Voice cleared chance, barely (random forest, AUC 0.63, permutation p = .049). Ventral striatal BOLD did not (logistic regression, AUC 0.58, p = .057). The two are statistically non-inferior to each other, which is a statement about how modest both are.
Fig. — AUC-ROC with 95% bootstrap CI, stratified 5-fold CV. Primary preregistered analysis. Voice: eGeMAPSv02, diarized participant speech · DAIC-WOZ, n=142. fMRI: Nucleus accumbens BOLD, BART · ds000030, n=234. The voice result is borderline: p = .049 uncorrected, and it does not survive Bonferroni correction for three classifiers (α/3 = .017). Independent cohorts and different anhedonia instruments (PHQ-8 items 1–2 vs Chapman), so this is a benchmark across datasets, not a within-subject comparison. Both streams overfit heavily (train AUC 1.0, gap > 0.35) on 447 features and 32 positive cases. Stream B is also pipeline-dependent: fMRIPrep 23.x gives 0.45, below chance. Preregistered at osf.io/4d6ey.
PRAXIS
Psychiatry Research, Analytics & eXperimental Innovation Society
From theory into tools that reach patients.
An undergraduate research group at USC working where machine learning meets clinical mental health. I founded it in February 2026 and lead it: we run original studies, preregister them, and publish what we find including the results that come back null.
Founded
Feb 2026
Host
USC Dornsife
Sponsor
Dr. Laurent Itti
My role
Founder, project lead
Original research applying machine learning to clinical populations, preregistered on OSF before the data are touched.
A twenty-paper journal-club curriculum taking undergraduates from the founding papers of the field through to algorithmic bias.
A biweekly speaker series, including researchers from the NIMH.
Open-source code and computational psychiatry resources, so the methods can be checked by anyone who wants to check them.
My father lost his vision to retinal detachment. He cannot fill out a visual analog scale, which is how most of psychiatry still measures how a person feels. I build instruments that do not require the patient to be a reliable narrator of their own symptoms.
ModelRead Lab · USC
A Rescorla-Wagner simulation of how reward learning collapses when the dopaminergic learning rate falls and effort stops being worth spending.
Whether that collapse is audible. An open-source pipeline that pulls acoustic biomarkers out of clinical interviews without the audio ever leaving the room.
What the circuit is doing while it happens. MEG source localization, gamma-band power, and signal complexity in the insula as a marker of suicidal ideation.
Local-first, air-gapped clinical interview transcription and speech-biomarker pipeline. Whisper for transcription, pyannote for diarisation, OpenSMILE for eGeMAPS features.
Computational Psychiatry: An Undergraduate Syllabus
The curriculum PRAXIS runs, written to take an undergraduate from the founding papers of the field through reinforcement learning, Bayesian models of psychosis, and biomarker methodology to algorithmic bias in clinical prediction. Every reading is linked to its publisher record, English and Simplified Chinese, citable by DOI.