Deep Learning‐Based Prediction Techniques for Medical Care: Opportunities and Challenges

Emergency Departments (EDs) provide an imperative source of medical care. Central to the ED workflow is the patientcaregiver scheduling, directed at getting the right patient to the right caregiver at the right time. Unfortunately, common ED scheduling practices are based on ad-hoc heuristics which may not be aligned with the complex and partially conflicting ED’s objectives. In this paper, we propose a novel online deep-learning scheduling approach for the automatic assignment and scheduling of medical personnel to arriving patients. Our approach allows for the optimization of explicit, hospitalspecific multi-variate objectives and takes advantage of available data, without altering the existing workflow of the ED. In an extensive empirical evaluation, using real-world data, we show that our approach can significantly improve an ED’s performance metrics.

Download Full-text

A Deep Learning Model for Estimation of Patients with Undiagnosed Diabetes

Applied Sciences ◽

10.3390/app10010421 ◽

2020 ◽

Vol 10 (1) ◽

pp. 421 ◽

Cited By ~ 1

Author(s):

Kwang Sun Ryu ◽

Sang Won Lee ◽

Erdenebileg Batbaatar ◽

Jae Wook Lee ◽

Kui Son Choi ◽

...

Keyword(s):

Deep Learning ◽

Medical Care ◽

Smoking Status ◽

Learning Model ◽

Machine Learning Techniques ◽

Undiagnosed Diabetes ◽

Training Dataset ◽

Family History Of Diabetes ◽

Screening Model ◽

Deep Learning Model

A screening model for undiagnosed diabetes mellitus (DM) is important for early medical care. Insufficient research has been carried out developing a screening model for undiagnosed DM using machine learning techniques. Thus, the primary objective of this study was to develop a screening model for patients with undiagnosed DM using a deep neural network. We conducted a cross-sectional study using data from the Korean National Health and Nutrition Examination Survey (KNHANES) 2013–2016. A total of 11,456 participants were selected, excluding those with diagnosed DM, an age < 20 years, or missing data. KNHANES 2013–2015 was used as a training dataset and analyzed to develop a deep learning model (DLM) for undiagnosed DM. The DLM was evaluated with 4444 participants who were surveyed in the 2016 KNHANES. The DLM was constructed using seven non-invasive variables (NIV): age, waist circumference, body mass index, gender, smoking status, hypertension, and family history of diabetes. The model showed an appropriate performance (area under curve (AUC): 80.11) compared with existing previous screening models. The DLM developed in this study for patients with undiagnosed diabetes could contribute to early medical care.

Download Full-text

Emergency Department Online Patient-Caregiver Scheduling

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.3301695 ◽

2019 ◽

Vol 33 ◽

pp. 695-701 ◽

Cited By ~ 1

Author(s):

Hanan Rosemarin ◽

Ariel Rosenfeld ◽

Sarit Kraus

Keyword(s):

Emergency Department ◽

Deep Learning ◽

Medical Care ◽

Real World ◽

Ad Hoc ◽

Performance Metrics ◽

Empirical Evaluation ◽

Medical Personnel ◽

Real World Data ◽

The Right

Emergency Departments (EDs) provide an imperative source of medical care. Central to the ED workflow is the patientcaregiver scheduling, directed at getting the right patient to the right caregiver at the right time. Unfortunately, common ED scheduling practices are based on ad-hoc heuristics which may not be aligned with the complex and partially conflicting ED's objectives. In this paper, we propose a novel online deep-learning scheduling approach for the automatic assignment and scheduling of medical personnel to arriving patients. Our approach allows for the optimization of explicit, hospital-specific multi-variate objectives and takes advantage of available data, without altering the existing workflow of the ED. In an extensive empirical evaluation, using real-world data, we show that our approach can significantly improve an ED's performance metrics.

Download Full-text

Deep Learning to Predict the Feasibility of Priority-Based Ethernet Network Configurations

ACM Transactions on Cyber-Physical Systems ◽

10.1145/3468890 ◽

2021 ◽

Vol 5 (4) ◽

pp. 1-26

Author(s):

Tieu Long Mai ◽

Nicolas Navet

Keyword(s):

Deep Learning ◽

Design Space Exploration ◽

Schedulability Analysis ◽

Training Data ◽

Traffic Patterns ◽

Ethernet Network ◽

Ethernet Networks ◽

Deadline Constraints ◽

Prediction Techniques ◽

Time Systems

Machine learning has been recently applied in real-time systems to predict whether Ethernet network configurations are feasible in terms of meeting deadline constraints without executing conventional schedulability analysis. However, the existing prediction techniques require domain expertise to choose the relevant input features and do not perform consistently when topologies or traffic patterns differ significantly from the ones in the training data. To overcome these problems, we propose a Graph Neural Network (GNN) prediction model that synthesizes relevant features directly from the raw data. This deep learning model possesses the ability to exploit relations among flows, links, and queues in switched Ethernet networks and generalizes to unseen topologies and traffic patterns. We also explore the use of ensembles of GNNs and show that it enhances the robustness of the predictions. An evaluation on heterogeneous testing sets comprising realistic automotive networks shows that ensembles of 32 GNN models feature a prediction accuracy ranging from 79.3% to 90% for Ethernet networks using priorities as the Quality-of-Service mechanism. The use of ensemble models provides a speedup factor ranging from 77 to 1,715 compared to schedulability analysis, which allows a far more extensive design space exploration.

Download Full-text

Visualizing veins from color skin images using convolutional neural networks

Journal of Innovative Optical Health Sciences ◽

10.1142/s1793545820500200 ◽

2020 ◽

Vol 13 (04) ◽

pp. 2050020

Author(s):

Chaoying Tang ◽

Yimin Yuan ◽

Shuhang Xia ◽

Gehua Ma ◽

Biao Wang

Keyword(s):

Deep Learning ◽

Medical Care ◽

Near Infrared ◽

Venous Access ◽

Color Transfer ◽

Auxiliary Equipment ◽

Transfer Scheme ◽

Medical Treatments ◽

Vein Access ◽

Optimization Parameters

Intravenous cannulation is the most important phase in medical practices. Currently, limited literature is available about visibility of veins and the characteristics of patients associated with difficult intravenous access. In modern medical treatment, a major challenge is locating veins for patients who have difficult venous access. Presently, some products of vein locators are available in the market to improve vein access, but they need auxiliary equipment such as near infrared (NIR) illumination and camera, which add weight and cost to the devices, and cause inconveniences to daily medical care. In this paper, a vein visualization algorithm based on the deep learning method was proposed. Based on a group of synchronous RGB/NIR arm images, a convolutional neural network (CNN) model was designed to implement the mapping from RGB to NIR images, where veins can be detected from skin. The model has a simple structure and less optimization parameters. A color transfer scheme was also proposed to make the network adaptive to the images taken by smartphone in daily medical treatments. Comprehensive experiments were conducted on three datasets to evaluate the proposed method. Subjective and objective evaluations showed the effectiveness of the proposed method. These results indicated that the deep learning-based method can be used for visualizing veins in medical care applications.

Download Full-text