Dataset Information

Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors.

ABSTRACT: Infants' spontaneous and voluntary movements mirror developmental integrity of brain networks since they require coordinated activation of multiple sites in the central nervous system. Accordingly, early detection of infants with atypical motor development holds promise for recognizing those infants who are at risk for a wide range of neurodevelopmental disorders (e.g., cerebral palsy, autism spectrum disorders). Previously, novel wearable technology has shown promise for offering efficient, scalable and automated methods for movement assessment in adults. Here, we describe the development of an infant wearable, a multi-sensor smart jumpsuit that allows mobile accelerometer and gyroscope data collection during movements. Using this suit, we first recorded play sessions of 22 typically developing infants of approximately 7 months of age. These data were manually annotated for infant posture and movement based on video recordings of the sessions, and using a novel annotation scheme specifically designed to assess the overall movement pattern of infants in the given age group. A machine learning algorithm, based on deep convolutional neural networks (CNNs) was then trained for automatic detection of posture and movement classes using the data and annotations. Our experiments show that the setup can be used for quantitative tracking of infant movement activities with a human equivalent accuracy, i.e., it meets the human inter-rater agreement levels in infant posture and movement classification. We also quantify the ambiguity of human observers in analyzing infant movements, and propose a method for utilizing this uncertainty for performance improvements in training of the automated classifier. Comparison of different sensor configurations also shows that four-limb recording leads to the best performance in posture and movement classification.

SUBMITTER: Airaksinen M

PROVIDER: S-EPMC6957504 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors.

Airaksinen Manu M Räsänen Okko O Ilén Elina E Häyrinen Taru T Kivi Anna A Marchi Viviana V Gallen Anastasia A Blom Sonja S Varhe Anni A Kaartinen Nico N Haataja Leena L Vanhatalo Sampsa S

Scientific reports 20200113 1

Infants' spontaneous and voluntary movements mirror developmental integrity of brain networks since they require coordinated activation of multiple sites in the central nervous system. Accordingly, early detection of infants with atypical motor development holds promise for recognizing those infants who are at risk for a wide range of neurodevelopmental disorders (e.g., cerebral palsy, autism spectrum disorders). Previously, novel wearable technology has shown promise for offering efficient, sca ...[more]

PMID: 31932616

Similar Datasets

Project description:Describing and understanding close proximity interactions between infant and family members can provide key information on transmission opportunities of respiratory infections within households. Among respiratory infections, pertussis represents a public health priority. Pertussis infection can be particularly harmful to young, unvaccinated infants and for these patients, family members represent the main sources of transmission. Here, we report on the use of wearable proximity sensors based on RFID technology to measure face-to-face proximity between family members within 16 households with infants younger than 6 months for 2-5 consecutive days of data collection. The sensors were deployed over the course of approximately 1 year, in the context of a national research project aimed at the improvement of infant pertussis prevention strategies. We investigated differences in close-range interactions between family members and we assessed whether demographic variables or feeding practices affect contact patterns between parents and infants. A total of 5,958 contact events were recorded between 55 individuals: 16 infants, 4 siblings, 31 parents and 4 grandparents. The aggregated contact networks, obtained for each household, showed a heterogeneous distribution of the cumulative time spent in proximity with the infant by family members. Contact matrices defined by age and by family role showed that most of the contacts occurred between the infant and other family members (70%), while 30% of contacts was among family members (infants excluded). Many contacts were observed between infants and adults, in particular between infant and mother, followed by father, siblings and grandparents. A larger number of contacts and longer contact durations between infant and other family members were observed in families adopting exclusive breastfeeding, compared to families in which the infant receives artificial or mixed feeding. Our results demonstrate how a high-resolution measurement of contact matrices within infants' households is feasible using wearable proximity sensing devices. Moreover, our findings suggest the mother is responsible for the large majority of the infant's contact pattern, thus being the main potential source of infection for a transmissible disease. As the contribution to the infants' contact pattern by other family members is very variable, vaccination against pertussis during pregnancy is probably the best strategy to protect young, unvaccinated infants.

Project description:The use of wearable sensors allows continuous recordings of physical activity from participants in free-living or at-home clinical studies. The large amount of data collected demands automatic analysis pipelines to extract gait parameters that can be used as clinical endpoints. We introduce a deep learning-based automatic pipeline for wearables that processes tri-axial accelerometry data and extracts gait events-bout segmentation, initial contact (IC), and final contact (FC)-from a single sensor located at either the lower back (near L5), shin or wrist. The gait events detected are posteriorly used for gait parameter estimation, such as step time, length, and symmetry. We report results from a leave-one-subject-out (LOSO) validation on a pilot study dataset of five participants clinically diagnosed with Parkinson's disease (PD) and six healthy controls (HC). Participants wore sensors at three body locations and walked on a pressure-sensing walkway to obtain reference gait data. Mean absolute errors (MAE) for the IC events ranged from 22.82 to 33.09 milliseconds (msecs) for the lower back sensor while for the shin and wrist sensors, MAE ranges were 28.56-64.66 and 40.19-72.50 msecs, respectively. For the FC-event detection, MAE ranges were 29.06-48.42, 40.19-72.70 and 36.06-60.18 msecs for the lumbar, wrist and shin sensors, respectively. Intraclass correlation coefficients, ICC(2,k), between the estimated parameters and the reference data resulted in good-to-excellent agreement (ICC ≥ 0.84) for the lumbar and shin sensors, excluding the double support time (ICC = 0.37 lumbar and 0.38 shin) and swing time (ICC = 0.55 lumbar and 0.59 shin). The wrist sensor also showed good agreements, but the ICCs were lower overall than for the other two sensors. Our proposed analysis pipeline has the potential to extract up to 100 gait-related parameters, and we expect our contribution will further support developments in the fields of wearable sensors, digital health, and remote monitoring in clinical trials.

Project description:Fetal movements (FM) are an important factor in the assessment of fetal health. However, there is currently no reliable way to monitor FM outside clinical environs. While extensive research has been carried out using accelerometer-based systems to monitor FM, the desired accuracy of detection is yet to be achieved. A major challenge has been the difficulty of testing and calibrating sensors at the pre-clinical stage. Little is known about fetal movement features, and clinical trials involving pregnant women can be expensive and ethically stringent. To address these issues, we introduce a novel FM simulator, which can be used to test responses of sensor arrays in a laboratory environment. The design uses a silicon-based membrane with material properties similar to that of a gravid abdomen to mimic the vibrations due to fetal kicks. The simulator incorporates mechanisms to pre-stretch the membrane and to produce kicks similar to that of a fetus. As a case study, we present results from a comparative study of an acoustic sensor, an accelerometer, and a piezoelectric diaphragm as candidate vibration sensors for a wearable FM monitor. We find that the acoustic sensor and the piezoelectric diaphragm are better equipped than the accelerometer to determine durations, intensities, and locations of kicks, as they have a significantly greater response to changes in these conditions than the accelerometer. Additionally, we demonstrate that the acoustic sensor and the piezoelectric diaphragm can detect weaker fetal movements (threshold wall displacements are less than 0.5 mm) compared to the accelerometer (threshold wall displacement is 1.5 mm) with a trade-off of higher power signal artefacts. Finally, we find that the piezoelectric diaphragm produces better signal-to-noise ratios compared to the other two sensors in most of the cases, making it a promising new candidate sensor for wearable FM monitors. We believe that the FM simulator represents a key development towards enabling the eventual translation of wearable FM monitoring garments.

Dataset Information

Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors.

Publications

Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets