banner
causalab.bsky.social
CAUSALab
@causalab.bsky.social
3K followers 3 following 260 posts
Actionable #causalinference with real-world impact. We use health data to help decision makers make better decisions. We train investigators at Harvard T.H. Chan School of Public Health. Connect with CAUSALab: https://linktr.ee/causalab
linktr.ee
Posts Media Videos Starter Packs
causalab.bsky.social
CAUSALab @causalab.bsky.social · 2d
“The major takeaway for me is that we can use AI tools to significantly accelerate target trial emulation and the way clinical trials are designed and analyzed” said Piersilvio De Bartolomeis.
causalab.bsky.social
CAUSALab @causalab.bsky.social · 2d
A new editorial in @ai.nejm.org explores how AI computational tools can transform causal analyses.

Researchers examine how AI can support #targettrial emulation, enhance observational data extraction and analysis, and improve efficiency of clinical trials.

🔗 ai.nejm.org/doi/full/10....
New publication: Trial Emulation, Simulation, and Augmentation Using Electronic Health Records and Generative AI
1 1
causalab.bsky.social
CAUSALab @causalab.bsky.social · 7d
Register now to attend next Tuesday's Methods talk 🔎
causalab.bsky.social
CAUSALab @causalab.bsky.social · 15d
2️⃣ weeks! 2025 Methods Series @ki.se continues.

"Promoting the use of causal inference methods in applied health research by integrating causal reasoning into academic curricula: barriers and solutions."

📆 Oct 7, 2025
⏰ 15.00 CEST/9.00 ET
📍 Online

Register 👇
stats.sender.net/forms/e7JD1d...
October 7 Methods Series talk, "Promoting the use of causal inference methods in applied health research by integrating causal reasoning into academic curricula: barriers and solutions "
causalab.bsky.social
CAUSALab @causalab.bsky.social · 15d
2️⃣ weeks! 2025 Methods Series @ki.se continues.

"Promoting the use of causal inference methods in applied health research by integrating causal reasoning into academic curricula: barriers and solutions."

📆 Oct 7, 2025
⏰ 15.00 CEST/9.00 ET
📍 Online

Register 👇
stats.sender.net/forms/e7JD1d...
October 7 Methods Series talk, "Promoting the use of causal inference methods in applied health research by integrating causal reasoning into academic curricula: barriers and solutions "
2 4
causalab.bsky.social
CAUSALab @causalab.bsky.social · 16d
September is in full swing!

CAUSALab kicked off the semester with a team social welcoming new members to our lab. Here's to a fall season full of collaboration and exciting projects ahead!

#causalinference #harvardchan #causalab
CAUSALab Fall 2025 social
2
causalab.bsky.social
CAUSALab @causalab.bsky.social · 21d
Thank you, Epi postdocs!
causalab.bsky.social
CAUSALab @causalab.bsky.social · 22d
Let's talk causal mediation and separable treatments.

Vanessa Didelez (Leibniz Institute for Prevention Research and Epidemiology) continues the 2025 Methods Series @ki.se next week.

📆 Sep 23, 2025
⏰ 15.00 CEST/9.00 ET
📍 Virtual

Register to attend online 👇
stats.sender.net/forms/e7JD1d...
Vanessa Didelez September 23 Methods Series talk, "Causal mediation and separable treatments in time-to-event analyses."
3 8
causalab.bsky.social
CAUSALab @causalab.bsky.social · 23d
Pictured: @chelseaboccagno.bsky.social, @jeremypb.bsky.social, @megcuppbuxton.bsky.social, Juan Gago, Katherine Kurgansky, Jing Li, Katherine Guilin Li, Emma McGee, Rienna Russo, Wenling Zhang
causalab.bsky.social
CAUSALab @causalab.bsky.social · 23d
Today kicks off National Postdoc Appreciation Week!

We are thankful to have a team of incredible postdocs who help make our #causalinference research @hsph.harvard.edu possible.

We appreciate your key contributions & hard work!
#NPAW2025 #causalab #harvardchan #publichealth
National Postdoc Appreciation Week 2025
1 1 3
Reposted by CAUSALab
harvardepi.bsky.social
Harvard Epidemiology @harvardepi.bsky.social · May 23
New publication: Effect of colonoscopy screening on risks of colorectal cancer and related death: instrumental variable estimation of per-protocol effects now in the European Journal of Epidemiology

➡️ Read here: link.springer.com/article/10.1...

#cancer #screening #colorectal
Effect of colonoscopy screening on risks of colorectal cancer and related death: instrumental variable estimation of per-protocol effects - European Journal of Epidemiology
Background We recently reported per-protocol estimates of colonoscopy screening on colorectal cancer incidence and mortality in NordICC, a large-scale randomized trial. Our results may be affected by ...
link.springer.com
2 2 12
causalab.bsky.social
CAUSALab @causalab.bsky.social · 29d
The CAUSALab Methods Series @ki.se is back!

Fall 2025 lineup kicks off Sep 23 with Vanessa Didelez (BIPS), “Causal mediation and separable treatments in time-to-event analyses.”

All talks are virtual, except for Nov. 4, 2025 hybrid session.

Learn more & register:
hsph.harvard.edu/research/cau...
https://hsph.harvard.edu/research/causalab/seminars/
4 9
Reposted by CAUSALab
miguelhernan.org
Miguel Hernan @miguelhernan.org · Sep 3
When using observational data for #causalinference, the choice isn’t between emulating or not emulating a #TargetTrial, but between reporting or not reporting the target trial that we are emulating.

For those who prefer to be explicit about what they do, we have developed the TARGET Statement 👇
hjhansford.bsky.social
hjhansford.bsky.social @hjhansford.bsky.social · Sep 3
🎯 TARGET Guideline published 🎉

TARGET is a reporting guideline for observational studies of interventions that use the target trial framework.

Over 3 years the @TARGETGuideline was rigorously developed and was co-published today in @jama.com & @bmj.com

doi.org/10.1001/jama.2025.13350

#episky
1 7 21
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 4
Fall applications are OPEN for CAUSALab Clinics!

Free #causalinference consulting open to Boston-based, junior clinical investigators. Postdoc fellows provide guidance pertaining to #studydesign, data analysis and results for works in progress.

Learn more & apply:
hsph.harvard.edu/research/cau...
Fall 2025 CAUSALab Clinics dates
1 1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
(9/9) Learn more about CSRP: csrp.mgh.harvard.edu/about/

See a list of mental health resources compiled by CSRP: csrp.mgh.harvard.edu/resources/
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
(8/9) CSRP is holding its 2nd annual conference September 9th, 2025. Topics include suicide prevention for service members, AI and ethics in suicide prevention, and more. Registration is free & open to the public. Register: partners.zoom.us/webinar/regi...
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
🌟Center for Suicide Research and Prevention 🌟
(7/9) @csrp.bsky.social is a center committed to advancing innovative suicide prevention research, including prediction and prevention. CSRP also collaborates directly with clinicians working in healthcare settings with at-risk patients.
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
(6/9) FEP-CAUSAL aims to identify effective interventions—such as suicide prevention strategies—to guide treatment decisions for patients with FEP, particularly in contexts where randomized trials are lacking. Learn more: hsph.harvard.edu/research/cau...
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
🌟 FEP-CAUSAL 🌟
(5/9) International consortium of prospective studies focused on individuals experiencing a first episode of psychosis (FEP). Coordinated by LEAP’s Methods Core, the team brings together investigators from participating sites and the coordinating center.
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
(4/9) By integrating cutting-edge methodology, real-world data, and collaborative reanalyses of landmark trials, Dr. Szmulewicz is advancing a systemwide, data-driven approach to suicide prevention, particularly for U.S. veterans.
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
(3/9) Recently, he led a reanalysis of VA CSP-590 randomized trial, which had suggested lithium was ineffective in reducing veteran suicide risk. Using causal methods to address issues (treatment non-adherence), his team found evidence of potential protective effect of lithium on suicidality.
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
(2/9) A central component of Alejandro's work utilizes Veterans Health Administration (VA) databases, which provide a rich platform for comparative effectiveness research on suicide death.
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
🌟 Dr. Alejandro Szmulewicz 🌟
(1/9) Faculty member Alejandro Szmulewicz leverages #causalinference methods and large-scale electronic health records (EHR) to advance suicide prevention. He applies #targettrial emulation to assess effectiveness and safety of interventions.
1
causalab.bsky.social
CAUSALab @causalab.bsky.social · Sep 3
It's National Suicide Prevention Month. 💙💜

This year, CAUSALab is shining a spotlight on researchers furthering the field of suicide prevention. (See comments)
National Suicide Prevention Month
1 4
Reposted by CAUSALab
harvardepi.bsky.social
Harvard Epidemiology @harvardepi.bsky.social · Sep 2
Welcome back students! Joining us from 29 different countries hailing from 6 continents across the various degree programs are: 72 PhD students, 15 SM1 students, 13 SM1 summer-only students, 62 SM2 students, and 76 MPH Epi students in the Department of Epidemiology @hsph.harvard.edu.
Image of people walking down the stairs at the front of the Kresge building, Harvard T.H. Chan School of Public Health, Boston, MA. Welcome back sign.
4 4
Reposted by CAUSALab
myramcguinness.bsky.social
Myra McGuinness @myramcguinness.bsky.social · Aug 11
September @vicbiostat.bsky.social seminar:

Camila Olarte Parra from @causalab.bsky.social Karolinska will speak on combining information from trial participants and non-participants in registry-based trials.

All welcome online 25 September.

More info:
www.vicbiostat.org.au/event/combin...
Combining information from trial participants and non-participants in registry-based trials
Even though the advantages of randomised tria
www.vicbiostat.org.au
3 6