Christian Webb, PhD

Join us at the Technology in Psychiatry Summit (TIPS) #TIPS2025! Dec 11–12 | Virtual | 11 AM–5 PM ET

💡 Topics:
• AI-driven mental health apps
• LLMs in dementia caregiving
• Digital Navigators bridging tech + care
• AI for eating-disorder treatment
...& much more

🔗 tips.societyconference.com/v2/

Check out this write-up of a recent DPN article from @bbrfoundation.bsky.social highlighting BBRF awardees @christianwebb.bsky.social, @erika-forbes.bsky.social, and @diegopizzagalli.bsky.social. Congrats!

bbrfoundation.org/content/smar...

Smartphone Sensors + ChatGPT Successfully Tracked & Predicted Symptoms in Adolescents with Anhedonia | Brain & Behavior Research Foundation The ubiquity of smartphones and the rapid advance and widespread public adoption of “AI” tools like ChatGPT (especially among the young) have raised hopes among some researchers that such technologies...

Thanks to @bbrfoundation.bsky.social for highlighting our lab's study (led by @hadarfisher.bsky.social & @nigeljaffe.bsky.social) using📱smartphone sensors + LLM-derived text ratings to track behavioral activation and symptom change in teens with anhedonia.
bbrfoundation.org/content/smar...

📢 New large study of ~1.5 million patients in NHS Talking Therapies finds that teens/young adults (ages 16-24) had 17-26% *lower* odds of reliably improving vs 25-65 year-olds. Time to rethink youth-centred mental-health delivery?
🔗 tinyurl.com/532y6v67

Great work Hadar!

Now out in NPP – Digital Psychiatry and Neuroscience! 📱🧠

Can LLMs and smartphone sensing help us track therapy progress in real time?

🆕 study by @hadarfisher.bsky.social @nigeljaffe.bsky.social @diegopizzagalli.bsky.social @christianwebb.bsky.social tested whether smartphone mobility sensing & LLM ratings of text can track behavioral activation in teens to boost engagement in rewarding activities

www.nature.com/articles/s44...

Grateful to @willemkuyken.bsky.social for being such a gracious host and insightful guide at Oxford — and to Jamie Delgadillo for the same at King’s College London. Inspiring conversations, wonderful campuses, and a fantastic trip all around. 🇬🇧🎓

Balfour Mount, who revolutionized end-of-life care, died at palliative unit named in his honour | CBC News Mount devoted his life to caring for others and alleviating suffering. In interviews, his family and colleagues remembered him as both deeply compassionate and as a fierce advocate for the humanity of...

"Dr. Balfour Mount, who coined the term 'palliative care' and whose profound empathy helped revolutionize health-care in North America, died peacefully on Sept. 25 at the palliative care unit that bears his name." www.cbc.ca/news/canada/...

@mcleanhospital.bsky.social Technology in Psychiatry Summit #TIPS returns this year Dec 11-12. We have exciting keynotes lined up, including Drs. Pattie Maes (MIT Media Lab), Isaac Galatzer-Levy (Google DeepMind), and Derrick Hull (Slingshot AI). Submissions are now open. See below for info.

collab w/ the wonderful @sgoldbergphd.bsky.social @lorihilt.bsky.social @hadarfisher.bsky.social @carolineswords.bsky.social and Dan Bolt

Conventional self-report and EMA measures of rumination provide distinct and clinically meaningful information. When deciding to use EMA in intervention studies, researchers should carefully consider the psychometric properties of their measures and the precise construct they intend to capture

We found larger changes in rumination for the conventional self-report measures relative to EMA. Notably, change in both self-report and EMA rumination accounted for unique variance in overall depressive symptom improvement, demonstrating incremental predictive validity. 5/n

Conventional self-report and EMA rumination were only modestly correlated, particularly w/ regards to change over time, which may be due to the lower reliability of change scores and that they tap different “selves” (e.g., experiencing vs. remembering self) 4/n

While the reliability of both conventional self-report rumination (at baseline and post-intervention) and mean EMA rumination scores were high, we found a substantial decline in reliability when assessing change over time, especially for EMA. 3/n

We analyzed data from 4 app-based meditation trials (N=412) to assess the reliability, validity, and sensitivity to change of conventional retrospective self-report vs. EMA measures of improvement in rumination. 2/n

Ecological Momentary Assessment as a Measure of Intervention Change: Evaluation in 4 Digital Mental Health Trials Background: Ecological momentary assessment (EMA) is increasingly being incorporated into intervention studies to acquire a more fine-grained and ecologically valid assessment of change. The added uti...

📱EMA is increasingly used in intervention studies to acquire a more fine-grained and ecologically valid assessment of change. But EMA is relatively burdensome. What's the added value? We tried to address this question in our new paper now out @jmirpub.bsky.social www.jmir.org/2025/1/e69297 1/n

There is still time to submit your symposium, workshop, or poster for the 2025 Technology in Psychiatry Summit (TIPS). Submission deadline is Oct 9. TIPS is taking place virtually as a 2-day meeting Dec 11th and 12th, 2025. #TIPS #technologyinpsychiatry

Link: techinpsych.org

Thanks, Charly. in general it was teens with lower levels of symptoms (e.g., fewer emotional difficulties (SDQ), lower depressive symptoms (CESD), and less executive function difficulties (BRIEF)). Details in the paper

Preprint now available here: osf.io/preprints/ps...

🚨 New research alert

We applied machine learning to the large MYRIAD trial (84 schools and 8,376 UK teens) to ask:

👉 Which adolescents benefit most from mindfulness delivered in schools?

Bottom line: One-size-fits-all doesn’t work.

Paper link: tinyurl.com/vvpvfunh

1/n

Coauthors @willemkuyken.bsky.social @hinzeverena.bsky.social and bluesky-less Drs. Ren, Dalgeish, Ford, Greenberg, and Montero-Marin (hope not missing any bluesky accounts)

Focusing only on individual-level interventions risks overlooking broader influences. Future precision prevention should integrate multilevel data—capturing both individual and contextual drivers of outcomes.
6/n

Youth mental health ≠ just individual factors.
School climate, poverty & inequities matter too.
Prevention must move beyond one-size-fits-all to integrate both personal + systemic influences.
5/n

Machine learning can identify which adolescents are more likely to benefit from SBMT vs. TAU.

This may point to a path toward precision prevention in schools. Next step: prospective trials testing whether algorithm-guided intervention assignment improves outcomes. 4/n

We used ML on baseline student + school characteristics to predict change in depression in SBMT vs. TAU.

Results:
• 19% of students fared better with SBMT (d = 0.22)
• 37% fared better with TAU (d = 0.22)
• Compared to negligible average between-group effects in the trial (d = 0.03)
3/n

Are We Talking Too Much About Mental Health? (Published 2024)

The MYRIAD trial compared school-based mindfulness training (SBMT) vs. teaching as usual (TAU) in > 8,000 teens in 84 UK schools. SBMT did *not* outperform TAU in the overall trial. Background via NYT: www.nytimes.com/2024/05/06/h... 2/n

🚨 New research alert

We applied machine learning to the large MYRIAD trial (84 schools and 8,376 UK teens) to ask:

👉 Which adolescents benefit most from mindfulness delivered in schools?

Bottom line: One-size-fits-all doesn’t work.

Paper link: tinyurl.com/vvpvfunh

1/n

Postdoctoral Research Scholar, The Cognition, Affect, and Temperament Lab, College of the Liberal Arts, Department of Psychology-2 APPLICATION INSTRUCTIONS: CURRENT PENN STATE EMPLOYEE (faculty, staff, technical service, or student), please login to Workday to complete the internal application process. Please do not apply here, a...

My lab has an open post-doc position!

We will begin reviewing applications as they come in.

The post-doc will work with a vibrant research team at Penn State in the Department of Psychology and the Child Study Center.

psu.wd1.myworkdayjobs.com/PSU_Academic...

1/3

Large Language Models are Advanced Anonymizers Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, ...

Does your uni have any firewalled LLMs (contained in your institution and doesn't share data with the web/AI companies). Maybe some LLM solution like arxiv.org/abs/2402.13846
Hadar may have more ideas (she's traveling). Julian Rubel or Justin Baker may have thoughts too. Happy to reach out to them