|
1
|
Hariharan V, Harland TA, Young C, Sagar A, Gomez MM, Pilitsis JG. Machine Learning in Spinal Cord Stimulation for Chronic Pain. Oper Neurosurg (Hagerstown) 2023; 25:112-116. [PMID: 37219574 PMCID: PMC10586864 DOI: 10.1227/ons.0000000000000774] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Accepted: 04/17/2023] [Indexed: 05/24/2023] Open
Abstract
Spinal cord stimulation (SCS) is an effective treatment for chronic neuropathic pain. The success of SCS is dependent on candidate selection, response to trialing, and programming optimization. Owing to the subjective nature of these variables, machine learning (ML) offers a powerful tool to augment these processes. Here we explore what work has been done using data analytics and applications of ML in SCS. In addition, we discuss aspects of SCS which have narrowly been influenced by ML and propose the need for further exploration. ML has demonstrated a potential to complement SCS to an extent ranging from assistance with candidate selection to replacing invasive and costly aspects of the surgery. The clinical application of ML in SCS shows promise for improving patient outcomes, reducing costs of treatment, limiting invasiveness, and resulting in a better quality of life for the patient.
Collapse
Affiliation(s)
- Varun Hariharan
- Department of Clinical Neurosciences, Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, Florida, USA
| | - Tessa A. Harland
- Department of Neurosurgery, Albany Medical College, Albany, New York, USA
| | - Christopher Young
- Department of Clinical Neurosciences, Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, Florida, USA
| | - Amit Sagar
- Department of Clinical Neurosciences, Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, Florida, USA
| | - Maria Merlano Gomez
- Department of Clinical Neurosciences, Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, Florida, USA
| | - Julie G. Pilitsis
- Department of Clinical Neurosciences, Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, Florida, USA
| |
Collapse
|
|
2
|
Memar K, Varghese SN, Morrison AG, Clonch DA, Lam CM, Holwerda SW. Low- and high-frequency spinal cord stimulation and arterial blood pressure in patients with chronic pain and hypertension: a retrospective study. Clin Auton Res 2023; 33:443-449. [PMID: 37171770 DOI: 10.1007/s10286-023-00947-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2023] [Accepted: 04/15/2023] [Indexed: 05/13/2023]
Abstract
PURPOSE Evidence suggests that traditional low-frequency spinal cord stimulation (LF-SCS) reduces arterial blood pressure (BP) in patients with chronic pain and hypertension independent of improved pain symptoms. However, it remains unclear whether high-frequency spinal cord stimulation (HF-SCS) also lowers BP in chronic pain patients with hypertension. Therefore, in a retrospective study design, we tested the hypothesis that clinic BP would be significantly reduced following implantation of HF-SCS in patients with chronic pain and hypertension. METHODS Clinic BP within 3 months before and after surgical implantation of either a LF-SCS or HF-SCS device between 2010 and 2020 were collected from electronic medical records at The University of Kansas Health System (TUKHS). RESULTS A total of 132 patients had available records of clinic BP (64 ± 13 years of age). Patients with hypertension (n = 32) demonstrated a significantly greater reduction in systolic BP (-8 ± 12 versus 2 ± 9 mmHg, P < 0.001) following implantation compared with normotensive patients (n = 100). Importantly, the change in BP was inversely related to baseline BP independent of age and sex following implantation of HF-SCS (n = 70, R = -0.50, P < 0.001) or LF-SCS (n = 62, R = -0.42, P = 0.001). Higher pain scores before implantation were not associated with reduction in systolic BP (R = 0.10, P = 0.43) or diastolic BP (R = -0.08, P = 0.53) (n = 69) after implantation. CONCLUSION These findings confirm previous studies showing reduced BP following implantation of LF-SCS in patients with chronic pain and hypertension and provide novel data regarding reduced BP following implantation of newer generation HF-SCS devices.
Collapse
Affiliation(s)
- Kimia Memar
- Department of Anesthesiology, University of Kansas Medical Center, 3901 Rainbow Blvd, Mail Stop 7013, Kansas City, KS, 66160-7415, USA
| | - Sunita N Varghese
- Department of Anesthesiology, University of Kansas Medical Center, 3901 Rainbow Blvd, Mail Stop 7013, Kansas City, KS, 66160-7415, USA
| | - Austin G Morrison
- Department of Cell Biology and Physiology, University of Kansas Medical Center, Kansas City, KS, USA
| | - Davina A Clonch
- Department of Anesthesiology, University of Kansas Medical Center, 3901 Rainbow Blvd, Mail Stop 7013, Kansas City, KS, 66160-7415, USA
| | - Christopher M Lam
- Department of Anesthesiology, University of Kansas Medical Center, 3901 Rainbow Blvd, Mail Stop 7013, Kansas City, KS, 66160-7415, USA
| | - Seth W Holwerda
- Department of Anesthesiology, University of Kansas Medical Center, 3901 Rainbow Blvd, Mail Stop 7013, Kansas City, KS, 66160-7415, USA.
- Department of Cell Biology and Physiology, University of Kansas Medical Center, Kansas City, KS, USA.
| |
Collapse
|
|
3
|
Ounajim A, Billot M, Goudman L, Louis PY, Slaoui Y, Roulaud M, Bouche B, Page P, Lorgeoux B, Baron S, Adjali N, Nivole K, Naiditch N, Wood C, Rigoard R, David R, Moens M, Rigoard P. Machine Learning Algorithms Provide Greater Prediction of Response to SCS Than Lead Screening Trial: A Predictive AI-Based Multicenter Study. J Clin Med 2021; 10:4764. [PMID: 34682887 PMCID: PMC8538165 DOI: 10.3390/jcm10204764] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2021] [Revised: 10/08/2021] [Accepted: 10/11/2021] [Indexed: 12/12/2022] Open
Abstract
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 outco mes, 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 machine 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 objective being to confront model predictions with lead trial results using a 1-year composite outcome from 103 patients. While almost all models have demonstrated superiority on lead trialing, the RLR model appears to represent the best compromise between complexity and interpretability in the 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.
Collapse
Affiliation(s)
- Amine Ounajim
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
- Laboratoire de Mathématiques et Applications, UMR 7348, Poitiers University and CNRS, 86000 Poitiers, France;
| | - Maxime Billot
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Lisa Goudman
- Department of Neurosurgery, Universitair Ziekenhuis Brussel, 1090 Brussels, Belgium; (L.G.); (M.M.)
- STUMULUS Research Group, Vrije Universiteit Brussel, 1090 Brussels, Belgium
| | - Pierre-Yves Louis
- AgroSup Dijon, PAM UMR 02.102, Université Bourgogne Franche-Comté, 21000 Dijon, France;
- Institut de Mathématiques de Bourgogne, UMR 5584 CNRS, Université Bourgogne Franche-Comté, 21000 Dijon, France
| | - Yousri Slaoui
- Laboratoire de Mathématiques et Applications, UMR 7348, Poitiers University and CNRS, 86000 Poitiers, France;
| | - Manuel Roulaud
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Bénédicte Bouche
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Philippe Page
- Department of Spine Surgery & Neuromodulation, Poitiers University Hospital, 86021 Poitiers, France;
| | - Bertille Lorgeoux
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Sandrine Baron
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Nihel Adjali
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Kevin Nivole
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Nicolas Naiditch
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
- Dyname, UMR 7367, Faculty of Social Sciences, University of Strasbourg, 67083 Strasbourg, France
| | - Chantal Wood
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
| | - Raphaël Rigoard
- CEA Cadarache, Département de Support Technique et Gestion, Service des Technologies de L’Information et de la Communication, 13108 Saint-Paul-Lez-Durance, France;
| | - Romain David
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
- Physical and Rehabilitation Medicine Unit, Poitiers University Hospital, University of Poitiers, 86021 Poitiers, France
| | - Maarten Moens
- Department of Neurosurgery, Universitair Ziekenhuis Brussel, 1090 Brussels, Belgium; (L.G.); (M.M.)
- STUMULUS Research Group, Vrije Universiteit Brussel, 1090 Brussels, Belgium
| | - Philippe Rigoard
- PRISMATICS Lab (Predictive Research in Spine/Neuromodulation Management and Thoracic Innovation/Cardiac Surgery), Poitiers University Hospital, 86021 Poitiers, France; (M.B.); (M.R.); (B.B.); (B.L.); (S.B.); (N.A.); (K.N.); (N.N.); (C.W.); (R.D.); (P.R.)
- Department of Spine Surgery & Neuromodulation, Poitiers University Hospital, 86021 Poitiers, France;
- Prismatics Lab & Spine Surgery and Neuromodulation Department, Poitiers University Hospital, 86021 Poitiers, France
| |
Collapse
|
|
4
|
Goudman L, Van Buyten JP, De Smedt A, Smet I, Devos M, Jerjir A, Moens M. Predicting the Response of High Frequency Spinal Cord Stimulation in Patients with Failed Back Surgery Syndrome: A Retrospective Study with Machine Learning Techniques. J Clin Med 2020; 9:E4131. [PMID: 33371497 DOI: 10.3390/jcm9124131] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2020] [Revised: 12/11/2020] [Accepted: 12/18/2020] [Indexed: 12/13/2022] Open
Abstract
Despite the proven clinical value of spinal cord stimulation (SCS) for patients with failed back surgery syndrome (FBSS), factors related to a successful SCS outcome are not yet clearly understood. This study aimed to predict responders for high frequency SCS at 10 kHz (HF-10). Data before implantation and the last available data was extracted for 119 FBSS patients treated with HF-10 SCS. Correlations, logistic regression, linear discriminant analysis, classification and regression trees, random forest, bagging, and boosting were applied. Based on feature selection, trial pain relief, predominant pain location, and the number of previous surgeries were relevant factors for predicting pain relief. To predict responders with 50% pain relief, 58.33% accuracy was obtained with boosting, random forest and bagging. For predicting responders with 30% pain relief, 70.83% accuracy was obtained using logistic regression, linear discriminant analysis, boosting, and classification trees. For predicting pain medication decrease, accuracies above 80% were obtained using logistic regression and linear discriminant analysis. Several machine learning techniques were able to predict responders to HF-10 SCS with an acceptable accuracy. However, none of the techniques revealed a high accuracy. The inconsistent results regarding predictive factors in literature, combined with acceptable accuracy of the currently obtained models, might suggest that routinely collected baseline parameters from clinical practice are not sufficient to consistently predict the SCS response with a high accuracy in the long-term.
Collapse
|