61 Medizin und Gesundheit
Filtern
Dokumenttyp
Sprache
- Englisch (37)
Volltext vorhanden
- ja (37)
Gehört zur Bibliographie
- nein (37)
Schlagworte
- Rückenschmerz (11)
- Physikalische Therapie (5)
- Maschinelles Lernen (4)
- low back pain (4)
- stratified care (4)
- Elektrode (3)
- Intervention <Medizin> (3)
- Jugend (3)
- Sport (3)
- Sportler (3)
Institut
Background: Improving movement control might be a promising treatment goal during chronic non-specific low back pain (CLBP) rehabilitation. The objective of the study is to evaluate the effect of a single bout of game-based real-time feedback intervention on trunk movement in patients with CLBP.
Methods: Thirteen CLBP patients (8female;41 ± 16 years;173 ± 10 cm;78 ± 22 kg) were included in this randomized cross-over pilot trial. During one laboratory session (2 h), participants performed three identical measurements on trunk movement all including: first, maximum angle of lateral flexion was assessed. Secondly, a target trunk lateral flexion (angle: 20°) was performed. Main outcome was maximum angle ([°]; MA). Secondary outcomes were deviation [°] from the target angle (angle reproduction; AR) and MA of the secondary movement planes (rotation; extension/flexion) during lateral flexion. The outcomes were assessed by an optical 3D-motion-capture-system (2-segment-trunk-model). The measurements were separated by 12-min of intervention and/or resting (randomly). The intervention involved a sensor-based trunk exergame (guiding an avatar through virtual worlds). After carryover effect-analysis, pre-to-post intervention data were pooled between the two sequences followed by analyses of variances (paired t-test).
Results: No significant change from pre to post intervention for MA or AR for any segment occurred for the main movement plane, lateral flexion (p > .05). The upper trunk segment showed a significant decrease of the MA for trunk extension/flexion from pre to post intervention ((4.4° ± 4.4° (95% CI 7.06–1.75)/3.5° ± 1.29° (95% CI 6.22–0.80); p = 0.02, d = 0.20).
Conclusions: A single bout of game-based real-time feedback intervention lead to changes in the secondary movement planes indicating reduced evasive motion during trunk movement.
Background: High numbers of consumable medical materials (eg, sterile needles and swabs) are used during the daily routine of intensive care units (ICUs) worldwide. Although medical consumables largely contribute to total ICU hospital expenditure, many hospitals do not track the individual use of materials. Current tracking solutions meeting the specific requirements of the medical environment, like barcodes or radio frequency identification, require specialized material preparation and high infrastructure investment. This impedes the accurate prediction of consumption, leads to high storage maintenance costs caused by large inventories, and hinders scientific work due to inaccurate documentation. Thus, new cost-effective and contactless methods for object detection are urgently needed.
Objective: The goal of this work was to develop and evaluate a contactless visual recognition system for tracking medical consumable materials in ICUs using a deep learning approach on a distributed client-server architecture.
Methods: We developed Consumabot, a novel client-server optical recognition system for medical consumables, based on the convolutional neural network model MobileNet implemented in Tensorflow. The software was designed to run on single-board computer platforms as a detection unit. The system was trained to recognize 20 different materials in the ICU, while 100 sample images of each consumable material were provided. We assessed the top-1 recognition rates in the context of different real-world ICU settings: materials presented to the system without visual obstruction, 50% covered materials, and scenarios of multiple items. We further performed an analysis of variance with repeated measures to quantify the effect of adverse real-world circumstances.
Results: Consumabot reached a >99% reliability of recognition after about 60 steps of training and 150 steps of validation. A desirable low cross entropy of <0.03 was reached for the training set after about 100 iteration steps and after 170 steps for the validation set. The system showed a high top-1 mean recognition accuracy in a real-world scenario of 0.85 (SD 0.11) for objects presented to the system without visual obstruction. Recognition accuracy was lower, but still acceptable, in scenarios where the objects were 50% covered (P<.001; mean recognition accuracy 0.71; SD 0.13) or multiple objects of the target group were present (P=.01; mean recognition accuracy 0.78; SD 0.11), compared to a nonobstructed view. The approach met the criteria of absence of explicit labeling (eg, barcodes, radio frequency labeling) while maintaining a high standard for quality and hygiene with minimal consumption of resources (eg, cost, time, training, and computational power).
Conclusions: Using a convolutional neural network architecture, Consumabot consistently achieved good results in the classification of consumables and thus is a feasible way to recognize and register medical consumables directly to a hospital’s electronic health record. The system shows limitations when the materials are partially covered, therefore identifying characteristics of the consumables are not presented to the system. Further development of the assessment in different medical circumstances is needed.