A Computational Framework for Modeling Biobehavioral Rhythms from Mobile and Wearable Data Streams

Yan, Runze; Liu, Xinwen; Dutcher, Janine M.; Tumminia, Michael; Villalba, Daniella K.; Cohen, Sheldon; Creswell, David; Creswell, Kasey G.; Mankoff, Jennifer; Dey, Anind K.; Doryab, Afsaneh

doi:10.1145/3510029

Cited by 10 publications

(15 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This finding highlights the need for empirical investigation of the threshold while using the Stable FS approach. This finding also extends the previous studies which used random thresholds of 0.25 [47] and 0.75 [48] to select features for depression identification and also in other contexts (e.g., [72] used a threshold of 0.90 in neurobehavioral symptoms identification). While comparing the FS approaches, we found that to achieve the same performance (precision=73.1%, sensitivity 74.5%) of an ML model developed using around 5 features selected by Boruta, we needed 6, 9, and around 14 features of the filter, wrapper, and Stable approaches respectively.…”

Section: The Implication Of the Findingssupporting

confidence: 85%

“…We created 1000 bootstrapped subsamples and used a Logistic Regression classifier as the base estimator which fit on the bootstrapped subsamples. In previous studies of depression identification, researchers used random thresholds (e.g., 0.25 [47], 0.75 [48]) to select the features. Since there is no evidence of getting optimal performance using those thresholds only, in our study, we did an empirical investigation to present the optimal threshold.…”

Section: Feature Selectionmentioning

confidence: 99%

See 1 more Smart Citation

A Minimal and Faster System to Identify Depression Through Smartphone: An Explainable Machine Learning-Based Approach

Ahmed¹,

Ahmed²

2023

Preprint

View full text Add to dashboard Cite

Background: The robust pervasive device-based existing systems to detect depression developed in recent years requiring data collected over a long period of time may not be effective in cases where early detection is crucial. In addition, due to the requirement of running systems in the background for prolonged periods, the existing promising systems may not be resource efficient. As a result, these systems can be infeasible in low-resource settings.Objective: Our main objective was to develop a minimal system to identify depression that works on data retrieved in the fastest possible time. Another objective of this study was to explain the machine learning (ML) models which performed best in identifying depression.Methods: We developed a faster tool that retrieves the past 7 days’ app usage data in a second (mean=0.31 second, SD=1.10 second) . In our study, 100 students from Bangladesh participated and our tool collected their app usage data and responses to the Patient Health Questionnaire-9 (PHQ-9) scale. To identify the depressed and non-depressed participants, we developed a diverse set of ML models including linear, tree-based, and neural network-based models. We selected the important features by the Stable approach along with the 3 main types of feature selection (FS) approaches: Filter, Wrapper, and Embedded. We developed and validated the models using nested cross validation method. Additionally, we explained the best ML models through the SHapley Additive exPlanations (SHAP) method.Results: Leveraging only the app usage data retrieved in a second, our Light GBM model using the Stable approach selected features identified 82.4% depressed correctly (precision=75%, F1 score=78.5%). Moreover, after comprehensive exploration, we presented a parsimonious Stacking model where around 5 features selected by the all-relevant FS approach Boruta were used in each iteration of validation and had a maximum precision of 77.4% (balanced accuracy=77.95%). Feature importance analysis presents app usage behavioral markers containing the diurnal usage patterns as more important compared to the aggregated data-based markers. Apart from these, SHAP analysis on our best models presented the behavioral markers that have a relation with depression. For instance, the non-depressed students’ spending time on Education apps was higher on weekdays while depressed students used a higher number of Photo & Video apps and also had a higher deviation in using Photo & Video apps over the day of the weekend.Conclusions: Due to the faster and minimalistic nature, our system may make a worthwhile contribution to identifying depression in underdeveloped and developing regions. In addition, our detailed discussion about the implication of findings can facilitate the development of resource insensitive systems, in better understanding the depressed students and taking steps in intervention.

show abstract

Section: The Implication Of the Findingssupporting

confidence: 85%

Section: Feature Selectionmentioning

confidence: 99%

A Minimal and Faster System to Identify Depression Through Smartphone: An Explainable Machine Learning-Based Approach

Ahmed¹,

Ahmed²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Although a recent study extracted parametric rhythmic feature–dominant periods from smartphone usage data [ 32 ], the study was limited by not exploring rhythmic features, such as the acrophase, interdaily stability (IS), intradaily variability (IV), and relative amplitude (RA). In addition, the study explored mere screen usage, without any exploration of more informative features [ 33 ], such as entropy data–based features.…”

Section: Introductionmentioning

confidence: 99%

“…In human life, physiological changes reappear in a cyclable waveform [ 38 ]. Rhythm features based on physiological data have been explored in both the chronobiology [ 39 ] and pervasive health [ 32 ] areas. Researchers have found a relation between physiological data–based rhythmic markers and health status [ 32 ].…”

Section: Introductionmentioning

confidence: 99%

“…Rhythm features based on physiological data have been explored in both the chronobiology [ 39 ] and pervasive health [ 32 ] areas. Researchers have found a relation between physiological data–based rhythmic markers and health status [ 32 ]. These markers can find out subtle differences that enable marker-based features to predict hospital readmission [ 40 ] and to identify loneliness and the depression class [ 32 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigating Rhythmicity in App Usage to Predict Depressive Symptoms: Protocol for Personalized Framework Development and Validation Through a Countrywide Study

Ahmed,

Hasan,

Islam

et al. 2024

JMIR Res Protoc

View full text Add to dashboard Cite

Background Understanding a student’s depressive symptoms could facilitate significantly more precise diagnosis and treatment. However, few studies have focused on depressive symptom prediction through unobtrusive systems, and these studies are limited by small sample sizes, low performance, and the requirement for higher resources. In addition, research has not explored whether statistically significant rhythms based on different app usage behavioral markers (eg, app usage sessions) exist that could be useful in finding subtle differences to predict with higher accuracy like the models based on rhythms of physiological data. Objective The main objective of this study is to explore whether there exist statistically significant rhythms in resource-insensitive app usage behavioral markers and predict depressive symptoms through these marker-based rhythmic features. Another objective of this study is to understand whether there is a potential link between rhythmic features and depressive symptoms. Methods Through a countrywide study, we collected 2952 students’ raw app usage behavioral data and responses to the 9 depressive symptoms in the 9-item Patient Health Questionnaire (PHQ-9). The behavioral data were retrieved through our developed app, which was previously used in our pilot studies in Bangladesh on different research problems. To explore whether there is a rhythm based on app usage data, we will conduct a zero-amplitude test. In addition, we will develop a cosinor model for each participant to extract rhythmic parameters (eg, acrophase). In addition, to obtain a comprehensive picture of the rhythms, we will explore nonparametric rhythmic features (eg, interdaily stability). Furthermore, we will conduct regression analysis to understand the association of rhythmic features with depressive symptoms. Finally, we will develop a personalized multitask learning (MTL) framework to predict symptoms through rhythmic features. Results After applying inclusion criteria (eg, having app usage data of at least 2 days to explore rhythmicity), we kept the data of 2902 (98.31%) students for analysis, with 24.48 million app usage events, and 7 days’ app usage of 2849 (98.17%) students. The students are from all 8 divisions of Bangladesh, both public and private universities (19 different universities and 52 different departments). We are analyzing the data and will publish the findings in a peer-reviewed publication. Conclusions Having an in-depth understanding of app usage rhythms and their connection with depressive symptoms through a countrywide study can significantly help health care professionals and researchers better understand depressed students and may create possibilities for using app usage–based rhythms for intervention. In addition, the MTL framework based on app usage rhythmic features may more accurately predict depressive symptoms due to the rhythms’ capability to find subtle differences. International Registered Report Identifier (IRRID) DERR1-10.2196/51540

show abstract

Exploring Structure Incentive Domain Adversarial Learning for Generalizable Sleep Stage Classification

Ma,

Zhang,

Chen

et al. 2024

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Sleep stage classification is crucial for sleep state monitoring and health interventions. In accordance with the standards prescribed by the American Academy of Sleep Medicine, a sleep episode follows a specific structure comprising five distinctive sleep stages that collectively form a sleep cycle. Typically, this cycle repeats about five times, providing an insightful portrayal of the subject’s physiological attributes. The progress of deep learning and advanced domain generalization methods allows automatic and even adaptive sleep stage classification. However, applying models trained with visible subject data to invisible subject data remains challenging due to significant individual differences among subjects. Motivated by the periodic category-complete structure of sleep stage classification, we propose a Structure Incentive Domain Adversarial learning (SIDA) method that combines the sleep stage classification method with domain generalization to enable cross-subject sleep stage classification. SIDA includes individual domain discriminators for each sleep stage category to decouple subject dependence differences among different categories and fine-grained learning of domain-invariant features. Furthermore, SIDA directly connects the label classifier and domain discriminators to promote the training process. Experiments on three benchmark sleep stage classification datasets demonstrate that the proposed SIDA method outperforms other state-of-the-art sleep stage classification and domain generalization methods and achieves the best cross-subject sleep stage classification results.

show abstract

A Computational Framework for Modeling Biobehavioral Rhythms from Mobile and Wearable Data Streams

Cited by 10 publications

References 62 publications

A Minimal and Faster System to Identify Depression Through Smartphone: An Explainable Machine Learning-Based Approach

A Minimal and Faster System to Identify Depression Through Smartphone: An Explainable Machine Learning-Based Approach

Investigating Rhythmicity in App Usage to Predict Depressive Symptoms: Protocol for Personalized Framework Development and Validation Through a Countrywide Study

Exploring Structure Incentive Domain Adversarial Learning for Generalizable Sleep Stage Classification

Contact Info

Product

Resources

About