Digital phenotyping in bipolar disorder: Using longitudinal Fitbit data and personalized machine learning to predict mood symptomatology DOI Open Access
Jessica M. Lipschitz, Shuwen Lin, Soroush Saghafian

et al.

Acta Psychiatrica Scandinavica, Journal Year: 2024, Volume and Issue: 151(3), P. 434 - 447

Published: Oct. 13, 2024

Effective treatment of bipolar disorder (BD) requires prompt response to mood episodes. Preliminary studies suggest that predictions based on passive sensor data from personal digital devices can accurately detect episodes (e.g., between routine care appointments), but date do not use methods designed for broad application. This study evaluated whether a novel, personalized machine learning approach, trained entirely Fitbit data, with limited filtering could symptomatology in BD patients. We analyzed 54 adults BD, who wore Fitbits and completed bi-weekly self-report measures 9 months. applied (ML) models aggregated over two-week observation windows occurrences depressive (hypo)manic symptomatology, which were defined as scores above established clinical cutoffs the Patient Health Questionnaire-8 (PHQ-8) Altman Self-Rating Mania Scale (ASRM) respectively. As hypothesized, among several ML algorithms, Binary Mixed Model (BiMM) forest achieved highest area under receiver operating curve (ROC-AUC) validation process. In testing set, ROC-AUC was 86.0% depression 85.2% (hypo)mania. Using optimized thresholds calculated Youden's J statistic, predictive accuracy 80.1% (sensitivity 71.2% specificity 85.6%) 89.1% (hypo)mania 80.0% 90.1%). sound performance detecting patients using Findings expand upon evidence produce accurate predictions. Additionally, best our knowledge, this represents first application BiMM prediction. Overall, results move field step toward algorithms suitable full population patients, rather than only those high compliance, access specialized devices, or willingness share invasive data.

Language: Английский

Digital Neuropsychology beyond Computerized Cognitive Assessment: Applications of Novel Digital Technologies DOI

Che Harris,

Yingfei Tang,

Eliana Birnbaum

et al.

Archives of Clinical Neuropsychology, Journal Year: 2024, Volume and Issue: 39(3), P. 290 - 304

Published: March 22, 2024

Compared with other health disciplines, there is a stagnation in technological innovation the field of clinical neuropsychology. Traditional paper-and-pencil tests have number shortcomings, such as low-frequency data collection and limitations ecological validity. While computerized cognitive assessment may help overcome some these issues, current paradigms do not address majority limitations. In this paper, we review recent literature on applications novel digital approaches, including momentary assessment, smartphone-based sensors, wearable devices, passive driving smart homes, voice biomarkers, electronic record mining, neurological populations. We describe how each tool be applied to neurologic care traditional neuropsychological assessment. Ethical considerations, research, well our proposed future practice are also discussed.

Language: Английский

Citations

17
Digital Phenotyping: Data-Driven Psychiatry to Redefine Mental Health DOI Creative Commons
Antoine Oudin, Redwan Maatoug, Alexis Bourla

et al.

Journal of Medical Internet Research, Journal Year: 2023, Volume and Issue: 25, P. e44502 - e44502

Published: Aug. 21, 2023

The term "digital phenotype" refers to the digital footprint left by patient-environment interactions. It has potential for both research and clinical applications but challenges our conception of health care opposing 2 distinct approaches medicine: one centered on illness with aim classifying curing disease, other patients, their personal distress, lived experiences. In context mental psychiatry, benefits phenotyping include creating new avenues treatment enabling patients take control own well-being. However, this comes at cost sacrificing fundamental human element psychotherapy, which is crucial addressing patients' distress. viewpoint paper, we discuss advances rendered possible highlight risk that technology may pose partially excluding professionals from diagnosis therapeutic process, thereby foregoing an essential dimension care. We conclude setting out concrete recommendations how improve current so it can be harnessed redefine empowering without alienating them.

Language: Английский

Citations

37
Digital biomarkers in depression: A systematic review and call for standardization and harmonization of feature engineering DOI

Carolin Zierer,

Corinna Behrendt,

Anja Christina Lepach-Engelhardt

et al.

Journal of Affective Disorders, Journal Year: 2024, Volume and Issue: 356, P. 438 - 449

Published: April 5, 2024

Language: Английский

Citations

4
Machine learning applied to digital phenotyping: A systematic literature review and taxonomy DOI
Marília Pit dos Santos, Wesllei Felipe Heckler, Rodrigo Simon Bavaresco

et al.

Computers in Human Behavior, Journal Year: 2024, Volume and Issue: 161, P. 108422 - 108422

Published: Aug. 24, 2024

Language: Английский

Citations

4
Voice Quality as Digital Biomarker in Bipolar Disorder: A Systematic Review DOI
Giovanni Briganti, Jérôme R. Lechien

Journal of Voice, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Prospects for the Use of Machine Learning for Mood Disorders DOI Creative Commons
Ekaterina Mosolova, A. Е. Alfimov, E G Kostyukova

et al.

Digital Diagnostics, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 28, 2025

Relevance. Mental disorders are one of the key medical and social issues. Over last years artificial intelligence (AI) methods including machine deep learning have been actively developing. This narrative review aimed to identify current promising areas for development application AI into clinical practice using example patients with depression bipolar disorder. Methods. The search publications was performed in January ─ February 2024 PubMed, Google Scholar, elibrary databases combination keywords: psychiatry, mental health, psychiatric disorder, depression, depressive episode, major learning, intelligence. included original articles on use devoted problems applying psychiatry published Russian or English 10 years. Results. Most often, neuroimaging (mainly MRI EEG), text, audio video data, electronic device molecular genetics, data its combination, used (ML) models mood disorders. Despite potential benefits implementation is currently challenging due number difficulties, such as small sample sizes, low representativeness, lack standardization, inclusion “noise” correlated variables models, model testing independent samples. Conclusion. Studies ML shown results early diagnosis affective episodes predicting response therapy. However, has a limitations, primarily insufficient validation. There need well-designed prospective cohort studies, well extensive high-quality capable identifying new relationships between order overcome these limitations.

Language: Английский

Citations

0
Digital Footprints and Machine Learning in Psychological Assessment DOI
Renato Gil Gomes Carvalho, Daniel Castro

European Psychologist, Journal Year: 2025, Volume and Issue: unknown

Published: April 24, 2025

Abstract: The digitalization of psychological assessment has introduced new paradigms in the collection, processing, and analysis data. This paper explores transformation testing context digital footprints rise machine learning (ML) tools. emergence smartphones, wearables, social media platforms allowed for collection passive data, significantly impacting how states are evaluated. shift offers enhanced insights into personality traits symptoms, while reducing reliance on traditional self-report methods. However, use to interpret large volumes behavioral data raises concerns about ethical implications, particularly regarding privacy, consent, algorithmic transparency. Furthermore, methodological challenges, such as reliability validity AI-based assessments, complicate integration these tools mainstream practice. aims critically evaluate benefits limitations ML assessment, emphasizing need frameworks robust methodologies ensure their effective safe implementation.

Language: Английский

Citations

0
Developing a suicide risk prediction model for hospitalized adolescents with depression in China DOI Creative Commons
Juan Zhao, Ying Li,

Yangjie Chen

et al.

Frontiers in Psychiatry, Journal Year: 2025, Volume and Issue: 16

Published: May 2, 2025

Introduction Adolescent suicide risk, particularly among individuals with depression, is a growing public health concern in China, driven by increasing social pressures and evolving family dynamics. However, limited research has focused on prediction models tailored for hospitalized Chinese adolescents depression. This study aims to develop risk model early identification of high-risk using internal validation, providing insights future clinical applications. Methods The involved 229 aged 13–18 diagnosed admitted hospital Shanxi, China. Feature selection was performed Least Absolute Shrinkage Selection Operator (Lasso) regression, key predictors were incorporated into multivariate logistic regression model. Model performance assessed the area under receiver operating characteristic curve (AUC), Hosmer-Lemeshow test, calibration curves, decision analysis (DCA), impact curves (CIC). Results demonstrated AUC values 0.839 (95% CI: 0.777, 0.899) training set 0.723 0.601, 0.845) testing set, indicating strong discrimination capability. Significant included gender, frequency, parental relationships, self-harm behavior, experiences loss, sleep duration. DCA CIC supported model’s predictive potential. Conclusion suggesting potential value assessment its generalizability remains be confirmed. Further external validation larger, multi-center cohorts required assess robustness applicability.

Language: Английский

Citations

0
Predicting and Monitoring Symptoms in Diagnosed Depression Using Smartphone Data: An Observational Study (Preprint) DOI Creative Commons
Arsi Ikäheimonen, Nguyen Luong, Ilya Baryshnikov

et al.

Journal of Medical Internet Research, Journal Year: 2024, Volume and Issue: 26, P. e56874 - e56874

Published: Sept. 24, 2024

Background Clinical diagnostic assessments and the outcome monitoring of patients with depression rely predominantly on interviews by professionals use self-report questionnaires. The ubiquity smartphones other personal consumer devices has prompted research into potential data collected via these to serve as digital behavioral markers for indicating presence depression. Objective This paper explores using detect monitor symptoms in diagnosed Specifically, it investigates whether this can accurately classify depression, well changes depressive states over time. Methods In a prospective cohort study, we smartphone up 1 year. study consists observations from 164 participants, including healthy controls (n=31) various disorders: major disorder (MDD; n=85), MDD comorbid borderline personality (n=27), episodes bipolar (n=21). Data were labeled based severity 9-item Patient Health Questionnaire (PHQ-9) scores. We performed statistical analysis used supervised machine learning observe state Results Our correlation revealed 32 associated state. classified who are depressed an accuracy 82% (95% CI 80%-84%) change 75% 72%-76%). Notably, most important features classifying screen-off events, battery charge levels, communication patterns, app usage, location data. Similarly, predicting state, related location, level, screen, accelerometer patterns. Conclusions supplement clinical evaluations may aid detecting particularly if combined intermittent symptoms.

Language: Английский

Citations

3
Integration of passive sensing technology to enhance delivery of psychological interventions for mothers with depression: the StandStrong study DOI Creative Commons
Alastair van Heerden, Anubhuti Poudyal, Ashley Hagaman

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 12, 2024

Psychological interventions delivered by non-specialist providers have shown mixed results for treating maternal depression. mHealth solutions hold the possibility unobtrusive behavioural data collection to identify challenges and reinforce change in psychological interventions. We conducted a proof-of-concept study using passive sensing integrated into depression intervention non-specialists twenty-four adolescents young mothers (30% 15-17 years old; 70% 18-25 old) with infants (< 12 months rural Nepal. All showed reduction symptoms as measured Beck Depression Inventory. There were trends toward increased movement away from house (greater distance through GPS data) more time spent infant (less proximity Bluetooth beacon) improved. was considerable heterogeneity these changes other passively collected (speech, physical activity) throughout intervention. This demonstrated that can be feasibly used low-resource settings personalize Care must taken when implementing such an approach ensure confidentiality, protection, meaningful interpretation of enhance

Language: Английский

Citations

2