Relapse prediction in schizophrenia with smartphone digital phenotyping during COVID-19: a prospective, three-site, two-country, longitudinal study

Schizophrenia, Journal Year: 2023, Volume and Issue: 9(1)

Published: Jan. 27, 2023

Smartphone technology provides us with a more convenient and less intrusive method of detecting changes in behavior symptoms that typically precede schizophrenia relapse. To take advantage the aforementioned, this study examines feasibility predicting relapse by identifying statistically significant anomalies patient data gathered through mindLAMP, an open-source smartphone app. Participants, recruited Boston, MA United States, Bangalore Bhopal India, were invited to use mindLAMP for up year. The passive (geolocation, accelerometer, screen state), active (surveys), quality metrics collected app then retroactively fed into prediction model utilizes anomaly detection. Overall, 2.12 times frequent month preceding 2.78 following compared intervals without relapses. detection incorporating proved better predictor than naive utilizing only survey data. These results demonstrate models can warn clinician potential

Language: Английский

---

From smartphone data to clinically relevant predictions: A systematic review of digital phenotyping methods in depression

Neuroscience & Biobehavioral Reviews, Journal Year: 2024, Volume and Issue: 158, P. 105541 - 105541

Published: Jan. 11, 2024

Smartphone-based digital phenotyping enables potentially clinically relevant information to be collected as individuals go about their day. This could improve monitoring and interventions for people with Major Depressive Disorder (MDD). The aim of this systematic review was investigate current features methods used in MDD. We searched PubMed, PsycINFO, Embase, Scopus Web Science (10/11/2023) articles including: (1) MDD population, (2) smartphone-based features, (3) validated ratings. Risk bias assessed using several sources. Studies were compared within analysis goals (correlating depression, predicting symptom severity, diagnosis, mood state/episode, other). Twenty-four studies (9801 participants) included. achieved moderate performance. Common themes included challenges from complex missing data (leading a risk bias), lack external validation. made progress towards relating phenotypes clinical variables, often focusing on time-averaged features. Methods investigating temporal dynamics more directly may beneficial patient monitoring. European Research Council consolidator grant: 101001118, Prospero: CRD42022346264, Open Framework: https://osf.io/s7ay4

Language: Английский

---

Longitudinal Relationships Between Depressive Symptom Severity and Phone-Measured Mobility: Dynamic Structural Equation Modeling Study

JMIR Mental Health, Journal Year: 2022, Volume and Issue: 9(3), P. e34898 - e34898

Published: Jan. 12, 2022

The mobility of an individual measured by phone-collected location data has been found to be associated with depression; however, the longitudinal relationships (the temporal direction relationships) between depressive symptom severity and phone-measured have yet fully explored.

Language: Английский

---

Long-term participant retention and engagement patterns in an app and wearable-based multinational remote digital depression study

npj Digital Medicine, Journal Year: 2023, Volume and Issue: 6(1)

Published: Feb. 17, 2023

Abstract Recent growth in digital technologies has enabled the recruitment and monitoring of large diverse populations remote health studies. However, generalizability inference drawn from remotely collected data could be severely impacted by uneven participant engagement attrition over course study. We report findings on long-term retention patterns a multinational observational study for depression containing active (surveys) passive sensor via Android smartphones, Fitbit devices 614 participants up to 2 years. Majority (67.6%) continued remain engaged after 43 weeks. Unsupervised clustering participants’ apps usage showed 3 distinct subgroups each stream. found: (i) least group had highest severity (4 PHQ8 points higher) across all streams; (ii) (completed 4 bi-weekly surveys) took significantly longer respond survey notifications (3.8 h more) were 5 years younger compared most 20 surveys); (iii) considerable proportion (44.6%) who stopped completing surveys 8 weeks share (average 42 weeks). Additionally, multivariate survival models age, ownership brand sites associated with Together these inform design future studies enable equitable balanced collection populations.

Language: Английский

---

Wearable Technology in Clinical Practice for Depressive Disorder

New England Journal of Medicine, Journal Year: 2023, Volume and Issue: 389(26), P. 2457 - 2466

Published: Dec. 27, 2023

Sleep patterns and physical activity can be monitored by wearable technology. The authors describe the state of art for using data from devices in diagnosing managing depression.

Language: Английский

---

Increasing the value of digital phenotyping through reducing missingness: a retrospective review and analysis of prior studies

BMJ Mental Health, Journal Year: 2023, Volume and Issue: 26(1), P. e300718 - e300718

Published: Feb. 1, 2023

Digital phenotyping methods present a scalable tool to realise the potential of personalised medicine. But underlying this is need for digital data represent accurate and precise health measurements.To assess impact population, clinical, research technological factors on quality as measured by rates missing data.This study analyses retrospective cohorts mindLAMP smartphone application studies run at Beth Israel Deaconess Medical Center between May 2019 March 2022 involving 1178 participants (studies college students, people with schizophrenia depression/anxiety). With large combined set, we report sampling frequency, active engagement application, phone type (Android vs Apple), gender protocol features missingness/data quality.Missingness from sensors in related user application. After 3 days no engagement, there was 19% decrease average coverage both Global Positioning System accelerometer. Data sets high degrees missingness can generate incorrect behavioural that may lead faulty clinical interpretations.Digital requires ongoing technical efforts minimise missingness. Adding run-in periods, education hands-on support tools easily monitor are all productive strategies use today.While it feasible capture diverse populations, clinicians should consider degree before using them decision-making.

Language: Английский

---

The usability of daytime and night-time heart rate dynamics as digital biomarkers of depression severity

Psychological Medicine, Journal Year: 2023, Volume and Issue: 53(8), P. 3249 - 3260

Published: May 15, 2023

Alterations in heart rate (HR) may provide new information about physiological signatures of depression severity. This 2-year study individuals with a history recurrent major depressive disorder (MDD) explored the intra-individual variations HR parameters and their relationship severity.Data from 510 participants (Number observations = 6666) were collected three centres Netherlands, Spain, UK, as part remote assessment disease relapse-MDD study. We analysed between severity, assessed every 2 weeks Patient Health Questionnaire-8, week before assessment, such features during all day, resting periods day at night, activity evaluated wrist-worn Fitbit device. Linear mixed models used random intercepts for countries. Covariates included age, sex, BMI, smoking alcohol consumption, antidepressant use co-morbidities other medical health conditions.Decreases variation related an increased severity both univariate multivariate analyses. Mean night was higher more severe symptoms.Our findings demonstrate that alterations are associated These early warning worsening symptoms which could allow clinicians to take responsive treatment measures promptly.

Language: Английский

---

Personalized mood prediction from patterns of behavior collected with smartphones

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: Feb. 28, 2024

Abstract Over the last ten years, there has been considerable progress in using digital behavioral phenotypes, captured passively and continuously from smartphones wearable devices, to infer depressive mood. However, most phenotype studies suffer poor replicability, often fail detect clinically relevant events, use measures of depression that are not validated or suitable for collecting large longitudinal data. Here, we report high-quality assessments mood computerized adaptive testing paired with continuous behavior smartphone sensors up 40 weeks on 183 individuals experiencing mild severe symptoms depression. We apply a combination cubic spline interpolation idiographic models generate individualized predictions future achieving high prediction accuracy severity three advance ( R 2 ≥ 80%) 65.7% reduction error over baseline model which predicts based past alone. Finally, our study verified feasibility obtaining clinical population predicting symptom collected Our results indicate possibility expanding repertoire patient-specific enable psychiatric research.

Language: Английский

---

Multimodal Mental Health Digital Biomarker Analysis From Remote Interviews Using Facial, Vocal, Linguistic, and Cardiovascular Patterns

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2024, Volume and Issue: 28(3), P. 1680 - 1691

Published: Jan. 10, 2024

Psychiatric evaluation suffers from subjectivity and bias, is hard to scale due intensive professional training requirements. In this work, we investigated whether behavioral physiological signals, extracted tele-video interviews, differ in individuals with psychiatric disorders.

Language: Английский

---

Omics approaches open new horizons in major depressive disorder: from biomarkers to precision medicine

Frontiers in Psychiatry, Journal Year: 2024, Volume and Issue: 15

Published: June 13, 2024

Major depressive disorder (MDD) is a recurrent episodic mood that represents the third leading cause of disability worldwide. In MDD, several factors can simultaneously contribute to its development, which complicates diagnosis. According practical guidelines, antidepressants are first-line treatment for moderate severe major episodes. Traditional strategies often follow one-size-fits-all approach, resulting in suboptimal outcomes many patients who fail experience response or recovery and develop so-called “therapy-resistant depression”. The high biological clinical inter-variability within lack robust biomarkers hinder finding specific therapeutic targets, contributing failure rates. this frame, precision medicine, paradigm tailors medical interventions individual characteristics, would help allocate most adequate effective each patient while minimizing side effects. particular, multi-omic studies may unveil intricate interplays between genetic predispositions exposure environmental through study epigenomics, transcriptomics, proteomics, metabolomics, gut microbiomics, immunomics. integration flow information into molecular pathways produce better than current psychopharmacological targets singular mainly related monoamine systems, disregarding complex network our organism. concept system biomedicine involves analysis enormous datasets generated with different technologies, creating “patient fingerprint”, defines underlying mechanisms every patient. This review, centered on explores approaches as tools prediction MDD at single-patient level. It investigates how combining existing technologies used diagnostic, stratification, prognostic, treatment-response discovery artificial intelligence improve assessment MDD.

Language: Английский

---