","unstructured":"Staartjes VE, de Wispelaere MP, Vandertop WP, Schroder ML: Deep learning-based preoperative predictive analytics for patient-reported outcomes following lumbar diskectomy: feasibility of center-specific modeling. Spine J 19:853\u2013861, 201910.1016\/j.spinee.2018.11.00930453080"},{"key":"b22","series-title":"Spine (Phila Pa 1976)","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1097\/BRS.0000000000002937","article-title":"30- and 90-day unplanned readmission rates, causes, and risk factors after cervical fusion: a single-institution analysis","volume":"44","author":"Zaki O","year":"2019","unstructured":"Zaki O, Jain N, Yu EM, Khan SN: 30- and 90-day unplanned readmission rates, causes, and risk factors after cervical fusion: a single-institution analysis. Spine (Phila Pa 1976) 44:762\u2013769, 201910.1097\/BRS.0000000000002937"}],"container-title":["Journal of Neurosurgery: Spine"],"original-title":[],"link":[{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/32\/3\/article-p399.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/32\/3\/article-p399.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg-spine\/32\/3\/article-p399.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T22:56:20Z","timestamp":1681599380000},"score":1,"resource":{"primary":{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg-spine\/32\/3\/article-p399.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":22,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3171\/2019.9.spine19860","relation":{},"ISSN":["1547-5654"],"issn-type":[{"value":"1547-5654","type":"print"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}