a group of men are dancing with the words bye bye bye in the background ALT: a group of men are dancing with the words bye bye bye in the background

So long, Blue Sky! I'm consolidating my social media presence and planning to no longer actively post here. Please follow me on LinkedIn:
www.linkedin.com/in/sunnyxtang/

Can we automate clinical assessment of thought disorder by finetuning an #LLM? Come find out at our #ACNP2026 poster this evening (Tue) #12!

Shhhhh! I know you're not supposed to choose favorites as a PI, but I might be attending #ACNP2026 with my favorite @stanglab.bsky.social member 🥰🤪🤩.

North Shore Therapeutics Digital Therapeutics for serious mental illness

This work was funded and completed by North Shore Therapeutics, a startup company I co-founded. Really proud of our team: Moein Foroughi, @drbrinen.bsky.social, Michael Birnbaum, @sarahberretta.bsky.social , @leilyb.bsky.social, John Kane, Ed Yoon, and Bill Cronin... 5/5
northshore.health

We observed small shifts in defeatist beliefs and self-esteem in the intended directions. More impressively, at 1-week follow-up, the overwhelming majority of participants (90%) reported making progress in at least one of the real-life tasks they had identified... 4/5

20 participants tried a single session with a researcher, and then were asked to use it on their own for 1 week with no additional incentives. The app was feasible and acceptable with 19 of the 20 participants able to access and willing to use it on their own ... 3/5

The prototype for NST-SPARK delivers a single session of treatment - eliciting unhelpful beliefs that exacerbate negative symptoms, then providing alternative adaptive beliefs that are reinforced with behavioral experiments carried out via AR... 2/5

Preliminary Findings From an Augmented Reality (AR) App Delivering Recovery‐Oriented Cognitive Therapy for Negative Symptoms in Schizophrenia Background NST-SPARK is a novel digital therapeutic targeting negative symptoms in schizophrenia spectrum disorders (SSD). It is a smartphone application delivering recovery-oriented cognitive thera...

#NewPaperAlert 😎! We developed a prototype for an Augmented Reality (#AR) smartphone app (NST-SPARK) that delivers recovery-oriented cognitive therapy targeting negative symptoms of schizophrenia and completed a preliminary study... 1/5
dx.doi.org/10.1111/eip....

And congrats to our coauthors: Yan Cong, Aarush Mehta, Amir Nikzad, @sarahberretta.bsky.social, @leilyb.bsky.social, @myl1947.bsky.social. 5/5

And also distinctive patterns for latency, whereas pause was similar between SSD and depression. 4/5

And there was a graded effect on number of semantic clusters. But there was a more distinctive pattern for people with schizophrenia spectrum disorders on the size of semantic clusters... 3/5

We found a graded effect on fluency performance... 2/5

New paper alert! Check out our new manuscript in @SchizRes Cognition, led by Sunghye Cho. Here we used automated speech and language analysis to compare verbal fluency responses from people with psychosis, depression, and healthy controls. 1/5
lnkd.in/eg8Y-gGJ

Grateful to the press team at @northwellhealth.bsky.social for the lovely feature on my recent R01! Thanks for doing so much to raise the visibility of our science. Couldn't do this without our fantastic team, past and present.
feinstein.northwell.edu/news/the-lat...

‘There Will Always Only Be One Jane Goodall’

I'm saddened this morning by the death of Jane Goodall. Growing up as a little girl in the 90's, she was one of two women scientists (+Marie Curie) who had a real presence as role models. I feel very grateful that now, there are so many more.
www.nytimes.com/2025/10/01/s...

Congrats to Aarush Mehta from our lab on his first first-author publication! He started working with us as a high school student and is now a senior at
@stonybrooku.bsky.social. Thanks to coauthors:
Amir Nikzad, Yan Cong, Sunghye Cho, Sameer Pradhan
4/4

A negative relationship between Happiness and Thought Disturbance and a positive relationship between Anger and Hostile Suspiciousness were replicated across samples... 3/4

A negative relationship between Dominance and Anxious Depression symptoms and a positive relationship between Surprise and Hostile Suspiciousness were replicated across timepoints.... 2/4

Glad to share our new article out in
Cognitive Neuropsychiatry! We assessed relationships between symptoms and sentiment in speech during picture descriptions from people with psychosis across 2 cohorts and 2 timepoints... 1/4

doi.org/10.1080/1354...

Very honored for our work (with Julianna Olah) to be featured by @bbrfoundation.bsky.social! We showed that a brief speech sample could provide meaningful signal informing on psychosis-related disorders. Original publication in Translational Psychiatry.
bbrfoundation.org/content/5-mi...

Super stoked to share that we received the #NOA for our R01!!! We will be using speech and language markers to develop personalized, adaptive markers for #psychosis. Very grateful for the support from the NIMH.

🔍 By analyzing both linguistic and paralinguistic speech characteristics, our approach demonstrated robust disorder-specific learning across multiple groups, including those with sub-clinical psychotic experiences & major depressive disorder. 📊 #PrecisionMedicine 3/3

The machine learning model achieved 86% accuracy distinguishing conditions on the schizophrenia-bipolar spectrum using speech features. 2/3

Detecting schizophrenia, bipolar disorder, psychosis vulnerability and major depressive disorder from 5 minutes of online-collected speech - Translational Psychiatry Translational Psychiatry - Detecting schizophrenia, bipolar disorder, psychosis vulnerability and major depressive disorder from 5 minutes of online-collected speech

🚨 New findings from a study led by Juliana Olah! Our recent study highlights the potential of 5-minute remote speech assessments to accurately diagnose complex mental health conditions, including schizophrenia, bipolar disorder, and MDD. 🧠💬 1/3 www.nature.com/articles/s41...

Check it out! Our work on using automated speech and language features for longitudinal modeling of #psychosis symptoms is featured in this podcast-style summary from
@dpn-journal.bsky.social !

Correcting the tag here ;) @dpn-journal.bsky.social. Thanks for publishing our work! What a great venue for research on digital psychiatry and neuroscience.

Many thanks to wonderful collaborators as always!! 6/6

@mspilka.bsky.social, Majnu John, @michaelbirnbaum.bsky.social, Ema Saito, @sarahberretta.bsky.social, @leilyb.bsky.social, ‪@myl1947.bsky.social‬, Anil Malhotra, Bill Simpson, John Kane @northwellhealth.bsky.social

Thought Disorder was particularly related to features describing subordinated constructions, efficient identification of picture elements, and decreased semantic distance between sentences. Negative Symptoms was related to features describing decreased speech complexity. 5/6

Examining one feature at-a-time, we can identify quite a few which predict each of the psychosis symptoms domains at a significance level that survives corrections for multiple comparisons. These relationships were largely robust to interactions with gender andrace. 4/6

A single component score representing the 357 speech and language features significantly predicted psychosis symptoms over time for all three domains. 3/6