BACKGROUND: Activities of daily living (ADL) are essential for independence and personal well-being, reflecting an individual\'s functional status. Impairment in executing these tasks can limit autonomy and negatively affect quality of life. The assessment of physical function during ADL is crucial for the prevention and rehabilitation of movement limitations. Still, its traditional evaluation based on subjective observation has limitations in precision and objectivity.
OBJECTIVE: The primary objective of this study is to use innovative technology, specifically wearable inertial sensors combined with artificial intelligence techniques, to objectively and accurately evaluate human performance in ADL. It is proposed to overcome the limitations of traditional methods by implementing systems that allow dynamic and noninvasive monitoring of movements during daily activities. The approach seeks to provide an effective tool for the early detection of dysfunctions and the personalization of treatment and rehabilitation plans, thus promoting an improvement in the quality of life of individuals.
METHODS: To monitor movements, wearable inertial sensors were developed, which include accelerometers and triaxial gyroscopes. The developed sensors were used to create a proprietary database with 6 movements related to the shoulder and 3 related to the back. We registered 53,165 activity records in the database (consisting of accelerometer and gyroscope measurements), which were reduced to 52,600 after processing to remove null or abnormal values. Finally, 4 deep learning (DL) models were created by combining various processing layers to explore different approaches in ADL recognition.
RESULTS: The results revealed high performance of the 4 proposed models, with levels of accuracy, precision, recall, and F1-score ranging between 95% and 97% for all classes and an average loss of 0.10. These results indicate the great capacity of the models to accurately identify a variety of activities, with a good balance between precision and recall. Both the convolutional and bidirectional approaches achieved slightly superior results, although the bidirectional model reached convergence in a smaller number of epochs.
CONCLUSIONS: The DL models implemented have demonstrated solid performance, indicating an effective ability to identify and classify various daily activities related to the shoulder and lumbar region. These results were achieved with minimal sensorization-being noninvasive and practically imperceptible to the user-which does not affect their daily routine and promotes acceptance and adherence to continuous monitoring, thus improving the reliability of the data collected. This research has the potential to have a significant impact on the clinical evaluation and rehabilitation of patients with movement limitations, by providing an objective and advanced tool to detect key movement patterns and joint dysfunctions.

In the era of big data, ecological research is experiencing a transformative shift, yet advancements in thermal ecology and the study of animal responses to climate conditions remain limited. This review discusses how big data analytics and artificial intelligence (AI) can significantly enhance our understanding of microclimates and animal behaviors under changing climatic conditions. We explore AI\'s potential to refine microclimate models and analyze data from advanced sensors and camera technologies, which capture detailed, high-resolution information. This integration allows researchers to dissect complex ecological and physiological processes with unprecedented precision. We describe how AI can enhance microclimate modeling through improved bias correction and downscaling techniques, providing more accurate estimates of the conditions that animals face under various climate scenarios. Additionally, we explore AI\'s capabilities in tracking animal responses to these conditions, particularly through innovative classification models that utilize sensors such as accelerometers and acoustic loggers. Moreover, the widespread usage of camera traps can benefit from AI-driven image classification models to accurately identify thermoregulatory responses, such as shade usage and panting. AI is therefore instrumental in monitoring how animals interact with their environments, offering vital insights into their adaptive behaviors. Finally, we discuss how these advanced data-driven approaches can inform and enhance conservation strategies. Detailed mapping of microhabitats essential for species survival under adverse conditions can guide the design of climate-resilient conservation and restoration programs that prioritize habitat features crucial for biodiversity resilience. In conclusion, the convergence of AI, big data, and ecological science heralds a new era of precision conservation, essential for addressing the global environmental challenges of the 21st century.

UNASSIGNED: More responsive, reliable, and clinically valid endpoints of disability are essential to reduce size, duration, and burden of clinical trials in adult persons with spinal muscular atrophy (aPwSMA).
UNASSIGNED: The aim is to investigate the feasibility of smartphone-based assessments in aPwSMA and provide evidence on the reliability and construct validity of sensor-derived measures (SDMs) of mobility and manual dexterity collected remotely in aPwSMA.
UNASSIGNED: Data were collected from 59 aPwSMA (23 walkers, 20 sitters and 16 non-sitters) and 30 age-matched healthy controls (HC). SDMs were extracted from five smartphone-based tests capturing mobility and manual dexterity, which were administered in-clinic and remotely in daily life for four weeks. Reliability (Intraclass Correlation Coefficients, ICC) and construct validity (ability to discriminate between HC and aPwSMA and correlations with Revised Upper Limb Module, RULM and Hammersmith Functional Scale - Expanded HFMSE) were quantified for all SDMs.
UNASSIGNED: The smartphone-based assessments proved feasible, with 92.1% average adherence in aPwSMA. The SDMs allowed to reliably assess both mobility and dexterity (ICC > 0.75 for 15/22 SDMs). Twenty-one out of 22 SDMs significantly discriminated between HC and aPwSMA. The highest correlations with the RULM were observed for SDMs from the manual dexterity tests in both non-sitters (Typing, ρ= 0.78) and sitters (Pinching, ρ= 0.75). In walkers, the highest correlation was between mobility tests and HFMSE (5 U-Turns, ρ= 0.79).
UNASSIGNED: This exploratory study provides preliminary evidence for the usability of smartphone-based assessments of mobility and manual dexterity in aPwSMA when deployed remotely in participants\' daily life. Reliability and construct validity of SDMs remotely collected in real-life was demonstrated, which is a pre-requisite for their use in longitudinal trials. Additionally, three novel smartphone-based performance outcome assessments were successfully established for aPwSMA. Upon further validation of responsiveness to interventions, this technology holds potential to increase the efficiency of clinical trials in aPwSMA.

UNASSIGNED: There is limited information about the relationship between physical activity (PA) and sedentary behaviors in chronic kidney disease (CKD). Therefore, this study aims to explore the associations of accelerometer-measured PA and sedentary behaviors with CKD.
UNASSIGNED: A cross-sectional study was conducted using data from the National Health and Nutrition Examination Survey in the 2003-2004 and 2005-2006 survey cycles. A uniaxial accelerometer measured physical activity (PA) and sedentary time (ST). The associations of PA and ST with estimated glomerular filtration rate (eGFR) and odds of CKD adopted the generalized linear regression, multivariable logistic regression, and isotemporal substitution models.
UNASSIGNED: A total of 5,990 adults with 605 CKD patients were included in this study. Compared with the individuals in the first quartile group, participants in the fourth quartile of low-intensity physical activity (LIPA), moderate to vigorous physical activity (MVPA), and ST were associated with 52% (35%, 65%) and 42% (14%, 62%) lower odds of CKD and 64% (17%, 131%) higher odds of CKD, respectively. Substituting 30 min/day of ST with equivalent LIPA/MVPA contributed to risk reduction in CKD.
UNASSIGNED: The findings suggest that increased LIPA and MVPA and reduced ST were associated with a lower risk of CKD and that replacing ST with LIPA may decrease the risk of CKD.

In recent decades, much work has been implemented in heart rate (HR) analysis using electrocardiographic (ECG) signals. We propose that algorithms developed to calculate HR based on detected R-peaks using ECG can be applied to seismocardiographic (SCG) signals, as they utilize common knowledge regarding heart rhythm and its underlying physiology. We implemented the experimental framework with methods developed for ECG signal processing and peak detection to be applied and evaluated on SCGs. Furthermore, we assessed and chose the best from all combinations of 15 peak detection and 6 preprocessing methods from the literature on the CEBS dataset available on Physionet. We then collected experimental data in the lab experiment to measure the applicability of the best-selected technique to the real-world data; the abovementioned method showed high precision for signals recorded during sitting rest (HR difference between SCG and ECG: 0.12 ± 0.35 bpm) and a moderate precision for signals recorded with interfering physical activity-reading out a book loud (HR difference between SCG and ECG: 6.45 ± 3.01 bpm) when compared to the results derived from the state-of-the-art photoplethysmographic (PPG) methods described in the literature. The study shows that computationally simple preprocessing and peak detection techniques initially developed for ECG could be utilized as the basis for HR detection on SCG, although they can be further improved.

The use of wearable sensors, such as inertial measurement units (IMUs), and machine learning for human intent recognition in health-related areas has grown considerably. However, there is limited research exploring how IMU quantity and placement affect human movement intent prediction (HMIP) at the joint level. The objective of this study was to analyze various combinations of IMU input signals to maximize the machine learning prediction accuracy for multiple simple movements. We trained a Random Forest algorithm to predict future joint angles across these movements using various sensor features. We hypothesized that joint angle prediction accuracy would increase with the addition of IMUs attached to adjacent body segments and that non-adjacent IMUs would not increase the prediction accuracy. The results indicated that the addition of adjacent IMUs to current joint angle inputs did not significantly increase the prediction accuracy (RMSE of 1.92° vs. 3.32° at the ankle, 8.78° vs. 12.54° at the knee, and 5.48° vs. 9.67° at the hip). Additionally, including non-adjacent IMUs did not increase the prediction accuracy (RMSE of 5.35° vs. 5.55° at the ankle, 20.29° vs. 20.71° at the knee, and 14.86° vs. 13.55° at the hip). These results demonstrated how future joint angle prediction during simple movements did not improve with the addition of IMUs alongside current joint angle inputs.

UNASSIGNED: Acetabular dysplasia (AD) causes pain, limited function, and development of early hip osteoarthritis. Periacetabular osteotomy (PAO) is a surgical treatment for AD that aims to reposition the acetabulum to reduce pain and improve function.
UNASSIGNED: To examine pain recovery and physical activity (PA) before and during the six months after PAO.
UNASSIGNED: Case series, prospective.
UNASSIGNED: Individuals with AD scheduled for PAO were enrolled. Pain intensity was evaluated before PAO and at one week and one, three, and six months following PAO. PA levels was evaluated before and six months following PAO using accelerometers (time spent in sedentary behavior, light PA, moderate-to-vigorous PA [MVPA], and daily steps) and the International Physical Activity Questionnaire (IPAQ; time spent in walking and in MVPA). Pain improvements was examined over time following PAO using a repeated-measures one-way ANOVA as well as improvements in PA levels before and six months after PAO using paired-sample t tests. In addition, time spent in MVPA was qualitatively summarized at each time point (before and six months after PAO) measured by both the accelerometers and IPAQ.
UNASSIGNED: Out of 49 screened participants, 28 were enrolled, and 23 individuals (22 females; age=23.1±7.9 years) completed both study visits. Compared to pre-PAO pain, participants reported significant improvements in pain at one month and onward following PAO (p\\<0.011). However, PA levels at six months following PAO did not differ from pre-PAO PA levels (p>0.05). Qualitatively, participants reported spending more time in MVPA recorded by the IPAQ (pre-PAO=73.3±150.2 mins/day; six-months after PAO=121.2±192.2 mins/day), compared with MVPA recorded by accelerometers (pre-PAO=22.6±25.2 mins/day; six-months after PAO=25.0±21.4 mins/day).
UNASSIGNED: Individuals with AD reported significant pain reduction at one month and up to six months after PAO, but PA levels did not change six months after PAO compared to baseline testing. Future studies should consider examining longitudinal pain recovery and PA improvements over longer periods of time with larger samples of individuals with AD undergoing PAO and identifying modifiable factors to minimize pain and increase PA participation.
UNASSIGNED: III.

[This corrects the article DOI: 10.3389/fped.2024.1361757.].

Length of the menstrual cycle was positively associated with antral follicle number in women. If this pattern is consistent in cattle, a value-added benefit to using automated activity monitors to determine estrous status could be the ability to predict antral follicle count (AFC). We, therefore, hypothesized that as inter-estrous interval increased ultrasonographic AFC would be greater in crossbred beef heifers. Over 3 yr, crossbred beef heifers (n = 1,394) were fitted with automated activity monitors for 81 d. From days 42 to 46, heifers were submitted for ultrasonographic examination to determine AFC. From days 60 to 81, heifers were visually observed twice daily for 45 min for signs of behavioral estrus. Heifers that had a behavioral estrus that coincided with a sensor-based estrus and had a previous sensor-based estrus between 15 and 26 d earlier were used for the analysis (n = 850). A combination of regression analyses and correlation analyses were applied to understand the association between data collected by sensors and follicle number determined by ultrasonographic examination. Antral follicle count was analyzed using the GLM procedure of SAS with estrous cycle length (15 to 26 d) as a fixed effect. Estrus was more likely to initiate in the early morning hours and peak activity was greater (P < 0.0001) when estrus initiated between 0200 and 0800 hours then when estrus initiated at other times of the day. Antral follicle count did not differ due to length of the estrous cycle (P = 0.87). Thus, length of the estrous cycle obtained from three-axis accelerometers cannot be used to predict follicle number in crossbred beef heifers; however, machine learning approaches that combine multiple features could be used to integrate parameters of activity with other relevant environmental and management data to quantify AFC and improve reproductive management in beef cows.

Accelerometers worn by animals produce distinct behavioral signatures, which can be classified accurately using machine learning methods such as random forest decision trees. The objective of this study was to identify accelerometer signal separation among parsimonious behaviors. We achieved this objective by (1) describing functional differences in accelerometer signals among discrete behaviors, (2) identifying the optimal window size for signal pre-processing, and (3) demonstrating the number of observations required to achieve the desired level of model accuracy,. Crossbred steers (Bos taurus indicus; n = 10) were fitted with GPS collars containing a video camera and tri-axial accelerometers (read-rate = 40 Hz). Distinct behaviors from accelerometer signals, particularly for grazing, were apparent because of the head-down posture. Increasing the smoothing window size to 10 s improved classification accuracy (p < 0.05), but reducing the number of observations below 50% resulted in a decrease in accuracy for all behaviors (p < 0.05). In-pasture observation increased accuracy and precision (0.05 and 0.08 percent, respectively) compared with animal-borne collar video observations.