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 Objective The natural history of Friedreich ataxia is being investigated in a multi‐center longitudinal study designated the Friedreich ataxia Clinical Outcome Measures Study (FACOMS). To understand the utility of this study in analysis of clinical trials, we performed a propensity‐matched comparison of data from the open‐label MOXIe extension (omaveloxolone) to that from FACOMS. Methods MOXIe extension patients were matched to FACOMS patients using logistic regression to estimate propensity scores based on multiple covariates: sex, baseline age, age of onset, baseline modified Friedreich Ataxia Rating scale (mFARS) score, and baseline gait score. The change from baseline in mFARS at Year 3 for the MOXIe extension patients compared to the matched FACOMS patients was analyzed as the primary efficacy endpoint using mixed model repeated measures analysis. Results Data from the MOXIe extension show that omaveloxolone provided persistent benefit over 3 years when compared to an untreated, matched cohort from FACOMS. At each year, in all analysis populations, patients in the MOXIe extension experienced a smaller change from baseline in mFARS score than matched FACOMS patients. In the primary pooled population (136 patients in each group) by Year 3, patients in the FACOMS matched set progressed 6.6 points whereas patients treated with omaveloxolone in MOXIe extension progressed 3 points (difference = −3.6; nominal p value = 0.0001). Interpretation These results suggest a meaningful slowing of Friedreich ataxia progression with omaveloxolone, and consequently detail how propensity‐matched analysis may contribute to understanding of effects of therapeutic agents. This demonstrates the direct value of natural history studies in clinical trial evaluations.

BackgroundDeep brain stimulation (DBS) has shown promise in effectively treating chronic pain. This study aimed to assess the efficacy of DBS in this context.MethodsWe conducted a systematic literature search using PubMed, Scopus, and Web of Science, following the PRISMA guidelines. A well-constructed search strategy was utilized. Our literature search identified two groups of subjects: one group underwent DBS specifically for chronic pain treatment (DBS-P), while the second group received DBS for other indications (DBS-O), such as Parkinson’s disease or dystonia, with pain perception investigated as a secondary outcome in this population. Meta-analysis was performed using R version 4.2.3 software. Heterogeneity was assessed using the tau^2 and I^2 indices, and Cochran’s Q-test was conducted.ResultsThe analysis included 966 patients in 43 original research studies with chronic pain who underwent DBS (340 for DBS-P and 625 for DBS-O). Subgroup analysis revealed that DBS-P exhibited a significant effect on chronic pain relief, with a standardized mean difference (SMD) of 1.65 and a 95% confidence interval (CI) of [1.31; 2.00]. Significant heterogeneity was observed among the studies, with an I^2 value of 85.8%. However, no significant difference was found between DBS-P and DBS-O subgroups. Subgroup analyses based on study design, age, pain diseases, and brain targets demonstrated varying levels of evidence for the effectiveness of DBS across different subgroups. Additionally, meta-regression analyses showed no significant relationship between age or pain duration and DBS effectiveness for chronic pain.ConclusionThese findings significantly contribute to the expanding body of knowledge regarding the utility of DBS in the management of chronic pain. The study underscores the importance of conducting further research to enhance treatment outcomes and elucidate patient-specific factors that are associated with treatment response.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/display_record.php?RecordID=428442, identifier CRD42023428442.

ObjectiveSubstance use disorder (SUD) is a significant public health issue with a high mortality rate. Deep brain stimulation (DBS) has shown promising results in treating SUD in certain cases. In this study, we conducted a meta-analysis to evaluate the efficacy of DBS in the treatment of SUD and reduction of relapse rates.MethodsWe performed a thorough and methodical search of the existing scientific literature, adhering to the PRISMA guidelines, to identify 16 original studies that fulfilled our inclusion criteria. We used the evidence levels recommended by the Oxford Centre for Evidence-Based Medicine to assess bias. The R version 4.2.3 software was utilized to calculate the mean effect size. We estimated study heterogeneity by employing tau2 and I2 indices and conducting Cochran’s Q test.ResultsThe results showed that DBS treatment resulted in a significant improvement in the clinical SUD scales of patients, with an average improvement of 59.6%. The observed relapse rate was 8%. The meta-analysis estimated a mean effect size of 55.9 [40.4; 71.4]. Heterogeneity analysis showed a large degree of heterogeneity among the included studies. Subgroup and meta-regression analysis based on age and SUD type suggested that DBS may be more effective for patients above 45 years of age, and for alcohol and opioid addiction compared to nicotine addiction.ConclusionThe current literature suggests that DBS has a moderate effect on SUD symptoms. However, the limited number of studies and small sample size indicate that more research is needed to better understand the factors that influence its effectiveness.

Abstract Background Friedreich's ataxia (FRDA) is an autosomal recessive disease, whereby homozygous inheritance of an expanded GAA trinucleotide repeat expansion in the first intron of the FXN gene leads to transcriptional repression of the encoded protein frataxin. FRDA is a progressive neurodegenerative disorder, but the primary cause of death is heart disease which occurs in 60% of the patients. Several functions of frataxin have been proposed, but none of them fully explain why its deficiency causes the FRDA phenotypes nor why the most affected cell types are neurons and cardiomyocytes. Methods To investigate, we generated iPSC‐derived neurons (iNs) and cardiomyocytes (iCMs) from an FRDA patient and upregulated FXN expression via lentivirus without altering genomic GAA repeats at the FXN locus. Results RNA‐seq and differential gene expression enrichment analyses demonstrated that frataxin deficiency affected the expression of glycolytic pathway genes in neurons and extracellular matrix pathway genes in cardiomyocytes. Genes in these pathways were differentially expressed when compared to a control and restored to control levels when FRDA cells were supplemented with frataxin. Conclusions These results offer novel insight into specific roles of frataxin deficiency pathogenesis in neurons and cardiomyocytes.

Introduction: Friedreich ataxia (FRDA) is a recessive neurodegenerative disease characterized by progressive ataxia, dyscoordination, and loss of vision. The variable length of the pathogenic GAA triplet repeat expansion in the FXN gene in part explains the interindividual variability in the severity of disease. The GAA repeat expansion leads to epigenetic silencing of FXN; therefore, variability in properties of epigenetic effector proteins could also regulate the severity of FRDA.Methods: In an exploratory analysis, DNA from 88 individuals with FRDA was analyzed to determine if any of five non-synonymous SNPs in HDACs/SIRTs predicted FRDA disease severity. Results suggested the need for a full analysis at the rs352493 locus in SIRT6 (p.Asn46Ser). In a cohort of 569 subjects with FRDA, disease features were compared between subjects homozygous for the common thymine SIRT6 variant (TT) and those with the less common cytosine variant on one allele and thymine on the other (CT). The biochemical properties of both variants of SIRT6 were analyzed and compared.Results: Linear regression in the exploratory cohort suggested that an SNP (rs352493) in SIRT6 correlated with neurological severity in FRDA. The follow-up analysis in a larger cohort agreed with the initial result that the genotype of SIRT6 at the locus rs352493 predicted the severity of disease features of FRDA. Those in the CT SIRT6 group performed better on measures of neurological and visual function over time than those in the more common TT SIRT6 group. The Asn to Ser amino acid change resulting from the SNP in SIRT6 did not alter the expression or enzymatic activity of SIRT6 or frataxin, but iPSC-derived neurons from people with FRDA in the CT SIRT6 group showed whole transcriptome differences compared to those in the TT SIRT6 group.Conclusion: People with FRDA in the CT SIRT6 group have less severe neurological and visual dysfunction than those in the TT SIRT6 group. Biochemical analyses indicate that the benefit conferred by T to C SNP in SIRT6 does not come from altered expression or enzymatic activity of SIRT6 or frataxin but is associated with changes in the transcriptome.

Abstract Objective The objective of this study was to characterize the incidence and progression of scoliosis in the natural history of Friedreich’s ataxia (FRDA) and document the factors leading to the requirement for corrective surgery. Methods Data on the prevalence of scoliosis and scoliosis surgery from up to 17 years of follow‐up collected during a large natural history study in FRDA (1116 patients at 4928 visits) were summarized descriptively and subjected to time to event analyses. Results Well over 90% of early or typical FRDA patients (as determined by age of onset) developed intermediate to severe scoliosis, while patients with a later onset (>14 years) had no or much lower prevalence of scoliosis. Diagnosis of scoliosis occurs during the onset of ataxia and in rare cases even prior to that. Major progression follows throughout the growth phase and puberty, leading to the need for surgical intervention in more than 50% of individuals in the most severe subgroup. The youngest patients appear to delay surgery until the end of the growth period, leading to further progression before surgical intervention. Age of onset of FRDA before or after reaching 15 years sharply separated severe and relatively mild incidence and progression of scoliosis. Interpretation Scoliosis is an important comorbidity of FRDA. Our comprehensive documentation of scoliosis progression in this natural history study provides a baseline for comparison as novel treatments become available.

Background: Postural tremor can sometimes occur in spinocerebellar ataxias (SCAs). However, the prevalence and clinical characteristics of postural tremor in SCAs are poorly understood, and whether SCA patients with postural tremor have different ataxia progression is not known.Methods: We studied postural tremor in 315 patients with SCA1, 2, 3, and 6 recruited from the Clinical Research Consortium for Spinocerebellar Ataxias (CRC-SCA), which consists of 12 participating centers in the United States, and we evaluated ataxia progression in these patients from January 2010 to August 2012.Results: Among 315 SCA patients, postural tremor was most common in SCA2 patients (SCA1, 5.8%; SCA2, 27.5%; SCA3, 12.4%; SCA6, 16.9%; p = 0.007). SCA3 patients with postural tremor had longer CAG repeat expansions than SCA3 patients without postural tremor (73.67 ± 3.12 vs. 70.42 ± 3.96, p = 0.003). Interestingly, SCA1 and SCA6 patients with postural tremor had a slower rate of ataxia progression (SCA1, β = –0.91, p < 0.001; SCA6, β = –1.28, p = 0.025), while SCA2 patients with postural tremor had a faster rate of ataxia progression (β = 1.54, p = 0.034). We also found that the presence of postural tremor in SCA2 patients could be influenced by repeat expansions of ATXN1 (β = –1.53, p = 0.037) and ATXN3 (β = 0.57, p = 0.018), whereas postural tremor in SCA3 was associated with repeat lengths in TBP (β = 0.63, p = 0.041) and PPP2R2B (β = –0.40, p = 0.032).Discussion: Postural tremor could be a clinical feature of SCAs, and the presence of postural tremor could be associated with different rates of ataxia progression. Genetic interactions between ataxia genes might influence the brain circuitry and thus affect the clinical presentation of postural tremor.

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease characterized by degeneration of motor neurons in the spinal cord and brain. This disease clinically manifests as gradual muscular weakness and atrophy leading to paralysis and death by respiratory failure. While multiple interdependent factors may contribute to the pathogenesis of ALS, increasing evidence shows the possible presence of autoimmune mechanisms that promote disease progression. The potential use of plasma derived from human umbilical cord blood (hUCB) as a therapeutic tool is currently in its infancy. The hUCB plasma is rich in cytokines and growth factors that are required for growth and survival of cells during hematopoiesis. In this study, we investigated the effects of hUCB plasma on the mitogen-induced proliferation of mononuclear cells (MNCs) isolated from the peripheral blood of ALS patients and apoptotic activity by detection of caspase 3/7 expression of the isolated MNCs in vitro. Three distinct responses to phytohemagglutinin (PHA)-induced proliferation of MNCs were observed, which were independent of age, disease duration, and the ALS rating scale: Group I responded normally to PHA, Group II showed no response to PHA, while Group III showed a hyperactive response to PHA. hUCB plasma attenuated the hyperactive response (Group III) and potentiated the normal response in Group I ALS patients, but did not alter that of the nonresponders to PHA (Group II). The elevated activity of caspase 3/7 observed in the MNCs from ALS patients was significantly reduced by hUCB plasma treatment. Thus, study results showing different cell responses to mitogen suggest alteration in lymphocyte functionality in ALS patients that may be a sign of immune deficiency in the nonresponders and autoimmunity alterations in the hyperactive responders. The ability of hUCB plasma to modulate the mitogen cell response and reduce caspase activity suggests that the use of hUCB plasma alone, or with stem cells, may prove useful as a therapeutic in ALS patients.

Background: The contributions of vascular risk factors to spinocerebellar ataxia (SCA) are not known.Methods: We studied 319 participants with SCA 1, 2, 3, and 6 and repeatedly measured clinical severity using the Scale for Assessment and Rating of Ataxia (SARA) for 2 years. Vascular risk factors were summarized by CHA2DS2-VASc scores as the vascular risk factor index. We employed regression models to study the effects of vascular risk factors on ataxia onset and progression after adjusting for age, sex, and pathological CAG repeats. Our secondary analyses took hyperlipidemia into account.Results: Nearly 60% of SCA participants were at low vascular risks with CHA2DS2-VASc = 0, and 31% scored 2 or greater. Higher CHA2DS2-VASc scores were not associated with either earlier onset or faster progression of ataxia. These findings were not altered after accounting for hyperlipidemia. Discussion: Vascular risks are not common in SCAs and are not associated with earlier onset or faster ataxia progression.