A5073571265- Voice and Speech Disorders
- Tracheal and airway disorders
- Dysphagia Assessment and Management
- Artificial Intelligence in Healthcare and Education
- Esophageal and GI Pathology
- Radiomics and Machine Learning in Medical Imaging
- Respiratory and Cough-Related Research
- Surgical Simulation and Training
- Gastroesophageal reflux and treatments
- Head and Neck Cancer Studies
- Medical Malpractice and Liability Issues
- Speech Recognition and Synthesis
- Airway Management and Intubation Techniques
- Helicobacter pylori-related gastroenterology studies
- Hearing Loss and Rehabilitation
- Infection Control and Ventilation
- Child Nutrition and Feeding Issues
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Hate Speech and Cyberbullying Detection
- Ethics in Clinical Research
- Sinusitis and nasal conditions
- Musculoskeletal pain and rehabilitation
- Diversity and Career in Medicine
- Cardiac, Anesthesia and Surgical Outcomes
Cornell University
2018-2025
Parker Hannifin (United States)
2021-2025
Parker Institute for Cancer Immunotherapy
2022-2025
Weill Cornell Medicine
2020-2024
Temple University
2023-2024
Harvard University
2023-2024
American Academy of Otolaryngology — Head and Neck Surgery
2020-2024
AID Atlanta
2023
Presbyterian Hospital
2021
New York Hospital Queens
2021
This Viewpoint discusses the need to create standards for audiomics identify unique audio biomarkers of health and disease—now possible because more efficient voice data analysis available through use artificial intelligence (AI)—and improve patient care.
Background Machine learning driven clinical decision support tools (ML‐CDST) are on the verge of being integrated into settings, including in Otolaryngology‐Head & Neck Surgery. In this study, we investigated whether such CDST may influence otolaryngologists' diagnostic judgement. Methods Otolaryngologists were recruited virtually across United States for experiment human–AI interaction. Participants shown 12 different video‐stroboscopic exams from patients with previously diagnosed...
This state of the art review aims to examine contemporary advances in applications artificial intelligence (AI) screening, detection, management, and prognostication laryngeal cancer (LC).Four bibliographic databases were searched: PubMed, EMBASE, Cochrane, IEEE.A structured current literature (up January 2022) was performed. Search terms related topics AI LC identified queried by 2 independent reviewers. Citations selected studies articles also evaluated ensure comprehensiveness.AI have...
This study aims to develop and validate a convolutional neural network (CNN)-based algorithm for automatic selection of informative frames in flexible laryngoscopic videos. The classifier has the potential aid development computer-aided diagnosis systems reduce data processing time clinician-computer scientist teams.A dataset 22,132 was extracted from 137 laryngostroboscopic videos 115 patients. 55 were healthy patients with no laryngeal pathology 82 vocal fold polyps. manually labeled as or...
To develop and validate a deep-learning classifier trained on voice data extracted from videolaryngostroboscopy recordings, differentiating between three different vocal fold (VF) states: healthy (HVF), unilateral paralysis (UVFP), VF lesions, including benign malignant pathologies. Patients with UVFP (n = 105), lesions 63), HVF 41) were retrospectively identified. Voice samples stroboscopic videos (Pentax Laryngeal Strobe Model 9400), sustained /i/ phonation, pitch glide, sniff task....
ABSTRACT Foundation models (FMs) are general‐purpose artificial intelligence (AI) neural networks trained on massive datasets, including code, text, audio, images, and video, to handle myriad tasks from generating texts analyzing images or composing music. We evaluated Google Gemini 1.5 Pro, currently the largest token context window multimodal FM best‐performing commercial model for video analysis, interpreting laryngoscopy frames videos Images YouTube. recognized procedure as in 87/88...
Abstract INTRODUCTION Eating and swallowing difficulties are prevalent distressing among persons living with dementia (PLWD). These challenges may be especially burdensome for PLWD in lower‐resourced settings, where environmental factors such as social support, health‐care infrastructure, food access critical meeting quality standards of eating care. However, clinical practices research methods have not sufficiently focused on the lived environment to promote high‐quality, socially...
The 2024 Voice AI Symposium presented by the Bridge2AI-Voice Consortium, was a 2-day event which took place May 1st-May 2nd in Tampa, FL. included four interactive panel sessions, are summarized here. All panels featured an innovative format, designed to maximize engagement and facilitate deep discussions. Each began with 45 min segment where moderators posed targeted questions expert panelists, delving into complex topics within field of voice AI. This followed “stakeholder forum,” during...
To report the odds of dysphagia treatment among adults with self-reported before and after implementation Affordable Care Act (ACA). Cross-sectional analysis. National Health Interview Survey (NHIS). Multivariate logistic regression. This study included 490 million individuals from 2012 2022 NHIS in weighted responses. Among 235 2012, 9.4 (4.0%) reported (median age, 56.0 years; interquartile range [IQR], 40.0-68.0 60% female). 255 2022, 15 (5.9%) 58.0 IQR, 40.0-71.0 57% After adjusting for...
The aims of this work were 1) to investigate whether office laryngoscopy is an aerosol-generating procedure with optical particle sizer (OPS) during clinical simulation on healthy volunteers, and 2) critically discuss methods for assessment aerosolizing potentials in invasive interventions.Prospective quantification aerosol droplet generation rigid flexible laryngoscopy.Two volunteers recruited undergo both laryngoscopy. An OPS was used quantify aerosols droplets generated four positive...
In the final stage of fasting, skeletal muscle mass and protein content drastically decrease when maintenance efficient locomotor activity becomes crucial for animals to reactivate feeding behaviour survive a very long period starvation. As mitochondrial metabolism represents main physiological link between endogenous energy store animal performance, aim this study was determine how long, natural fasting affected bioenergetics in king penguin chicks (Aptenodytes patagonicus). Rates oxidative...
Objectives Transgender individuals' voices are closely related to gender identity. A primary goal of gender‐affirming voice modification is help individuals alter their improve congruence; however, there a paucity research support this approach. This study aimed evaluate the outcomes 12‐week and communication program. Study Design Retrospective cohort study. Methods retrospective consecutive case series transgender women enrolled in program was performed. Demographics, Trans Woman Voice...
Objective An increased prevalence of mood and anxiety disorders in patients with dysphagia has been noted previously, but whether severity may be exacerbated by depression never studied before. The purpose this study is to identify the effect pre‐existing diagnosis and/or (anxiety/depression) on Eating Assessment Tool (EAT‐10), a validated patient‐reported outcome measure for dysphagia. We hypothesized that normal instrumental evaluation have higher EAT‐10 score presence depression. Methods...
This study aims to examine the prevalence of comparisons surgery drug regimens, strength evidence such and whether or intervention was favoured. Systematic review systematic reviews (umbrella review). Cochrane Database Reviews. attempt compare surgical interventions. We extracted found any randomised controlled trials (RCTs) for eligible comparisons. Individual trial results were directly from review. The outcomes each meta-analysis resynthesised into random-effects meta-analyses. Egger's...