Deep learning paired with wearable passive sensing data predicts deterioration in anxiety disorder symptoms across 17–18 years

Jacobson, Nicholas C.; Lekkas, Damien; Huang, Raphael; Thomas, Natalie

doi:10.1016/j.jad.2020.12.086

Cited by 45 publications

(44 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wearable sensor technologies are slowly replacing human-based phenotyping in the medical industry. The capacity of digital biomarkers to offer phenotypic predictions of long-term prognosis using wearable sensors has been demonstrated for predicting anxiety symptoms [25], estimating depression severity [26], and detecting daily life stress [27]. There are plenty of reasons that support this digitally dependent shift, but here are two of the most prominent reasons relating to agriculture.…”

Section: Wearable Sensor Technologies In Phenotypingmentioning

confidence: 99%

Digital Phenotyping in Livestock Farming

Neethirajan

Kemp

2021

Animals

View full text Add to dashboard Cite

Currently, large volumes of data are being collected on farms using multimodal sensor technologies. These sensors measure the activity, housing conditions, feed intake, and health of farm animals. With traditional methods, the data from farm animals and their environment can be collected intermittently. However, with the advancement of wearable and non-invasive sensing tools, these measurements can be made in real-time for continuous quantitation relating to clinical biomarkers, resilience indicators, and behavioral predictors. The digital phenotyping of humans has drawn enormous attention recently due to its medical significance, but much research is still needed for the digital phenotyping of farm animals. Implications from human studies show great promise for the application of digital phenotyping technology in modern livestock farming, but these technologies must be directly applied to animals to understand their true capacities. Due to species-specific traits, certain technologies required to assess phenotypes need to be tailored efficiently and accurately. Such devices allow for the collection of information that can better inform farmers on aspects of animal welfare and production that need improvement. By explicitly addressing farm animals’ individual physiological and mental (affective states) needs, sensor-based digital phenotyping has the potential to serve as an effective intervention platform. Future research is warranted for the design and development of digital phenotyping technology platforms that create shared data standards, metrics, and repositories.

show abstract

Section: Wearable Sensor Technologies In Phenotypingmentioning

confidence: 99%

Digital Phenotyping in Livestock Farming

Neethirajan

Kemp

2021

Animals

View full text Add to dashboard Cite

show abstract

“…Wearable sensor technologies are slowly replacing human-based phenotyping in the medical industry. The capacity of digital biomarkers to offer phenotypic predictions of long-term prognosis using wearable sensors has been demonstrated for predicting anxiety symptoms [22], estimating depression severity [23], and detection of daily life stress [24]. There are plenty of reasons that support this digitally dependent shift, but here are two of the most prominent reasons relating to agriculture.…”

Section: Wearable Sensor Technologies In Phenotypingmentioning

confidence: 99%

Digital Phenotyping in Livestock Farming

Neethirajan¹,

Kemp²

2021

Preprint

View full text Add to dashboard Cite

Currently, large volumes of data are being collected on farms using multimodal sensor technol-ogies. These sensors measure the activity, housing conditions, feed intake, and health of farm animals. With traditional methods, the data from farm animals and their environment can be collected intermittently. However, with the advancement of wearable and non-invasive sensing tools, these measurements can be made in real-time for continuous quantitation relating to clinical biomarkers, resilience indicators, and behavioral predictors. The digital phenotyping of humans has drawn enormous attention recently due to its medical significance, but much research is still needed for the digital phenotyping of farm animals. Implications from human studies show great promise for the application of digital phenotyping technology in modern livestock farming, but these technologies must be directly applied to animals to understand their true capacities. Due to species-specific traits, certain technologies required to assess phenotypes need to be tailored ef-ficiently and accurately. Such devices allow for the collection of information that can better inform farmers on aspects of animal welfare and production that need improvement. By explicitly ad-dressing farm animals’ individual physiological and mental (affective states) needs, sensor-based digital phenotyping has the potential to serve as an effective intervention platform. Future re-search is warranted for the design and development of digital phenotyping technology platforms that create shared data standards, metrics, and repositories.

show abstract

“…Study 2. Jacobson et al (2020) use actigraphy data to predict longer term deterioration in generalized anxiety disorder and panic disorder symptoms. The actigraphy data involved continuously monitored movement data from both rest/sleep and activity periods.…”

Section: Moving Beyond Exploratory and Confirmatorymentioning

confidence: 99%

“…This data was then engineered to generate derivative and periodicity data, resulting in a total set of 800 features. Their hypothesis is stated as: "…we hypothesized we could predict deterioration in anxiety symptoms over 17-18 years with high precision using machine learning models based on digital biomarkers formed from movement data" (p. 105; Jacobson et al, 2020).…”

Section: Moving Beyond Exploratory and Confirmatorymentioning

confidence: 99%

“…The clear answer is no and can be attributed to the large number of variables, complexity in performing dimension reduction, and uncertainty with regards to the functional form of a large number of predictors. I view the Jacobson et al (2020) study as being representative of an increasing degree of modern psychological research that is predictive in nature as opposed to based solely on explanatory aims. In prediction research, hypotheses often take much different forms, as was demonstrated above.…”

Section: Moving Beyond Exploratory and Confirmatorymentioning

confidence: 99%

See 1 more Smart Citation

A Critique of Using the Labels Confirmatory and Exploratory in Modern Psychological Research

Jacobucci¹

2021

Preprint

View full text Add to dashboard Cite

Psychological science has seen a rise in the application of complex statistical models to ever larger datasets, while at the same time, had a renewed focus on applying research in a confirmatory manner. This presents a fundamental conflict for psychological researchers as more complex forms of modeling necessarily eschew as stringent of theoretical constraints. In this paper, I argue that this is less of a conflict, and more a result of a continued adherence to applying the overly simplistic labels of exploratory and confirmatory. I make the case that psychological science would be better off replacing these terms with reporting higher levels of detail regarding the ever-increasing number of data and model decisions that are made, such as discussing whether the study is primarily concerned with theory generation, development, or appraisal, the study has the goal of explanation or prediction, the study involves non-traditional hypotheses, among others. This is demonstrated through the examination of two previously published studies that are both characteristic of the challenges faced by new forms of data and models in psychological science.

show abstract

Deep learning paired with wearable passive sensing data predicts deterioration in anxiety disorder symptoms across 17–18 years

Cited by 45 publications

References 51 publications

Digital Phenotyping in Livestock Farming

Digital Phenotyping in Livestock Farming

Digital Phenotyping in Livestock Farming

A Critique of Using the Labels Confirmatory and Exploratory in Modern Psychological Research

Contact Info

Product

Resources

About