Allison Chang

The LEGACY study (opening ~Dec 2025) will aim to build a large, diverse dataset of chest CTs + clinical information from people w/ a family history of lung cancer. We will offer free screening chest CTs to qualifying participants. If interested: mghlegacylungstudy@mgb.org 5/5

Really impactful talk by Alex Potter (@alexandra_p_24) on long-term (5+ years) quality of life after #LungCancer surgery. Data from the Boston Lung Cancer Study show survivors have high quality of life, comparable to the U.S. general population. Early detection matters—it can help lead to good long-term outcomes for patients!! #AATS2026

Such a privilege to be on the @UpstageLungCanc podcast discussing familial lung cancer risk and the future of #lungcancerscreening with @LeciaSequist and Hildy Grossman. #lcsm #AI @MassGeneralNews @MGHThoracicOnc

maybe this is not yet clear, so let me state it plainly: as of right now Anthropic, and really a small number of individuals at Anthropic, has the capacity to directly attack and cause major damage to the United States Government, China, and generally global superpowers. government agencies like the NSA do not have internal models or defense capabilities that outclass frontier models. if they chose to do so, they could likely exfiltrate top secret information from government systems, gain control over critical infrastructure including military infrastructure, sabotage or modify communications between members of government at the highest level, and potentially carry on activities for some time without detection. the thing about having access to a huge number of zerodays your adversaries don't know about is it gives you a massive asymmetric advantage. they did not exploit this to gain power or destabilize the world order. they publicly released the information that they had these capabilities and worked to mitigate these flaws. you should be grateful american frontier labs have proven themselves remarkably trustworthy and concerned with the public good. but it's critical you understand we are in a new regime. private entities now have power that directly rivals and impacts the government's monopoly on influence and violence. and anthropic is certainly not the only one, there's little chance OpenAI's internal models are far behind. this trend will accelerate on virtually every dimension, not slow down. my prediction for how it plays out is the relatively imminent seizure and nationalization of labs by the US government, sometime over the next two years. it's very tough for me to see how they accept the existence of this kind of threat. but this adds a whole new class of governance issues, as then we've handed these extremely wide-reaching capabilities from private entities to public ones.

@ashebytes Whoa

tiny beautiful things: turning your handwriting into font 1. write down a-z, A-Z, 1-9 and punctuation on a piece of paper 2. give it to claude to create a font from 3. pull it into your next project

@emilyswlau @BrighamWomens @MGBWomenHeart Congratulations, Emily!

📢Personal update! ✨Thrilled to share that I’ll be moving my clinical practice to @BrighamWomens as Director of Women’s Heart Health. So grateful to my many mentors, colleagues & friends 🙏. Excited for this next chapter working to advance women’s 🫀 health! @MGBWomenHeart

Absolutely inspirational Patterson plenary lecture on #lungcancerscreening at AATS #ITSOS2025 by @DouglasEWood1!! Dr. Wood has been a relentless advocate and was instrumental in getting #lungcancerscreening covered by health insurance in the US. He also emphasized the need to simplify lung cancer screening guidelines: get rid of 15 years since quit, and use smoking duration instead of pack years to guide eligibility criteria (go w/ #Pottercriteria)

@MaxJordan_N No real way to tease it apart at the moment—we’ve only been able to explain about 10-15% of lung cancer’s heritability with germline genetics (compared with closer to 35-40% in breast cancer). So, it’s the latter: family history is a marker of cumulative risk factors.

@aebchang So interesting. Anyway to tease apart how much of the relative’s cancer is from smoking vs genetics? Or first degree relative implies a combo of shared genes+environment including exposure to 2nd hand smoke?

The cumulative risk of lung cancer among those with >1 first- or second-degree relative is at least as high as (and perhaps even higher than) that among people with a significant smoking history. #WCLC2025 4/5

So impressed with @MaryPasquinelli’s work where she demonstrated that Sybil, an AI algorithm, can accurately predict 6-year #lungcancer risk from one baseline CT scan, in diverse cohorts, with minimal bias!! #WCLC25

@YoungLungCancer Yes, but only if you are coming for a scan (you just need to be 18+ to donate images). Here are the age requirements for those getting a scan through the study.

@aebchang Is there an age requirement for eligibility ?

@SLPChitChat Yes we can screen him for eligibility as well!

@SLPChitChat Send us an email at mghlegacylungstudy@mgb.org and I will add her to our list! When the study opens, we will reach out to screen for eligibility.

@motherofswans @IASLC I’m so sorry for your loss.

@aebchang @IASLC My grandfather, father and uncles all died of lung cancer. I didn’t grow up with any in the same house but in the same city.

Evidence keeps building for the addition of lung cancer family history to #lungcancerscreening criteria. 🧵 #lcsm @IASLC 1/5

One of the biggest influences on my career is Dr. Ross Camidge - a mentor and friend, an intellectual giant in the field of lung cancer who was diagnosed with this unforgiving disease himself. We are all at risk - and must all work to move the field. news.cuanschutz.edu/cancer-center/…

The TALENT study by Dr. Yang and his team in Taiwan continues to demonstrate a significant benefit of #lungcancerscreening among those with a family history of lung cancer, with a clear reduction in stage IV disease. #WCLC2025 @IASLC 3/5

Lung cancer family history is an important risk marker b/c it can reflect the interaction between multiple different exposures (eg, air pollution, radon, etc) and genetics, many of which are shared between relatives. It’s also something we can actually capture in clinic. 2/5

COMPEL(ing) study at #WCLC25. Limitations noted below, but in EGFR+ NSCLC with NON-CNS progression on 1L osi, CONTINUING osi w/ chemo improved outcomes: ▫️PFS: 8.4 vs 4.4 mo (HR 0.43) ▫️Fewer new brain mets: 10% vs 27% Osi to remain our backbone across lines? #WCLC25 @IASLC

A labor of love! @MaryPasquinelli masterfully explaining how we implemented Sybil, a machine learning model of lung cancer risk, at @UICancerCenter @UIHealth . Would not be possible without the Sybil implementation consortium. @LeciaSequist @F_Fintelmann_MD @aebchang @reginabard