TY - JOUR
T1 - FUSE-ML: development and external validation of a clinical prediction model for mid-term outcomes after lumbar spinal fusion for degenerative disease
AU - Staartjes, Victor E
AU - Stumpo, Vittorio
AU - Ricciardi, Luca
AU - Maldaner, Nicolai
AU - Eversdijk, Hubert A J
AU - Vieli, Moira
AU - Ciobanu-Caraus, Olga
AU - Raco, Antonino
AU - Miscusi, Massimo
AU - Perna, Andrea
AU - Proietti, Luca
AU - Lofrese, Giorgio
AU - Dughiero, Michele
AU - Cultrera, Francesco
AU - Nicassio, Nicola
AU - An, Seong Bae
AU - Ha, Yoon
AU - Amelot, Aymeric
AU - Alcobendas, Irene
AU - Viñuela-Prieto, Jose M
AU - Gandía-González, Maria L
AU - Girod, Pierre-Pascal
AU - Lener, Sara
AU - Kögl, Nikolaus
AU - Abramovic, Anto
AU - Safa, Nico Akhavan
AU - Laux, Christoph J
AU - Farshad, Mazda
AU - O'Riordan, Dave
AU - Loibl, Markus
AU - Mannion, Anne F
AU - Scerrati, Alba
AU - Molliqaj, Granit
AU - Tessitore, Enrico
AU - Schröder, Marc L
AU - Vandertop, W Peter
AU - Stienen, Martin N
AU - Regli, Luca
AU - Serra, Carlo
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Clinical prediction model
KW - Machine learning
KW - Spinal fusion
KW - Outcome prediction
KW - Predictive analytics
KW - Neurosurgery
KW - Clinical prediction model
KW - Machine learning
KW - Spinal fusion
KW - Outcome prediction
KW - Predictive analytics
KW - Neurosurgery
UR - http://hdl.handle.net/10807/304700
U2 - 10.1007/s00586-022-07135-9
DO - 10.1007/s00586-022-07135-9
M3 - Article
SN - 1432-0932
VL - 31
SP - 2629
EP - 2638
JO - European Spine Journal
JF - European Spine Journal
ER -