I had a great time giving my first conference talks, sharing my work on depression assessment and digital phenotyping at #APS26BCN! Grateful to my mentor (@depressionlab.bsky.social), my collaborators (Drs. Fried, Allen, Craske, Sachdeva, and many others), and everyone I met and learned from there.

*Everyone* wants to know how we can use intensive longitudinal data to advance predictive models of mental health outcomes! #APS2026BCN @psychscience.bsky.social

3/5 FRI 12:30pm: Discussant in a symposium organized by @dawsonhaddox.bsky.social on "Advancing Predictive Models of Mental Health Outcomes Using Intensive Longitudinal Data". Will make this very brief to make sure presenters get as many questions about their work as possible.

Turns out empirically derived phenotypes (data-driven symptom sets) nested within traditional mental disorders can help reduce diagnostic heterogeneity! We learned so much cool and interesting stuff in this study. I could talk (/post) about it all day, but here’s a few highlights (🧵)

Super interesting read!

1/n Out today in @jamapsychiatry.com: Interpretation Issues With the Patient Health Questionnaire Instructions. We find troubling variability in whether people think they should respond based on the frequency of the Sx or the frequency of being bothered by the Sx. jamanetwork.com/journals/jam...

What a week! After 5 days, the #mitnb workshop has come to an end. We had a keynote on time scales and two workshops on careless responding and reliability. The central part of the workshops were the hackathons. We had super diverse hackathons, all designed to assess measurement in #ESM. (1/4)

We built the openESM database: ▶️60 openly available experience sampling datasets (16K+ participants, 740K+ obs.) in one place ▶️Harmonized (meta-)data, fully open-source software ▶️Filter & search all data, simply download via R/Python Find out more: 🌐 openesmdata.org 📝 doi.org/10.31234/osf...