RESUMO
[This corrects the article DOI: 10.3389/fpubh.2021.763621.].
RESUMO
Health-related data being collected by smartphones offer a promising complementary approach to in-clinic assessments. Despite recent contributions, the trade-off between privacy, optimization, stability and research-grade data quality is not well met by existing platforms. Here we introduce the JTrack platform as a secure, reliable and extendable open-source solution for remote monitoring in daily-life and digital-phenotyping. JTrack is an open-source (released under open-source Apache 2.0 licenses) platform for remote assessment of digital biomarkers (DB) in neurological, psychiatric and other indications. JTrack is developed and maintained to comply with security, privacy and the General Data Protection Regulation (GDPR) requirements. A wide range of anonymized measurements from motion-sensors, social and physical activities and geolocation information can be collected in either active or passive modes by using JTrack Android-based smartphone application. JTrack also provides an online study management dashboard to monitor data collection across studies. To facilitate scaling, reproducibility, data management and sharing we integrated DataLad as a data management infrastructure. Smartphone-based Digital Biomarker data may provide valuable insight into daily-life behaviour in health and disease. As illustrated using sample data, JTrack provides as an easy and reliable open-source solution for collection of such information.
Assuntos
Aplicativos Móveis , Biomarcadores , Reprodutibilidade dos Testes , SmartphoneRESUMO
BACKGROUND: Disentangling psychopathological heterogeneity in schizophrenia is challenging, and previous results remain inconclusive. We employed advanced machine learning to identify a stable and generalizable factorization of the Positive and Negative Syndrome Scale and used it to identify psychopathological subtypes as well as their neurobiological differentiations. METHODS: Positive and Negative Syndrome Scale data from the Pharmacotherapy Monitoring and Outcome Survey cohort (1545 patients; 586 followed up after 1.35 ± 0.70 years) were used for learning the factor structure by an orthonormal projective non-negative factorization. An international sample, pooled from 9 medical centers across Europe, the United States, and Asia (490 patients), was used for validation. Patients were clustered into psychopathological subtypes based on the identified factor structure, and the neurobiological divergence between the subtypes was assessed by classification analysis on functional magnetic resonance imaging connectivity patterns. RESULTS: A 4-factor structure representing negative, positive, affective, and cognitive symptoms was identified as the most stable and generalizable representation of psychopathology. It showed higher internal consistency than the original Positive and Negative Syndrome Scale subscales and previously proposed factor models. Based on this representation, the positive-negative dichotomy was confirmed as the (only) robust psychopathological subtypes, and these subtypes were longitudinally stable in about 80% of the repeatedly assessed patients. Finally, the individual subtype could be predicted with good accuracy from functional connectivity profiles of the ventromedial frontal cortex, temporoparietal junction, and precuneus. CONCLUSIONS: Machine learning applied to multisite data with cross-validation yielded a factorization generalizable across populations and medical systems. Together with subtyping and the demonstrated ability to predict subtype membership from neuroimaging data, this work further disentangles the heterogeneity in schizophrenia.
