Dataset Information

Detecting relapse in youth with psychotic disorders utilizing patient-generated and patient-contributed digital data from Facebook.

ABSTRACT: Although most patients who experience a first-episode of psychosis achieve remission of positive psychotic symptoms, relapse is common. Existing relapse evaluation strategies are limited by their reliance on direct and timely contact with professionals, and accurate reporting of symptoms. A method by which to objectively identify early relapse warning signs could facilitate swift intervention. We collected 52,815 Facebook posts across 51 participants with recent onset psychosis (mean age?=?23.96 years; 70.58% male) and applied anomaly detection to explore linguistic and behavioral changes associated with psychotic relapse. We built a one-class classification model that makes patient-specific personalized predictions on risk to relapse. Significant differences were identified in the words posted to Facebook in the month preceding a relapse hospitalization compared to periods of relative health, including increased usage of words belonging to the swear (p?< 0.0001, Wilcoxon signed rank test), anger (p?< 0.001), and death (p?< 0.0001) categories, decreased usage of words belonging to work (p?=?0.00579), friends (p?< 0.0001), and health (p?< 0.0001) categories, as well as a significantly increased use of first (p?< 0.0001) and second-person (p??< 0.001) pronouns. We additionally observed a significant increase in co-tagging (p?< 0.001) and friending (p?< 0.0001) behaviors in the month before a relapse hospitalization. Our classifier achieved a specificity of 0.71 in predicting relapse. Results indicate that social media activity captures objective linguistic and behavioral markers of psychotic relapse in young individuals with recent onset psychosis. Machine-learning models were capable of making personalized predictions of imminent relapse hospitalizations at the patient-specific level.

SUBMITTER: Birnbaum ML

PROVIDER: S-EPMC6779748 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Detecting relapse in youth with psychotic disorders utilizing patient-generated and patient-contributed digital data from Facebook.

Birnbaum M L ML Ernala S K SK Rizvi A F AF Arenare E E R Van Meter A A De Choudhury M M Kane J M JM

NPJ schizophrenia 20191007 1

Although most patients who experience a first-episode of psychosis achieve remission of positive psychotic symptoms, relapse is common. Existing relapse evaluation strategies are limited by their reliance on direct and timely contact with professionals, and accurate reporting of symptoms. A method by which to objectively identify early relapse warning signs could facilitate swift intervention. We collected 52,815 Facebook posts across 51 participants with recent onset psychosis (mean age = 23.96 ...[more]

PMID: 31591400

Similar Datasets

Project description:BackgroundAssociating temporal variation of biomarkers with the onset of psychotic relapse could help demystify the pathogenesis of psychosis as a pathological brain state, while allowing for timely intervention, thus ameliorating clinical outcome. In this systematic review, we evaluated the predictive accuracy of a broad spectrum of biomarkers for psychotic relapse. We also underline methodological concerns, focusing on the value of prospective studies for relapse onset estimation.MethodsFollowing the PRISMA (Preferred Reporting Items for Systematic Review and Meta-Analysis) guidelines, a list of search strings related to biomarkers and relapse was assimilated and run against the PubMed and Scopus databases, yielding a total of 808 unique records. After exclusion of studies related to the distinction of patients from controls or treatment effects, the 42 remaining studies were divided into 5 groups, based on the type of biomarker used as a predictor: the genetic biomarker subgroup (n = 4, or 9%), the blood-based biomarker subgroup (n = 15, or 36%), the neuroimaging biomarker subgroup (n = 10, or 24%), the cognitive-behavioral biomarker subgroup (n = 5, or 12%) and the wearables biomarker subgroup (n = 8, or 19%).ResultsIn the first 4 groups, several factors were found to correlate with the state of relapse, such as the genetic risk profile, Interleukin-6, Vitamin D or panels consisting of multiple markers (blood-based), ventricular volume, grey matter volume in the right hippocampus, various functional connectivity metrics (neuroimaging), working memory and executive function (cognition). In the wearables group, machine learning models were trained based on features such as heart rate, acceleration, and geolocation, which were measured continuously. While the achieved predictive accuracy differed compared to chance, its power was moderate (max reported AUC = 0.77).DiscussionThe first 4 groups revealed risk factors, but cross-sectional designs or sparse sampling in prospective studies did not allow for relapse onset estimations. Studies involving wearables provide more concrete predictions of relapse but utilized markers such as geolocation do not advance pathophysiological understanding. A combination of the two approaches is warranted to fully understand and predict relapse.

Project description:We examined whether self-generated (status updates) or other-generated (wall-posts) information on Facebook influenced the impression formed of the target individual. Along with examining reliance on particular types of information, we explored the valence (positive/ neutral/ negative) of the information, as reliance on self-generated or other-generated information may depend on whether self-presentation is perceived (i.e., presenting oneself positively / not negatively). Self-presentation may be perceived if the targets have positive/ neutral statuses, while negative statuses would indicate a lack of self-presentation. In line with previous research, participants should rely on other-generated information (wall-posts) to form an impression when participants are viewed to have self-presented (positive / neutral status updates), as this information could be viewed as unreliable. Forty participants rated nine Facebook profiles where statuses and wall-posts portrayed personality traits varying in valence. Each profile consisted of a neutral profile photo, three status updates (all positive, negative, or neutral) and three wall-posts (all positive, negative, or neutral). Materials were established in two pilots. Impression formation was measured as perceived social, task, and physical attractiveness of the target individual. Participants also ranked the profiles for likeability. Supporting our expectations, other-generated information (wall-posts) dominated impression formation for social attractiveness when self-generated information (status updates) was positive/ neutral. Task attractiveness was affected by information valence, regardless of source (self or other). Despite the inclusion of neutral photos, physical attractiveness was affected by self-generated information, with negative statuses lowering physical attractiveness. We suggest that these findings have implications for impression formation beyond the Facebook setting. The 557 traits analyzed in Pilot 1 are available as supporting information (S1 Dataset) and may be useful for other impression formation researchers.

Project description:BackgroundTherapists and their patients increasingly discuss digital data from social media, smartphone sensors, and other online engagements within the context of psychotherapy.ObjectiveWe examined patients' and mental health therapists' experiences and perceptions following a randomized controlled trial in which they both received regular summaries of patients' digital data (eg, dashboard) to review and discuss in session. The dashboard included data that patients consented to share from their social media posts, phone usage, and online searches.MethodsFollowing the randomized controlled trial, patient (n=56) and therapist (n=44) participants completed a debriefing survey after their study completion (from December 2021 to January 2022). Participants were asked about their experience receiving a digital data dashboard in psychotherapy via closed- and open-ended questions. We calculated descriptive statistics for closed-ended questions and conducted qualitative coding via NVivo (version 10; Lumivero) and natural language processing using the machine learning tool latent Dirichlet allocation to analyze open-ended questions.ResultsOf 100 participants, nearly half (n=48, 49%) described their experience with the dashboard as "positive," while the other half noted a "neutral" experience. Responses to the open-ended questions resulted in three thematic areas (nine subcategories): (1) dashboard experience (positive, neutral or negative, and comfortable); (2) perception of the dashboard's impact on enhancing therapy (accountability, increased awareness over time, and objectivity); and (3) dashboard refinements (additional sources, tailored content, and privacy).ConclusionsPatients reported that receiving their digital data helped them stay "accountable," while therapists indicated that the dashboard helped "tailor treatment plans." Patient and therapist surveys provided important feedback on their experience regularly discussing dashboards in psychotherapy.

Project description:BackgroundMeasuring patient-reported outcomes (PROs) requires an individual's perspective on their symptoms, functional status, and quality of life. Digital health enables remote electronic PRO (ePRO) assessments as a clinical decision support tool to facilitate meaningful provider interactions and personalized treatment.ObjectiveThis study explored the feasibility and acceptability of collecting ePROs using validated health-related quality of life (HRQoL) questionnaires for prostate cancer.MethodsUsing Apple ResearchKit software, the Strength Through Insight app was created with content from validated HRQoL tools 26-item Expanded Prostate Cancer Index Composite (EPIC) or EPIC for Clinical Practice and 8-item Functional Assessment of Cancer Therapy Advanced Prostate Symptom Index. In a single-arm pilot study with patients receiving prostate cancer treatment at Thomas Jefferson University Hospital and affiliates, participants were recruited, and instructed to download Strength Through Insight and complete ePROs once a week over 12 weeks. A mixed methods approach, including qualitative pre- and poststudy interviews, was used to evaluate the feasibility and acceptability of Strength Through Insight for the collection and care management of cancer treatment.ResultsThirty patients consented to the study; 1 patient failed to complete any of the questionnaires and was left out of the analysis of the intervention. Moreover, 86% (25/29) reached satisfactory questionnaire completion (defined as completion of 60% of weekly questions over 12 weeks). The lower bound of the exact one-sided 95% CI was 71%, exceeding the 70% feasibility threshold. Most participants self-identified with having a high digital literacy level (defined as the ability to use, understand, evaluate, and analyze information from multiple formats from a variety of digital sources), and only a few participants identified with having a low digital literacy level (defined as only having the ability to gather information on the Web). Interviews were thematically analyzed to reveal the following: (1) value of emotional support and wellness in cancer treatment, (2) rise of social patient advocacy in online patient communities and networks, (3) patient concerns over privacy, and (4) desire for personalized engagement tools.ConclusionsStrength Through Insight was demonstrated as a feasible and acceptable method of data collection for ePROs. A high compliance rate confirmed the app as a reliable tool for patients with localized and advanced prostate cancer. Nearly all participants reported that using the smartphone app is easier than or equivalent to the traditional paper-and-pen approach, providing evidence of acceptability and support for the use of remote PRO monitoring. This study expands on current research involving the value of digital health, as a social and behavioral science, augmented with technology, can begin to contribute to population health management, as it shapes psychographic segmentation by demographic, socioeconomic, health condition, or behavioral factors to group patients by their distinct personalities and motivations, which influence their choices.Trial registrationClinicalTrials.gov NC03197948; http://clinicaltrials.gov/ct2/show/NC03197948.

Project description:BackgroundThere is a growing need for the integration of patient-generated health data (PGHD) into research and clinical care to enable personalized, preventive, and interactive care, but technical and organizational challenges, such as the lack of standards and easy-to-use tools, preclude the effective use of PGHD generated from consumer devices, such as smartphones and wearables.ObjectiveThis study outlines how we used mobile apps and semantic web standards such as HTTP 2.0, Representational State Transfer, JSON (JavaScript Object Notation), JSON Schema, Transport Layer Security (version 1.3), Advanced Encryption Standard-256, OpenAPI, HTML5, and Vega, in conjunction with patient and provider feedback to completely update a previous version of mindLAMP.MethodsThe Learn, Assess, Manage, and Prevent (LAMP) platform addresses the abovementioned challenges in enhancing clinical insight by supporting research, data analysis, and implementation efforts around PGHD as an open-source solution with freely accessible and shared code.ResultsWith a simplified programming interface and novel data representation that captures additional metadata, the LAMP platform enables interoperability with existing Fast Healthcare Interoperability Resources-based health care systems as well as consumer wearables and services such as Apple HealthKit and Google Fit. The companion Cortex data analysis and machine learning toolkit offer robust support for artificial intelligence, behavioral feature extraction, interactive visualizations, and high-performance data processing through parallelization and vectorization techniques.ConclusionsThe LAMP platform incorporates feedback from patients and clinicians alongside a standards-based approach to address these needs and functions across a wide range of use cases through its customizable and flexible components. These range from simple survey-based research to international consortiums capturing multimodal data to simple delivery of mindfulness exercises through personalized, just-in-time adaptive interventions.

Dataset Information

Detecting relapse in youth with psychotic disorders utilizing patient-generated and patient-contributed digital data from Facebook.

Publications

Detecting relapse in youth with psychotic disorders utilizing patient-generated and patient-contributed digital data from Facebook.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets