CTML - Center for Targeted Machine Learning and Causal Inference

Mark your calendars: CTML graduate student researchers Wenxin Zhang, Kaiwen Hou, and Alissa Gordon will be presenting their work next week at the 2025 Joint Statistical Meetings (JSM), held August 2–7 in Nashville, Tennessee. Innovations in causal inference, adaptive study design, and statistical methodology will be highlighted. If you’re attending JSM, don’t miss their sessions—come show your support!

CTML GSRs Wenxin Zhang, Kaiwen Hou, and Alissa Gordon will be presenting their work next week at the 2025 Joint Statistical Meetings (JSM). Innovations in causal inference, adaptive study design, and statistical methodology will be highlighted.
If you’re attending JSM—come show your support!

CTML Visiting Student Researcher alum Carlos Garcia Meixide and CTML co-director Mark van der Laan present a new approach to causal inference. The new paper challenges the traditional assumption-based identification to what can be learned directly from observed data using implied interventions. By leveraging instrumental variable structure and Highly Adaptive Lasso (Hal), the authors propose a transparent G-computation formula that identifies causal effects without needing to specify everything up front.

CTML VSR alum Carlos Meixide and CTML co-director Mark van der Laan present a new approach to causal inference. The new paper challenges the traditional assumption-based identification to what can be learned directly from observed data using implied interventions. Link in bio! 🔗

Utilizing mediation analysis methods developed by CTML, a recent study by the University of Edinburgh in EMBO Molecular Medicine uncovered strong biological signatures linked to ME/CFS (Chronic Fatigue Syndrome).

Utilizing mediation analysis methods developed by #CTML, a recent study by the #UniversityofEdinburgh in #EMBOMolecularMedicine uncovered strong biological signatures linked to ME/CFS (Chronic Fatigue Syndrome).

Click the link here or scan the QR code below! 👉 www.embopress.org/doi/full/10....

CTML Faculty Laura Balzer was honored to present her talk, “Machine Learning in Randomized Trials? We Can & We Should!” at the Statistical Issues in Clinical Trials conference, hosted by the University of Pennsylvania on April 7th. This annual conference addresses active areas of biostatistical research, including important conversations on how to effectively and validly implement covariate adjustment to improve statistical power in randomized trials. Speakers covered topics of broad relevance—such as covariate adjustment in group-sequential and re-randomization designs, complexities of adjustment in the face of missing covariate data, machine learning for covariate selection, and the role of covariate adjustment in the drug and device approval process.

CTML Faculty Laura Balzer presented her talk at the Statistical Issues in Clinical Trials conference. This conference addresses areas of biostatistical research, including conversations on how to effectively & validly implement covariate adjustment to improve statistical power in randomized trials.

Great synergy at Global Health Equity Initiative visit with Gilead Sciences on May 13!

Co-moderated by Gilead's Anand Chokkalingam & UCB's Art Reingold, CTML's Dr. Maya Petersen spoke during “Optimizing Industry-Academic Partnerships to Advance Global Public Health” panel.

Thank you to all the incredible presenters who made the Biostatistics Research Showcase such a success! We were thrilled to feature 10 lightning talks and 9 poster presentations. A heartfelt thank you to all the students, faculty, and staff who attended and supported the event.
#CTML #ucberkeley

CTML Graduate Student Researchers Kaiwen Hou, Wenxin Zhang, Kaitlyn Lee, and Sky Qiu will present their research at the 2025 American Causal Inference Conference (ACIC), taking place in Detroit, Michigan, from May 13 to 16. Kaiwen Hou will lead a short course and present a poster. Wenxin Zhang and Kaitlyn Lee will each give a lightning talk and present a poster. Sky Qiu will also present a poster, contributing to the wide range of CTML research being shared.

CTML Graduate Student Researchers Kaiwen Hou, Wenxin Zhang, Kaitlyn Lee, and Sky Qiu will present their research at the 2025 American Causal Inference Conference (ACIC), taking place in Detroit, Michigan, from May 13 to 16.
#BerkeleyCTML #ACIC2025

Stay for the Biostatistics Poster Presentations on Friday, May 2, 2024, from 3:00–4:00 PM at Berkeley Way West (Room 1102)! Explore innovative research in statistical methodology and health applications from our biostatistics community. All are welcome.

#UCBerkeley #CTML

Join us for the Lightning Talks session at the Biostatistics Research Showcase this Friday, May 2nd from 2:00–3:00 PM at Berkeley Way West (Room 1104)! Come hear rapid-fire presentations from biostatistics researchers on cutting-edge methods in causal inference, machine learning, and public health applications. Open to the biostatistics community. For accessibility accommodations, contact cdasilva@berkeley.edu.

Join us for the Lightning Talks session at the Biostatistics Research Showcase this Friday, May 2nd from 2:00–3:00 PM at Berkeley Way West (Room 1104)! Open to the biostatistics community. For accessibility accommodations, contact cdasilva@berkeley.edu.
#BerkeleyCTML

CTML Graduate Student Researchers Featured at the April 29th Frontiers in Computational Health Conference! Be sure to check out exciting poster presentations by CTML GSRs Sylvia Cheng, Nolan Gunter, Kaiwen Hou, Kaitlyn Lee, and Wenxin Zhang. Their research spans causal inference, machine learning, and statistical methods—driving innovation in precision health.

📣 CTML Graduate Student Researchers Featured at the April 29th Frontiers in Computational Health Conference!

Be sure to check out their exciting poster presentations! Their research spans causal inference, machine learning, and statistical methods—driving innovation in precision health.💡📈

Come and be part of our next seminar discussion on April 30th! Carlos García Meixide, CTML's Visiting Student Researcher, will present his talk on "Causal Inference Via Proxy Interventions." The talk will take place at 12 PM at Berkeley Way West, 5th Floor, Room 5401.

#UCBerkeley #CTML #Berkeley

Come join us for our next talk in our seminar series on April 23rd. Joy Nakato, CTML GSR will present her talk at 12 PM at Berkeley Way West, 5th Floor, Room 5101 (Caravan Room).

Please note the room change this week.

A growing body of epidemiologic research is examining the health effects of social policies. In this area, researchers face multiple challenges to causal inference, because policies are nuanced and rarely randomized, effects are often imprecisely estimated, and distinct subsets of population are affected differently. In this talk, I will discuss a framework for thinking about these challenges, and address two of them in depth: heterogeneity in the effects of policies across population subgroups and treatment-confounder feedback. For each challenge, I will describe the problem, characterize its magnitude, and discuss practical solutions.

On April 16 our CTML Seminar Series welcomes Ellie Matthay, Assistant Professor of Population Health at NYU Grossman School of Medicine. This exciting talk will take place at 12:00PM at Berkeley Way West, 5th Floor, Room 5401. Speaker will be presenting remotely.*

Calling Berkeley Biostatistics students, postdocs & staff! Join us for the Biostatistics Research Showcase!

Visit our website for more details on presentation formats
👉 ctml.berkeley.edu/5225-biostat...

📣 Want to present? Email Jessica Angell (jessica.angell@berkeley.edu) by Friday, April 11th.

CTML is pleased to announce that our graduate researchers will be presenting at the 2025 European Causal Inference Meeting (EuroCIM), taking place in Ghent, Belgium, from April 8–11. Kaitlyn Lee, Alissa Gordon, and Wenxin Zhang will present their research during the conference’s contributed session. We encourage attendees to engage with their work and connect with CTML during these sessions.

CTML graduate researchers Kaitlyn Lee, Alissa Gordon, and Wenxin Zhang will present at the 2025 European Causal Inference Meeting (EuroCIM) in Ghent, Belgium, from April 8–11. Attendees are encouraged to engage with their work and connect with CTML. #EuroCIM2025 #berkeleyctml #Causalinference

Join us next week for another exciting talk in our CTML Seminar Series! CTML GSR, Kirsten Landsiedel will be presenting her talk on "Improving the Efficiency of Estimators for Survival in Resampling Designs." This talk will take place on April 9th at 12:00PM at Berkeley Way West, 5th Floor, Room 5401. You won't want to miss it!

Survival is a key metric for evaluating current standards of care for individuals living with HIV. In resource-limited settings, high rates of loss to follow-up (LTFU) often result in underestimation of mortality when only observed deaths are considered. Resampling, which tracks a subset of LTFU patients to ascertain their outcomes, mitigates bias and improves survival estimates. However, common estimators for survival in resampling designs—such as weighted Kaplan-Meier (KM)—fail to leverage covariate information collected during repeated clinic visits, even though this information is highly predictive of survival. We propose a novel Targeted Maximum Likelihood Estimator (TMLE) for survival in resampling designs, which addresses these limitations by leveraging baseline and longitudinal covariates to achieve greater efficiency. We present: (1) a fully efficient TMLE for data from resampling studies with fixed follow-up time for all participants and (2) an inverse probability of censoring weighted (IPCW) TMLE that accounts for varied follow-up times by stratifying on patients with sufficient follow-up to evaluate survival. This IPCW-TMLE can be made highly efficient through nonparametric or targeted estimation of the follow-up censoring mechanism.

Join us next week for another exciting talk in our CTML Seminar Series! CTML GSR, Kirsten Landsiedel will be presenting her talk on "Improving the Efficiency of Estimators for Survival in Resampling Designs." This talk will take place on April 9th at 12PM at BWW, 5th Fl, Rm 5401. #BerkeleyCTML

Text: Our CTML Seminar Series continues on April 2nd with an exciting talk led by Nolan Gunter on "Improving Finite Sample Performance in Auto-Debiased Causal Neural Networks with RieszDragon." Don't miss this talk taking place at 12:00PM at Berkeley Way West, 5th Floor, Room 5401.

The Riesz representation theorem allows us to express any target parameter as an inner product of a conditional mean and the Riesz representer, sparking new causal inference work to directly estimate the Riesz representer instead of solving for its analytical form. Causal neural networks are a popular choice for double machine learning Riesz regression estimators because they are universal function approximators. However, existing structures poorly estimate the Riesz representer and are susceptible to under-coverage or variance blow up under positivity violations. We propose RieszDragon, a neural network architecture combining Riesz-based regression weighting and collaborative, stratified potential outcome modeling to improve MSE and coverage in finite samples.

Our CTML Seminar Series continues on April 2nd with an exciting talk led by CTML GSR Nolan Gunter on "Improving Finite Sample Performance in Auto-Debiased Causal Neural Networks with RieszDragon." Don't miss this talk taking place at 12:00PM at Berkeley Way West, 5th Fl, Rm 5401.

Text: CTML is thrilled to announce that our graduate researchers will be presenting at the 2025 Eastern North American Region International Biometric Society (ENAR) Conference, taking place in New Orleans, LA, from March 23–26. Sky Qiu and Kirsten Landsiedel will deliver their presentations during the conference's contributed session, while Nolan Gunter will showcase his work in the conference's poster session. We invite attendees to engage with their cutting-edge research and connect with CTML during these exciting sessions!

CTML's graduate researchers will be presenting at the 2025 ENAR Conference! Sky Qiu & Kirsten Landsiedel will deliver their presentations during the conference's contributed session, while Nolan Gunter will showcase his work in the conference's poster session. #ENAR2025 #BerkeleyCTML

Happening This Week!🌟Join us for an engaging session with leading biostatistics experts. Get to know them before the event 🔗 https://ctml.berkeley.edu/31925-biostatistics-career-panel-spring-2025 Date: Wednesday, March 19th Time: 12:00pm-1:30pm (12pm sharp) Location: Berkeley Way West, Rm 5401

Happening This Week!🌟Join us for an engaging session with leading biostatistics experts.

Get to know them before the event
🔗 ctml.berkeley.edu/31925-biosta...

Date: Wednesday, March 19th
Time: 12:00pm-1:30pm (12pm sharp)
Location: Berkeley Way West, Rm 5401

Big Give Is Almost Over! 🚨

There’s still time to support @berkeleyctml.bsky.social’s graduate students as they develop cutting-edge research in causal inference and machine learning to improve public health. 💙💛

Donate today! give.berkeley.edu/fund/FN4309000 #CalBigGive #BerkeleyCTML

Big Give Starts Today at 9 PM! Support the Future of Public Health Innovation by donating to CTML! 💡Your gift today directly supports the students driving these innovations. Be part of the global impact and support our future public health leaders—donate today! 🎉 give.berkeley.edu/fund/FN4309000

Don't miss the next session of the CTML Seminar Series on March 12, where Karissa Huang & Philip Lee will discuss "Surrogate Modeling for Infectious Disease Dynamics Using Machine Learning." This talk will take place from 12:00PM-1:00PM at Berkeley Way West, 5th Floor, Room 5401.

Big Give, UCB's annual fundraiser, is next week on 3/13! Today, we’re spotlighting Wendy, a CTML Biostatistics PhD student! She shares: "Presenting my poster at ACIC offers a valuable opportunity to showcase my project and receive feedback from a broader audience in causal inference. I feel really motivated by the interest from the audience and sincerely appreciate this incredible experience sponsored by CTML." The next breakthroughs in public health and clinical medicine start with cutting-edge research in causal inference and machine learning. Our GSRs are leading the way—join us in supporting their work on March 13th!

🌟 Big Give, UCB's annual fundraiser, is next week on 3/13! Today, we’re spotlighting Wendy, a CTML Biostatistics PhD student! Our GSRs are leading the way—join us in supporting their work on March 13th! 💙 #BigGive #CTML #UCBerkeley

@berkeleyctml.bsky.social Seminar Series continues on March 5th! Join us for an exciting talk on "The Object Bagplot for Non-Euclidean Spaces: A Visualization and Outlier Detection Tool for Hyperbolic Data" by CTML GSR Andy Kim.

Time: 12 - 1 PM
Location: Berkeley Way West, 5th Floor, Room 5401.

Join us on Wednesday, March 19 for an engaging Biostatistics Career Panel! This panel will feature professionals from industry, academia, and government, all sharing their experiences and insights on navigating a career in biostatistics.
#Biostatistics #CareerPanel #Networking #BerkeleyCTML

CTML GSR Kaitlyn Lee will be presenting twice on her work, "RieszBoost: Gradient Boosting for Riesz Regression." Her 1st presentation will take place at the CAMSE-CLIMB Mini-Conference, followed by a 2nd presentation at the CTML Seminar Series. Don't miss this opportunity to check out her research!

Artificial Intelligence–Based Copilots to Generate Causal Evidence While there is growing consensus that real-world data should play a larger role in generating causal evidence for health care, it is less clear whether and how AI can help. Current approaches to AI...

Real world data (RWD) analyses need diverse expertise in medicine/stats/causality. As a result, RWD causal analysis is slow and prone to error. AI tools can help.

Perspective in NEJM AI w/Maya Petersen, @amalaa.bsky.social, Chris Holmes, Mark van der Laan

ai.nejm.org/stoken/defau...