Good Days and Bad Days: Measuring Health-Related Quality of Life in People With Epilepsy.

OBJECTIVES: Cost-effectiveness analyses typically require measurement of health-related quality of life (HRQoL) to estimate quality-adjusted life-years. Challenges with measuring HRQoL arise in the context of episodic conditions if patients are less likely-or even unable-to complete surveys when having disease symptoms. This article explored whether HRQoL measured at regular time intervals adequately reflects the HRQoL of people with epilepsy (PWE). METHODS: Follow-up data from the Epilepsy Support Dog Evaluation study on the (cost-)effectiveness of seizure dogs were used in which HRQoL is measured in 25 PWE with the EQ-5D at baseline and every 3 months thereafter. Seizure count is recorded daily using a seizure diary. Regression models were employed to explore whether PWE were more likely to complete the HRQoL survey on a good day (ie, when seizures are absent or low in frequency compared with other days) and to provide an estimate of the impact of reporting HRQoL on a good day on EQ-5D utility scores. RESULTS: A total of 111 HRQoL measurements were included in the analyses. Regression analyses indicated that the day of reporting HRQoL was associated with a lower seizure count (P<.05) and that a lower seizure count was associated with a higher EQ-5D utility score (P<.05). CONCLUSIONS: When HRQoL is measured at regular time intervals, PWE seem more likely to complete these surveys on good days. Consequently, HRQoL might be overestimated in this population. This could lead to underestimation of the effectiveness of treatment and to biased estimates of cost-effectiveness.

Deep brain stimulation of the anterior nucleus of the thalamus for drug-resistant epilepsy.

Despite the use of first-choice anti-epileptic drugs and satisfactory seizure outcome rates after resective epilepsy surgery, a considerable percentage of patients do not become seizure free. ANT-DBS may provide for an alternative treatment option in these patients. This literature review discusses the rationale, mechanism of action, clinical efficacy, safety, and tolerability of ANT-DBS in drug-resistant epilepsy patients. A review using systematic methods of the available literature was performed using relevant databases including Medline, Embase, and the Cochrane Library pertaining to the different aspects ANT-DBS. ANT-DBS for drug-resistant epilepsy is a safe, effective and well-tolerated therapy, where a special emphasis must be given to monitoring and neuropsychological assessment of both depression and memory function. Three patterns of seizure control by ANT-DBS are recognized, of which a delayed stimulation effect may account for an improved long-term response rate. ANT-DBS remotely modulates neuronal network excitability through overriding pathological electrical activity, decrease neuronal cell loss, through immune response inhibition or modulation of neuronal energy metabolism. ANT-DBS is an efficacious treatment modality, even when curative procedures or lesser invasive neuromodulative techniques failed. When compared to VNS, ANT-DBS shows slightly superior treatment response, which urges for direct comparative trials. Based on the available evidence ANT-DBS and VNS therapies are currently both superior compared to non-invasive neuromodulation techniques such as t-VNS and rTMS. Additional in-vivo research is necessary in order to gain more insight into the mechanism of action of ANT-DBS in localization-related epilepsy which will allow for treatment optimization. Randomized clinical studies in search of the optimal target in well-defined epilepsy patient populations, will ultimately allow for optimal patient stratification when applying DBS for drug-resistant patients with epilepsy.

2018 ACC/HRS/NASCI/SCAI/SCCT Expert Consensus Document on Optimal Use of Ionizing Radiation in Cardiovascular Imaging-Best Practices for Safety and Effectiveness, Part 2: Radiological Equipment Operation, Dose-Sparing Methodologies, Patient and Medical Personnel Protection.

The stimulus to create this document was the recognition that ionizing radiation-guided cardiovascular procedures are being performed with increasing frequency, leading to greater patient radiation exposure and, potentially, to greater exposure to clinical personnel. While the clinical benefit of these procedures is substantial, there is concern about the implications of medical radiation exposure. ACC leadership concluded that it is important to provide practitioners with an educational resource that assembles and interprets the current radiation knowledge base relevant to cardiovascular procedures. By applying this knowledge base, cardiovascular practitioners will be able to select procedures optimally, and minimize radiation exposure to patients and to clinical personnel. "Optimal Use of Ionizing Radiation in Cardiovascular Imaging - Best Practices for Safety and Effectiveness" is a comprehensive overview of ionizing radiation use in cardiovascular procedures and is published online. To provide the most value to our members, we divided the print version of this document into 2 focused parts. "Part I: Radiation Physics and Radiation Biology" addresses radiation physics, dosimetry and detrimental biologic effects. "Part II: Radiologic Equipment Operation, Dose-Sparing Methodologies, Patient and Medical Personnel Protection" covers the basics of operation and radiation delivery for the 3 cardiovascular imaging modalities (x-ray fluoroscopy, x-ray computed tomography, and nuclear scintigraphy). For each modality, it includes the determinants of radiation exposure and techniques to minimize exposure to both patients and to medical personnel.

2018 ACC/HRS/NASCI/SCAI/SCCT Expert Consensus Document on Optimal Use of Ionizing Radiation in Cardiovascular Imaging-Best Practices for Safety and Effectiveness, Part 1: Radiation Physics and Radiation Biology: A Report of the American College of Cardiology Task Force on Expert Consensus Decision Pathways Developed in Collaboration With Mended Hearts.

The stimulus to create this document was the recognition that ionizing radiation-guided cardiovascular procedures are being performed with increasing frequency, leading to greater patient radiation exposure and, potentially, to greater exposure for clinical personnel. Although the clinical benefit of these procedures is substantial, there is concern about the implications of medical radiation exposure. The American College of Cardiology leadership concluded that it is important to provide practitioners with an educational resource that assembles and interprets the current radiation knowledge base relevant to cardiovascular procedures. By applying this knowledge base, cardiovascular practitioners will be able to select procedures optimally, and minimize radiation exposure to patients and to clinical personnel. Optimal Use of Ionizing Radiation in Cardiovascular Imaging: Best Practices for Safety and Effectiveness is a comprehensive overview of ionizing radiation use in cardiovascular procedures and is published online. To provide the most value to our members, we divided the print version of this document into 2 focused parts. Part I: Radiation Physics and Radiation Biology addresses the issue of medical radiation exposure, the basics of radiation physics and dosimetry, and the basics of radiation biology and radiation-induced adverse effects. Part II: Radiological Equipment Operation, Dose-Sparing Methodologies, Patient and Medical Personnel Protection covers the basics of operation and radiation delivery for the 3 cardiovascular imaging modalities (x-ray fluoroscopy, x-ray computed tomography, and nuclear scintigraphy) and will be published in the next issue of the Journal.

The long-term effect of vagus nerve stimulation on quality of life in patients with pharmacoresistant focal epilepsy: the PuLsE (Open Prospective Randomized Long-term Effectiveness) trial.

OBJECTIVE: To evaluate whether vagus nerve stimulation (VNS) as adjunct to best medical practice (VNS + BMP) is superior to BMP alone in improving long-term health-related quality of life (HRQoL). METHODS: PuLsE (Open Prospective Randomized Long-term Effectiveness) was a prospective, randomized, parallel-group, open-label, and long-term effectiveness study (conducted at 28 sites in Europe and Canada). Adults with pharmacoresistant focal seizures (n = 112) received VNS + BMP or BMP (1:1 ratio). Medications and VNS parameters could be adjusted as clinically indicated for optimal seizure control while minimizing adverse effects. Primary endpoint was mean change from baseline HRQoL (using Quality of Life in Epilepsy Inventory-89 total score; QOLIE-89). Secondary endpoints included changes in seizure frequency, responder rate (≥50% decrease in seizure frequency), Centre for Epidemiologic Studies Depression scale (CES-D), Neurological Disorders Depression Inventory-Epilepsy scale (NDDI-E), Clinical Global Impression-Improvement scale (CGI-I), Adverse Event Profile (AEP), and antiepileptic drug (AED) load. The study was prematurely terminated due to recruitment difficulties prior to completing the planned enrollment of n = 362. Results for n = 96 who had baseline and at least one follow-up QOLIE-89 assessment (from months 3-12) were included in this analysis. Mixed model repeated measures (MMRM) analysis of variance was performed on change from baseline for the primary and secondary endpoints. RESULTS: Significant between-group differences in favor of VNS + BMP were observed regarding improvement in HRQoL, seizure frequency, and CGI-I score (respective p-values < 0.05, 0.03, and 0.01). More patients in the VNS + BMP group (43%) reported adverse events (AEs) versus BMP group (21%) (p = 0.01), a difference reflecting primarily mostly transient AEs related to VNS implantation or stimulation. No significant difference between treatment groups was observed for changes in CES-D, NDDI-E, AEP, and AED load. SIGNIFICANCE: VNS therapy as a treatment adjunct to BMP in patients with pharmacoresistant focal seizures was associated with a significant improvement in HRQoL compared with BMP alone. A PowerPoint slide summarizing this article is available for download in the Supporting Information section here.

Should risk from medical imaging be assessed in the absence of benefit and vice versa?

Diagnostic radiology has an image problem. In its effort to develop a better understanding of benefit-risk in medical radiology, data on potential risks associated with medical imaging have been welcomed into the medical community. As such, risk perspectives and mantras from the occupational health profession have been adopted and applied to patients. These perspectives often focus on risk with only casual, incidental, or no reference to the benefits experienced by patients. These occupational health viewpoints have accumulated over decades, have overshadowed a very limited perspective about the benefits of medical X-rays, and have become an integrated part of our profession. This review argues that the medical profession should abandon perspectives on risk that are adopted from occupational health professions and focus on perspectives that realistically focus on the medical benefit-risk for patients.

If it is published in the peer-reviewed literature, it must be true?

Epidemiological research correlating cancer rates in a population of patients with radiation doses from medical X-rays is fraught with confounding factors that obfuscate the likelihood that any positive relationship is causal. This is a review of four studies involving some of those confounding factors. Comparisons of findings with other studies not encumbered by similar confounding factors can enhance assertions of causation between medical X-rays and cancer rates. Even so, such assertions rest significantly on opinions of researchers regarding the degree of consistency between findings among various studies. The question as to what degree any findings truly represent cause and effect will likely still meet with controversy. The importance of these findings to medicine should therefore not lie in any controversy regarding causation, but in what the findings potentially mean with regard to benefit and risk for patients and the professional practice of medicine.

Surgical complications of vagus nerve stimulation surgery: A 14-years single-center experience.

Introduction: Vagus nerve stimulation (VNS) is the most frequently used neuromodulation treatment for Drug-Resistant Epilepsy (DRE) patients. Complications of VNS surgery include surgical site infection and unilateral vocal cord paresis. Complication rates vary across studies. Research question: What is the safety profile of VNS related surgeries? Materials and methods: Retrospective cohort study using patient files of DRE-patients who had undergone primary implantation of a VNS-system, replacement of the VNS pulse generator, replacement of the lead, replacement of both pulse generator and lead, or VNS removal surgery in the Maastricht UMC+. Multiple Imputation was used for missing data. Univariable and multivariable logistic regression analysis were performed to analyze possible risk factors, in case of a small sample size, an independent-samples t-test and Fisher's exact test or Pearson's X2-test were used. The complication rate was calculated as percentage. Results: This study included a total of 606 VNS surgical procedures, leading to 67 complications of which 3 permanent complications. Complication rate after primary implantation was 13.4%; 2,5% for pulse generator replacement; 21.4% for lead revision and 27.3% for complete VNS removal. No statistically significant results were found when analyzing the results of adults and children <18 years separately. Discussion and conclusion: Complication rates of VNS-related surgeries in our own institutional series are low and comparable to previously reported series. VNS surgery is a relatively safe procedure. The complication rate differs per type of surgery and mean surgery duration was longer for patients with complications after lead revision surgery compared to patients without complications.

DeepFLAIR: A neural network approach to mitigate signal and contrast loss in temporal lobes at 7 Tesla FLAIR images.

BACKGROUND AND PURPOSE: Higher magnetic field strength introduces stronger magnetic field inhomogeneities in the brain, especially within temporal lobes, leading to image artifacts. Particularly, T2-weighted fluid-attenuated inversion recovery (FLAIR) images can be affected by these artifacts. Here, we aimed to improve the FLAIR image quality in temporal lobe regions through image processing of multiple contrast images via machine learning using a neural network. METHODS: Thirteen drug-resistant MR-negative epilepsy patients (age 29.2 ± 9.4y, 5 females) were scanned on a 7 T MRI scanner. Magnetization-prepared (MP2RAGE) and saturation-prepared with 2 rapid gradient echoes, multi-echo gradient echo with four echo times, and the FLAIR sequence were acquired. A voxel-wise neural network was trained on extratemporal-lobe voxels from the acquired structural scans to generate a new FLAIR-like image (i.e., deepFLAIR) with reduced temporal lobe inhomogeneities. The deepFLAIR was evaluated in temporal lobes through signal-to-noise (SNR), contrast-to-noise (CNR) ratio, the sharpness of the gray-white matter boundary and joint-histogram analysis. Saliency mapping demonstrated the importance of each input image per voxel. RESULTS: SNR and CNR in both gray and white matter were significantly increased (p < 0.05) in the deepFLAIR's temporal ROIs, compared to the FLAIR. The gray-white matter boundary sharpness was either preserved or improved in 10/13 right-sided temporal regions and was found significantly increased in the ROIs. Multiple image contrasts were influential for the deepFLAIR reconstruction with the MP2RAGE second inversion image being the most important. CONCLUSIONS: The deepFLAIR network showed promise to restore the FLAIR signal and reduce contrast attenuation in temporal lobe areas. This may yield a valuable tool, especially when artifact-free FLAIR images are not available.

Effectiveness of Seizure Dogs for People With Severe Refractory Epilepsy: Results From the EPISODE Study.

BACKGROUND AND OBJECTIVES: The aim of this study was to evaluate whether people living with severe medically refractory epilepsy (PSRE) benefit from a seizure dog. METHODS: An individual-level stepped-wedge randomized controlled trial was conducted. The study was conducted in the Netherlands among adults with daily to weekly seizures. All participants were included simultaneously (on June 1, 2019) while receiving usual care. Then, during the 36-month follow-up, they received a seizure dog in a randomized sequence. Participants kept a seizure diary and completed 3-monthly surveys. Seizure frequency was the primary outcome. Secondary outcomes included seizure-free days, seizure severity, health-related quality of life (HRQoL), and well-being. Data were analyzed using generalized linear mixed modeling (GLMM). The models assumed a delayed intervention effect, starting when the seizure dog reached an advanced stage of training. Effects were calculated as changes per 28-day period with the intervention. RESULTS: Data were collected from 25 participants, of whom 20 crossed over to the intervention condition. The median follow-up was 19 months with usual care and 12 months with the intervention. On average, participants experienced 115 (SD 164) seizures per 28-day period in the usual care condition and 73 (SD 131) seizures in the intervention condition. Seven participants achieved a reduction of 50% or more at the end of follow-up. GLMM indicated a 3.1% decrease in seizure frequency for each consecutive 28-day period with the intervention (0.969, 95% CI 0.960-0.977). Furthermore, an increase in the number of seizure-free days was observed (1.012, 95% CI 1.009, 1.015), but no effect on seizure severity measured with the NHS3. Generic HRQoL scores improved, as reflected in the decrease in EQ-5D-5L utility decrement (0.975, 95% CI 0.954-0.997). Smaller improvements were observed on overall self-rated HRQoL, epilepsy-specific HRQoL, and well-being, measured with the EQ VAS, QOLIE-31-P, and ICECAP-A, respectively. DISCUSSION: Seizure dogs reduce seizure frequency, increase the number of seizure-free days, and improve the quality of life of PSRE. The magnitude of the effect on generic HRQoL indicates that seizure dogs benefit PSRE beyond the impact on seizure frequency alone. Early discontinuation of seizure dog partnerships suggests that this intervention is not suitable for all PSRE and requires further study. TRIAL REGISTRATION INFORMATION: This study was registered in the Dutch Trial Register (NL6682) on November 28, 2017. Participants were enrolled on June 1, 2019. CLASSIFICATION OF EVIDENCE: This study provides Class III evidence that seizure dogs are associated with a decrease in seizure frequency in adult patients with medically refractory epilepsy.

Decoding executed and imagined grasping movements from distributed non-motor brain areas using a Riemannian decoder.

Using brain activity directly as input for assistive tool control can circumventmuscular dysfunction and increase functional independence for physically impaired people. The motor cortex is commonly targeted for recordings, while growing evidence shows that there exists decodable movement-related neural activity outside of the motor cortex. Several decoding studies demonstrated significant decoding from distributed areas separately. Here, we combine information from all recorded non-motor brain areas and decode executed and imagined movements using a Riemannian decoder. We recorded neural activity from 8 epilepsy patients implanted with stereotactic-electroencephalographic electrodes (sEEG), while they performed an executed and imagined grasping tasks. Before decoding, we excluded all contacts in or adjacent to the central sulcus. The decoder extracts a low-dimensional representation of varying number of components, and classified move/no-move using a minimum-distance-to-geometric-mean Riemannian classifier. We show that executed and imagined movements can be decoded from distributed non-motor brain areas using a Riemannian decoder, reaching an area under the receiver operator characteristic of 0.83 ± 0.11. Furthermore, we highlight the distributedness of the movement-related neural activity, as no single brain area is the main driver of performance. Our decoding results demonstrate a first application of a Riemannian decoder on sEEG data and show that it is able to decode from distributed brain-wide recordings outside of the motor cortex. This brief report highlights the perspective to explore motor-related neural activity beyond the motor cortex, as many areas contain decodable information.

Resective Epilepsy Surgery, QUality of life and Economic evaluation (RESQUE): the change in quality of life after resective epilepsy surgery-protocol for a multicentre, prospective cohort study.

INTRODUCTION: Resective epilepsy surgery is often seen as a last resort when treating drug-resistant epilepsy. Positive results on quality of life (QoL) and economic benefits after surgery argue for a less restrictive attitude towards epilepsy surgery for drug-resistant epilepsy. QoL and economic benefits are country-dependent. The objective of the Resective Epilepsy Surgery, QUality of life and Economic evaluation (RESQUE) trial is to evaluate the change in QoL before and after epilepsy surgery in Dutch people with drug-resistant epilepsy. The results will form part of an economic evaluation of epilepsy surgery in people with epilepsy (PWE) in The Netherlands. METHODS AND ANALYSIS: A longitudinal prospective multicentre cohort study involving 100 PWE undergoing epilepsy surgery between 2019 and 2025 is being performed in three Dutch academic hospitals. Excluded are PWE who have a lower level of intelligence (TIQ<70) or who do not master the Dutch language. Before surgery and 3, 6, 12 and 24 months after surgery, PWE receive validated online questionnaires (QOLIE-31, EQ-5D, iMCQ and iPCQ) on QoL, cost of care, expectations and satisfaction. Primary outcome is the change in QoL. Secondary outcomes are change in generic QoL, seizure reduction (International League Against Epilepsy Outcome Classification), medical consumption, productivity, the correlation between QoL and seizure reduction and expectation of and satisfaction with the surgery. ETHICS AND DISSEMINATION: The study design has been approved by the Medical Ethics Review Committee (METC) of Maastricht UMC+ (2019-1134) and the Amsterdam UMC (vu). At the time of writing, UMC Utrecht is in the process of considering approval. The study will be conducted according to the Dutch Medical Research Involving Human Subjects Act and the Declaration of Helsinki. The results will be publicly disclosed and submitted for publication in international peer-reviewed scientific journals. There is no veto on publication by the involved parties. TRIAL REGISTRATION: NL8278; Pre-results.

Dataset of Speech Production in intracranial.Electroencephalography.

Speech production is an intricate process involving a large number of muscles and cognitive processes. The neural processes underlying speech production are not completely understood. As speech is a uniquely human ability, it can not be investigated in animal models. High-fidelity human data can only be obtained in clinical settings and is therefore not easily available to all researchers. Here, we provide a dataset of 10 participants reading out individual words while we measured intracranial EEG from a total of 1103 electrodes. The data, with its high temporal resolution and coverage of a large variety of cortical and sub-cortical brain regions, can help in understanding the speech production process better. Simultaneously, the data can be used to test speech decoding and synthesis approaches from neural data to develop speech Brain-Computer Interfaces and speech neuroprostheses.

Burden of illness in people with medically refractory epilepsy who suffer from daily to weekly seizures: 12-month follow-up of participants in the EPISODE study.

Background: A small group of people with epilepsy suffers from frequent seizures despite the available pharmacological and non-pharmacological interventions. The impact of epilepsy on these people extends beyond health-related quality of life (HRQoL), impacting a person's broader well-being and ability to participate in society. This study describes the burden of medically refractory epilepsy in people who suffer from daily to weekly seizures, in terms of HRQoL, well-being, and societal costs. Methods: Data from the EPISODE study on (cost-) effectiveness of seizure dogs for adults with severe medically refractory epilepsy were used, collected in 25 patients during the first 12 months before they were partnered with a certified seizure dog. Data comprised seizure diaries covering 365 days and five three-monthly surveys, including the EQ-5D-5L, QOLIE-31-P, and ICECAP-A to measure HRQoL and well-being. A societal perspective was applied to estimate costs using the iMCQ and iPCQ questionnaires about healthcare use, informal care, and productivity losses. Results: Daily seizure frequency and survey data were collected in 25 patients. A minimum of 114 observations was available for each instrument included in the survey. A total of 80% of participants experienced seizures on three or more days per week, with a median ranging from 1 to 17 seizures per seizure day. The mean EQ-5D-5L utility score was 0.682 (SD 0.235), which is considerably lower than the age-adjusted general population average. The mean QOLIE-31-P and ICECAP-A scores were 55.8 (SD 14.0) and 0.746 (SD 0.172), respectively. The average annual total cost amounted to €39,956 (range €3,804-€132,64). Informal care accounted for the largest share of costs (50%); those who received informal care reported, on average, 26 h per week (SD 30). Conclusions: Severe medically refractory epilepsy is associated with a considerable burden of illness at the patient and societal level. People with this condition have significantly reduced HRQoL and well-being and are limited in their ability to work while having substantial medical costs and a strong dependency on informal care.

Managing radiation use in medical imaging: a multifaceted challenge.

This special report aims to inform the medical community about the many challenges involved in managing radiation exposure in a way that maximizes the benefit-risk ratio. The report discusses the state of current knowledge and key questions in regard to sources of medical imaging radiation exposure, radiation risk estimation, dose reduction strategies, and regulatory options.

Resident education in the radiological sciences: what now?

OBJECTIVE: With the dizzying changes in the rapidly evolving profession of radiology, the structure of resident education in the associated sciences of imaging, physics, radiobiology, and radiation effects must be reevaluated continually. What roles do these basic radiologic sciences play in bolstering the neophyte radiologist on a career of patient care? How should we define the spectrum of material that should be learned? How should that spectrum be taught? Who decides these things? With the impending changes in the radiology board certification process, questions have been raised as to how these changes will affect education in a residency program. Should the basic science curriculum be enhanced or scaled back? With the emphasis on practical applied physics, what is considered old school and what is new school material? CONCLUSION: This article describes one approach adopted by a large residency program to address these issues.

Can radiation risks to patients be reduced without reducing radiation exposure? The status of chemical radioprotectants.

OBJECTIVE: Medical radiation exposure has increased sixfold since 1980 and is the largest controllable source of exposure. Many efforts have been devoted to reducing dose or eliminating unnecessary examinations but with limited success. The concern regarding nuclear terrorism has focused a large amount of attention on radioprotective drugs. The purpose of this article is twofold: to review the current concepts, potential, and limitations of chemical radioprotectants in reducing stochastic and deterministic effects and to assess the potential application to diagnostic and interventional medical radiation procedures. CONCLUSION: There are a wide variety of chemical compounds that have been studied for radioprotective effects. Although there is promising research, chemical radioprotectants have not been shown to be very effective and, with one limited exception, are not the standard of care in medicine.

Continuously Decoding Grasping Movements using Stereotactic Depth Electrodes.

Brain-Computer Interfaces (BCIs) that decode a patient's movement intention to control a prosthetic device could restore some independence to paralyzed patients. An important step on the road towards naturalistic prosthetic control is to decode movement continuously with low-latency. BCIs based on intracortical micro-arrays provide continuous control of robotic arms, but require a minor craniotomy. Surface recordings of neural activity using EEG have made great advances over the last years, but suffer from high noise levels and large intra-session variance. Here, we investigate the use of minimally invasive recordings using stereotactically implanted EEG (sEEG). These electrodes provide a sparse sampling across many brain regions. So far, promising decoding results have been presented using data measured from the subthalamic nucleus or trial-to-trial based methods using depth electrodes. In this work, we demonstrate that grasping movements can continuously be decoded using sEEG electrodes, as well. Beta and high-gamma activity was extracted from eight participants performing a grasping task. We demonstrate above chance level decoding of movement vs rest and left vs right, from both frequency bands with accuracies up to 0.94 AUC. The vastly different electrode locations between participants lead to large variability. In the future, we hope that sEEG recordings will provide additional information for the decoding process in neuroprostheses.

Speech Synthesis from Stereotactic EEG using an Electrode Shaft Dependent Multi-Input Convolutional Neural Network Approach.

Neurological disorders can lead to significant impairments in speech communication and, in severe cases, cause the complete loss of the ability to speak. Brain-Computer Interfaces have shown promise as an alternative communication modality by directly transforming neural activity of speech processes into a textual or audible representations. Previous studies investigating such speech neuroprostheses relied on electrocorticography (ECoG) or microelectrode arrays that acquire neural signals from superficial areas on the cortex. While both measurement methods have demonstrated successful speech decoding, they do not capture activity from deeper brain structures and this activity has therefore not been harnessed for speech-related BCIs. In this study, we bridge this gap by adapting a previously presented decoding pipeline for speech synthesis based on ECoG signals to implanted depth electrodes (sEEG). For this purpose, we propose a multi-input convolutional neural network that extracts speech-related activity separately for each electrode shaft and estimates spectral coefficients to reconstruct an audible waveform. We evaluate our approach on open-loop data from 5 patients who conducted a recitation task of Dutch utterances. We achieve correlations of up to 0.80 between original and reconstructed speech spectrograms, which are significantly above chance level for all patients (p < 0.001). Our results indicate that sEEG can yield similar speech decoding performance to prior ECoG studies and is a promising modality for speech BCIs.