@SynhoDo

Director Lab of Medical Imaging and Computation, Assistant Professor MGH and Harvard Medical School, Affiliated Faculty Kempner Institute, Harvard University

 Boston, MA
lmic.mgh.harvard.edu
Joined December 2013
  • Tweets171
  • Following716
  • Followers445
22Media
Accuracy ≠ safety. A new npj Digital Medicine paper introduces SA-ROC, a framework that asks the real question: when is it operationally safe to trust clinical AI? Instead of just reporting AUC, it defines: • “Safe zones” for autonomous action • A “gray zone” requiring human review • A metric to quantify the cost of indecision In one case study, the model with better AUC was actually less safe in practice. Maybe it’s time we stop equating performance with safety. nature.com/articles/s41746-0…
2
4
2
10
1,083
Microbiome research is a sea of data. We built a map. MINERVA—microbiome network research and visualization atlas: a scalable knowledge graph for mapping microbiome-disease associations academic.oup.com/bib/article… Platform: minervabio.org/

MINERVA—microbiome network research and visualization atlas: a scalable knowledge graph for mapping...

Abstract. Bacterial pathogens contribute significantly to the global burden of disease. Understanding their complex interactions with human health is essen

academic.oup.com
1
4
70
Commentary on risk score thresholds to evaluate performance of a commercial #AI system for breast cancer detection and diagnosis doi.org/10.1148/ryai.240184 @SynhoDo @MGHImaging #MammoRad #cancer #ML
1
2
704
Trade-offs between sensitivity and specificity when deploying a #BreastCancer AI system in clinical practice doi.org/10.1148/ryai.240184 @SynhoDo @MGHImaging #cancer #DeepLearning #ML
1
1
535
Trade-offs between sensitivity and specificity when deploying a #BreastCancer AI system in clinical practice doi.org/10.1148/ryai.240184 @SynhoDo @MGHImaging #MammoRad #DeepLearning #AI
2
6
697
Fuel your passion for healthcare innovation at Mass General Brigham MESH Core! Join us in Boston May 20-21 for two days of learning, networking, and key insights in our peer-reviewed innovation course. @MGBInnovation @MassGenBrigham Learn more: mesh2024.meshincubator.org/
3
4
488
#AI needs to be safe for clinical care. @SynhoDo talks about novel approaches and challenges to making AI in medicine a reality now in @MGBInnovation Grand Rounds @MGHImaging @mgbmeshnetwork
1
5
25
2,040
Join us on Sept 13 for Mass General Brigham Innovation Grand Rounds. @SynhoDo will share his journey through research & commercial translation of several #ArtificialIntelligence-based products for clinical care @MassGenBrigham and beyond! Register: partners.zoom.us/webinar/reg…
4
1
6
995
📅 Join @Radiology_AI for the Sept. #RadAIchat this Wed. Sept. 6th at 8 PM ET on "Quantifying uncertainty in #radiology #AI" moderated by @bcalvesnatlia and featuring @ShahriarFaghani @MDohopolski @SynhoDo #radiomics #AI #ML #DL #radres @RSNA @cekahn @HElhalawaniMD
6
12
1,522
When the previously developed #Cryptographic technologies are tested and implemented in the healthcare data flow, value generation through AI algorithm will become possible. #AI #cloud #cloudsecurity @SynhoDo @harvardmed healthtechmagazines.com/smar…

Smart and Secure PACS (Picture Archiving and Communication System) on Clouds

he advantage of the cloud is its easy scalability. Users do not have to worry about hardware problems. There are also various models of the

healthtechmagazines.com
2
2
Congrats DSO members @SynhoDo, Ph.D., Ramon Gonzalez, MD, Ph.D. + @MichaelLevMD, MD, for receiving a US patent for explainable artificial intelligence that accurately diagnoses brain hemorrhage even with a small dataset developed at Mass General Hospital! patents.google.com/patent/US…
1
2
4
Fantastic talk by @SynhoDo at the #WMIF on SafeAI, and AI to reduce medical errors @MGBInnovation @MGHImaging
1
6
8,594
At #WMIF2023, Synho Do, PhD @SynhoDo @MGHImaging shares a First Look at SafeAI, and the potential for #AI to improve #healthcare, enhance decision-making and stremline provider workflow. #ArtificialIntelligence #AIinHealthcare
3
5
1,008
Our perspective on the following questions was published in #NatureBME. 1. Can we develop AI that doesn't make mistakes? 2. Can we find cases where AI is not confident? 3. Could we be aware of the weaknesses of AI in advance? rdcu.be/c2s0k #MGB #HMS #AI
1
6
35
4,722
Tackling prediction uncertainty in machine learning for healthcare rdcu.be/c2tbt
3
10
42
7,935
Congratulations to the @MassGenBrigham team for their recent publication in Nature Scientific Reports! @SynhoDo Read article here: lnkd.in/dYJJftRg
1
3
13
Synho Do, PhD retweeted
Marc Succi, MD
@MarcSucciMD9 Dec 2022
Congratulations @SynhoDo lab for this paper in @nature Scientific Reports “Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: efficient development of auditable risk prediction models via a fine-tuning approach” @MGH_RI
2
9
Accurate auto-labeling of chest X-ray images based on quantitative similarity to an explainable AI model disq.us/t/46m5pss
5
Synho Do, PhD retweeted
Marc Succi, MD
@MarcSucciMD6 Apr 2022
Congratulations to @SynhoDo + coauthors for their new paper in @NatureComms! Accurate auto-labeling of chest X-ray images based on quantitative similarity to an explainable AI model #machinelearning @MGH_RI @MGHImaging
Synho Do, PhD@SynhoDo6 Apr 2022
Read my latest #research on #ExplainableAI,#Autolabeling, and #qSim, published with @SpringerNature in @NatureComms. Read here: rdcu.be/cKLX5
3
7
Read my latest #research on #ExplainableAI,#Autolabeling, and #qSim, published with @SpringerNature in @NatureComms. Read here: rdcu.be/cKLX5
2
1
9
Load more