On the public side, NIH is continuing to build infrastructure for biomedical AI. Bridge2AI is shifting from creating AI-ready datasets and best-practice frameworks toward trusted AI applications. bridge2ai.org/ At the same time, All of Us is expanding its national research platform, with a planned 2026 release expected to include roughly 535,000 short-read whole genome sequences and broader multi-omics data. allofus.nih.gov/

Great to be at the NIH in Bethesda for the AIM-AHEAD BRIDGE2AI meeting! Our team presented our preliminary data on a multimodal AI model for predicting VAP. Huge thanks to the team for the hard work and to the NIH for hosting such an inspiring gathering of minds dedicated to health equity and AI innovation. #AI #Medicine #NIH #DataScience #ICU #Bridge2AI #AIMAHEAD

Day 1 at Bridge2AI 2026 All-Hands Meeting in Rockville, MD. AIM-AHEAD trainees from the AI-READI and Clinical Care programs are presenting, pitching, and collaborating across the consortium. Learn More: Link in Bio!

Our work with Bridge2AI and AIREADI has been so rewarding. We are honored to work with such high-level academics and thought leaders in the AI space. We were happy to host the AIREADI Teaming, Data Tools and Data Collection Primary Investigators In the Cheyenne River Sioux Nation

🧠 Ready to explore the future of AI in biomedical and behavioral research? Registration is now open for the Bridge2AI meeting, From Data to Wisdom: Bridging the Future of AI. 🗓️ April 28–29, 2026 📍 Rockville, MD | 💻 Virtual option available 🔗 Register now: cvent.me/kwME2o

Really interesting @SciTechDaily1 article, "#AI May Soon Detect #Cancer Just by Listening to You Speak," about the #Bridge2AI consortium that @WCMEnglanderIPM Director Olivier Elemento, PhD (@ElementoLab) helped create! scitechdaily.com/ai-may-soon…

AI May Soon Detect Cancer Just by Listening to You Speak | Frontiers, SciTechDaily New research explores how hidden patterns in the human voice could serve as early indicators of disease. Cancer of the larynx, often called the voice box, remains a major global health concern. In 2021, about 1.1 million people were diagnosed worldwide, and roughly 100,000 died from the disease. Smoking, heavy alcohol use, and infection with human papillomavirus are key risk factors. Survival rates vary widely, ranging from 35% to 78% over five years with treatment, depending on where the tumor develops and how advanced it is at diagnosis. Early detection plays a critical role in improving outcomes. Today, diagnosis typically relies on video nasal endoscopy and tissue biopsies, which are invasive and can be difficult to access quickly. Delays in seeing a specialist may slow diagnosis and treatment. New research published in Frontiers in Digital Health suggests a different approach. Scientists found that subtle changes in a person’s voice can reveal abnormalities in the vocal folds. These “vocal fold lesions” may be harmless, such as nodules or polyps, but they can also signal early-stage laryngeal cancer. The findings point to a potential new use for artificial intelligence: identifying early warning signs of cancer through voice analysis. “Here we show that with this dataset we could use vocal biomarkers to distinguish voices from patients with vocal fold lesions from those without such lesions,” said Dr Phillip Jenkins, a postdoctoral fellow in clinical informatics at Oregon Health & Science University, and the study’s corresponding author. Voice messages Jenkins and his team are part of the ‘Bridge2AI-Voice’ project within the US National Institute of Health’s ‘Bridge to Artificial Intelligence’ (Bridge2AI) consortium. This nationwide effort aims to apply AI to complex biomedical problems. For this study, the researchers examined tone, pitch, volume, and clarity using the first public release of the Bridge2AI-Voice dataset, which includes 12,523 recordings from 306 participants across North America. Only a portion of these recordings came from people with diagnosed laryngeal cancer, benign vocal fold lesions, or other voice disorders such as spasmodic dysphonia and unilateral vocal fold paralysis. The team analyzed several measurable features of speech. These included mean fundamental frequency, or pitch, along with jitter, which reflects small variations in pitch, and shimmer, which captures changes in amplitude. They also measured the harmonic-to-noise ratio, which compares structured sound to background noise in speech. Clear differences emerged in the harmonic-to-noise ratio and pitch among men without voice disorders, men with benign lesions, and men with laryngeal cancer. Similar patterns were not identified in women, although the researchers note that a larger dataset may reveal meaningful trends. The study suggests that changes in the harmonic-to-noise ratio may help track how vocal fold lesions develop and could support early detection of laryngeal cancer, particularly in men. “Our results suggest that ethically sourced, large, multi-institutional datasets like Bridge2AI-Voice could soon help make our voice a practical biomarker for cancer risk in clinical care,” said Jenkins. Building a bridge to AI With these initial results in place, the next step is to apply the algorithms to larger datasets and evaluate their performance in clinical settings. “To move from this study to an AI tool that recognizes vocal fold lesions, we would train models using an even larger dataset of voice recordings, labeled by professionals. We then need to test the system to make sure it works equally well for women and men,” said Jenkins. “Voice-based health tools are already being piloted. Building on our findings, I estimate that with larger datasets and clinical validation, similar tools to detect vocal fold lesions might enter pilot testing in the next couple of years,” predicted Jenkins. Read more: scitechdaily.com/ai-may-soon…

🗣 AI may soon detect cancer just by listening to you speak Scientists found that subtle changes in a person’s voice can reveal abnormalities in the vocal folds. These “vocal fold lesions” may be harmless, such as nodules or polyps, but they can also signal early-stage laryngeal cancer. The findings point to a potential new use for AI: identifying early warning signs of cancer through voice analysis. With this dataset scientists could use vocal biomarkers to distinguish voices from patients with vocal fold lesions from those without such lesions. The researchers examined tone, pitch, volume, and clarity using the first public release of the Bridge2AI-Voice dataset, which includes 12,523 recordings from 306 participants across North America. The results suggest that Bridge2AI-Voice could soon help make the voice a practical biomarker for cancer risk in clinical care. @MediaQSI

What happens when you break down AI training silos across health disciplines? 🤖 A recent NIH Bridge2AI pilot put this to the test through the AI-READI Bootcamp—bringing scientists, engineers & clinicians together to build shared AI skills. Learn more ➡️ go.nih.gov/y7klZG4

Honored to announce that I have been awarded the AIM-AHEAD BRIDGE2AI grant I look forward to contributing to the advancement of ethical AI and health equity. As well as advancing the use of AI/ML for clincial decision making in the ICU! Thank you to @AIM_AHEAD and Bridge2AI consortiums for this incredible opportunity! #AI #Machinelearning #HealthEquity #ClinicalResearch #MedTwitter #Neurology

Thanks to my NIH Bridge2AI collaborators for getting this publication out the door! Read all about the governance challenges for building and maintaing data repositories for #health #AI technologies. Led by @genomemom academic.oup.com/jamiaopen/a…

From @uwsomwwami @WashUMedDOVS @NIH_CommonFund (#Bridge2AI program): @aaronylee, Cecilia Lee, et al released Year 3 of a dataset researchers can use to identify factors influencing Type 2 diabetes. #NIHfunded Details: brnw.ch/21wXSQD brnw.ch/21wXSQE

The bonus of @AMIAinformatics 2025 at Atlanta is to be able to visit Emory and Dr Xiao Hu, my collaborator in @Bridge2AI CHoRUS, the first time in person.

🚀 Call for Science is Open! Submit your abstracts by December 5th and be part of the future of health technology. 🔗 SUBMIT YOUR ABSTRACT HERE: eventsquid.com/register/3002… #VoiceAI #HealthTech #Innovation #Bridge2AI #CallForScience

Register now open for the 2026 Bridge2AI Voice Symposium Hackathon! Submit abstracts by Dec. 5: ow.ly/cBXZ50XiZyK #VoiceAISymposium #Bridge2AI #USFHealth

We (well, the @NIH Bridge2AI ELSI working group) just published our framework for ethical sourcing of #health #data for #AI. Thanks for the leadership @cnebeker! @laurielovett @genomemom @WonderMixTape @KadijaFerryman @BelislePipon @roses1800 academic.oup.com/jamiaopen/a…

💡Program Spotlight: AIM-AHEAD Bridge2AI for Clinical Care Training Program is accepting applications! There will be an informational webinar today at 2 PM CT / 3:00 PM ET. Register for today's webinar and learn more about our open Call for Applications: LINK IN BIO!

💡 Program Spotlight: AIM-AHEAD Bridge2AI AI-READI Training Program is accepting applications for Cohort 2. There will be an informational webinar today at 2 PM CT / 3:00 PM ET. 🔗 signup.aim-ahead.net/event/p… Learn more about our open Call for Applications: LINK IN BIO!

كشف باحثون من جامعة أوريغون للصحة والعلوم بالولايات المتحدة عن إمكانية الاستفادة من الذكاء الاصطناعي في رصد العلامات المبكرة للسرطان عبر تحليل صوت المريض، حيث أظهرت دراستهم المنشورة في مجلة آفاق الصحة الرقمية أن التسجيلات الصوتية يمكن أن تكشف وجود آفات في الحبال الصوتية، سواء كانت حميدة أو مرتبطة بالمراحل الأولى لسرطان الحنجرة. قاد فريق البحث الدكتور "فيليب جينكينز" ضمن مشروع "جسر إلى الذكاء الاصطناعي المتعلق بالصوت" (Bridge2AI-Voice)، التابع للمعهد الوطني الأميركي للصحة، حيث جرى تحليل أكثر من 12 ألف تسجيل صوتي لـ306 مشاركين من أميركا الشمالية. ركزت الدراسة على خصائص دقيقة مثل النبرة والطبقة والحجم والوضوح، ونجح الباحثون في التمييز بين الأصوات الطبيعية وتلك التي تعكس وجود آفات أو اضطرابات صوتية، بما في ذلك حالات السرطان أو التشوهات الحميدة، إضافة إلى اضطرابات أخرى مثل خلل النطق التشنجي وشلل الحبال الصوتية الأحادي. يستعد الفريق العلمي الآن إلى تدريب نماذج الذكاء الاصطناعي على بيانات أوسع وأكثر تنوعا، على أن يتم تصنيفها من قبل متخصصين في الصوتيات الطبية، بهدف اختبار النظام سريريا وضمان دقته لكلا الجنسين. يرجّح "جينكينز" أن تشهد السنوات القليلة المقبلة إدخال هذه الأدوات في التجارب السريرية، الأمر الذي قد يفتح المجال أمام تقنيات غير جراحية وسريعة للكشف المبكر عن سرطان الحنجرة، ويُحدِث نقلة نوعية في وسائل التشخيص ويمنح المرضى فرصة أكبر للنجاة. يُشكِّل سرطان الحنجرة تحديا صحيا بارزا على مستوى العالم، إذ سُجِّلت في عام 2021 أكثر من 1.1 مليون إصابة، وأدى المرض إلى وفاة ما يقرب من 100 ألف شخص. ترتبط عوامل الخطر بالإفراط في التدخين والكحول، إضافة إلى الإصابة بفيروس الورم الحليمي البشري. أما نسب البقاء على قيد الحياة بعد العلاج فتتراوح بين 35% و78% بحسب مرحلة الورم وموقعه داخل الحنجرة.