FUSE-ML: development and external validation of a clinical prediction model for mid-term outcomes after lumbar spinal fusion for degenerative disease

Abstract

Background Indications and outcomes in lumbar spinal fusion for degenerative disease are notoriously heterogenous. Selected subsets of patients show remarkable benefit. However, their objective identification is often difficult. Decision-making may be improved with reliable prediction of long-term outcomes for each individual patient, improving patient selection and avoiding ineffective procedures. Methods Clinical prediction models for long-term functional impairment [Oswestry Disability Index (ODI) or Core Outcome Measures Index (COMI)], back pain, and leg pain after lumbar fusion for degenerative disease were developed. Achievement of the minimum clinically important difference at 12 months postoperatively was defined as a reduction from baseline of at least 15 points for ODI, 2.2 points for COMI, or 2 points for pain severity. Results Models were developed and integrated into a web-app (https://neurosurgery.shinyapps.io/fuseml/) based on a multinational cohort [N = 817; 42.7% male; mean (SD) age: 61.19 (12.36) years]. At external validation [N = 298; 35.6% male; mean (SD) age: 59.73 (12.64) years], areas under the curves for functional impairment [0.67, 95% confidence interval (CI): 0.59–0.74], back pain (0.72, 95%CI: 0.64–0.79), and leg pain (0.64, 95%CI: 0.54–0.73) demonstrated moderate ability to identify patients who are likely to benefit from surgery. Models demonstrated fair calibration of the predicted probabilities. Conclusions Outcomes after lumbar spinal fusion for degenerative disease remain difficult to predict. Although assistive clinical prediction models can help in quantifying potential benefits of surgery and the externally validated FUSE-ML tool may aid in individualized risk–benefit estimation, truly impacting clinical practice in the era of “personalized medicine” necessitates more robust tools in this patient population.

Clinical Decision Support System Used in Spinal Disorders: Scoping Review

“…Of the 31 CDSS studies reviewed, 11 (35%) prognostic CDSS studies ( Table 4 ) were knowledge based [ 44 , 45 , 47 - 54 , 59 ], with regression-based predictive algorithms. White-box models were used across all studies; most CDSSs were presented as web-based calculators, whereas others were presented as independent software.…”

Development of an online calculator for the prediction of seizure freedom following pediatric hemispherectomy using the Hemispherectomy Outcome Prediction Scale (HOPS)

“…17,18,22,[30][31][32] The format of an online calculator renders complex statistical models more accessible with the potential for broad clinical impact. 17,18,22,[30][31][32] The HOPS calculator thus builds on the previously reported HOPS study, which identified five important predictors of post-hemispheric surgery seizure freedom (age greater than 3.5 years at seizure onset, absence of generalized seizure semiology, absence of contralateral FDG-PET hypometabolism, stroke-induced seizure etiology, and absence of prior resective neurosurgery) and developed an easyto-use seizure outcome prediction score. 1 As a result, this online calculator renders the original prediction tool readily and widely used by clinicians to estimate the potential benefits of hemispheric surgery in a given patient into a tool that epilepsy centers and families worldwide can access, utilize, and comprehend more easily.…”

“…29 Online calculators are useful, cost-free tools that can assist physicians in risk-and-benefit estimations and inform joint decision-making with patients and/or guardians. 17,18,22,[30][31][32] The format of an online calculator renders complex statistical models more accessible with the potential for broad clinical impact. 17,18,22,[30][31][32] The HOPS calculator thus builds on the previously reported HOPS study, which identified five important predictors of post-hemispheric surgery seizure freedom (age greater than 3.5 years at seizure onset, absence of generalized seizure semiology, absence of contralateral FDG-PET hypometabolism, stroke-induced seizure etiology, and absence of prior resective neurosurgery) and developed an easyto-use seizure outcome prediction score.…”

“…The decision‐making process to undergo hemispheric surgery for DRE requires accurate evidence‐based estimation of risks and benefits within a framework that considers patient and caregiver‐based values and preferences 29 . Online calculators are useful, cost‐free tools that can assist physicians in risk‐and‐benefit estimations and inform joint decision‐making with patients and/or guardians 17,18,22,30–32 . The format of an online calculator renders complex statistical models more accessible with the potential for broad clinical impact 17,18,22,30–32 .…”

Predicting Proximal Junctional Kyphosis After Adult Spinal Deformity Surgery: A Step Towards True “Precision” Medicine?: Commentary on “Development and Validation of an Online Calculator to Predict Proximal Junctional Kyphosis After Adult Spinal Deformity Surgery Using Machine Learning”

“…Still, many prediction tasks appear simply too difficult in the real-world (meaning, with proper external validation)-probably, it is simply unrealistic to expect to be able to predict the future with any great amount of accuracy. 6 Conceptually, this is even clearer in medical prediction modeling: Predicting future outcomes that depend on hundreds of factors would-of course -require collection and integration of these hundreds of factors. Apart from the impracticality of collecting and inputing such wealths of data into an online calculator in daily practice, in medicine, we usually do not even have the case numbers to allow for training of models with hundreds of factors (which would require tens of thousands of patients for proper clinical prediction modeling).…”