Dataset Information

Predicting the Response of High Frequency Spinal Cord Stimulation in Patients with Failed Back Surgery Syndrome: A Retrospective Study with Machine Learning Techniques.

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.

SUBMITTER: Goudman L

PROVIDER: S-EPMC7767526 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting the Response of High Frequency Spinal Cord Stimulation in Patients with Failed Back Surgery Syndrome: A Retrospective Study with Machine Learning Techniques.

Goudman Lisa L Van Buyten Jean-Pierre JP De Smedt Ann A Smet Iris I Devos Marieke M Jerjir Ali A Moens Maarten M

Journal of clinical medicine 20201221 12

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 ...[more]

PMID: 33371497

Similar Datasets

Project description:BackgroundAlthough results of case series support the use of spinal cord stimulation in failed back surgery syndrome patients with predominant low back pain, no confirmatory randomized controlled trial has been undertaken in this patient group to date. PROMISE is a multicenter, prospective, randomized, open-label, parallel-group study designed to compare the clinical effectiveness of spinal cord stimulation plus optimal medical management with optimal medical management alone in patients with failed back surgery syndrome and predominant low back pain.Method/designPatients will be recruited in approximately 30 centers across Canada, Europe, and the United States. Eligible patients with low back pain exceeding leg pain and an average Numeric Pain Rating Scale score ≥5 for low back pain will be randomized 1:1 to spinal cord stimulation plus optimal medical management or to optimal medical management alone. The investigators will tailor individual optimal medical management treatment plans to their patients. Excluded from study treatments are intrathecal drug delivery, peripheral nerve stimulation, back surgery related to the original back pain complaint, and experimental therapies. Patients randomized to the spinal cord stimulation group will undergo trial stimulation, and if they achieve adequate low back pain relief a neurostimulation system using the Specify® 5-6-5 multi-column lead (Medtronic Inc., Minneapolis, MN, USA) will be implanted to capture low back pain preferentially in these patients. Outcome assessment will occur at baseline (pre-randomization) and at 1, 3, 6, 9, 12, 18, and 24 months post randomization. After the 6-month visit, patients can change treatment to that received by the other randomized group. The primary outcome is the proportion of patients with ≥50% reduction in low back pain at the 6-month visit. Additional outcomes include changes in low back and leg pain, functional disability, health-related quality of life, return to work, healthcare utilization including medication usage, and patient satisfaction. Data on adverse events will be collected. The primary analysis will follow the intention-to-treat principle. Healthcare use data will be used to assess costs and long-term cost-effectiveness.DiscussionRecruitment began in January 2013 and will continue until 2016.Trial registrationClinicaltrials.gov: NCT01697358 (http://www.clinicaltrials.gov).

Project description:BackgroundWhile the evolution of technology provides new opportunities to manage chronic refractory pain using different waveform modalities of spinal cord stimulation in failed back surgery syndrome (FBSS), there is no randomized controlled trial available to compare the efficacy of these different stimulations waveforms to date. MULTIWAVE is a prospective, randomized, double-blinded, crossover trial study designed to compare the clinical efficacy of tonic conventional stimulation (TCS), burst stimulation (BURST) and high-frequency stimulation (HF) in FBSS patients over a 15-month period in SCS implanted patients.Methods/designTwenty-eight patients will be recruited in the Poitiers University Hospital, in Niort and La Rochelle Hospitals in France. Eligible patients with post-operative low back and leg pain with an average visual analog scale (VAS) score ≥ 5 for low back pain are implanted and randomly assigned to one of the six arms (in a 1:1:1:1:1:1 ratio), where they receive a 3-month combination of TCS, BURST and HF including one treatment modality per month and varying the order of the modality received within the six possible combinations. Patients receiving intrathecal drug delivery, peripheral nerve stimulation and back resurgery related to the original back pain complaint and experimental therapies are excluded from this study. Patients included in the spinal cord stimulation group undergo trial stimulation, and they all receive a TCS treatment for 2 months, as the gold standard modality. Thereafter, patients are randomly assigned to one of the six arms for the total duration of 3-month crossover period. Then, patients choose their preferred stimulation modality (TCS, BURST, or HF) for the follow-up period of 12 months. Outcome assessments are performed at baseline (first implant), before randomization (2 months after baseline) and at 1, 2, 3, 6, 9 and 15 months post-randomization. Our primary outcome is the average global VAS of pain over 5-day pain diary period between baseline and after each period of stimulation. Additional outcomes include changes in leg and back pain intensity, functional disability, quality of life, psychological state, paraesthesia intensity perception, patient satisfaction and the number of adverse events.DiscussionRecruitment began in February 2017 and will continue through 2019.Trial registrationClinicaltrials.gov NCT03014583 . Registered on 9 January 2017.

Project description:INTRODUCTION:Kilohertz frequency spinal cord stimulation (kHz-SCS) deposits significantly more power in tissue compared to SCS at conventional frequencies, reflecting increased duty cycle (pulse compression). We hypothesize kHz-SCS increases local tissue temperature by joule heat, which may influence the clinical outcomes. METHODS:To establish the role of tissue heating in KHZ-SCS, a decisive first step is to characterize the range of temperature changes expected during conventional and KHZ-SCS protocols. Fiber optic probes quantified temperature increases around an experimental SCS lead in a bath phantom. These data were used to verify a SCS lead heat-transfer model based on joule heat. Temperature increases were then predicted in a seven-compartment (soft tissue, vertebral bone, fat, intervertebral disc, meninges, spinal cord with nerve roots) geometric human spinal cord model under varied parameterization. RESULTS:The experimentally constrained bio-heat model shows SCS waveform power (waveform RMS) determines tissue heating at the spinal cord and surrounding tissues. For example, we predict temperature increased at dorsal spinal cord of 0.18-1.72?°C during 3.5?mA peak 10?KHz stimulation with a 40-10-40 ?s biphasic pulse pattern, 0.09-0.22?°C during 3.5?mA 1?KHz 100-100-100 ?s stimulation, and less than 0.05?°C during 3.5?mA 50?Hz 200-100-200 ?s stimulation. Notably, peak heating of the spinal cord and other tissues increases superlinearly with stimulation power and so are especially sensitive to incremental changes in SCS pulse amplitude or frequency (with associated pulse compression). Further supporting distinct SCS intervention strategies based on heating; the spatial profile of temperature changes is more uniform compared to electric fields, which suggests less sensitivity to lead position. CONCLUSIONS:Tissue heating may impact short and long-term outcomes of KHZ-SCS, and even as an adjunct mechanism, suggests distinct strategies for lead position and programming optimization.

Dataset Information

Predicting the Response of High Frequency Spinal Cord Stimulation in Patients with Failed Back Surgery Syndrome: A Retrospective Study with Machine Learning Techniques.

Publications

Predicting the Response of High Frequency Spinal Cord Stimulation in Patients with Failed Back Surgery Syndrome: A Retrospective Study with Machine Learning Techniques.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets