Christian Webb, PhD
@christianwebb.bsky.social
Associate Professor | Harvard Medical School
Co-Director | Center for Depression, Anxiety, & Stress Research
Director | Treatment & Etiology of Depression in Youth Lab | McLean Hospital | www.WebbsLab.com
McGill & UPenn alum | Canadian in Boston
Co-Director | Center for Depression, Anxiety, & Stress Research
Director | Treatment & Etiology of Depression in Youth Lab | McLean Hospital | www.WebbsLab.com
McGill & UPenn alum | Canadian in Boston
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/
💡 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/
November 7, 2025 at 9:23 PM
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/
💡 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/
📢 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
🔗 tinyurl.com/532y6v67
October 22, 2025 at 2:07 PM
📢 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
🔗 tinyurl.com/532y6v67
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. 🇬🇧🎓
October 12, 2025 at 10:13 AM
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. 🇬🇧🎓
@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.
September 16, 2025 at 1:48 PM
@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.
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
September 12, 2025 at 8:30 PM
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
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
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
August 22, 2025 at 8:13 PM
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
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
If you’re heading to @sprofficial.bsky.social meeting in Krakow, check out our panels on tech, personalization, & precision in psychotherapy!
📱 Enhancing Clinical Practice w/ EMA (Fri, 11:30am)
📊 Innovations in Personalization/Precision in Therapy (Sat, 2pm)
🧠 Neuroscience in Therapy (Sat, 3:15pm)
📱 Enhancing Clinical Practice w/ EMA (Fri, 11:30am)
📊 Innovations in Personalization/Precision in Therapy (Sat, 2pm)
🧠 Neuroscience in Therapy (Sat, 3:15pm)
June 24, 2025 at 4:30 PM
If you’re heading to @sprofficial.bsky.social meeting in Krakow, check out our panels on tech, personalization, & precision in psychotherapy!
📱 Enhancing Clinical Practice w/ EMA (Fri, 11:30am)
📊 Innovations in Personalization/Precision in Therapy (Sat, 2pm)
🧠 Neuroscience in Therapy (Sat, 3:15pm)
📱 Enhancing Clinical Practice w/ EMA (Fri, 11:30am)
📊 Innovations in Personalization/Precision in Therapy (Sat, 2pm)
🧠 Neuroscience in Therapy (Sat, 3:15pm)
Smartphone location (GPS) variables were the most predictive features overall. Critically, there was LOTS of heterogeneity between individuals in the association between smartphone features and negative emotional states. 4/n
May 19, 2025 at 9:15 PM
Smartphone location (GPS) variables were the most predictive features overall. Critically, there was LOTS of heterogeneity between individuals in the association between smartphone features and negative emotional states. 4/n
The ensemble ML approach (i.e., which involved a data-driven search of the optimal combination of subject-specific models) outperformed a fully idiographic model (i.e., person-specific models that do not borrow any information from other individuals’ models). 3/n
May 19, 2025 at 9:15 PM
The ensemble ML approach (i.e., which involved a data-driven search of the optimal combination of subject-specific models) outperformed a fully idiographic model (i.e., person-specific models that do not borrow any information from other individuals’ models). 3/n
A personalized ensemble ML algorithm outperformed other statistical approaches (including simpler models), achieving an AUC of 0.72 (for irritability) - 0.79 (for loneliness) in predicting different negative emotions 2/n
May 19, 2025 at 9:14 PM
A personalized ensemble ML algorithm outperformed other statistical approaches (including simpler models), achieving an AUC of 0.72 (for irritability) - 0.79 (for loneliness) in predicting different negative emotions 2/n
🚨New Postdoc Opportunity
We have an opening for a postdoc jointly mentored by
Justin Baker and me for work on digital therapeutics and passive sensing using smartphones and wearables (smartwatches + smart rings). More info 👉: webbslab.com/job-postings
Please RT & share!
We have an opening for a postdoc jointly mentored by
Justin Baker and me for work on digital therapeutics and passive sensing using smartphones and wearables (smartwatches + smart rings). More info 👉: webbslab.com/job-postings
Please RT & share!
May 5, 2025 at 8:30 PM
🚨New Postdoc Opportunity
We have an opening for a postdoc jointly mentored by
Justin Baker and me for work on digital therapeutics and passive sensing using smartphones and wearables (smartwatches + smart rings). More info 👉: webbslab.com/job-postings
Please RT & share!
We have an opening for a postdoc jointly mentored by
Justin Baker and me for work on digital therapeutics and passive sensing using smartphones and wearables (smartwatches + smart rings). More info 👉: webbslab.com/job-postings
Please RT & share!
Excited and grateful to have received an R01 to expand our lab's work using passively collected data from smartphones and wearables to detect negative emotional states and predict depression risk in youth (working w/ Justin Baker, Habib Rahimi, and Boyu Ren)
April 2, 2025 at 6:56 PM
Excited and grateful to have received an R01 to expand our lab's work using passively collected data from smartphones and wearables to detect negative emotional states and predict depression risk in youth (working w/ Justin Baker, Habib Rahimi, and Boyu Ren)
If you're attending the ADAA conference in Vegas this week and you're interested in smartphone-delivered mindfulness interventions for youth with depression and anxiety come check out our Saturday symposium!
April 2, 2025 at 6:54 PM
If you're attending the ADAA conference in Vegas this week and you're interested in smartphone-delivered mindfulness interventions for youth with depression and anxiety come check out our Saturday symposium!
I have the exact same tea, but I just rip off the whole side of the box like a barbarian (the organic turmeric and ginger tea-drinking kind)
March 5, 2025 at 2:48 PM
I have the exact same tea, but I just rip off the whole side of the box like a barbarian (the organic turmeric and ginger tea-drinking kind)
Honored and excited to be speaking at the UCLA STAND ALACRITY Center tomorrow. If interested in learning more about our work on depression treatment in youth, register here to join: lnkd.in/eAwEvPVY
December 17, 2024 at 9:56 PM
Honored and excited to be speaking at the UCLA STAND ALACRITY Center tomorrow. If interested in learning more about our work on depression treatment in youth, register here to join: lnkd.in/eAwEvPVY
If you're at #ACNP2024 come see our panel on new developments in research on affect disruption in adolescent affective disorders w/ Dr. Forbes, Kaiser and Gupta
@acnporg.bsky.social
@acnporg.bsky.social
December 6, 2024 at 2:36 AM
If you're at #ACNP2024 come see our panel on new developments in research on affect disruption in adolescent affective disorders w/ Dr. Forbes, Kaiser and Gupta
@acnporg.bsky.social
@acnporg.bsky.social
New large study (n ~ 6 million) in @JAMApsych tracking mental disorder trends in Denmark showing increases in mood disorders in recent birth cohorts tinyurl.com/c5nyfd8k
November 27, 2024 at 9:08 PM
New large study (n ~ 6 million) in @JAMApsych tracking mental disorder trends in Denmark showing increases in mood disorders in recent birth cohorts tinyurl.com/c5nyfd8k
if you're still around #ABCT Sunday AM and are a fan of digital phenotyping, come check out our symposium "New Research Findings in Digital Phenotyping of Psychological Phenomena" w/ Drs. Mohr, Jacobson, Weingarden, Pedrelli and Stamatis.
November 14, 2024 at 2:33 PM
if you're still around #ABCT Sunday AM and are a fan of digital phenotyping, come check out our symposium "New Research Findings in Digital Phenotyping of Psychological Phenomena" w/ Drs. Mohr, Jacobson, Weingarden, Pedrelli and Stamatis.
If you're at SPR Brno later this week come join us at our semi-plenary on Digital Technologies & AI in Psychotherapy w/ Drs. Jaime Delgadillo, Zac Imel, Brian Schwartz, and Derek Richards
September 9, 2024 at 8:22 PM
If you're at SPR Brno later this week come join us at our semi-plenary on Digital Technologies & AI in Psychotherapy w/ Drs. Jaime Delgadillo, Zac Imel, Brian Schwartz, and Derek Richards
Smartphone location (GPS) variables were the most predictive features overall. Critically, there was LOTS of heterogeneity between individuals in the association between smartphone features and negative emotional states. 4/n
July 19, 2024 at 8:47 PM
Smartphone location (GPS) variables were the most predictive features overall. Critically, there was LOTS of heterogeneity between individuals in the association between smartphone features and negative emotional states. 4/n
The ensemble ML approach (i.e., which involved a data-driven search of the optimal combination of subject-specific models) outperformed a fully idiographic model (i.e., person-specific models that do not borrow any information from other individuals’ models). 3/n
July 19, 2024 at 8:47 PM
The ensemble ML approach (i.e., which involved a data-driven search of the optimal combination of subject-specific models) outperformed a fully idiographic model (i.e., person-specific models that do not borrow any information from other individuals’ models). 3/n
A personalized ensemble ML algorithm outperformed other statistical approaches (including simpler models), achieving an area under the receiver operating characteristic curve(AUC) of 0.72 (for irritability) -0.79 (for loneliness) in predicting different negative emotions 2/n
July 19, 2024 at 8:47 PM
A personalized ensemble ML algorithm outperformed other statistical approaches (including simpler models), achieving an area under the receiver operating characteristic curve(AUC) of 0.72 (for irritability) -0.79 (for loneliness) in predicting different negative emotions 2/n
Come see lab postdoc Dr. Hadar Fisher present on her work predicting negative emotional states from machine learning applied to teen text data (+ other very interesting talks)
#SPROttawa2024
#SPROttawa2024
June 26, 2024 at 2:58 PM
Come see lab postdoc Dr. Hadar Fisher present on her work predicting negative emotional states from machine learning applied to teen text data (+ other very interesting talks)
#SPROttawa2024
#SPROttawa2024
New study with 700k teens with some evidence that mood, anxiety and eating disorders may be transmitted within adolescent peer networks.
jamanetwork.com/journals/jam...
jamanetwork.com/journals/jam...
May 29, 2024 at 9:18 PM
New study with 700k teens with some evidence that mood, anxiety and eating disorders may be transmitted within adolescent peer networks.
jamanetwork.com/journals/jam...
jamanetwork.com/journals/jam...
Meta-analysis of placebo response. Largest placebo effect in MDD followed by GAD (lowest schizophrenia)
jamanetwork.com/journals/jam...
jamanetwork.com/journals/jam...
May 29, 2024 at 9:17 PM
Meta-analysis of placebo response. Largest placebo effect in MDD followed by GAD (lowest schizophrenia)
jamanetwork.com/journals/jam...
jamanetwork.com/journals/jam...