Machine Learning Algorithms Provide Greater Prediction of Response to Scs Than Lead Screening Trial: A Predictive AI-Based Multicenter Study

Amine Ounajim (1, 2) , Maxime Billot (1) , Lisa Goudman (3) , Pierre-Yves Louis (4, 5) , Yousri Slaoui (2) , Manuel Roulaud (1) , Bénédicte Bouche (1) , Philippe Page (6) , Bertille Lorgeoux (1) , Sandrine Baron (1) , Nihel Adjali (1) , Kevin Nivole (1) , Nicolas Naiditch (1, 7) , Chantal Wood (1) , Raphael Rigoard (8) , Romain David (1, 6) , Maarten Moens (3) , Philippe Rigoard (1, 9)

1 PRISMATICS - prismatics
2 LMA-Poitiers - Laboratoire de Mathématiques et Applications
3 VUB - Vrije Universiteit Brussel
4 PAM - Procédés Alimentaires et Microbiologiques [Dijon]
5 IMB - Institut de Mathématiques de Bourgogne [Dijon]
6 CHU Poitiers - Centre hospitalier universitaire de Poitiers
7 DynamE - Dynamiques européennes
8 STIC - Service des Technologies de l’Information et de la Communication
9 PPRIME - Institut Pprime

Persistent Pain after Spinal Surgery can be successfully addressed by Spinal Cord Stimulation (SCS). International guidelines strongly recommend that a lead trial be performed before any permanent implantation. Recent clinical data highlight some major limitations of this approach. First, it appears that patient outcomes, WITH OR WITHOUT lead trial, are similar. In contrast, during trialing, infection rate drops drastically within time and can compromise the therapy. Using composite pain assessment experience and previous research, we hypothesized that ma-chine learning models could be robust screening tools and reliable predictors of long-term SCS efficacy. We developed several algorithms including logistic regression, Regularized Logistic Regression (RLR), naive Bayes classifier, artificial neural networks, random forest and gradient boosted trees to test this hypothesis and to perform internal and external validations, the objec-tive being to confront model predictions with lead trial results using a 1-year composite out-come from 103 patients. While almost all models have demonstrated superiority on lead trial-ing, the RLR model appears to represent the best compromise between complexity and inter-pretability in prediction of SCS efficacy. These results underscore the need to use AI based-predictive medicine, as a synergistic mathematical approach, aimed at helping implanters to optimize their clinical choices on daily practice.

Keywords: spinal cord stimulation; screening trial; lead trial; infection; supervised learning; machine learning; predictive modeling; patient outcome

Domains: Neurons and Cognition [q-bio.NC]; Santé publique et épidémiologie; Machine Learning [stat.ML]

Amine Ounajim, Maxime Billot, Lisa Goudman, Pierre-Yves Louis, Yousri Slaoui, et al.. Machine Learning Algorithms Provide Greater Prediction of Response to Scs Than Lead Screening Trial: A Predictive AI-Based Multicenter Study. Journal of Clinical Medicine, 2021, 10 (20), pp.4764. ⟨10.3390/jcm10204764⟩. ⟨hal-03343630⟩