Dataset Information

A feasibility study on AI-controlled closed-loop electrical stimulation implants.

ABSTRACT: Miniaturized electrical stimulation (ES) implants show great promise in practice, but their real-time control by means of biophysical mechanistic algorithms is not feasible due to computational complexity. Here, we study the feasibility of more computationally efficient machine learning methods to control ES implants. For this, we estimate the normalized twitch force of the stimulated extensor digitorum longus muscle on n = 11 Wistar rats with intra- and cross-subject calibration. After 2000 training stimulations, we reach a mean absolute error of 0.03 in an intra-subject setting and 0.2 in a cross-subject setting with a random forest regressor. To the best of our knowledge, this work is the first experiment showing the feasibility of AI to simulate complex ES mechanistic models. However, the results of cross-subject training motivate more research on error reduction methods for this setting.

SUBMITTER: Eickhoff S

PROVIDER: S-EPMC10287710 | biostudies-literature | 2023 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A feasibility study on AI-controlled closed-loop electrical stimulation implants.

Eickhoff Steffen S Garcia-Agundez Augusto A Haidar Daniela D Zaidat Bashar B Adjei-Mosi Michael M Li Peter P Eickhoff Carsten C

Scientific reports 20230622 1

Miniaturized electrical stimulation (ES) implants show great promise in practice, but their real-time control by means of biophysical mechanistic algorithms is not feasible due to computational complexity. Here, we study the feasibility of more computationally efficient machine learning methods to control ES implants. For this, we estimate the normalized twitch force of the stimulated extensor digitorum longus muscle on n = 11 Wistar rats with intra- and cross-subject calibration. After 2000 tra ...[more]

PMID: 37349359

Similar Datasets

Project description:ImportanceBecause Tourette syndrome (TS) is a paroxysmal disorder, symptomatic relief in individuals with TS may be possible through the application of stimulation only during the manifestation of human tic neural signatures. This technique could be capable of suppressing both motor and vocal tics and would have similar effectiveness to conventional continuous deep brain stimulation (DBS).ObjectiveTo evaluate the feasibility, safety, and clinical effectiveness of bilateral centromedian-parafascicular complex thalamic closed-loop DBS as a treatment for medication-refractory TS.Design, setting, and participantsThis single-center double-blinded safety and feasibility trial was conducted between February 2014 and June 2020. Six individuals with TS were screened and recruited from the Norman Fixel Institute at the University of Florida. The primary outcome was measured at 6 months, and participants were followed up for the duration of the neurostimulator battery life. Independent ratings that compared closed-loop and conventional DBS were videotaped. The first 2 of 6 individuals with TS were excluded from the study because the technology for embedded closed-loop capability was not yet available. The date of analysis was August 2020.InterventionsDBS therapy controlled by an embedded closed-loop stimulation system.Main outcomes and measuresThe primary clinical outcome measure was a minimum of a 40% reduction in the YGTSS score at 6 months following DBS. There was also a comparison of conventional DBS with closed-loop DBS using the Modified Rush Videotape Rating Scale for Tic.ResultsThe mean (SD) age at TS diagnosis for the cohort was 8.5 (2.9), and the mean (SD) disease duration was 23.7 (5.8) years. Four individuals with TS were analyzed (2 male, 2 female; mean [SD] age, 23.7 [5.8] years). The study showed the closed-loop approach was both feasible and safe. One of the novelties of this study was that a patient-specific closed-loop paradigm was created for each participant. The features and stimulation transition speed were customized based on the signal quality and the tolerance to adverse reactions. The mean (SD) therapeutic outcome with conventional DBS was 33.3% (35.7%) improvement on the YGTSS and 52.8% (21.9%) improvement on the Modified Rush Videotape Rating Scale. Two of 4 participants had a primary outcome variable improvement of 40% meeting the primary efficacy target. When comparing closed-loop DBS with conventional DBS using a Wilcoxon sign-rank test, there was no statistical difference between tic severity score and both approaches revealed a lower tic severity score compared with baseline. The study was feasible in all 4 participants, and there were 25 total reported adverse events with 3 study-related events (12%). The most common adverse events were headache and anxiety.Conclusions and relevanceEmbedded closed-loop deep DBS was feasible, safe, and had a comparable outcome to conventional TS DBS for the treatment of tics.Trial registrationClinicalTrials.gov Identifier: NCT02056873.

Dataset Information

A feasibility study on AI-controlled closed-loop electrical stimulation implants.

Publications

A feasibility study on AI-controlled closed-loop electrical stimulation implants.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets