Skip to content

[Researchers] Digital phenotyping

Eli Jones edited this page Sep 27, 2021 · 1 revision

Definition

Digital phenotyping is the “moment-by-moment quantification of the individual-level human phenotype ''in situ'' using data from personal digital devices,” in particular smartphones. This is our definition of the concept and it highlights some of the important aspects of digital phenotyping, such as using existing personal devices rather than introducing additional instrumentation. To truly leverage moment-by-moment data collected ''in situ'', in the wild, one must rely on the use of passive data, i.e., smartphone sensor and usage data.

Digital Phenotyping vs. Text-Based Surveys

Of the many different phenotype classes, behavior has presented special challenges for phenomics, the systematic study of phenotypes on a genome-wide scale, because of its temporal nature and context dependence. The traditional approach to behavioral phenotyping has relied on pen-and-paper surveys, but these self-reported accounts tend to be highly unreliable and subject to different kinds of recall biases. Ecological momentary assessment (EMA) is an approach that attempts to survey subjects’ behaviors and experiences in real time in their natural environments. EMA used to be carried out using specialized hardware, such personal digital assistants, limiting its scalability, but can now be implemented on smartphones. While EMA can certainly provide interesting insights into behavior, as a survey methodology it suffers from the same problems that all surveys do, mainly ''reliance on subjective accounts of behavior rather than objective measurement of behavior''. Other limitations are that frequent surveys require active user engagement, which may be difficult with certain clinical populations, and long-term adherence is also typically low. Frequent surveying also causes respondent fatigue, and may inadvertently constitute an intervention. Finally, our preliminary findings suggest that subjects are less likely to take surveys under two diagonally opposite situations, either when they are doing very well or when they are doing very poorly. This means that survey data tend to be unavailable at times when it may be most insightful.

Phenotypes Acquired Using Digital Phenotyping

To date, Onnela Lab has focused on phenotyping behavioral patterns including sleep, social interactions, physical mobility, gross motor activity, cognitive functioning, and speech production, among others using passively collected data from smartphones. Digital phenotyping is also compatible with the RDoC research framework for studying mental disorders. As defined by the NIMH, the framework consists of a matrix, where the rows represent specific dimension of function (Domains and Constructs) and the columns represent areas for study (Units of Analysis). The five domains of the RDoC matrix are negative valence systems (responsible for responses to averse situations), positive valence systems (responsible to positive situations), cognitive systems (responsible for cognitive processes), systems for social processes (mediating responses to interpersonal settings), and arousal / regulatory systems (responsible for generating activation of neural systems). The daily use of smartphones generates a byproduct of rich social and behavioral data, and when complemented with surveys and audio diary entries, these data can address several of the RDoC domains and several units of analysis (self-report, behavior, and physiology).

Mobile Health (mHealth) vs. Digital Phenotyping

Mobile health (also, mHealth or m-health) is a broad category and can be defined in different ways, but it usually refers to the “delivery of healthcare services via mobile communication devices.” Digital phenotyping, by definition, refers to the collection and analysis of moment-by-moment individual-level human phenotype data in situ, in the wild, using data from personal digital devices, in particular smartphones. The main goal of digital phenotyping is to advance evidence-based research in the biomedical sciences, and as such it can be seen as part of deep phenotyping, which supports other approaches to phenotyping and natural complements genotyping and genome sequencing.

Cost

The digital phenotyping approach is incredibly cost effective and scalable. In the near future, we anticipate that one will be able to carry out digital phenotyping for as little as $1 per subject-year, which translates to about $75 per lifetime cost. It is important to point out that these are very early days for digital phenotyping in terms of technology, data, data analysis, and science. Phenotyping is often contrasted with genotyping. The first sequencing of the whole human genome cost roughly $2.7 billion in 2003, whereas in 2017, research-grade whole genome sequencing costs around $750. These numbers are certainly approximate, but they suggest that the life-time cost of smartphone-based digital phenotyping would be about 10% of the cost of sequencing.

If you're interested in using Beiwe for your digital phenotyping research, investigators have two different ways of using Beiwe in their studies:

  1. Beiwe Service Center. For more information, see Beiwe Service Center.

  2. Beiwe Open Source. The Beiwe research platform source code is available to investigators worldwide for free on Github under the permissive 3-clause BSD open source license. Under this model, individuals or institutions interested in using Beiwe will set up their own AWS account and then deploy Beiwe using one of two different ways (single server deployment vs. server cluster deployment). The Beiwe apps, named Beiwe2 for open source users, are available for free on Apple’s App Store and Google’s Play Store. In this model, the investigators using the open source version would naturally be responsible for all expenses.

Clone this wiki locally