Chris Le

In June 2023, the regional Medicare Administrative Contractors (MACs) almost uniformly introduced draft policy language indicating cessation of coverage for many MIGS procedures, including goniotomy and cyclophotocoagulation.

lots of talk about Vision OS, but what about Vision OD?

I don't talk much about this - I obtained one of the first FDA approvals in ML + radiology and it informs much of how I think about AI systems and their impact on the world. If you're a pure technologist, you should read the following: There's so much to unpack for both why Geoff was wrong, and why his future predictions should not be taken seriously either. Geoff made a classic error that technologists often make, which is to observe a particular behavior (identifying some subset of radiology scans correctly) against some task (identifying hemorrhage on CT head scans correctly), and then to extrapolate based on that task alone. The reality is that reducing any job, especially a wildly complex job that requires a decade of training, to a handful of tasks is quite absurd. Here's a bunch of stuff you wouldn't know about radiologists unless you built an AI company WITH them instead of opining about their job disappearing from an ivory tower. (1) Radiologists are NOT performing 2d pattern recognition - they have a 3d world model of the brain and its physical dynamics in their head. The motion and behavior of their brain to various traumas informs their prediction of hemorrhage determination. (2) Radiologists have a whole host of grounded models to make determinations, and actually, one of the most important first order determination they make is whether there is anything notably wrong with a brain structure that "feels" off. As a result, classifiers aren’t actually performing the same task even as radiologists. (3) Radiologists, because they have a grounded brain model, only need to see a single example of a rare and obscure condition to both remember it and identify it in the future. This long tail of rare conditions to avoid missing is a large part of their training, and no one has any clue how to make a model that acts similar in this way. (4) There’s so many ways to make Radiologist lives easier instead of just replacing them, it doesn’t even make sense to try. I interviewed and hired 25 radiologists, whose primary and chief complaint was that they had to reboot their computers several times a day. (5) A large part of the radiologist job is communicating their findings with physicians, so if you are thinking about automating them away you also need to understand the complex interactions between them and different clinics, which often are unique. (6) Every hospital is a snowflake, data is held under lock and key, so your algorithm might not work in a bunch of hospitals. Worse, the imagenet datasets have such wildly different feature sets they don’t do much for pretraining for you. (7) Have you ever tried to make anything in healthcare? The entire system is optimized to avoid introducing any harm to patients - explaining the ramifications of that would take an entire book, but suffice to say even if you had an algorithm that could automate away radiologists I don’t even know if you could create a viable adoption strategy in the US regulatory environment. (8) The reality is that for every application, the amount of specific and UNKNOWABLE domain knowledge is immense. LONG STORY SHORT: thinkers have a pattern where they are so divorced from implementation details that applications seem trivial, when in reality, the small details are exactly where value accrues. Should you be worried about GPT5 being used to automate vulnerability detection on websites before they’re patched? Maybe. Should you be worried GPT5 is going to interact with SOCIAL systems and destroy our society single-handedly? No absolutely not.

We are excited to announce that our blinded randomized clinical trial of AI LVEF (EchoNet-Dynamic) has been published in @nature! @bryandhe @james_y_zou @StanfordDBDS @CedarsSinaiMed nature.com/articles/s4158… 1/n

@ericsongg @Ophthalmologymg Smeagol is going to have such a busy practice

@Ophthalmologymg @ChristopherTNLe add to the list.

Can a long-spine porcupine pufferfish receive cataract surgery? Meet Dill Prickle. buff.ly/3PqIUby

Thrilled to welcome our newest matched class of #match2022 #radiology #radres!!!

@TrishaMiglani @UMmedschool @GoldFdtn Congrats 👏

I am honored and humbled to have been inducted into the Gold Humanism Honor Society at @UMmedschool. I will strive to continue providing humanistic and patient-centered care throughout my medical career! #MedTwitter #MedStudentTwitter #goldhumanism

NEW PREPRINT The increasingly popular class imbalance approaches (such as SMOTE) for risk prediction modeling: they are likely to do more harm than good arxiv.org/abs/2202.09101

@EmXuMed @OhioStateEye YESSSSSS CONGRATS!

BEYOND THRILLED TO TRAIN AT OSU FOR 🤩 👀 We’re about to embark on a new chapter and I’m so grateful to have you all by my side 🥲 #Ophthotwitter #match2022 #ophthomatch2022 @OhioStateEye

@lyna_azzouz Congrats!

As always - immensely grateful to co-authors for their collaboration on this study and to @ojsaeedi for his mentorship and getting me interested in the world of ocular blood flow in glaucoma

I remember as an M1 thinking how neat it was to see erythrocyte velocity profiles roughly align with systole-diastole. Now, we not only can reliably measure high-res flow waveforms, but have identified waveform characteristics that could help with glaucoma diagnosis in the future

Excited and humbled to share our recently published work in @AAOjournal #Glaucoma looking at the intra/intersession repeatability and differences in real-time dynamic blood flow velocity index measures in glaucoma, suspects, and controls sciencedirect.com/science/articl…

@ojsaeedi @NatEyeInstitute @NIH @UMmedschool @UMDEye @US_FDA Congratulations!

Honored to receive an R01 grant from the @NatEyeInstitute @NIH for collaborative work between my lab at @UMmedschool @UMDEye and Drs. Hammer and Liu at @US_FDA #glaucoma #ocularbloodflow #UMB #AO #ophthalmology medschool.umaryland.edu/news/2021/UM-S…

Fantastic and approachable episode for anyone interested in learning about pediatric ophthalmology from an incredible educator at @UMDEye

Me: wow look at this cool ophtho thing @ElizabethYLiu: wow look at this cool rads thing 🤝:

Work from @ojsaeedi shows that a newly FDA cleared retinal laser speckle contrast imaging device may hold promise as a new tool in the diagnosis of glaucoma. @ChristopherTNLe #bloodflow #glaucoma #biomarker #ophthalmology ow.ly/O1ZH50GxQSx

Why is medical data sharing so incredibly hard? Our latest episode of @AIHealthPodcast with Prof. Zak Kohane (@zakkohane) goes into the incentives, standards, and breakthroughs that are core to medical data sharing! I'm excited to share this with you! theaihealthpodcast.com/episodes/thou-…

Huge thanks to the mentorship of @ojsaeedi, co-authors and collaborators at the @FDA, and a talented and bright co-first author Ricardo Villanueva, now M1 at USF!

This study was limited by its cross sectional nature and sample size, so no definite answers on timing/mechanism yet but definitely cool to see how the capability to visualize single ganglion cells in small fields of view using AO-OCT may add to the narrative

Cell – Vessel Mismatch in Glaucoma: Correlation of Ganglion Cell Layer Soma and Capillary Densities | IOVS | ARVO Journals iovs.arvojournals.org/article.aspx?a… Hot of the press, here's a 🧵 on our recent paper in IOVS (1/a lot I'm sorry)