AssemblyAI (@AssemblyAI)

임상 워크플로우용 Medical Mode가 공개되었습니다. 일반적인 음성인식 정확도가 높아도 임상에서는 약물명 같은 핵심 토큰 오류 때문에 실사용이 어렵다는 문제를 해결하려는 기능입니다.

https://x.com/AssemblyAI/status/2036822463347302652

#medicalai #speechrecognition #clinicalworkflow #asr #healthcare

AssemblyAI (@AssemblyAI) on X

Medical Mode is now available for clinical workflows. We built Medical Mode because a transcript that's 95% accurate can still be unusable in a clinical setting. Errors in general-purpose ASR are often concentrated on exactly the tokens clinicians care about most: drug names,

X (formerly Twitter)

Deena Mousa (@deenamousa)

최전선 AI 모델들이 영어가 아닌 대부분의 언어에서 여전히 큰 성능 저하를 보인다는 분석입니다. 일부 모델은 영어 대비 12~29%p 낮았고, 의료 진단처럼 다국어 글로벌 배포가 늘어나는 상황에서 중요한 문제로 지적됩니다.

https://x.com/deenamousa/status/2035060063627296809

#ai #multilingual #llm #medicalai

Deena Mousa (@deenamousa) on X

My new piece in @TheEconomist: frontier AI models still underperform badly in most languages — 12-29 percentage points worse than in English depending on the model A real issue as global deployment for use cases like medical diagnosis is accelerating

X (formerly Twitter)

Our #Fosstodon #Introduction:

Medical teams make hundreds of high-pressure decisions daily. #AMPEL helps making the right decisions.

Developed by the Leipzig University Hospital, this non-profit platform provides all you need for real-time monitoring to catch critical risks in #PatientCare.

By 2026, we are going #OpenSource, bringing #ForEvidence clinical decision support to university clinics with full MDR compliance.

#HealthInnovation #DigitalHealth #MedicalAI #PatientSafety #CDS #CDSS

OpenAI (@OpenAI)

AI가 환자와 의사들의 실제 의료 문제 해결을 돕기 시작했다는 발표. OpenAI의 Head of Health Dr. Nate Gross와 Health AI Research Lead Karan Singhal이 Andrew Mayne과 함께 세계 보건 수요를 충족하기 위해 새로운 모델과 제품을 개발하는 방식에 대해 논의한다는 내용.

https://x.com/OpenAI/status/2033589167905734668

#openai #healthcare #healthai #medicalai

X

X (formerly Twitter)
Is AI replacing the work of skilled radiologists? They give us their thoughts | The-14

Radiologists explain how AI assists medical imaging without replacing experts yet, improving detection and workflow while raising new questions about skills

The-14 Pictures
Medical AI is driving standardization in epilepsy surgery: A Chinese researcher is pioneering AI systems to analyze brain recordings and detect signals associated with seizure-generating regions. The Omni-iEEG framework brings together pre-surgical recordings from eight epilepsy centers, covering 302 patients and 178 hours of data, to link AI outputs to post-operative outcomes. https://www.technologynewschina.com/2026/03/medical-ai-growth-leads-to.html #China #Tech #AI #MedicalAI
Medical AI growth leads to standardization in epilepsy surgery

(China Daily) As artificial intelligence (AI) becomes increasingly common in healthcare research, a Chinese medical doctor working on machin...

BrianEMcGrath (@BrianEMcGrath)

방사선과 분야가 'AI가 스캔을 판독하고 사람이 확인하는' 흐름으로 전환 중이라는 주장입니다. 즉, AI가 영상 판독을 수행하고 인간이 이를 확인하는 모델로 이미 이행이 시작되었다는 관찰이며, 관련 영상은 @rohanpaul_ai 제작입니다. 의료영상 AI의 임상 적용 트렌드를 강조합니다.

https://x.com/BrianEMcGrath/status/2028842582202368305

#medicalai #radiology #ai #healthcare

BrianEMcGrath (@BrianEMcGrath) on X

Radiology is following the same curve as grocery checkout. AI reads the scan. Human confirms. We're already in the transition. Most people just haven't been the patient yet. Video by @rohanpaul_ai

X (formerly Twitter)

Ultralytics (@ultralytics)

Ultralytics의 YOLO26을 사용해 뇌종양 MRI 데이터셋에서 탐지 모델을 훈련하는 안내입니다. 경량 연구용 데이터셋으로 탐지 파이프라인을 테스트하고 의료 AI 워크플로를 검증하는 데 적합하다고 소개합니다.

https://x.com/ultralytics/status/2028515820683337790

#ultralytics #yolo26 #medicalai #mri #objectdetection

Ultralytics (@ultralytics) on X

Train Ultralytics YOLO26 on the brain tumor dataset! 🧠 Detect tumors in MRI images using this lightweight research dataset, ideal for testing detection pipelines and validating medical AI workflows. Start training ➡️ https://t.co/clSb7BT6YJ #Ultralytics #YOLO26 #AI #MedicalAI

X (formerly Twitter)