Filtern
Erscheinungsjahr
- 2019 (2) (entfernen)
Dokumenttyp
- Wissenschaftlicher Artikel (Fachzeitschriften) (2) (entfernen)
Sprache
- Englisch (2)
Volltext vorhanden
- ja (2) (entfernen)
Gehört zur Bibliographie
- nein (2)
Schlagworte
- Bilderkennung (1)
- CO2 emissions (1)
- Convolutional Neural Network (1)
- Deep learning (1)
- Gesundheitsökonomie (1)
- Intensivpflege (1)
- Klimaschutz (1)
- Kohlendioxidemission (1)
- Künstliche Intelligenz (1)
- Maschinelles Lernen (1)
- Personenkraftwagen (1)
- artificial intelligence (1)
- climate policy (1)
- convolutional neural networks (1)
- critical care (1)
- deep learning (1)
- efficiency trade-offs (1)
- image recognition (1)
- intensive care (1)
- machine learning (1)
- medical consumables (1)
- medical economics (1)
- passenger cars (1)
- vehicle mass (1)
- vehicle power (1)
Institut
Passenger cars in Europe have become both heavier and more powerful over the past decades. This trend has increased vehicle utility but it might have also offset technical improvements in powertrain efficiency. Here, we analyze efficiency trade-offs and CO2 emissions for three popular compact cars in Germany. We find that mass, power, and front area of model variants has increased by 66%, 147%, and 22%, respectively between 1980 and 2018. In the same period, fuel consumption decreased 14% for gasoline models but it increased 9% for diesel models. However, if vehicle mass, power, and front area had remained at 1980 levels, technical efficiency improvements would have decreased the fuel consumption of gasoline and diesel models by 23% and 24%, respectively. The related efficiency trade-offs amount to 24 g CO2/km or 13% of the current fuel consumption for gasoline models and 40 g CO2/km or 25% of the current fuel consumption for diesel models. These findings suggest that about half of the technical efficiency improvements in gasoline models and all of the technical efficiency improvements in diesel models are offset through other vehicle attributes. By accounting for the observed efficiency trade-offs, climate policy could become more effective.
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.