Search

IntroductionThe 2024 Voice AI Symposium, hosted by the Bridge2AI-Voice Consortium in Tampa, FL, featured two keynote speeches that addressed the intersection of voice AI, healthcare, ethics, and law. Dr. Rupal Patel and Dr. Nicholson Price provided insights into the advancements, applications, and challenges of AI-driven voice tools in healthcare. The symposium aimed to advance cross-disciplinary collaboration and establish frameworks for the ethical use of AI technologies in healthcare.MethodsThe keynote speeches, delivered on May 1st and 2nd, were 30 minutes each, followed by 10-minutes Q&A sessions. The audio was recorded and transcribed using Whisper (v7.13.1). Content summaries were generated with the aid of ChatGPT (v4.0), and the authors reviewed and edited the final transcripts to ensure accuracy and clarity.ResultsDr. Rupal Patel’s keynote, “Reflections and New Frontiers in Voice AI”, explored the potential of voice AI for early detection of health conditions, monitoring disease progression, and promoting non-invasive global health management. She highlighted innovative uses beyond traditional applications, such as examining menopause-related symptoms. Dr. Nicholson Price’s keynote, “Governance for Clinical Voice AI”, addressed the regulatory and ethical challenges posed by AI in healthcare. He stressed the need for context-aware systems and dynamic legal frameworks to address liability and accountability.ConclusionsThe 2024 Voice AI Symposium highlighted the transformative potential of voice AI for early detection, health monitoring, and reducing healthcare disparities. It also underscored the importance of dynamic governance to address the ethical and regulatory challenges of deploying AI in clinical settings.

IntroductionThe 2024 Voice AI Symposium, presented by the Bridge2AI-Voice Consortium, featured deep-dive educational workshops conducted by experts from diverse fields to explore the latest advancements in voice biomarkers and artificial intelligence (AI) applications in healthcare. Through five workshops, attendees learned about topics including international standardization of vocal biomarker data, real-world deployment of AI solutions, assistive technologies for voice disorders, best practices for voice data collection, and deep learning applications in voice analysis. These workshops aimed to foster collaboration between academia, industry, and healthcare to advance the development and implementation of voice-based AI tools.MethodsEach workshop featured a combination of lectures, case studies, and interactive discussions. Transcripts of audio recordings were generated using Whisper (Version 7.13.1) and summarized by ChatGPT (Version 4.0), then reviewed by the authors. The workshops covered various methodologies, from signal processing and machine learning operations (MLOps) to ethical concerns surrounding AI-powered voice data collection. Practical demonstrations of AI-driven tools for voice disorder management and technical discussions on implementing voice AI models in clinical and non-clinical settings provided attendees with hands-on experience.ResultsKey outcomes included the discussion of international standards to unify stakeholders in vocal biomarker research, practical challenges in deploying AI solutions outside the laboratory, review of Bridge2AI-Voice data collection processes, and the potential of AI to empower individuals with voice disorders. Additionally, presenters shared innovations in ethical AI practices, scalable machine learning frameworks, and advanced data collection techniques using diverse voice datasets. The symposium highlighted the successful integration of AI in detecting and analyzing voice signals for various health applications, with significant advancements in standardization, privacy, and clinical validation processes.DiscussionThe symposium underscored the importance of interdisciplinary collaboration to address the technical, ethical, and clinical challenges in the field of voice biomarkers. While AI models have shown promise in analyzing voice data, challenges such as data variability, security, and scalability remain. Future efforts must focus on refining data collection standards, advancing ethical AI practices, and ensuring diverse dataset inclusion to improve model robustness. By fostering collaboration among researchers, clinicians, and technologists, the symposium laid a foundation for future innovations in AI-driven voice analysis for healthcare diagnostics and treatment.

Abstract As data sharing has become more prevalent, three pillars - archives, standards, and analysis tools - have emerged as critical components in facilitating effective data sharing and collaboration. This paper compares four freely available intracranial neuroelectrophysiology data repositories: Data Archive for the BRAIN Initiative (DABI), Distributed Archives for Neurophysiology Data Integration (DANDI), OpenNeuro, and Brain-CODE. The aim of this review is to describe archives that provide researchers with tools to store, share, and reanalyze both human and non-human neurophysiology data based on criteria that are of interest to the neuroscientific community. The Brain Imaging Data Structure (BIDS) and Neurodata Without Borders (NWB) are utilized by these archives to make data more accessible to researchers by implementing a common standard. As the necessity for integrating large-scale analysis into data repository platforms continues to grow within the neuroscientific community, this article will highlight the various analytical and customizable tools developed within the chosen archives that may advance the field of neuroinformatics.

Abstract Background Adolescence is characterized by a heightened vulnerability for Major Depressive Disorder (MDD) onset, and currently, treatments are only effective for roughly half of adolescents with MDD. Accordingly, novel interventions are urgently needed. This study aims to establish mindfulness-based real-time fMRI neurofeedback (mbNF) as a non-invasive approach to downregulate the default mode network (DMN) in order to decrease ruminatory processes and depressive symptoms. Methods Adolescents (N = 90) with a current diagnosis of MDD ages 13–18-years-old will be randomized in a parallel group, two-arm, superiority trial to receive either 15 or 30 min of mbNF with a 1:1 allocation ratio. Real-time neurofeedback based on activation of the frontoparietal network (FPN) relative to the DMN will be displayed to participants via the movement of a ball on a computer screen while participants practice mindfulness in the scanner. We hypothesize that within-DMN (medial prefrontal cortex [mPFC] with posterior cingulate cortex [PCC]) functional connectivity will be reduced following mbNF (Aim 1: Target Engagement). Additionally, we hypothesize that participants in the 30-min mbNF condition will show greater reductions in within-DMN functional connectivity (Aim 2: Dosing Impact on Target Engagement). Aim 1 will analyze data from all participants as a single-group, and Aim 2 will leverage the randomized assignment to analyze data as a parallel-group trial. Secondary analyses will probe changes in depressive symptoms and rumination. Discussion Results of this study will determine whether mbNF reduces functional connectivity within the DMN among adolescents with MDD, and critically, will identify the optimal dosing with respect to DMN modulation as well as reduction in depressive symptoms and rumination. Trial Registration This study has been registered with clinicaltrials.gov, most recently updated on July 6, 2023 (trial identifier: NCT05617495).

Abstract In the face of the global pandemic caused by the disease COVID-19, researchers have increasingly turned to simple measures to detect and monitor the presence of the disease in individuals at home. We sought to determine if measures of neuromotor coordination, derived from acoustic time series, as well as phoneme-based and standard acoustic features extracted from recordings of simple speech tasks could aid in detecting the presence of COVID-19. We further hypothesized that these features would aid in characterizing the effect of COVID-19 on speech production systems. A protocol, consisting of a variety of speech tasks, was administered to 12 individuals with COVID-19 and 15 individuals with other viral infections at University Hospital Galway. From these recordings, we extracted a set of acoustic time series representative of speech production subsystems, as well as their univariate statistics. The time series were further utilized to derive correlation-based features, a proxy for speech production motor coordination. We additionally extracted phoneme-based features. These features were used to create machine learning models to distinguish between the COVID-19 positive and other viral infection groups, with respiratory- and laryngeal-based features resulting in the highest performance. Coordination-based features derived from harmonic-to-noise ratio time series from read speech discriminated between the two groups with an area under the ROC curve (AUC) of 0.94. A longitudinal case study of two subjects, one from each group, revealed differences in laryngeal based acoustic features, consistent with observed physiological differences between the two groups. The results from this analysis highlight the promise of using nonintrusive sensing through simple speech recordings for early warning and tracking of COVID-19.

Abstract Accurate brain meningioma segmentation and volumetric assessment are critical for serial patient follow-up, surgical planning and monitoring response to treatment. Current gold standard of manual labeling is a time-consuming process, subject to inter-user variability. Fully-automated algorithms for meningioma segmentation have the potential to bring volumetric analysis into clinical and research workflows by increasing accuracy and efficiency, reducing inter-user variability and saving time. Previous research has focused solely on segmentation tasks without assessment of impact and usability of deep learning solutions in clinical practice. Herein, we demonstrate a three-dimensional convolutional neural network (3D-CNN) that performs expert-level, automated meningioma segmentation and volume estimation on MRI scans. A 3D-CNN was initially trained by segmenting entire brain volumes using a dataset of 10,099 healthy brain MRIs. Using transfer learning, the network was then specifically trained on meningioma segmentation using 806 expert-labeled MRIs. The final model achieved a median performance of 88.2% reaching the spectrum of current inter-expert variability (82.6–91.6%). We demonstrate in a simulated clinical scenario that a deep learning approach to meningioma segmentation is feasible, highly accurate and has the potential to improve current clinical practice.

Brain network interactions are commonly assessed via functional (network) connectivity, captured as an undirected matrix of Pearson correlation coefficients. Functional connectivity can represent static and dynamic relations, but often these are modeled using a fixed choice for the data window Alternatively, deep learning models may flexibly learn various representations from the same data based on the model architecture and the training task. However, the representations produced by deep learning models are often difficult to interpret and require additional posthoc methods, e.g., saliency maps. In this work, we integrate the strengths of deep learning and functional connectivity methods while also mitigating their weaknesses. With interpretability in mind, we present a deep learning architecture that exposes a directed graph layer that represents what the model has learned about relevant brain connectivity. A surprising benefit of this architectural interpretability is significantly improved accuracy in discriminating controls and patients with schizophrenia, autism, and dementia, as well as age and gender prediction from functional MRI data. We also resolve the window size selection problem for dynamic directed connectivity estimation as we estimate windowing functions from the data, capturing what is needed to estimate the graph at each time-point. We demonstrate efficacy of our method in comparison with multiple existing models that focus on classification accuracy, unlike our interpretability-focused architecture. Using the same data but training different models on their own discriminative tasks we are able to estimate task-specific directed connectivity matrices for each subject. Results show that the proposed approach is also more robust to confounding factors compared to standard dynamic functional connectivity models. The dynamic patterns captured by our model are naturally interpretable since they highlight the intervals in the signal that are most important for the prediction. The proposed approach reveals that differences in connectivity among sensorimotor networks relative to default-mode networks are an important indicator of dementia and gender. Dysconnectivity between networks, specially sensorimotor and visual, is linked with schizophrenic patients, however schizophrenic patients show increased intra-network default-mode connectivity compared to healthy controls. Sensorimotor connectivity was important for both dementia and schizophrenia prediction, but schizophrenia is more related to dysconnectivity between networks whereas, dementia bio-markers were mostly intra-network connectivity.

The neurophysiology of cells and tissues are monitored electrophysiologically and optically in diverse experiments and species, ranging from flies to humans. Understanding the brain requires integration of data across this diversity, and thus these data must be findable, accessible, interoperable, and reusable (FAIR). This requires a standard language for data and metadata that can coevolve with neuroscience. We describe design and implementation principles for a language for neurophysiology data. Our open-source software (Neurodata Without Borders, NWB) defines and modularizes the interdependent, yet separable, components of a data language. We demonstrate NWB’s impact through unified description of neurophysiology data across diverse modalities and species. NWB exists in an ecosystem, which includes data management, analysis, visualization, and archive tools. Thus, the NWB data language enables reproduction, interchange, and reuse of diverse neurophysiology data. More broadly, the design principles of NWB are generally applicable to enhance discovery across biology through data FAIRness.

The Connectomes Related to Human Diseases (CRHD) initiative was developed with the Human Connectome Project (HCP) to provide high-resolution, open-access, multi-modal MRI data to better understand the neural correlates of human disease. Here, we present an introduction to a CRHD project, the Boston Adolescent Neuroimaging of Depression and Anxiety (BANDA) study, which is collecting multimodal neuroimaging, clinical, and neuropsychological data from 225 adolescents (ages 14–17), 150 of whom are expected to have a diagnosis of depression and/or anxiety. Our transdiagnostic recruitment approach samples the full spectrum of depressed/anxious symptoms and their comorbidity, consistent with NIMH Research Domain Criteria (RDoC). We focused on an age range that is critical for brain development and for the onset of mental illness. This project sought to harmonize imaging sequences, hardware, and functional tasks with other HCP studies, although some changes were made to canonical HCP methods to accommodate our study population and questions. We present a thorough overview of our imaging sequences, hardware, and scanning protocol. We detail similarities and differences between this study and other HCP studies. We evaluate structural-, diffusion-, and functional-image-quality measures that may be influenced by clinical factors (e.g., disorder, symptomatology). Signal-to-noise and motion estimates from the first 140 adolescents suggest minimal influence of clinical factors on image quality. We anticipate enrollment of an additional 85 participants, most of whom are expected to have a diagnosis of anxiety and/or depression. Clinical and neuropsychological data from the first 140 participants are currently freely available through the National Institute of Mental Health Data Archive (NDA).

Emotional dysregulation symptoms in youth frequently predispose individuals to increased risk for mood disorders and other mental health difficulties. These symptoms are also known as a behavioral risk marker in predicting pediatric mood disorders. The underlying neural mechanism of emotional dysregulation, however, remains unclear. This study used the diffusion tensor imaging (DTI) technique to identify anatomically specific variation in white-matter microstructure that is associated with pediatric emotional dysregulation severity. Thirty-two children (mean age 9.53 years) with varying levels of emotional dysregulation symptoms were recruited by the Massachusetts General Hospital and underwent the DTI scans at Massachusetts Institute of Technology. Emotional dysregulation severity was measured by the empirically-derived Child Behavior Checklist Emotional Dysregulation Profile that includes the Attention, Aggression, and Anxiety/Depression subscales. Whole-brain voxel-wise regression tests revealed significantly increased radial diffusivity (RD) and decreased fractional anisotropy (FA) in the cingulum-callosal regions linked to greater emotional dysregulation in the children. The results suggest that microstructural differences in cingulum-callosal white-matter pathways may manifest as a neurodevelopmental vulnerability for pediatric mood disorders as implicated in the clinical phenotype of pediatric emotional dysregulation. These findings may offer clinically and biologically relevant neural targets for early identification and prevention efforts for pediatric mood disorders.

Adolescence is a neuroplastic period for self-processing and emotion regulation transformations, that if derailed, are linked to persistent depression. Neural mechanisms of adolescent self-processing and emotion regulation ought to be targeted via new treatments, given moderate effectiveness of current interventions. Thus, we implemented a novel neurofeedback protocol in adolescents to test the engagement of circuits sub-serving self-processing and emotion regulation. Methods: Depressed (n = 34) and healthy (n = 19) adolescents underwent neurofeedback training using a novel task. They saw their happy face as a cue to recall positive memories and increased displayed amygdala and hippocampus activity. The control condition was counting-backwards while viewing another happy face. A self vs. other face recognition task was administered before and after neurofeedback training. Results: Adolescents showed higher frontotemporal activity during neurofeedback and higher amygdala and hippocampus and hippocampi activity in time series and region of interest analyses respectively. Before neurofeedback there was higher saliency network engagement for self-face recognition, but that network engagement was lower after neurofeedback. Depressed youth exhibited higher fusiform, inferior parietal lobule and cuneus activity during neurofeedback, but controls appeared to increase amygdala and hippocampus activity faster compared to depressed adolescents. Conclusions: Neurofeedback recruited frontotemporal cortices that support social cognition and emotion regulation. Amygdala and hippocampus engagement via neurofeedback appears to change limbic-frontotemporal networks during self-face recognition. A placebo group or condition and contrasting amygdala and hippocampus, hippocampi or right amygdala versus frontal loci of neurofeedback, e.g. dorsal anterior cingulate cortex, with longer duration of neurofeedback training will elucidate dosage and loci of neurofeedback in adolescents. Keywords: Neurofeedback, Adolescence, Depression, Amygdala, Hippocampus, Dorsal anterior cingulate cortex, Self-face recognition

The proposed research develops new computational tools to identify, diagnose, and predict treatment outcome for different mental illnesses. The research will be applied first to major depressive disorder, which affects millions of Americans, but is intended to be applied to any mental illness, such as Alzheimer’s disease, bipolar disorder, schizophrenia – indeed to analyze differences in brain structure, activity, or connectivity between any two populations.

There has been a recent major upsurge in the concerns about reproducibility in many areas of science. Within the neuroimaging domain, one approach is to promote reproducibility is to target the re-executability of the publication. The information supporting such re-executability can enable the detailed examination of how an initial finding generalizes across changes in the processing approach, and sampled population, in a controlled scientific fashion. ReproNim: A Center for Reproducible Neuroimaging Computation is a recently funded initiative that seeks to facilitate the “last mile” implementations of core re-executability tools in order to reduce the accessibility barrier and increase adoption of standards and best practices at the neuroimaging research laboratory level. In this report, we summarize the overall approach and tools we have developed in this domain.

Introduction: Accuracy and validity of voice AI algorithms rely on substantial quality voice data. Although commensurable amounts of voice data are captured daily in voice centers across North America, there is no standardized protocol for acoustic data management, which limits the usability of these datasets for voice artificial intelligence (AI) research. Objective: The aim was to capture current practices of voice data collection, storage, analysis, and perceived limitations to collaborative voice research. Methods: A 30‐question online survey was developed with expert guidance from the voicecollab.ai members, an international collaborative of voice AI researchers. The survey was disseminated via REDCap to an estimated 200 practitioners at North American voice centers. Survey questions assessed respondents' current practices in terms of acoustic data collection, storage, and retrieval as well as limitations to collaborative voice research. Results: Seventy‐two respondents completed the survey of which 81.7% were laryngologists and 18.3% were speech language pathologists (SLPs). Eighteen percent of respondents reported seeing 40%–60% and 55% reported seeing >60 patients with voice disorders weekly (conservative estimate of over 4000 patients/week). Only 28% of respondents reported utilizing standardized protocols for collection and storage of acoustic data. Although, 87% of respondents conduct voice research, only 38% of respondents report doing so on a multi‐institutional level. Perceived limitations to conducting collaborative voice research include lack of standardized methodology for collection (30%) and lack of human resources to prepare and label voice data adequately (55%). Conclusion: To conduct large‐scale multi‐institutional voice research with AI, there is a pertinent need for standardization of acoustic data management, as well as an infrastructure for secure and efficient data sharing. Level of Evidence: 5 Laryngoscope, 134:1333–1339, 2024 [ABSTRACT FROM AUTHOR]