Veith Weilnhammer

Scalable assessments of mental illness, the leading driver of disability worldwide, remain a critical roadblock toward accessible and equitable care. Here, we show that human-computer interactions encode multiple dimensions of self-reported mental health and their changes over time. We introduce MAILA, a MAchine-learning framework for Inferring Latent mental states from digital Activity. We trained MAILA to predict 1.3 million mental-health self-reports from 20,000 cursor and touchscreen recordings recorded in 9,000 online participants. The dataset includes 2,000 individuals assessed longitudinally, 1,500 diagnosed with depression, and 500 with obsessive-compulsive disorder. MAILA tracks dynamic mental states along three orthogonal dimensions, generalizes across contexts, and achieves near-ceiling accuracy when predicting group-level mental health. The model translates from general to clinical populations, identifies individuals living with mental illness, and captures signatures of psychological function that are not conveyed by language. Our results demonstrate how everyday human-computer interactions can power passive, reliable, dynamic, and maximally scalable mental health assessments. The ability to decode mental states at zero marginal cost sets new benchmarks for precision medicine and public health, while raising important questions about privacy, agency, and autonomy online.

Perception integrates external sensory signals with internal predictions that reflect prior knowledge about the world. Previous research suggests that this integration is governed by slow alternations between an external mode, driven by sensory signals, and an internal mode, shaped by prior knowledge. Using a double-blind, placebo-controlled, cross-over experiment in healthy human participants, we investigated the effects of the N-Methyl-D-aspartate receptor (NMDAR) antagonist S-ketamine on the balance between external and internal modes. We found that S-ketamine causes a shift of perception toward the external mode. A case-control study revealed that individuals with paranoid Scz, a disorder repeatedly associated with NMDAR hypofunction, spend more time in the external mode. This NMDAR-dependent increase in the external mode suggests that the symptoms of schizophrenia are caused by recurring dissociations of perception from prior knowledge about the world.

In the search for the neural correlates of consciousness, it has remained controversial whether prefrontal cortex determines what is consciously experienced or, alternatively, serves only complementary functions, such as introspection or action. Here, we provide converging evidence from computational modeling and two functional magnetic resonance imaging experiments that indicated a key role of inferior frontal cortex in detecting perceptual conflicts caused by ambiguous sensory information. Crucially, the detection of perceptual conflicts by prefrontal cortex turned out to be critical in the process of transforming ambiguous sensory information into unambiguous conscious experiences: in a third experiment, disruption of neural activity in inferior frontal cortex through transcranial magnetic stimulation slowed down the updating of conscious experience that occurs in response to perceptual conflicts. These findings show that inferior frontal cortex actively contributes to the resolution of perceptual ambiguities. Prefrontal cortex is thus causally involved in determining the contents of conscious experience.