whoa... lost medai aleert
November 7, 2026 at 3:52 AM
whoa... lost medai aleert
🧪 Can generative AI chatbots close postpartum care gaps? Turns out GenAI isn't a panacea.
A new RCT tested Rosie (a chatbot) w/ 400 pregnant or postpartum individuals.
At 12 months, the bot failed to improve depression, anxiety, or ER visits over the control group.
#MedSky #MedAI #MaternalHealth
A new RCT tested Rosie (a chatbot) w/ 400 pregnant or postpartum individuals.
At 12 months, the bot failed to improve depression, anxiety, or ER visits over the control group.
#MedSky #MedAI #MaternalHealth
Generative AI and Maternal Health Outcomes in Pregnant and Postpartum Individuals
This randomized clinical trial evaluates whether access to a generative artificial intelligence (AI) maternal health chatbot improves 12-month maternal health outcomes.
jamanetwork.com
November 6, 2026 at 4:12 PM
🧪 Can generative AI chatbots close postpartum care gaps? Turns out GenAI isn't a panacea.
A new RCT tested Rosie (a chatbot) w/ 400 pregnant or postpartum individuals.
At 12 months, the bot failed to improve depression, anxiety, or ER visits over the control group.
#MedSky #MedAI #MaternalHealth
A new RCT tested Rosie (a chatbot) w/ 400 pregnant or postpartum individuals.
At 12 months, the bot failed to improve depression, anxiety, or ER visits over the control group.
#MedSky #MedAI #MaternalHealth
“SimEHR: A high-fidelity EHR environment for computer-use agents” enables reproducible, screenshot-based evaluation of clinical AI workflows using synthetic charts, auditable actions and open-source tooling. #MedAI #EHR #AIAgents buff.ly/5rKLvNa buff.ly/a59ZU4W
SimEHR: a high-fidelity EHR environment for computer-use agents
SimEHR is a pixel-level, interactive simulation of the EHR interface physicians use every day, built to evaluate computer-use agents the way a clinician works.
buff.ly
November 6, 2026 at 9:11 PM
“SimEHR: A high-fidelity EHR environment for computer-use agents” enables reproducible, screenshot-based evaluation of clinical AI workflows using synthetic charts, auditable actions and open-source tooling. #MedAI #EHR #AIAgents buff.ly/5rKLvNa buff.ly/a59ZU4W
WK Baan Para-Cycling succesvol afgerond in Apeldoorn met 42 deelnemende landen
Het WK Baan Para-Cycling in Omnisport Apeldoorn is afgerond, met sporters uit 42 landen die streden om 47 wereldtitels. Het evenement vond plaats over vier dagen in Apeldoorn en toonde indrukwekkende prestaties en…
Het WK Baan Para-Cycling in Omnisport Apeldoorn is afgerond, met sporters uit 42 landen die streden om 47 wereldtitels. Het evenement vond plaats over vier dagen in Apeldoorn en toonde indrukwekkende prestaties en…
WK Baan Para-Cycling succesvol afgerond in Apeldoorn met 42 deelnemende landen
Het WK Baan Para-Cycling in Omnisport Apeldoorn is afgerond, met sporters uit 42 landen die streden om 47 wereldtitels. Het evenement vond plaats over vier dagen in Apeldoorn en toonde indrukwekkende prestaties en persoonlijke verhalen. Het internationale toernooi bracht een recordaantal deelnemende landen naar Apeldoorn. Topsporters verlegden hun grenzen in diverse disciplines van het baanwielrennen. Groot-Brittannië kwam op het toernooi als sterkste uit de bus met acht wereldtitels en 27 medailles in totaal.
apeldoorn-actueel.nl
November 2, 2026 at 6:25 PM
WK Baan Para-Cycling succesvol afgerond in Apeldoorn met 42 deelnemende landen
Het WK Baan Para-Cycling in Omnisport Apeldoorn is afgerond, met sporters uit 42 landen die streden om 47 wereldtitels. Het evenement vond plaats over vier dagen in Apeldoorn en toonde indrukwekkende prestaties en…
Het WK Baan Para-Cycling in Omnisport Apeldoorn is afgerond, met sporters uit 42 landen die streden om 47 wereldtitels. Het evenement vond plaats over vier dagen in Apeldoorn en toonde indrukwekkende prestaties en…
🧪 Across 177k clinical vignettes, 5 LLMs defaulted to a single drug product 97.5% of the time, even with ~5.5 options per drug.
The LLMs matched the most-prescribed option under 30% of the time, heavily favoring brand-name drugs and web visibility.
#MedSky #MedAI
The LLMs matched the most-prescribed option under 30% of the time, heavily favoring brand-name drugs and web visibility.
#MedSky #MedAI
Large language models show product name convergence in drug recommendations - Nature Health
In a benchmark analysis spanning 123 disease–drug pairs and 1,440 sociodemographic profiles, five large language models recommended the same drug product for a given active ingredient in 97.5% of…
www.nature.com
October 28, 2026 at 2:59 PM
🩻 Study of 183 ICU chest X-rays found evaluated multimodal LLMs underperformed intensivists in CVC assessment. All 5 models missed pneumothorax-related findings in 5 positive cases.
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
October 28, 2026 at 7:48 AM
🩻 Study of 183 ICU chest X-rays found evaluated multimodal LLMs underperformed intensivists in CVC assessment. All 5 models missed pneumothorax-related findings in 5 positive cases.
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
🩻 Study of 183 ICU chest X-rays found evaluated multimodal LLMs underperformed intensivists in CVC assessment. All 5 models missed pneumothorax-related findings in 5 positive cases.
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
October 28, 2026 at 7:48 AM
🩻 Study of 183 ICU chest X-rays found evaluated multimodal LLMs underperformed intensivists in CVC assessment. All 5 models missed pneumothorax-related findings in 5 positive cases.
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
🔗 doi.org/10.3390/meds...
#MedAI #Radiology
Every medical 🩺 🏥application of AI 🤖 needs to be double checked by the level of clinical professional that would have done the task themselves.
Check every (not just a sample) instance.
MedAI is unreliable.
Human lives are at stake.
Cheapness of AI 💰 is not an excuse to rely on it.
Check every (not just a sample) instance.
MedAI is unreliable.
Human lives are at stake.
Cheapness of AI 💰 is not an excuse to rely on it.
October 25, 2026 at 3:09 PM
Every medical 🩺 🏥application of AI 🤖 needs to be double checked by the level of clinical professional that would have done the task themselves.
Check every (not just a sample) instance.
MedAI is unreliable.
Human lives are at stake.
Cheapness of AI 💰 is not an excuse to rely on it.
Check every (not just a sample) instance.
MedAI is unreliable.
Human lives are at stake.
Cheapness of AI 💰 is not an excuse to rely on it.
Patient/Industry Trade-off in Med. AI
🧠 Accurate cancer detection.
🚀 Improved health efficiency.
🔍 Need transparency, ethics.
👥 Collaborate patients, clinicians.
🏥 Balance short, long-term gains. #MedAI #Healthcare #Ethics #Transparency https://tnyp.me/PVuATQWG/s
🧠 Accurate cancer detection.
🚀 Improved health efficiency.
🔍 Need transparency, ethics.
👥 Collaborate patients, clinicians.
🏥 Balance short, long-term gains. #MedAI #Healthcare #Ethics #Transparency https://tnyp.me/PVuATQWG/s
October 22, 2026 at 7:05 AM
Patient/Industry Trade-off in Med. AI
🧠 Accurate cancer detection.
🚀 Improved health efficiency.
🔍 Need transparency, ethics.
👥 Collaborate patients, clinicians.
🏥 Balance short, long-term gains. #MedAI #Healthcare #Ethics #Transparency https://tnyp.me/PVuATQWG/s
🧠 Accurate cancer detection.
🚀 Improved health efficiency.
🔍 Need transparency, ethics.
👥 Collaborate patients, clinicians.
🏥 Balance short, long-term gains. #MedAI #Healthcare #Ethics #Transparency https://tnyp.me/PVuATQWG/s
MedAI #166: MedAI ASK An Agentic System for Biomedical Question Answering | Nhung Nguyen" covers J&J's agentic QA (>51k queries). Key insight: expert tool curation beats open catalogs. #BiomedicalAI #AgenticAI buff.ly/qJilV4r
October 9, 2026 at 3:36 PM
MedAI #166: MedAI ASK An Agentic System for Biomedical Question Answering | Nhung Nguyen" covers J&J's agentic QA (>51k queries). Key insight: expert tool curation beats open catalogs. #BiomedicalAI #AgenticAI buff.ly/qJilV4r
MedAI #166: MedAI ASK An Agentic System for Biomedical Question Answering | Nhung Nguyen" covers J&J's agentic QA (>51k queries). Key insight: expert tool curation beats open catalogs. #BiomedicalAI #AgenticAI buff.ly/qJilV4r
October 9, 2026 at 6:39 PM
MedAI #166: MedAI ASK An Agentic System for Biomedical Question Answering | Nhung Nguyen" covers J&J's agentic QA (>51k queries). Key insight: expert tool curation beats open catalogs. #BiomedicalAI #AgenticAI buff.ly/qJilV4r
🧪 New in The Lancet: testing conversational AI in actual clinic workflows.
Beth Israel Decon. evaluated Google's AMIE across 98 urgent primary care visits.
Physician observers never had to halt a session for safety, and the AI's top 7 differentials captured 90% of final diagnoses. #MedSky #MedAI
Beth Israel Decon. evaluated Google's AMIE across 98 urgent primary care visits.
Physician observers never had to halt a session for safety, and the AI's top 7 differentials captured 90% of final diagnoses. #MedSky #MedAI
Conversational diagnostic artificial intelligence in ambulatory primary care: a prospective feasibility study
Although further research is needed, this study shows the initial feasibility of conversational
AI in a real-world setting—assessed via conversation safety and quality, as well as
user acceptance—and ...
www.thelancet.com
October 9, 2026 at 5:03 PM
MedAI #166: Med.ai ASK: An Agentic System for Biomedical Question Answering | Nhung Nguyen
Stanford MedAI
youtu.be/X_xgRiS6-Ns?...
Stanford MedAI
youtu.be/X_xgRiS6-Ns?...
MedAI #166: Med.ai ASK: An Agentic System for Biomedical Question Answering | Nhung Nguyen
YouTube video by Stanford MedAI
youtu.be
October 8, 2026 at 7:25 AM
MedAI #166: Med.ai ASK: An Agentic System for Biomedical Question Answering | Nhung Nguyen
Stanford MedAI
youtu.be/X_xgRiS6-Ns?...
Stanford MedAI
youtu.be/X_xgRiS6-Ns?...
Examining patient/industry trade-offs in medical AI:
📉 85% of health research funds wasted
🧑⚕️Need for patient, physician involvement
⚖️ Emphasis on balance in partnerships
twitter
#MedAI #Ethics #GDPR #AIChasm #RCTs #LongitudinalStudies
https://tnyp.me/PVuATQWG/s
📉 85% of health research funds wasted
🧑⚕️Need for patient, physician involvement
⚖️ Emphasis on balance in partnerships
#MedAI #Ethics #GDPR #AIChasm #RCTs #LongitudinalStudies
https://tnyp.me/PVuATQWG/s
October 8, 2026 at 7:10 AM
Examining patient/industry trade-offs in medical AI:
📉 85% of health research funds wasted
🧑⚕️Need for patient, physician involvement
⚖️ Emphasis on balance in partnerships
twitter
#MedAI #Ethics #GDPR #AIChasm #RCTs #LongitudinalStudies
https://tnyp.me/PVuATQWG/s
📉 85% of health research funds wasted
🧑⚕️Need for patient, physician involvement
⚖️ Emphasis on balance in partnerships
#MedAI #Ethics #GDPR #AIChasm #RCTs #LongitudinalStudies
https://tnyp.me/PVuATQWG/s
La Corée du Sud a remporté une belle moisson de médailles aux Jeux asiatiques, qui se sont terminés dimanche 4 octobre. Pour certains jeunes athlètes, une médai...
Corée du Sud : les athlètes médaillés vont-ils échapper encore longtemps au service militaire ?
ebx.sh
October 7, 2026 at 11:07 PM
La Corée du Sud a remporté une belle moisson de médailles aux Jeux asiatiques, qui se sont terminés dimanche 4 octobre. Pour certains jeunes athlètes, une médai...
Corée du Sud : les athlètes médaillés vont-ils échapper encore longtemps au service militaire ?
Corée du Sud : les athlètes médaillés vont-ils échapper encore longtemps au service militaire ?
La Corée du Sud a remporté une belle moisson de médailles aux Jeux asiatiques, qui se sont terminés dimanche 4 octobre. Pour certains jeunes athlètes, une médai...
www.courrierinternational.com
October 7, 2026 at 2:50 PM
Corée du Sud : les athlètes médaillés vont-ils échapper encore longtemps au service militaire ?
🧪 In a new study, Google's open MedGemma 4B (4 billion parameters) outscored Gemini 2.5 Pro on zero-shot chest X-ray, pathology, and retina classification, with a 500-fold compute cost gap against the priciest model compared. Dermatology was the exception (71.8% vs. 81.0% accuracy). #MedSky #MedAI
An open vision-language model for diverse medical applications - Nature Medicine
MedGemma, a collection of medical vision-language foundation models based on Gemma 3, demonstrates advanced medical understanding and reasoning across images and text and multiple medical imaging…
www.nature.com
October 6, 2026 at 2:58 PM
Two Bridge2AI Investigators receive the IEEE Innovation in Societal Infrastructure Award 🏆 Read more about our Investigators awarded for their leadership in privacy-preserving clinical research: bit.ly/4doccGq
#ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #AISky #MLSky
#ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #AISky #MLSky
October 5, 2026 at 5:44 PM
Two Bridge2AI Investigators receive the IEEE Innovation in Societal Infrastructure Award 🏆 Read more about our Investigators awarded for their leadership in privacy-preserving clinical research: bit.ly/4doccGq
#ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #AISky #MLSky
#ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #AISky #MLSky
Zhang et al. tested when a local AI agent should hand a diagnosis to a clinician. It diagnosed 551 simulated cases (five runs each). If the runs agreed, it proceeded alone. If not, a clinician would review. That caught 49 of 52 errors but also flagged 230 correct answers.
#MedSky #MedAI
#MedSky #MedAI
The missing links in agentic AI autonomy - Nature Medicine
A new study tackles issues around operational and decisional trust of agentic artificial intelligence (AI), using locally deployed, on-premise agents and consistency-based gating to refer uncertain…
www.nature.com
October 5, 2026 at 3:45 PM
Tým v rozkladu, ale Češi to nejsou. Chorvatsko řeší vyhazov ikony
Varianta, že v této skupině Ligy národů bude jeden tým pod palbou a po debaklech, byla docela reálná. Ale že se to stane hrdým Chorvatům? Nestačíme. Zaostáváme. Liga je plná cizinců… Dvojnásobní medailisté z MS jsou v depresi.
Varianta, že v této skupině Ligy národů bude jeden tým pod palbou a po debaklech, byla docela reálná. Ale že se to stane hrdým Chorvatům? Nestačíme. Zaostáváme. Liga je plná cizinců… Dvojnásobní medailisté z MS jsou v depresi.
Tým v rozkladu, ale Češi to nejsou. Chorvatsko řeší vyhazov ikony - Seznam Zprávy
Varianta, že v této skupině Ligy národů bude jeden tým pod palbou a po debaklech, byla docela reálná. Ale že se to stane hrdým Chorvatům? Nestačíme. Zaostáváme. Liga je plná cizinců… Dvojnásobní medai...
www.seznamzpravy.cz
October 6, 2026 at 5:49 AM
Tým v rozkladu, ale Češi to nejsou. Chorvatsko řeší vyhazov ikony
Varianta, že v této skupině Ligy národů bude jeden tým pod palbou a po debaklech, byla docela reálná. Ale že se to stane hrdým Chorvatům? Nestačíme. Zaostáváme. Liga je plná cizinců… Dvojnásobní medailisté z MS jsou v depresi.
Varianta, že v této skupině Ligy národů bude jeden tým pod palbou a po debaklech, byla docela reálná. Ale že se to stane hrdým Chorvatům? Nestačíme. Zaostáváme. Liga je plná cizinců… Dvojnásobní medailisté z MS jsou v depresi.
A scoping review examines how AI and digital technologies are reshaping…
#AIinHealthcare #NeonatalCare #DigitalHealth #MedAI
https://news.google.com/rss/articles/CBMiX0FVX3lxTE5rUm9RS3dPQ1NRY2QwcVpuU3RxMF9ob2Q4N0VKeFRSenRWaGVfZ3RfdFQ3NUVfTmltRXFEUEZNaFFVQmtlQVMwdnJlSElILWRsZGJ0dTh6dG9KVUtoU3Rr
#AIinHealthcare #NeonatalCare #DigitalHealth #MedAI
https://news.google.com/rss/articles/CBMiX0FVX3lxTE5rUm9RS3dPQ1NRY2QwcVpuU3RxMF9ob2Q4N0VKeFRSenRWaGVfZ3RfdFQ3NUVfTmltRXFEUEZNaFFVQmtlQVMwdnJlSElILWRsZGJ0dTh6dG9KVUtoU3Rr
October 3, 2026 at 8:01 PM
A scoping review examines how AI and digital technologies are reshaping…
#AIinHealthcare #NeonatalCare #DigitalHealth #MedAI
https://news.google.com/rss/articles/CBMiX0FVX3lxTE5rUm9RS3dPQ1NRY2QwcVpuU3RxMF9ob2Q4N0VKeFRSenRWaGVfZ3RfdFQ3NUVfTmltRXFEUEZNaFFVQmtlQVMwdnJlSElILWRsZGJ0dTh6dG9KVUtoU3Rr
#AIinHealthcare #NeonatalCare #DigitalHealth #MedAI
https://news.google.com/rss/articles/CBMiX0FVX3lxTE5rUm9RS3dPQ1NRY2QwcVpuU3RxMF9ob2Q4N0VKeFRSenRWaGVfZ3RfdFQ3NUVfTmltRXFEUEZNaFFVQmtlQVMwdnJlSElILWRsZGJ0dTh6dG9KVUtoU3Rr
Join the CM4AI-AnVIL DREAM Challenge: Help pioneer in silico microscopy, build "virtual cells", and develop #GenerativeAI models for protein localization 🚀
🏆 Up to $25k cash + $40k GCP credits
🔗 bit.ly/4AK1uE9
#AISky #MLSky #ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #Genomics
🏆 Up to $25k cash + $40k GCP credits
🔗 bit.ly/4AK1uE9
#AISky #MLSky #ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #Genomics
October 1, 2026 at 6:20 PM
Join the CM4AI-AnVIL DREAM Challenge: Help pioneer in silico microscopy, build "virtual cells", and develop #GenerativeAI models for protein localization 🚀
🏆 Up to $25k cash + $40k GCP credits
🔗 bit.ly/4AK1uE9
#AISky #MLSky #ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #Genomics
🏆 Up to $25k cash + $40k GCP credits
🔗 bit.ly/4AK1uE9
#AISky #MLSky #ArtificialIntelligence #BiomedicalInformatics #MedSky #MedAI #Genomics
MedAI #165: AgentDS-BUS: An Agentic Framework for Breast Ultrasound Malignancy Cx. | Pengze Li
Stanford MedAI
youtu.be/GRPVRtYqcyw?...
Stanford MedAI
youtu.be/GRPVRtYqcyw?...
youtu.be
September 29, 2026 at 8:01 AM
MedAI #165: AgentDS-BUS: An Agentic Framework for Breast Ultrasound Malignancy Cx. | Pengze Li
Stanford MedAI
youtu.be/GRPVRtYqcyw?...
Stanford MedAI
youtu.be/GRPVRtYqcyw?...
I do think our media can provide a better vision for the future than constant dystopias, a story about a utopia without any real problems is definitely worse medai.
September 29, 2026 at 4:10 PM
I do think our media can provide a better vision for the future than constant dystopias, a story about a utopia without any real problems is definitely worse medai.
What if the AI layer at the bedside needed no cloud and no GPU? Duan runs clinical decision models on CPU with 2GB RAM, fully local. Open source: github.com/wipen/Duan #HealthAI #opensource #MedAI #DigitalHealth
I built Duan, an open-source System 1 model for healthcare.
It runs locally on CPU with ~2 GB RAM, making structured medical decision models easier to experiment with and deploy at the edge. Duan is a step toward decision-native AI for healthcare. GitHub: github.com/wipen/Duan
It runs locally on CPU with ~2 GB RAM, making structured medical decision models easier to experiment with and deploy at the edge. Duan is a step toward decision-native AI for healthcare. GitHub: github.com/wipen/Duan
September 27, 2026 at 12:06 PM
What if the AI layer at the bedside needed no cloud and no GPU? Duan runs clinical decision models on CPU with 2GB RAM, fully local. Open source: github.com/wipen/Duan #HealthAI #opensource #MedAI #DigitalHealth