Ecological Assessment of Transdiagnostic Clinical Symptoms in Serious Mental Illness with Daily Smartphone Surveys
Chung, Y.; Gillis, B. W.; Rahimi-Eichi, H.; Holstein, V.; Girard, J. M.; Rauch, S. L.; Ongur, D.; Liebenthal, E.; Baker, J. T.
Show abstract
Clinical symptoms in serious mental illness (SMI) fluctuate dynamically, yet standard interview-based assessments often fail to capture these daily changes. Smartphone-based ecological surveys offer a scalable approach to monitoring symptoms in naturalistic settings. We analyzed longitudinal data from 56 outpatients with psychotic or affective disorders who completed 12,984 daily surveys and 1,028 clinical assessments over one year. Machine learning models showed that smartphone surveys moderately estimated Montgomery-[A]sberg Depression Rating Scale (rrm = 0.57; p < 0.001) and Young Mania Rating Scale (rrm = 0.39; p < 0.001) and reliably captured within-person fluctuations. Positive symptoms measured by the Positive and Negative Syndrome Scale were also correlated (rrm = 0.24, p < 0.001), though with variable accuracy across participants. Factor modeling showed strongest convergence in negative affective domains, with symptom severity not affecting adherence. These findings highlight smartphone surveys as an ecologically valid tool for real-time symptom monitoring in SMI.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Predicting involuntary admission following inpatient psychiatric treatment using machine learning trained on electronic health record data 94%
- A computational approach to understanding effort-based decision-making in depression 92%
- Association between loneliness and hippocampal responses to dynamic social stimuli in psychotic disorders 92%
Similar papers in this journal
- Affinity Scores: An Individual-centric Fingerprinting Framework for Neuropsychiatric Disorders 94%
- Predicting remission after internet-delivered psychotherapy in patients with depression using machine learning and multi-modal data 94%
- Metabolic Disturbances, Hemoglobin A1c, and Social Cognition Impairment in Schizophrenia Spectrum Disorders 94%
Similar papers in this journal
- Neurocognitive measures of self-blame and risk prediction models of recurrence in major depressive disorder 92%
- Cerebellar-Prefrontal Connectivity Predicts Negative Symptom Severity Across the Psychosis Spectrum 92%
- Aberrant hierarchical prediction errors are associated with transition to psychosis: A computational single-trial analysis of the mismatch negativity 92%
Similar papers in this journal
- Latent Factors of Language Disturbance and Relationships to Quantitative Speech Features 94%
- Validation of an ICD-code-based case definition for psychotic illness across three health systems 94%
- Can we detect the undetected? Comparing the prodromes of individuals with first episode psychosis detected and undetected by clinical high risk for psychosis services: an electronic health record study 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.