Using machine learning to predict 30-day readmissions after posterior lumbar fusion: an NSQIP study involving 23,264 patients
Search for other papers by Benjamin S. Hopkins in
jns
Google Scholar
PubMed
Search for other papers by Jonathan T. Yamaguchi in
jns
Google Scholar
PubMed
Search for other papers by Roxanna Garcia in
jns
Google Scholar
PubMed
Search for other papers by Kartik Kesavabhotla in
jns
Google Scholar
PubMed
Search for other papers by Hannah Weiss in
jns
Google Scholar
PubMed
Search for other papers by Wellington K. Hsu in
jns
Google Scholar
PubMed
Search for other papers by Zachary A. Smith in
jns
Google Scholar
PubMed
Search for other papers by Nader S. Dahdaleh in
jns
Google Scholar
PubMed
OBJECTIVE
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.
METHODS
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).
RESULTS
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 > 48 hours.
CONCLUSIONS
Machine learning and artificial intelligence are powerful tools with the ability to improve understanding of predictive metrics in clinical spine surgery. The authors’ 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.
ABBREVIATIONS
AUC = area under the curve; CPT = Current Procedural Terminology; DNN = deep neural network; HRRP = Hospital Readmissions Reduction Program; INR = international normalized ratio; NPV = negative predictive value; NSQIP = National Surgical Quality Improvement Program; PPV = positive predictive value; ROC = receiver operating characteristic.Supplementary Materials
- Supplemental Fig. 1 (PDF 4.41 MB)
Kambin’s Triangle viewed as a 3D space. © Barrow Neurological Institute, Phoenix, Arizona. Used with permission. See the article by Fanous et al. (pp 390–398).
© Copyright 1944-2023 American Association of Neurological Surgeons