PSYCHE-D: predicting change in depression severity using person-generated health data (DATASET)

Makhmutova, Mariko; Kainkaryam, Raghu; Ferreira, Marta; Min, Jae; Jäggi, Martin; Clay, Ieuan

doi:10.5281/zenodo.5085146

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[9] People suffering from anxiety have elevated levels of heart beat and blood pressure. [10] Anxiety has been linked to nightly and early morning hypertension among hypertensive patients, according to a new blood pressure monitoring research. [11] These attributes can be easily monitored through these trackers and the data generated from them are pre-processed and analysed by the applications in our smartphones & tablets and can be shared with a medical professional.…”

Section: Monitoring Mental Health Through Iotmentioning

confidence: 99%

Role of IoT and data analysis in determining mental well-being

Sharma

Jyoti

2022

ijhs

View full text Add to dashboard Cite

IoT devices like Fitness bands and smartwatches can play a key role in determining the mental health of people. We have seen the rising trend in people integrating them in their lifestyle and smartphone applications being developed to detect step count and sleep monitoring through their sensory perceptions and GPS functions. Analyzing the data generated by them we can get clear insights into the factors to detect declining mental health. We analysed, data from The DISCover project to build a classification model in Logistic Regression to find if the patients mental health is declining, using the physical symptoms monitored in the commercially available wearable bands. Previous researches show a negative correlation between physical activities and phq9 scores of patients. We found that IoT devices can play a major role in researching mental health as done in the research Digital Signals in Chronic Pain done in Evidation Health, along with step count and activity tracking have a higher rate in predicting mental health compared to sleep data generated in fitness bands even without taking the emotional attributes.

show abstract

Section: Monitoring Mental Health Through Iotmentioning

confidence: 99%

Role of IoT and data analysis in determining mental well-being

Sharma

Jyoti

2022

ijhs

View full text Add to dashboard Cite

show abstract

Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study

Makhmutova¹,

Kainkaryam²,

Ferreira³

et al. 2022

JMIR Mhealth Uhealth

Self Cite

View full text Add to dashboard Cite

Background In 2017, an estimated 17.3 million adults in the United States experienced at least one major depressive episode, with 35% of them not receiving any treatment. Underdiagnosis of depression has been attributed to many reasons, including stigma surrounding mental health, limited access to medical care, and barriers due to cost. Objective This study aimed to determine if low-burden personal health solutions, leveraging person-generated health data (PGHD), could represent a possible way to increase engagement and improve outcomes. Methods Here, we present the development of PSYCHE-D (Prediction of Severity Change-Depression), a predictive model developed using PGHD from more than 4000 individuals, which forecasts the long-term increase in depression severity. PSYCHE-D uses a 2-phase approach. The first phase supplements self-reports with intermediate generated labels, and the second phase predicts changing status over a 3-month period, up to 2 months in advance. The 2 phases are implemented as a single pipeline in order to eliminate data leakage and ensure results are generalizable. Results PSYCHE-D is composed of 2 Light Gradient Boosting Machine (LightGBM) algorithm–based classifiers that use a range of PGHD input features, including objective activity and sleep, self-reported changes in lifestyle and medication, and generated intermediate observations of depression status. The approach generalizes to previously unseen participants to detect an increase in depression severity over a 3-month interval, with a sensitivity of 55.4% and a specificity of 65.3%, nearly tripling sensitivity while maintaining specificity when compared with a random model. Conclusions These results demonstrate that low-burden PGHD can be the basis of accurate and timely warnings that an individual’s mental health may be deteriorating. We hope this work will serve as a basis for improved engagement and treatment of individuals experiencing depression.

show abstract

Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study (Preprint)

Makhmutova¹,

Kainkaryam²,

Ferreira³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

BACKGROUND In 2017, an estimated 17.3 million adults in the US experienced at least one major depressive episode, with 35% of them not receiving any treatment. Under-diagnosis of depression has been attributed to many reasons including stigma surrounding mental health, limited access to medical care or barriers due to cost. OBJECTIVE To determine if low-burden personal health solutions, leveraging person-generated health data (PGHD), could represent a possible way to increase engagement and improve outcomes. METHODS Here we present the development of PSYCHE-D (Prediction of SeveritY CHange - Depression), a predictive model developed using PGHD from more than 4000 individuals, that forecasts long-term increase in depression severity. PSYCHE-D uses a two-phase approach: the first phase supplements self-reports with intermediate generated labels; the second phase predicts changing status over a 3 month period, up to 2 months in advance. The two phases are implemented as a single pipeline in order to eliminate data leakage, and ensure results are generalizable. RESULTS PSYCHE-D is composed of two Light Gradient Boosting Machine (LightGBM) algorithm-based classifiers that use a range of PGHD input features, including objective activity and sleep, self reported changes in lifestyle and medication, as well as generated intermediate observations of depression status. The approach generalizes to previously unseen participants to detect increase in depression severity over a 3-month interval with a sensitivity of 55.4% and a specificity of 65.3%, nearly tripling sensitivity, while maintaining specificity, versus a random model. CONCLUSIONS These results demonstrate that low-burden PGHD can be the basis of accurate and timely warnings that an individual's mental health may be deteriorating. We hope this work will serve as a basis for improved engagement and treatment of individuals suffering from depression. CLINICALTRIAL Data used to develop the model was derived from the Digital Signals in Chronic Pain (DiSCover) Project (Clintrials.gov identifier: NCT03421223)

show abstract

PSYCHE-D: predicting change in depression severity using person-generated health data (DATASET)

Cited by 3 publications

References 0 publications

Role of IoT and data analysis in determining mental well-being

Role of IoT and data analysis in determining mental well-being

Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study

Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study (Preprint)

Contact Info

Product

Resources

About