Using Machine Learning for Predicting the Best Outcomes With Electrical Muscle Stimulation for Tremors in Parkinson’s Disease

Recent studies have identified that peripheral stimulation in Parkinson’s disease (PD) is effective in tremor reduction, indicating that a peripheral feedback loop plays an important role in the tremor reset mechanism. This was an open-label, quasi-experimental, pre- and post-test design, single-blind, single-group study involving 20 tremor-dominant PD patients. The objective of this study is to explore the effect of electrical muscle stimulation (EMS) as an adjunctive treatment for resting tremor during “on” period and to identify the best machine learning model to predict the suitable stimulation level that will yield the longest period of tremor reduction or tremor reset time. In this study, we used a Parkinson’s glove to evaluate, stimulate, and quantify the tremors of PD patients. This adjustable glove incorporates a 3-axis gyroscope to measure tremor signals and an EMS to provide an on-demand muscle stimulation to suppress tremors. Machine learning models were applied to identify the suitable pulse amplitude (stimulation level) in five classes that led to the longest tremor reset time. The study was registered at the www.clinicaltrials.gov under the name “The Study of Rest Tremor Suppression by Using Electrical Muscle Stimulation” (NCT02370108). Twenty tremor-dominant PD patients were recruited. After applying an average pulse amplitude of 6.25 (SD 2.84) mA and stimulation period of 440.7 (SD 560.82) seconds, the total time of tremor reduction, or tremor reset time, was 329.90 (SD 340.91) seconds. A significant reduction in tremor parameters during stimulation was demonstrated by a reduction of Unified Parkinson’s Disease Rating Scale (UPDRS) scores, and objectively, with a reduction of gyroscopic data (p < 0.05, each). None of the subjects reported any serious adverse events. We also compared gyroscopic data with five machine learning techniques: Logistic Regression, Random Forest, Support Vector Machine (SVM), Neural Network (NN), and Long-Short-Term-Memory (LSTM). The machine learning model that gave the highest accuracy was LSTM, which obtained: accuracy = 0.865 and macro-F1 = 0.736. This study confirms the efficacy of EMS in the reduction of resting tremors in PD. LSTM was identified as the most effective model for predicting pulse amplitude that would elicit the longest tremor reset time. Our study provides further insight on the tremor reset mechanism in PD.

The Influences of TSH Stimulation Level, Stimulated Tg Level and Tg/TSH Ratio on the Therapeutic Effect of 131I Treatment in DTC Patients

PurposeTo study the influences of pre-ablation TSH stimulation level, sTg and sTg/TSH ratio on the therapeutic effect of the first 131I treatment in DTCs.MethodsAccording to the thyroid stimulating hormone (TSH) levels (mU/l), all the 479 differentiated thyroid cancer (DTC) patients were divided into two groups: TSH < 30 and TSH ≥ 30. The TSH ≥ 30 group was divided into three subgroups: 30 ≤ TSH < 60, 60 ≤ TSH < 90 and TSH ≥ 90. The clinical features and the therapeutic effects of the first 131I treatment were analyzed. The cutoffs of stimulated thyroglobulin (sTg) and sTg/TSH ratio were calculated to predict the therapeutic effect of 131I treatment.ResultsAmong the three subgroups, the TSH ≥ 90 subgroup was younger and less likely to be associated with cervical lymph node metastasis (LNM). The postoperative levothyroxine (L-T4) dose in the 60 ≤ TSH < 90 subgroup was the lowest. Between the two groups, patients in the TSH < 30 group had higher postoperative L-T4 dose and longer thyroid hormone withdrawal (THW) time. The excellent response rates six months after the first 131I treatment among the three subgroups and between the two groups were not of statistical significance. The distribution of different TSH stimulation levels among each response group was similar. The cutoffs for the better therapeutic effect of the first 131I treatment in sTg and sTg/TSH were < 9.51 ng/ml and < 0.11, respectively. Both univariate and multivariate logistic regressions showed that cervical LNM, distant metastasis, higher sTg and higher sTg/TSH ratio predicted poorer therapeutic effect.ConclusionsThere was no significant influence of TSH stimulation levels before the first 131I treatment on the therapeutic effect of DTC. The sTg/TSH ratio can be considered as another predictor of 131I therapeutic effect.

819 A RARE CASE OF RESPIRATORY SENSE LEAD DYSFUNCTION IN A PATIENT WITH A HYPOGLOSSAL NERVE STIMULATOR

Introduction In patients with moderate to severe obstructive sleep apnea (OSA) who are intolerant to PAP therapy, hypoglossal nerve stimulation (HGNS) is being increasingly considered as alternative treatment. Implantation involves placing cuff electrodes on inclusion branches of the hypoglossal nerve and a respiratory effort-sensing lead which is placed between the right intercostal muscle layers. These are connected to the implantable pulse generator which usually sits in a right infraclavicular pocket. Report of case(s) A 49-year-old male with severe OSA (AHI 30.8/hour) was implanted with a HGNS two years ago with successful activation a month later. He successfully up titrated his amplitude to the maximum stimulation level within his set range (0.9v – 1.7v). He underwent HGNS titration with AHI reduction to 13.9/hour at 2.1 volts and given a new higher range of 1.5 to 2.5 volts. This was accompanied by reduction in snoring, witnessed apneas and associated arousals with more consolidated sleep and improvement in his Epworth sleepiness score to 3 from 12 as noted prior to HGNS. The patient continued to up titrate over the next six months within his new range to 2.4 volts, when he reported increased sensitivity and intolerance at every stimulation level with recurrence of snoring and daytime sleepiness. He underwent interrogation of his device with subsequent awake endoscopy and change to his electrode configuration with a new lower range of 1.0 to 2.0 volts. However, he continued to have the same complaints. A second interrogation revealed increased impedance within the circuit of the respiratory sensing lead which was reproducible. The patient underwent sensing lead replacement in the operating room. He has since been able to increase stimulation levels without complaints and improvement in his OSA symptoms and is scheduled to have a follow-up hone sleep test (HST). Conclusion This case illustrates the importance of a structured approach in the evaluation of a reduced tolerance to HGNS. This includes assessing adherence, interrogation of the device’s circuitry, evaluating electrode configurations, stimulation thresholds with consideration for awake endoscopy. Repeating this process may be necessary to detect rare or delayed mechanical problems that may occur over time with HGNS. Support (if any):

Effects of luck beliefs on consumers' variety-seeking behavior

From a risk perspective and using the courage–ability–willingness theory in relation to consumer choice, we built a model with luck beliefs as the independent variable, psychological security and self-efficacy as mediating variables, optimum stimulation level as the moderating variable, and variety seeking as the outcome variable. We conducted an online survey and analyzed data from 593 participants using structural equation modeling. The results show that personal luckiness and belief in luck positively affected variety seeking, psychological security and self-efficacy mediated the influence of luck beliefs on variety seeking, and optimum stimulation level positively affected variety seeking and positively moderated the effect of personal luck on variety seeking. However, the moderating effect of belief in luck on variety seeking was nonsignificant. Practical and theoretical implications of the findings are discussed.

Using electrodermal activity to validate multilevel pain stimulation in healthy volunteers evoked by thermal grills

We have tested the feasibility of thermal grills, a harmless method to induce pain. The thermal grills consist of interlaced tubes that are set at cool or warm temperatures, creating a painful “illusion” (no tissue injury is caused) in the brain when the cool and warm stimuli are presented collectively. Advancement in objective pain assessment research is limited because the gold standard, the self-reporting pain scale, is highly subjective and only works for alert and cooperative patients. However, the main difficulty for pain studies is the potential harm caused to participants. We have recruited 23 subjects in whom we induced electric pulses and thermal grill (TG) stimulation. The TG effectively induced three different levels of pain, as evidenced by the visual analog scale (VAS) provided by the subjects after each stimulus. Furthermore, objective physiological measurements based on electrodermal activity showed a significant increase in levels as stimulation level increased. We found that VAS was highly correlated with the TG stimulation level. The TG stimulation safely elicited pain levels up to 9 out of 10. The TG stimulation allows for extending studies of pain to ranges of pain in which other stimuli are harmful.

Changes in Electroencephalography by Modulation of Interferential Current Stimulation

Interferential current (IFC) stimulation can alter pain perception. This study aimed to investigate the effects of IFC stimulation on motor cortex signals and observe how electroencephalography changes depend on IFC stimulation parameters. Forty-five healthy adults were divided into high frequency (HF)–low intensity (LI), HF–high intensity (HI), and low frequency (LF)–HI groups to compare their electroencephalography before, immediately after, and 30 min after current stimulation. The changes in relative beta power according to the intervention time showed significant differences between the HF–LI and HF–HI, as well as the LF–HI and HF–HI, groups in the C3 and P3 regions immediately after IFC stimulation. Similarly, the gamma band showed significant differences according to the intervention time between the LF–HI and HF–HI groups in the P3 region immediately following IFC intervention. For relative theta power, the interaction between group and time was significantly different in the Fp2, F3, F4, C3, C4, and P4 regions. Based on these results, we were able to map the activation in cerebral cortex regions according to the stimulation level, confirming changes in electroencephalogram activation through peripheral nerve stimulation. This study provides a foundation for future applications for selectively controlling feedback at a proper stimulation level in young adults.

Abstract 114: Diverse Patients Show Physiologic Benefit From Refined Sphenopalatine Ganglion Electrode Placement and Stimulation Level Selection to Augment Blood Flow and Neurologic Function in Acute Ischemic Stroke (The IMPACT-24M Trial)

Background: Two large RCTs have indicated sphenopalatine ganglion (SPG) stimulation reduces 3m disability in acute ischemic stroke patients with confirmed cortical involvement. The current trial evaluated two refinements in SPG stimulation technique: 1) SPG electrode placement with real-time optical tracking guidance; and 2) stimulation intensity comfortable tolerance level (CTL) selection using non-noxious facial physiologic markers. Methods: Single, active arm trial at 4 centers, enrolling patients with anterior circulation ischemic stroke <24h, NIHSS 1-6, not receiving recanalization therapies. Stimulation level was based on ipsilateral facial tingling sensation or lacrimation. SPG stimulation effects were assessed by volumetric blood flow in the ipsilateral common carotid artery (ultrasound) and affected hand grasp and pinch strength before and during stimulation, and by NIHSS change by day 7. Results: Among 50 enrolled patients, age was median 66y (IQR 60-74), 44% female, NIHSS median 5 (IQR 4-5), and median onset-to-screening time 18h (IQR 9-20). Median implantation skin-to-skin time was 4 minutes (IQR 3-7) and all 50 implants were placed correctly. CTL was found based on physiological biomarkers in 96% of patients, including 86% in the optimal, low-medium intensity range. SPG stimulation significantly increased common carotid artery peak systolic and end diastolic blood flow (up 44%, p<0.0001; and up 52%, p<0.0001) and improved pinch strength (up 42%, p<0.0001) and grasp strength (up 26%, p<0.0001). Degree of NIHSS recovery by day 7 was greater than in matched historic controls, median 75% vs 50%, p=0.0003. Forest plot analysis showed benefits were homogenous across the subgroups of: sex, age, time from onset, stroke side, NIHSS, and ASPECTS score. Conclusion: SPG stimulator placement with real-time optical tracking guidance was fast and accurate, and selection of optimal stimulation intensity levels based on non-noxious facial tingling and lacrimation was feasible in nearly all patients. SPG activation led to cranial blood flow augmentation and improved hand motor function during stimulation, and neurologic deficit reduction at 1 week, consistently across broad patient subsets of age, sex, side, severity, and time to treatment.

Switching from hotels to peer-to-peer accommodation: an empirical study

Purpose Peer-to-peer (P2P) accommodation has become increasingly popular in recent years, and hotels are facing unprecedented impacts. Attracting new consumers and retaining existing ones are critical to the success of P2P accommodation and hotels. The purpose of this paper is to examine three categories of antecedents for hotels consumers’ switching intention: push (i.e. satiation), pull (i.e. perceived value) and mooring (i.e. optimal stimulation level) factors using push–pull–mooring (PPM) model. Design/methodology/approach Airbnb was chosen as the research context. An online survey was conducted to examine the proposed research model and hypotheses. A total of 292 valid data were collected from Airbnb users through a survey. Findings The findings show that the three categories of factors have positive and significant effects on switching intention. Additionally, the mooring factor has a significant moderating effect on the relationship between pull factors and switching intention. Furthermore, the mooring factor affects both pull and push factors. Originality/value First, this is one of the early studies to pay attention to switching intention from hotels to P2P accommodation. Second, to provide a comprehensive understanding of consumers’ switching intention, the authors use PPM model to establish the research framework. This research improves the understanding of consumer’s switching intention by identifying the push and pull factors based on the differences between hotels and P2P accommodation in accordance with optimal stimulation level theory and consumer value theory.