Search Results

You are looking at 11 - 20 of 39 items for

  • Author or Editor: Michael S. Virk x
  • Refine by Access: all x
Clear All Modify Search
Free access

Leveraging machine learning to ascertain the implications of preoperative body mass index on surgical outcomes for 282 patients with preoperative obesity and lumbar spondylolisthesis in the Quality Outcomes Database

Nitin Agarwal, Alexander A. Aabedi, Andrew K. Chan, Vijay Letchuman, Saman Shabani, Erica F. Bisson, Mohamad Bydon, Steven D. Glassman, Kevin T. Foley, Christopher I. Shaffrey, Eric A. Potts, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Paul Park, Michael Y. Wang, Kai-Ming Fu, Jonathan R. Slotkin, Anthony L. Asher, Michael S. Virk, Regis W. Haid Jr., Dean Chou, and Praveen V. Mummaneni

OBJECTIVE

Prior studies have revealed that a body mass index (BMI) ≥ 30 is associated with worse outcomes following surgical intervention in grade 1 lumbar spondylolisthesis. Using a machine learning approach, this study aimed to leverage the prospective Quality Outcomes Database (QOD) to identify a BMI threshold for patients undergoing surgical intervention for grade 1 lumbar spondylolisthesis and thus reliably identify optimal surgical candidates among obese patients.

METHODS

Patients with grade 1 lumbar spondylolisthesis and preoperative BMI ≥ 30 from the prospectively collected QOD lumbar spondylolisthesis module were included in this study. A 12-month composite outcome was generated by performing principal components analysis and k-means clustering on four validated measures of surgical outcomes in patients with spondylolisthesis. Random forests were generated to determine the most important preoperative patient characteristics in predicting the composite outcome. Recursive partitioning was used to extract a BMI threshold associated with optimal outcomes.

RESULTS

The average BMI was 35.7, with 282 (46.4%) of the 608 patients from the QOD data set having a BMI ≥ 30. Principal components analysis revealed that the first principal component accounted for 99.2% of the variance in the four outcome measures. Two clusters were identified corresponding to patients with suboptimal outcomes (severe back pain, increased disability, impaired quality of life, and low satisfaction) and to those with optimal outcomes. Recursive partitioning established a BMI threshold of 37.5 after pruning via cross-validation.

CONCLUSIONS

In this multicenter study, the authors found that a BMI ≤ 37.5 was associated with improved patient outcomes following surgical intervention. These findings may help augment predictive analytics to deliver precision medicine and improve prehabilitation strategies.

Free access

Development of new postoperative neck pain at 12 and 24 months after surgery for cervical spondylotic myelopathy: a Quality Outcomes Database study

Brandon A. Sherrod, Giorgos D. Michalopoulos, Graham Mulvaney, Nitin Agarwal, Andrew K. Chan, Anthony L. Asher, Domagoj Coric, Michael S. Virk, Kai-Ming Fu, Kevin T. Foley, Paul Park, Cheerag D. Upadhyaya, John J. Knightly, Mark E. Shaffrey, Eric A. Potts, Christopher I. Shaffrey, Oren N. Gottfried, Khoi D. Than, Michael Y. Wang, Luis M. Tumialán, Dean Chou, Praveen V. Mummaneni, Mohamad Bydon, and Erica F. Bisson

OBJECTIVE

Patients who undergo surgery for cervical spondylotic myelopathy (CSM) will occasionally develop postoperative neck pain that was not present preoperatively, yet the incidence of this phenomenon is unclear. The authors aimed to elucidate patient and surgical factors associated with new-onset sustained pain after CSM surgery.

METHODS

The authors reviewed data from the Quality Outcomes Database (QOD) CSM module. The presence of neck pain was defined using the neck pain numeric rating scale (NRS). Patients with no neck pain at baseline (neck NRS score ≤ 1) were then stratified based on the presence of new postoperative pain development (neck NRS score ≥ 2) at 12 and 24 months postoperatively.

RESULTS

Of 1141 patients in the CSM QOD, 224 (19.6%) reported no neck pain at baseline. Among 170 patients with no baseline neck pain and available 12-month follow-up, 46 (27.1%) reported new postoperative pain. Among 184 patients with no baseline neck pain and available 24-month follow-up, 53 (28.8%) reported new postoperative pain. The mean differences in neck NRS scores were 4.3 for those with new postoperative pain compared with those without at 12 months (4.4 ± 2.2 vs 0.1 ± 0.3, p < 0.001) and 3.9 at 24 months (4.1 ± 2.4 vs 0.2 ± 0.4, p < 0.001). The majority of patients reporting new-onset neck pain reported being satisfied with surgery, but their satisfaction was significantly lower compared with patients without pain at the 12-month (66.7% vs 94.3%, p < 0.001) and 24-month (65.4% vs 90.8%, p < 0.001) follow-ups. The baseline Neck Disability Index (NDI) was an independent predictor of new postoperative neck pain at both the 12-month and 24-month time points (adjusted OR [aOR] 1.04, 95% CI 1.01–1.06; p = 0.002; and aOR 1.03, 95% CI 1.01–1.05; p = 0.026, respectively). The total number of levels treated was associated with new-onset neck pain at 12 months (aOR 1.34, 95% CI 1.09–1.64; p = 0.005), and duration of symptoms more than 3 months was a predictor of 24-month neck pain (aOR 3.22, 95% CI 1.01–10.22; p = 0.048).

CONCLUSIONS

Increased NDI at baseline, number of levels treated surgically, and duration of symptoms longer than 3 months preoperatively correlate positively with the risk of new-onset neck pain following CSM surgery. The majority of patients with new-onset neck pain still report satisfaction from surgery, suggesting that the risk of new-onset neck pain should not hinder indicated operations from being performed.

Free access

Does reduction of the Meyerding grade correlate with outcomes in patients undergoing decompression and fusion for grade I degenerative lumbar spondylolisthesis?

Andrew K. Chan, Praveen V. Mummaneni, John F. Burke, Rory R. Mayer, Erica F. Bisson, Joshua Rivera, Brenton Pennicooke, Kai-Ming Fu, Paul Park, Mohamad Bydon, Steven D. Glassman, Kevin T. Foley, Christopher I. Shaffrey, Eric A. Potts, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Michael Y. Wang, Jonathan R. Slotkin, Anthony L. Asher, Michael S. Virk, Panagiotis Kerezoudis, Mohammed A. Alvi, Jian Guan, Regis W. Haid, and Dean Chou

OBJECTIVE

Reduction of Meyerding grade is often performed during fusion for spondylolisthesis. Although radiographic appearance may improve, correlation with patient-reported outcomes (PROs) is rarely reported. In this study, the authors’ aim was to assess the impact of spondylolisthesis reduction on 24-month PRO measures after decompression and fusion surgery for Meyerding grade I degenerative lumbar spondylolisthesis.

METHODS

The Quality Outcomes Database (QOD) was queried for patients undergoing posterior lumbar fusion for spondylolisthesis with a minimum 24-month follow-up, and quantitative correlation between Meyerding slippage reduction and PROs was performed. Baseline and 24-month PROs, including the Oswestry Disability Index (ODI), EQ-5D, Numeric Rating Scale (NRS)–back pain (NRS-BP), NRS-leg pain (NRS-LP), and satisfaction (North American Spine Society patient satisfaction questionnaire) scores were noted. Multivariable regression models were fitted for 24-month PROs and complications after adjusting for an array of preoperative and surgical variables. Data were analyzed for magnitude of slippage reduction and correlated with PROs. Patients were divided into two groups: < 3 mm reduction and ≥ 3 mm reduction.

RESULTS

Of 608 patients from 12 participating sites, 206 patients with complete data were identified in the QOD and included in this study. Baseline patient demographics, comorbidities, and clinical characteristics were similarly distributed between the cohorts except for depression, listhesis magnitude, and the proportion with dynamic listhesis (which were accounted for in the multivariable analysis). One hundred four (50.5%) patients underwent lumbar decompression and fusion with slippage reduction ≥ 3 mm (mean 5.19, range 3 to 11), and 102 (49.5%) patients underwent lumbar decompression and fusion with slippage reduction < 3 mm (mean 0.41, range 2 to −2). Patients in both groups (slippage reduction ≥ 3 mm, and slippage reduction < 3 mm) reported significant improvement in all primary patient reported outcomes (all p < 0.001). There was no significant difference with regard to the PROs between patients with or without intraoperative reduction of listhesis on univariate and multivariable analyses (ODI, EQ-5D, NRS-BP, NRS-LP, or satisfaction). There was no significant difference in complications between cohorts.

CONCLUSIONS

Significant improvement was found in terms of all PROs in patients undergoing decompression and fusion for lumbar spondylolisthesis. There was no correlation with clinical outcomes and magnitude of Meyerding slippage reduction.

Free access

Does reduction of the Meyerding grade correlate with outcomes in patients undergoing decompression and fusion for grade I degenerative lumbar spondylolisthesis?

Andrew K. Chan, Praveen V. Mummaneni, John F. Burke, Rory R. Mayer, Erica F. Bisson, Joshua Rivera, Brenton Pennicooke, Kai-Ming Fu, Paul Park, Mohamad Bydon, Steven D. Glassman, Kevin T. Foley, Christopher I. Shaffrey, Eric A. Potts, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Michael Y. Wang, Jonathan R. Slotkin, Anthony L. Asher, Michael S. Virk, Panagiotis Kerezoudis, Mohammed A. Alvi, Jian Guan, Regis W. Haid, and Dean Chou

OBJECTIVE

Reduction of Meyerding grade is often performed during fusion for spondylolisthesis. Although radiographic appearance may improve, correlation with patient-reported outcomes (PROs) is rarely reported. In this study, the authors’ aim was to assess the impact of spondylolisthesis reduction on 24-month PRO measures after decompression and fusion surgery for Meyerding grade I degenerative lumbar spondylolisthesis.

METHODS

The Quality Outcomes Database (QOD) was queried for patients undergoing posterior lumbar fusion for spondylolisthesis with a minimum 24-month follow-up, and quantitative correlation between Meyerding slippage reduction and PROs was performed. Baseline and 24-month PROs, including the Oswestry Disability Index (ODI), EQ-5D, Numeric Rating Scale (NRS)–back pain (NRS-BP), NRS-leg pain (NRS-LP), and satisfaction (North American Spine Society patient satisfaction questionnaire) scores were noted. Multivariable regression models were fitted for 24-month PROs and complications after adjusting for an array of preoperative and surgical variables. Data were analyzed for magnitude of slippage reduction and correlated with PROs. Patients were divided into two groups: < 3 mm reduction and ≥ 3 mm reduction.

RESULTS

Of 608 patients from 12 participating sites, 206 patients with complete data were identified in the QOD and included in this study. Baseline patient demographics, comorbidities, and clinical characteristics were similarly distributed between the cohorts except for depression, listhesis magnitude, and the proportion with dynamic listhesis (which were accounted for in the multivariable analysis). One hundred four (50.5%) patients underwent lumbar decompression and fusion with slippage reduction ≥ 3 mm (mean 5.19, range 3 to 11), and 102 (49.5%) patients underwent lumbar decompression and fusion with slippage reduction < 3 mm (mean 0.41, range 2 to −2). Patients in both groups (slippage reduction ≥ 3 mm, and slippage reduction < 3 mm) reported significant improvement in all primary patient reported outcomes (all p < 0.001). There was no significant difference with regard to the PROs between patients with or without intraoperative reduction of listhesis on univariate and multivariable analyses (ODI, EQ-5D, NRS-BP, NRS-LP, or satisfaction). There was no significant difference in complications between cohorts.

CONCLUSIONS

Significant improvement was found in terms of all PROs in patients undergoing decompression and fusion for lumbar spondylolisthesis. There was no correlation with clinical outcomes and magnitude of Meyerding slippage reduction.

Free access

Correlation of return to work with patient satisfaction after surgery for lumbar spondylolisthesis: an analysis of the Quality Outcomes Database

Anthony M. DiGiorgio, Praveen V. Mummaneni, Paul Park, Andrew K. Chan, Erica F. Bisson, Mohamad Bydon, Kevin T. Foley, Steven D. Glassman, Christopher I. Shaffrey, Eric A. Potts, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Michael Y. Wang, Kai-Ming Fu, Anthony L. Asher, Michael S. Virk, Panagiotis Kerezoudis, Mohammed Ali Alvi, Jian Guan, Regis W. Haid Jr., and Jonathan R. Slotkin

OBJECTIVE

Return to work (RTW) and satisfaction are important outcome measures after surgery for degenerative spine disease. The authors queried the prospective Quality Outcomes Database (QOD) to determine if RTW correlated with patient satisfaction.

METHODS

The QOD was queried for patients undergoing surgery for degenerative lumbar spondylolisthesis. The primary outcome of interest was correlation between RTW and patient satisfaction, as measured by the North American Spine Society patient satisfaction index (NASS). Secondarily, data on satisfied patients were analyzed to see what patient factors correlated with RTW.

RESULTS

Of 608 total patients in the QOD spondylolisthesis data set, there were 292 patients for whom data were available on both satisfaction and RTW status. Of these, 249 (85.3%) were satisfied with surgery (NASS score 1–2), and 224 (76.7%) did RTW after surgery. Of the 68 patients who did not RTW after surgery, 49 (72.1%) were still satisfied with surgery. Of the 224 patients who did RTW, 24 (10.7%) were unsatisfied with surgery (NASS score 3–4). There were significantly more people who had an NASS score of 1 in the RTW group than in the non-RTW group (71.4% vs 42.6%, p < 0.05). Failure to RTW was associated with lower level of education, worse baseline back pain (measured with a numeric rating scale), and worse baseline disability (measured with the Oswestry Disability Index [ODI]).

CONCLUSIONS

There are a substantial number of patients who are satisfied with surgery even though they did not RTW. Patients who were satisfied with surgery and did not RTW typically had worse preoperative back pain and ODI and typically did not have a college education. While RTW remains an important measure after surgery, physicians should be mindful that patients who do not RTW may still be satisfied with their outcome.

Free access

Minimally invasive versus open transforaminal lumbar interbody fusion for grade I lumbar spondylolisthesis: 5-year follow-up from the prospective multicenter Quality Outcomes Database registry

Andrew K. Chan, Mohamad Bydon, Erica F. Bisson, Steven D. Glassman, Kevin T. Foley, Christopher I. Shaffrey, Eric A. Potts, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Paul Park, Michael Y. Wang, Kai-Ming Fu, Jonathan R. Slotkin, Anthony L. Asher, Michael S. Virk, Giorgos D. Michalopoulos, Jian Guan, Regis W. Haid, Nitin Agarwal, Christine Park, Dean Chou, and Praveen V. Mummaneni

OBJECTIVE

Minimally invasive transforaminal lumbar interbody fusion (MI-TLIF) has been used to treat degenerative lumbar spondylolisthesis and is associated with expedited recovery, reduced operative blood loss, and shorter hospitalizations compared to those with traditional open TLIF. However, the impact of MI-TLIF on long-term patient-reported outcomes (PROs) is less clear. Here, the authors compare the outcomes of MI-TLIF to those of traditional open TLIF for grade I degenerative lumbar spondylolisthesis at 60 months postoperatively.

METHODS

The authors utilized the prospective Quality Outcomes Database registry and queried for patients with grade I degenerative lumbar spondylolisthesis who had undergone single-segment surgery via an MI or open TLIF method. PROs were compared 60 months postoperatively. The primary outcome was the Oswestry Disability Index (ODI). The secondary outcomes included the numeric rating scale (NRS) for back pain (NRS-BP), NRS for leg pain (NRS-LP), EQ-5D, North American Spine Society (NASS) satisfaction, and cumulative reoperation rate. Multivariable models were constructed to assess the impact of MI-TLIF on PROs, adjusting for variables reaching p < 0.20 on univariable analyses and respective baseline PRO values.

RESULTS

The study included 297 patients, 72 (24.2%) of whom had undergone MI-TLIF and 225 (75.8%) of whom had undergone open TLIF. The 60-month follow-up rates were similar for the two cohorts (86.1% vs 75.6%, respectively; p = 0.06). Patients did not differ significantly at baseline for ODI, NRS-BP, NRS-LP, or EQ-5D (p > 0.05 for all). Perioperatively, MI-TLIF was associated with less blood loss (108.8 ± 85.6 vs 299.6 ± 242.2 ml, p < 0.001) and longer operations (228.2 ± 111.5 vs 189.6 ± 66.5 minutes, p < 0.001) but had similar lengths of hospitalizations (MI-TLIF 2.9 ± 1.8 vs open TLIF 3.3 ± 1.6 days, p = 0.08). Discharge disposition to home or home health was similar (MI-TLIF 93.1% vs open TLIF 91.1%, p = 0.60). Both cohorts improved significantly from baseline for the 60-month ODI, NRS-BP, NRS-LP, and EQ-5D (p < 0.001 for all comparisons). In adjusted analyses, MI-TLIF, compared to open TLIF, was associated with similar 60-month ODI, ODI change, odds of reaching ODI minimum clinically important difference, NRS-BP, NRS-BP change, NRS-LP, NRS-LP change, EQ-5D, EQ-5D change, and NASS satisfaction (adjusted p > 0.05 for all). The 60-month reoperation rates did not differ significantly (MI-TLIF 5.6% vs open TLIF 11.6%, p = 0.14).

CONCLUSIONS

For symptomatic, single-level grade I degenerative lumbar spondylolisthesis, MI-TLIF was associated with decreased blood loss perioperatively, but there was no difference in 60-month outcomes for disability, back pain, leg pain, quality of life, or satisfaction between MI and open TLIF. There was no difference in cumulative reoperation rates between the two procedures. These results suggest that in appropriately selected patients, either procedure may be employed depending on patient and surgeon preferences.

Free access

Letter to the Editor. Patient satisfaction after minimally invasive spine surgery

Suyash Singh, Jayesh Sardhara, Anant Mehrotra, and Sanjay Behari

Free access

Predictive model for long-term patient satisfaction after surgery for grade I degenerative lumbar spondylolisthesis: insights from the Quality Outcomes Database

Praveen V. Mummaneni, Mohamad Bydon, Mohammed Ali Alvi, Andrew K. Chan, Steven D. Glassman, Kevin T. Foley, Eric A. Potts, Christopher I. Shaffrey, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Paul Park, Michael Y. Wang, Kai-Ming Fu, Jonathan R. Slotkin, Anthony L. Asher, Michael S. Virk, Panagiotis Kerezoudis, Jian Guan, Regis W. Haid, and Erica F. Bisson

OBJECTIVE

Since the enactment of the Affordable Care Act in 2010, providers and hospitals have increasingly prioritized patient-centered outcomes such as patient satisfaction in an effort to adapt the “value”-based healthcare model. In the current study, the authors queried a prospectively maintained multiinstitutional spine registry to construct a predictive model for long-term patient satisfaction among patients undergoing surgery for Meyerding grade I lumbar spondylolisthesis.

METHODS

The authors queried the Quality Outcomes Database for patients undergoing surgery for grade I lumbar spondylolisthesis between July 1, 2014, and June 30, 2016. The primary outcome of interest for the current study was patient satisfaction as measured by the North American Spine Surgery patient satisfaction index, which is measured on a scale of 1–4, with 1 indicating most satisfied and 4 indicating least satisfied. In order to identify predictors of higher satisfaction, the authors fitted a multivariable proportional odds logistic regression model for ≥ 2 years of patient satisfaction after adjusting for an array of clinical and patient-specific factors. The absolute importance of each covariate in the model was computed using an importance metric defined as Wald chi-square penalized by the predictor degrees of freedom.

RESULTS

A total of 502 patients, out of a cohort of 608 patients (82.5%) with grade I lumbar spondylolisthesis, undergoing either 1- or 2-level decompression (22.5%, n = 113) or 1-level decompression and fusion (77.5%, n = 389), met the inclusion criteria; of these, 82.1% (n = 412) were satisfied after 2 years. On univariate analysis, satisfied patients were more likely to be employed and working (41.7%, n = 172, vs 24.4%, n = 22; overall p = 0.001), more likely to present with predominant leg pain (23.1%, n = 95, vs 11.1%, n = 10; overall p = 0.02) but more likely to present with lower Numeric Rating Scale score for leg pain (median and IQR score: 7 [5–9] vs 8 [6–9]; p = 0.05). Multivariable proportional odds logistic regression revealed that older age (OR 1.57, 95% CI 1.09–2.76; p = 0.009), preoperative active employment (OR 2.06, 95% CI 1.27–3.67; p = 0.015), and fusion surgery (OR 2.3, 95% CI 1.30–4.06; p = 0.002) were the most important predictors of achieving satisfaction with surgical outcome.

CONCLUSIONS

Current findings from a large multiinstitutional study indicate that most patients undergoing surgery for grade I lumbar spondylolisthesis achieved long-term satisfaction. Moreover, the authors found that older age, preoperative active employment, and fusion surgery are associated with higher odds of achieving satisfaction.

Free access

Characteristics of patients who return to work after undergoing surgery for cervical spondylotic myelopathy: a Quality Outcomes Database study

Stephen M. Bergin, Giorgos D. Michalopoulos, Christopher I. Shaffrey, Oren N. Gottfried, Eli Johnson, Erica F. Bisson, Michael Y. Wang, John J. Knightly, Michael S. Virk, Luis M. Tumialán, Jay D. Turner, Cheerag D. Upadhyaya, Mark E. Shaffrey, Paul Park, Kevin T. Foley, Domagoj Coric, Jonathan R. Slotkin, Eric A. Potts, Dean Chou, Kai-Ming G. Fu, Regis W. Haid Jr., Anthony L. Asher, Mohamad Bydon, Praveen V. Mummaneni, and Khoi D. Than

OBJECTIVE

Return to work (RTW) is an important surgical outcome for patients who are employed, yet a significant number of patients with cervical spondylotic myelopathy (CSM) who are employed undergo cervical spine surgery and fail to RTW. In this study, the authors investigated factors associated with failure to RTW in the CSM population who underwent cervical spine surgery and who were considered to have a good surgical outcome yet failed to RTW.

METHODS

This study retrospectively analyzed prospectively collected data from the cervical myelopathy module of a national spine registry, the Quality Outcomes Database. The CSM data set of the Quality Outcomes Database was queried for patients who were employed at the time of surgery and planned to RTW postoperatively. Distinct multivariable logistic regression models were fitted with 3-month RTW as an outcome for the overall population to identify risk factors for failure to RTW. Good outcomes were defined as patients who had no adverse events (readmissions or complications), who had achieved 30% improvement in Neck Disability Index score, and who were satisfied (North American Spine Society satisfaction score of 1 or 2) at 3 months postsurgery.

RESULTS

Of the 409 patients who underwent surgery, 80% (n = 327) did RTW at 3 months after surgery. At 3 months, 56.9% of patients met the criteria for a good surgical outcome, and patients with a good outcome were more likely to RTW (88.1% vs 69.2%, p < 0.01). Of patients with a good outcome, 11.9% failed to RTW at 3 months. Risk factors for failing to RTW despite a good outcome included preoperative short-term disability or leave status (OR 3.03 [95% CI 1.66–7.90], p = 0.02); a higher baseline Neck Disability Index score (OR 1.41 [95% CI 1.09–1.84], p < 0.01); and higher neck pain score at 3 months postoperatively (OR 0.81 [95% CI 0.66–0.99], p = 0.04).

CONCLUSIONS

Most patients with CSM who undergo spine surgery reenter the workforce within 3 months from surgery, with RTW rates being higher among patients who experience good outcomes. Among patients with good outcomes who were employed, failure to RTW was associated with being on preoperative short-term disability or leave status prior to surgery as well as higher neck pain scores at baseline and at 3 months postoperatively.

Free access

Developing nonlinear k-nearest neighbors classification algorithms to identify patients at high risk of increased length of hospital stay following spine surgery

Shane Shahrestani, Andrew K. Chan, Erica F. Bisson, Mohamad Bydon, Steven D. Glassman, Kevin T. Foley, Christopher I. Shaffrey, Eric A. Potts, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Paul Park, Michael Y. Wang, Kai-Ming Fu, Jonathan R. Slotkin, Anthony L. Asher, Michael S. Virk, Giorgos D. Michalopoulos, Jian Guan, Regis W. Haid, Nitin Agarwal, Dean Chou, and Praveen V. Mummaneni

OBJECTIVE

Spondylolisthesis is a common operative disease in the United States, but robust predictive models for patient outcomes remain limited. The development of models that accurately predict postoperative outcomes would be useful to help identify patients at risk of complicated postoperative courses and determine appropriate healthcare and resource utilization for patients. As such, the purpose of this study was to develop k-nearest neighbors (KNN) classification algorithms to identify patients at increased risk for extended hospital length of stay (LOS) following neurosurgical intervention for spondylolisthesis.

METHODS

The Quality Outcomes Database (QOD) spondylolisthesis data set was queried for patients receiving either decompression alone or decompression plus fusion for degenerative spondylolisthesis. Preoperative and perioperative variables were queried, and Mann-Whitney U-tests were performed to identify which variables would be included in the machine learning models. Two KNN models were implemented (k = 25) with a standard training set of 60%, validation set of 20%, and testing set of 20%, one with arthrodesis status (model 1) and the other without (model 2). Feature scaling was implemented during the preprocessing stage to standardize the independent features.

RESULTS

Of 608 enrolled patients, 544 met prespecified inclusion criteria. The mean age of all patients was 61.9 ± 12.1 years (± SD), and 309 (56.8%) patients were female. The model 1 KNN had an overall accuracy of 98.1%, sensitivity of 100%, specificity of 84.6%, positive predictive value (PPV) of 97.9%, and negative predictive value (NPV) of 100%. Additionally, a receiver operating characteristic (ROC) curve was plotted for model 1, showing an overall area under the curve (AUC) of 0.998. Model 2 had an overall accuracy of 99.1%, sensitivity of 100%, specificity of 92.3%, PPV of 99.0%, and NPV of 100%, with the same ROC AUC of 0.998.

CONCLUSIONS

Overall, these findings demonstrate that nonlinear KNN machine learning models have incredibly high predictive value for LOS. Important predictor variables include diabetes, osteoporosis, socioeconomic quartile, duration of surgery, estimated blood loss during surgery, patient educational status, American Society of Anesthesiologists grade, BMI, insurance status, smoking status, sex, and age. These models may be considered for external validation by spine surgeons to aid in patient selection and management, resource utilization, and preoperative surgical planning.