Machine learning for activity recognition : hip versus wrist data

Problem addressed Wrist-worn accelerometers are associated with greater compliance. However, validated algorithms for predicting activity type from wrist-worn accelerometer data are lacking. This study compared the activity recognition rates of an activity classifier trained on acceleration signal collected on the wrist and hip. Methodology 52 children and adolescents (mean age 13.7 +/- 3.1 year) completed 12 activity trials that were categorized into 7 activity classes: lying down, sitting, standing, walking, running, basketball, and dancing. During each trial, participants wore an ActiGraph GT3X+ tri-axial accelerometer on the right hip and the non-dominant wrist. Features were extracted from 10-s windows and inputted into a regularized logistic regression model using R (Glmnet + L1). Results Classification accuracy for the hip and wrist was 91.0% +/- 3.1% and 88.4% +/- 3.0%, respectively. The hip model exhibited excellent classification accuracy for sitting (91.3%), standing (95.8%), walking (95.8%), and running (96.8%); acceptable classification accuracy for lying down (88.3%) and basketball (81.9%); and modest accuracy for dance (64.1%). The wrist model exhibited excellent classification accuracy for sitting (93.0%), standing (91.7%), and walking (95.8%); acceptable classification accuracy for basketball (86.0%); and modest accuracy for running (78.8%), lying down (74.6%) and dance (69.4%). Potential Impact Both the hip and wrist algorithms achieved acceptable classification accuracy, allowing researchers to use either placement for activity recognition.

The effect of topical adrenergic and anticholinergic agents on the choroidal thickness of young healthy adults

The human choroid is capable of rapidly changing its thickness in response to a variety of stimuli. However little is known about the role of the autonomic nervous system in the regulation of the thickness of the choroid. Therefore, we investigated the effect of topical parasympatholytic and sympathomimetic agents upon the choroidal thickness and ocular biometrics of young healthy adult subjects. Fourteen subjects (mean age 27.9 ± 4 years) participated in this randomized, single-masked, placebo-controlled study. Each subject had measurements of choroidal thickness (ChT) and ocular biometrics of their right eye taken before, and then 30 and 60 min following the administration of topical pharmacological agents. Three different drugs: 2% homatropine hydrobromide, 2.5% phenylephrine hydrochloride and a placebo (0.3% hydroxypropyl methylcellulose) were tested in all subjects; each on different days (at the same time of the day) in randomized order. Participants were masked to the pharmacological agent being used at each testing session. The instillation of 2% homatropine resulted in a small but significant increase in subfoveal ChT at 30 and 60 min after drug instillation (mean change 7 ± 3 μm and 14 ± 2 μm respectively; both p < 0.0001). The parafoveal choroid also exhibited a similar magnitude, significant increase in thickness with time after 2% homatropine (p < 0.001), with a mean change of 7 ± 0.3 μm and 13 ± 1 μm (in the region located 0.5 mm from the fovea center), 6 ± 1 μm and 12.5 ± 1 μm (1 mm from the fovea center) and 6 ± 2 μm and 12 ± 2 μm (1.5 mm from the fovea center) after 30 and 60 min respectively. Axial length decreased significantly 60 min after homatropine (p < 0.01). There were also significant changes in lens thickness (LT) and anterior chamber depth (ACD) (p < 0.05) associated with homatropine instillation. No significant changes in choroidal thickness, or ocular biometrics were found after 2.5% phenylephrine or placebo at any examination points (p > 0.05). In human subjects, significant increases in subfoveal and parafoveal choroidal thickness occurred after administration of 2% homatropine and this implies an involvement of the parasympathetic system in the control of choroidal thickness in humans.

Promoting and maintaining physical activity in the transition to retirement: A systematic review of interventions for adults around retirement age

It has been argued that transition points in life, such as the approach towards, and early years of retirement present key opportunities for interventions to improve the health of the population. Research has also highlighted inequalities in health status in the retired population and in response to interventions which should be addressed. We aimed to conduct a systematic review to synthesise international evidence on the types and effectiveness of interventions to increase physical activity among people around the time of retirement. A systematic review of literature was carried out between February 2014 and April 2015. Searches were not limited by language or location, but were restricted by date to studies published from 1990 onwards. Methods for identification of relevant studies included electronic database searching, reference list checking, and citation searching. Systematic search of the literature identified 104 papers which described study populations as being older adults. However, we found only one paper which specifically referred to their participants as being around the time of retirement. The intervention approaches for older adults encompassed: training of health care professionals; counselling and advice giving; group sessions; individual training sessions; in-home exercise programmes; in-home computer-delivered programmes; in-home telephone support; in-home diet and exercise programmes; and community-wide initiatives. The majority of papers reported some intervention effect, with evidence of positive outcomes for all types of programmes. A wide range of different measures were used to evaluate effectiveness, many were self-reported and few studies included evaluation of sedentary time. While the retirement transition is considered a significant point of life change, little research has been conducted to assess whether physical activity interventions at this time may be effective in promoting or maintaining activity, or reducing health inequalities. We were unable to find any evidence that the transition to retirement period was, or was not a significant point for intervention. Studies in older adults more generally indicated that a range of interventions might be effective for people around retirement age.