Using Wearable Cameras to Investigate Health-Related Daily Life Experiences: A Literature Review of Precautions and Risks in Empirical Studies

Using Computer Vision to Annotate Video-Recoded Direct Observation of Physical Behavior

Direct observation is a ground-truth measure for physical behavior, but the high cost limits widespread use. The purpose of this study was to develop and test machine learning methods to recognize aspects of physical behavior and location from videos of human movement: Adults (N = 26, aged 18-59 y) were recorded in their natural environment for two, 2- to 3-h sessions. Trained research assistants annotated videos using commercially available software including the following taxonomies: (1) sedentary versus non-sedentary (two classes); (2) activity type (four classes: sedentary, walking, running, and mixed movement); and (3) activity intensity (four classes: sedentary, light, moderate, and vigorous). Four machine learning approaches were trained and evaluated for each taxonomy. Models were trained on 80% of the videos, validated on 10%, and final accuracy is reported on the remaining 10% of the videos not used in training. Overall accuracy was as follows: 87.4% for Taxonomy 1, 63.1% for Taxonomy 2, and 68.6% for Taxonomy 3. This study shows it is possible to use computer vision to annotate aspects of physical behavior, speeding up the time and reducing labor required for direct observation. Future research should test these machine learning models on larger, independent datasets and take advantage of analysis of video fragments, rather than individual still images.

Development and testing of methods to record and follow up spells in patients with alternating hemiplegia of childhood

BACKGROUND

Developing methods to record Alternating Hemiplegia of Childhood (AHC) spells is essential for clinical trials and patient care.

OBJECTIVES

Test the following hypotheses: 1) Video-library training improves participants' ability to correctly identify AHC spells. 2) A custom-designed event-calendar with weekly reviews results in consistent documentation of such events over time. 3) Use of an electronic diary (e-Diary) to register events is a useful tool.

METHODS

1) A video-library of AHC type spells was developed along with specific training; the effect of the training was tested in 36 caregivers. 2) An event-calendar was similarly developed and provided to 5 caregivers with weekly videoconference meetings for 8 weeks. 3) An e-Diary was developed and offered to 33 patients; time of usage and caregivers' feedback (telephone interview) were analyzed.

RESULTS

1) Video-library training: Wilcoxon test showed improvement in caregiver identification of spells (p = 0.047), Cohen's Kappa demonstrated high degree of agreement between caregivers'-experts' classifications (>0.9). 2) Event-calendar: 96.42% of entries had complete information; this did not change during follow up (p = 0.804). 3) e-Diary: whereas 52% of respondents used the e-Diary when offered (duration: 10.5 ± 8.1 months), 96.3% indicated they would use it in future studies. Those who used it for 13 months, were very likely to use it during the rest of that year.

CONCLUSIONS

Video-library training improved spell identification. Calendar with weekly reviews resulted in a sustained and consistent record keeping. Caregivers' e-Diary feedback was encouraging with long-term usage in many. These approaches could be helpful for AHC and, potentially, in similar disorders.

Now you see it! Using wearable cameras to gain insights into the lived experience of cardiovascular conditions

Wearable cameras offer an innovative way to discover new insights into the lived experience of people with cardiovascular conditions. Wearable cameras can be used alone or supplement more traditional research methods, such as interviews and participant observations. This paper provides an overview of the benefits of using wearable cameras for data collection and outlines some key considerations for researchers and clinicians interested in this method. We provide a case study describing a study design using wearable cameras and how the data were used.