Synho Do, PhD

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

[npj Digital Medicine @npjDigitalMed]

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.

https://t.co/zRqeag7IOq

[Synho Do, PhD @SynhoDo]

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 https://t.co/nWBQvN2xKH
Platform: https://t.co/r3DA5inLVd

[Radiology: Artificial Intelligence @Radiology_AI]

Commentary on risk score thresholds to evaluate performance of a commercial #AI system for breast cancer detection and diagnosis https://t.co/GDJZcjZZNM @SynhoDo @MGHImaging #MammoRad #cancer #ML

[Radiology: Artificial Intelligence @Radiology_AI]

Trade-offs between sensitivity and specificity when deploying a #BreastCancer AI system in clinical practice https://t.co/GDJZcjZZNM @SynhoDo @MGHImaging #cancer #DeepLearning #ML

[Radiology: Artificial Intelligence @Radiology_AI]

Trade-offs between sensitivity and specificity when deploying a #BreastCancer AI system in clinical practice https://t.co/GDJZcjZZNM @SynhoDo @MGHImaging #MammoRad #DeepLearning #AI

[MESH Incubator™ at Mass General Brigham @meshincubator]

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: https://t.co/mSqm6SWUML

[Marc Succi, MD @MarcSucciMD]

#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

[Mass General Brigham Innovation @MGBInnovation]

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: https://t.co/DYhEv9Rp4M

[Synho Do, PhD @SynhoDo]

@BcalvesNatlia @Radiology_AI Good question! With trustworthy AI that has UQ, we can automatically handle simple cases because we can rely on it. #RadAIchat

[Synho Do, PhD @SynhoDo]

@Radiology_AI It’s akin to an AI lie detector. #RadAIchat

[Synho Do, PhD @SynhoDo]

@Radiology_AI AI with UQ and without UQ are very different. One is trustworthy because it's honest; the other isn't. #RadAIchat

[Synho Do, PhD @SynhoDo]

@Radiology_AI It should be auditable. #RadAIchat, https://t.co/2fjxFPGAsK

[Synho Do, PhD @SynhoDo]

@Radiology_AI I'd prefer an honest AI (with uncertainty metrics) over a flashy AI (without uncertainty metrics) #RadAIchat

[Synho Do, PhD @SynhoDo]

@Radiology_AI We want to make an AI that, like a curious child, honestly says 'I don't know' and asks questions instead of just guessing. #RadAIchat

[Synho Do, PhD @SynhoDo]

@Radiology_AI We need to build AI that uses uncertainty metrics to show and admit its confidence. #RadAIchat

[Synho Do, PhD @SynhoDo]

@Radiology_AI When AI's flaws are hidden, Uncertainty Metrics can reveal them. #RadAIchat

[Synho Do, PhD @SynhoDo]

@Radiology_AI No algorithm is flawless, yet some excel in certain areas. We must identify their strengths and weaknesses, and uncertainty quantification helps achieve that. #RadAIChat

[Synho Do, PhD @SynhoDo]

@MDohopolski @ShahriarFaghani @BcalvesNatlia Here is another one. #RadAIChat, https://t.co/c5afAgnttf

[Synho Do, PhD @SynhoDo]

@Radiology_AI AI uncertainty quantification is like the brakes on a fast-moving AI car. It helps us confirm the AI's results by comparing them to the prediction probability of its output. Uncertainty metrics should be independent of the prediction probabilities given by AI output. 😊#RadAIchat