Background context:

The number of elective spinal fusion procedures performed each year continues to grow, making risk factors for post-operative complications following this procedure increasingly clinically relevant. Non-home discharge (NHD) is of particular interest due to its associations with increased costs of care and rates of complications. Notably, increased age has been found to influence rates of NHD.

Purpose:

To identify aged-adjusted risk factors for non-home discharge following elective lumbar fusion through the utilization of Machine Learning-generated predictions within stratified age groupings.

Study design:

Retrospective Database Study PATIENT SAMPLE: The American College of Surgeons National Quality Improvement Program (ACS-NSQIP) database years 2008-2018.

Outcome measures:

Postoperative discharge destination.

Methods:

ACS-NSQIP was queried to identify adult patients undergoing elective lumbar spinal fusion from 2008 to 2018. Patients were then stratified into the following age ranges: 30-44 years, 45-64 years, and ≥65 years. These groups were then analyzed by eight ML algorithms, each tasked with predicting post-operative discharge destination.

Results:

Prediction of NHD was performed with average AUCs of 0.591, 0.681, and 0.693 for those aged 30-44, 45-64, and ≥65 years respectively. In patients aged 30-44, operative time (p <0.001), African American/Black race (p = 0.003), female sex (p = 0.002), ASA class 3 designation (p = 0.002), and preoperative hematocrit (p = 0.002) were predictive of NHD. In ages 45-64, predictive variables included operative time, age, preoperative hematocrit, ASA class 2 or class 3 designation, insulin-dependent diabetes, female sex, BMI, and African American/Black race all with p < 0.001. In patients ≥65 years, operative time, adult spinal deformity, BMI, insulin-dependent diabetes, female sex, ASA class 4 designation, inpatient status, age, African American/Black race, and preoperative hematocrit were predictive of NHD with p < 0.001. Several variables were distinguished as predictive for only one age group including ASA Class 2 designation in ages 45-64 and adult spinal deformity, ASA class 4 designation, and inpatient status for patients ≥65 years.

Conclusions:

Application of ML algorithms to the ACS-NSQIP dataset identified a number of highly predictive and age-adjusted variables for NHD. As age is a risk factor for NHD following spinal fusion, our findings may be useful in both guiding perioperative decision-making and recognizing unique predictors of NHD among specific age groups.