Digital health technologies and major depressive disorder

CNS Spectrums, Journal Year: 2023, Volume and Issue: 28(6), P. 662 - 673

Published: April 12, 2023

Abstract There is an urgent need to improve the clinical management of major depressive disorder (MDD), which has become increasingly prevalent over past two decades. Several gaps and challenges in awareness, detection, treatment, monitoring MDD remain be addressed. Digital health technologies have demonstrated utility relation various conditions, including MDD. Factors related COVID-19 pandemic accelerated development telemedicine, mobile medical apps, virtual reality apps continued introduce new possibilities across mental care. Growing access acceptance digital present opportunities expand scope care close technology rapidly evolving options for nonclinical support patients with Iterative efforts validate optimize such technologies, therapeutics biomarkers, continue quality personalized The aim this review highlight existing depression discuss current future landscape as it applies faced by their healthcare providers.

Language: Английский

---

Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study

JMIR mhealth and uhealth, Journal Year: 2023, Volume and Issue: 11, P. e45405 - e45405

Published: March 20, 2023

Depressive and manic episodes within bipolar disorder (BD) major depressive (MDD) involve altered mood, sleep, activity, alongside physiological alterations wearables can capture. Firstly, we explored whether wearable data could predict (aim 1) the severity of an acute affective episode at intra-individual level 2) polarity euthymia among different individuals. Secondarily, which were related to prior predictions, generalization across patients, associations between symptoms data. We conducted a prospective exploratory observational study including patients with BD MDD on (manic, depressed, mixed) whose recorded using research-grade (Empatica E4) 3 consecutive time points (acute, response, remission episode). Euthymic healthy controls during single session (approximately 48 h). Manic assessed standardized psychometric scales. Physiological included following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), electrodermal activity (EDA). Invalid removed rule-based filter, channels aligned 1-second units segmented window lengths 32 seconds, as best-performing parameters. developed deep learning predictive models, channels' individual contribution permutation feature importance analysis, computed scales' items normalized mutual information (NMI). present novel, fully automated method for preprocessing analysis from device, viable supervised pipeline time-series analyses. Overall, 35 sessions (1512 hours) 12 mixed, euthymic) 7 (mean age 39.7, SD 12.6 years; 6/19, 32% female) analyzed. The mood was predicted moderate (62%-85%) accuracies 1), their (70%) accuracy 2). most relevant features former tasks ACC, EDA, HR. There fair agreement in classification (Kendall W=0.383). Generalization models unseen overall low accuracy, except models. ACC associated "increased motor activity" (NMI>0.55), "insomnia" (NMI=0.6), "motor inhibition" (NMI=0.75). EDA "aggressive behavior" (NMI=1.0) "psychic anxiety" (NMI=0.52). show potential identify specific mania depression quantitatively, both MDD. Motor stress-related (EDA HR) stand out digital biomarkers predicting depression, respectively. These findings represent promising pathway toward personalized psychiatry, allow early identification intervention episodes.

Language: Английский

---

Advances in biosensors for major depressive disorder diagnostic biomarkers

Biosensors and Bioelectronics, Journal Year: 2024, Volume and Issue: 258, P. 116291 - 116291

Published: April 16, 2024

Language: Английский

---

Harnessing Consumer Wearable Digital Biomarkers for Individualized Recognition of Postpartum Depression Using the All of Us Research Program Data Set: Cross-Sectional Study

JMIR mhealth and uhealth, Journal Year: 2024, Volume and Issue: 12, P. e54622 - e54622

Published: May 2, 2024

Background Postpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes underdiagnosis. Furthermore, recognizing symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for recognition. Objective main goal this study was showcase viability machine learning (ML) and related heart rate, physical activity, energy expenditure derived consumer-grade recognition PPD. Methods Using All Us Research Program Registered Tier v6 data set, performed computational phenotyping women with without following childbirth. Intraindividual ML models were developed Fitbit discern between prepregnancy, pregnancy, depression, (ie, diagnosis) periods. Models built generalized linear models, random forest, support vector machine, k-nearest neighbor algorithms evaluated κ statistic multiclass area under receiver operating characteristic curve (mAUC) determine algorithm best performance. specificity our individualized confirmed in cohort who gave birth did not experience Moreover, assessed impact previous history model We determined variable importance predicting period Shapley additive explanations results permutation approach. Finally, compared methodology against traditional cohort-based performance sensitivity, specificity, precision, recall, F1-score. Results Patient cohorts valid included <20 39 Our demonstrated that intraindividual discerned among periods, forest (mAUC=0.85; κ=0.80) outperforming (mAUC=0.82; κ=0.74), (mAUC=0.75; κ=0.72), (mAUC=0.74; κ=0.62). Model decreased PPD, illustrating method’s specificity. Previous efficacy found most predictive biomarker calories burned during basal metabolic rate. surpassed conventional detection. Conclusions This research establishes as promising tool identification highlights personalized approaches, could transform early disease detection strategies.

Language: Английский

---

Digital biomarkers for non-motor symptoms in Parkinson’s disease: the state of the art

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

Published: July 11, 2024

Digital biomarkers that remotely monitor symptoms have the potential to revolutionize outcome assessments in future disease-modifying trials Parkinson's disease (PD), by allowing objective and recurrent measurement of signs collected participant's own living environment. This biomarker field is developing rapidly for assessing motor features PD, but non-motor domain lags behind. Here, we systematically review assess digital under development measuring PD. We also consider relevant developments outside PD field. focus on technological readiness level evaluate whether identified progression, covering spectrum from prodromal advanced stages. Furthermore, provide perspectives deployment these trials. found various wearables show high promise autonomic function, constipation sleep characteristics, including REM behavior disorder. Biomarkers neuropsychiatric are less well-developed, increasing accuracy non-PD populations. Most not been validated specific use their sensitivity capture progression remains untested where need greatest. External validation real-world environments large longitudinal cohorts necessary integrating into research, ultimately daily clinical practice.

Language: Английский

---

Optimising the use of electronic medical records for large scale research in psychiatry

Translational Psychiatry, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 1, 2024

Abstract The explosion and abundance of digital data could facilitate large-scale research for psychiatry mental health. Research using so-called “real world data”—such as electronic medical/health records—can be resource-efficient, rapid hypothesis generation testing, complement existing evidence (e.g. from trials evidence-synthesis) may enable a route to translate into clinically effective, outcomes-driven care patient populations that under-represented. However, the interpretation processing real-world sources is complex because important ‘signal’ often contained in both structured unstructured (narrative or “free-text”) data. Techniques extracting meaningful information (signal) text exist have advanced re-use routinely collected clinical data, but these techniques require cautious evaluation. In this paper, we survey opportunities, risks progress made use medical record (real-world) psychiatric research.

Language: Английский

---

Designing, Developing, Evaluating, and Implementing a Smartphone-Delivered, Rule-Based Conversational Agent (DISCOVER): Development of a Conceptual Framework

JMIR mhealth and uhealth, Journal Year: 2022, Volume and Issue: 10(10), P. e38740 - e38740

Published: Aug. 26, 2022

Conversational agents (CAs), also known as chatbots, are computer programs that simulate human conversations by using predetermined rule-based responses or artificial intelligence algorithms. They increasingly used in health care, particularly via smartphones. There is, at present, no conceptual framework guiding the development of smartphone-based, CAs care. To fill this gap, we propose structured and tailored guidance for their design, development, evaluation, implementation.The aim study was to develop a implementation smartphone-delivered, rule-based, goal-oriented, text-based care.We followed approach Jabareen, which based on grounded theory method, framework. We performed 2 literature reviews focusing care frameworks mobile interventions. identified, named, categorized, integrated, synthesized information retrieved from then applied developing CA testing it feasibility study.The Designing, Developing, Evaluating, Implementing Smartphone-Delivered, Rule-Based Agent (DISCOVER) includes 8 iterative steps grouped into 3 stages, follows: comprising defining goal, creating an identity, assembling team, selecting delivery interface; including content building conversation flow; evaluation CA. were complemented cross-cutting considerations-user-centered design privacy security-that relevant all stages. This successfully support lifestyle changes prevent type diabetes.Drawing published evidence, DISCOVER provides step-by-step guide smartphone-delivered CAs. Further diverse areas settings variety users is needed demonstrate its validity. Future research should explore use deliver interventions, behavior change potential safety concerns.

Language: Английский

---

Depressed Mood Prediction of Elderly People with a Wearable Band

Sensors, Journal Year: 2022, Volume and Issue: 22(11), P. 4174 - 4174

Published: May 31, 2022

Depression in the elderly is an important social issue considering population aging of world. In particular, living alone who has narrowed relationship due to bereavement and retirement are more prone be depressed. Long-term depressed mood can a precursor eventual depression as disease. Our goal how predict single household from unobtrusive monitoring their daily life. We have selected wearable band with multiple sensors for people. questionnaire been surveyed periodically used labels. Instead working patients, we recruited 14 people nearby community. The provided activity biometric data 71 days. From data, generate prediction model. Multiple features collected sensor exploited model generation. One general generated baseline initial deployment. Personal models also refinement. high recall 80% MLP Individual achieved average 82.7%. this study, demonstrated that real living. work shown feasibility using even

Language: Английский

---

Using digital phenotyping to capture depression symptom variability: detecting naturalistic variability in depression symptoms across one year using passively collected wearable movement and sleep data

Translational Psychiatry, Journal Year: 2023, Volume and Issue: 13(1)

Published: Dec. 9, 2023

Abstract Major Depressive Disorder (MDD) presents considerable challenges to diagnosis and management due symptom variability across time. Only recent work has highlighted the clinical implications for interrogating depression variability. Thus, present investigates how sociodemographic, comorbidity, movement, sleep data is associated with long-term Participant information included ( N = 939) baseline sociodemographic comorbidity data, longitudinal, passively collected wearable Patient Health Questionnaire-9 (PHQ-9) scores over 12 months. An ensemble machine learning approach was used detect via: (i) a domain-driven feature selection (ii) an exhaustive feature-inclusion approach. SHapley Additive exPlanations (SHAP) were interrogate variable importance directionality. The composite inclusion models both capable of moderately detecting r 0.33 0.39, respectively). Our results indicate incremental predictive validity movement in

Language: Английский

---

Clinical research on neurological and psychiatric diagnosis and monitoring using wearable devices: A literature review

Deleted Journal, Journal Year: 2024, Volume and Issue: 2(4)

Published: May 11, 2024

Abstract Wearable devices have opened up exciting possibilities for monitoring and managing home health, particularly in the realm of neurological psychiatric diseases. These capture signals related to physiological behavioral changes, including heart rate, sleep patterns, motor functions. Their emergence has resulted significant advancements management such conditions. Traditional clinical diagnosis assessment methods heavily rely on patient reports evaluations conducted by healthcare professionals, often leading a detachment patients from their environment creating additional burdens both providers. The increasing popularity wearable offers potential solution these challenges. This review focuses utility diagnosing Through research findings practical examples, we highlight role conditions as autism spectrum disorder, depression, epilepsy, stroke prognosis, Parkinson's disease, dementia, other Additionally, discusses benefits limitations applications, while highlighting challenges they face. Finally, it provides prospects enhancing value

Language: Английский

---