Dataset Information

An automated ICU agitation monitoring system for video streaming using deep learning classification.

ABSTRACT:

Objective

To address the challenge of assessing sedation status in critically ill patients in the intensive care unit (ICU), we aimed to develop a non-contact automatic classifier of agitation using artificial intelligence and deep learning.

Methods

We collected the video recordings of ICU patients and cut them into 30-second (30-s) and 2-second (2-s) segments. All of the segments were annotated with the status of agitation as "Attention" and "Non-attention". After transforming the video segments into movement quantification, we constructed the models of agitation classifiers with Threshold, Random Forest, and LSTM and evaluated their performances.

Results

The video recording segmentation yielded 427 30-s and 6405 2-s segments from 61 patients for model construction. The LSTM model achieved remarkable accuracy (ACC 0.92, AUC 0.91), outperforming other methods.

Conclusion

Our study proposes an advanced monitoring system combining LSTM and image processing to ensure mild patient sedation in ICU care. LSTM proves to be the optimal choice for accurate monitoring. Future efforts should prioritize expanding data collection and enhancing system integration for practical application.

SUBMITTER: Dai PY

PROVIDER: S-EPMC10946151 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An automated ICU agitation monitoring system for video streaming using deep learning classification.

Dai Pei-Yu PY Wu Yu-Cheng YC Sheu Ruey-Kai RK Wu Chieh-Liang CL Liu Shu-Fang SF Lin Pei-Yi PY Cheng Wei-Lin WL Lin Guan-Yin GY Chung Huang-Chien HC Chen Lun-Chi LC

BMC medical informatics and decision making 20240318 1

<h4>Objective</h4>To address the challenge of assessing sedation status in critically ill patients in the intensive care unit (ICU), we aimed to develop a non-contact automatic classifier of agitation using artificial intelligence and deep learning.<h4>Methods</h4>We collected the video recordings of ICU patients and cut them into 30-second (30-s) and 2-second (2-s) segments. All of the segments were annotated with the status of agitation as "Attention" and "Non-attention". After transforming th ...[more]

PMID: 38500135

Similar Datasets

Project description:Malocclusions are a type of cranio-maxillofacial growth and developmental deformity that occur with high incidence in children. Therefore, a simple and rapid diagnosis of malocclusions would be of great benefit to our future generation. However, the application of deep learning algorithms to the automatic detection of malocclusions in children has not been reported. Therefore, the aim of this study was to develop a deep learning-based method for automatic classification of the sagittal skeletal pattern in children and to validate its performance. This would be the first step in establishing a decision support system for early orthodontic treatment. In this study, four different state-of-the-art (SOTA) models were trained and compared by using 1613 lateral cephalograms, and the best performance model, Densenet-121, was selected was further subsequent validation. Lateral cephalograms and profile photographs were used as the input for the Densenet-121 model, respectively. The models were optimized using transfer learning and data augmentation techniques, and label distribution learning was introduced during model training to address the inevitable label ambiguity between adjacent classes. Five-fold cross-validation was conducted for a comprehensive evaluation of our method. The sensitivity, specificity, and accuracy of the CNN model based on lateral cephalometric radiographs were 83.99, 92.44, and 90.33%, respectively. The accuracy of the model with profile photographs was 83.39%. The accuracy of both CNN models was improved to 91.28 and 83.98%, respectively, while the overfitting decreased after addition of label distribution learning. Previous studies have been based on adult lateral cephalograms. Therefore, our study is novel in using deep learning network architecture with lateral cephalograms and profile photographs obtained from children in order to obtain a high-precision automatic classification of the sagittal skeletal pattern in children.

Project description:BackgroundNystagmus identification and interpretation is challenging for non-experts who lack specific training in neuro-ophthalmology or neuro-otology. This challenge is magnified when the task is performed via telemedicine. Deep learning models have not been heavily studied in video-based eye movement detection.MethodsWe developed, trained, and validated a deep-learning system (aEYE) to classify video recordings as normal or bearing at least two consecutive beats of nystagmus. The videos were retrospectively collected from a subset of the monocular (right eye) video-oculography (VOG) recording used in the Acute Video-oculography for Vertigo in Emergency Rooms for Rapid Triage (AVERT) clinical trial (#NCT02483429). Our model was derived from a preliminary dataset representing about 10% of the total AVERT videos (n = 435). The videos were trimmed into 10-sec clips sampled at 60 Hz with a resolution of 240 × 320 pixels. We then created 8 variations of the videos by altering the sampling rates (i.e., 30 Hz and 15 Hz) and image resolution (i.e., 60 × 80 pixels and 15 × 20 pixels). The dataset was labeled as "nystagmus" or "no nystagmus" by one expert provider. We then used a filtered image-based motion classification approach to develop aEYE. The model's performance at detecting nystagmus was calculated by using the area under the receiver-operating characteristic curve (AUROC), sensitivity, specificity, and accuracy.ResultsAn ensemble between the ResNet-soft voting and the VGG-hard voting models had the best performing metrics. The AUROC, sensitivity, specificity, and accuracy were 0.86, 88.4, 74.2, and 82.7%, respectively. Our validated folds had an average AUROC, sensitivity, specificity, and accuracy of 0.86, 80.3, 80.9, and 80.4%, respectively. Models created from the compressed videos decreased in accuracy as image sampling rate decreased from 60 Hz to 15 Hz. There was only minimal change in the accuracy of nystagmus detection when decreasing image resolution and keeping sampling rate constant.ConclusionDeep learning is useful in detecting nystagmus in 60 Hz video recordings as well as videos with lower image resolutions and sampling rates, making it a potentially useful tool to aid future automated eye-movement enabled neurologic diagnosis.

Project description:BackgroundIn single-institution studies, overtriaging low-risk postoperative patients to ICUs has been associated with a low value of care; undertriaging high-risk postoperative patients to general wards has been associated with increased mortality and morbidity. This study tested the reproducibility of an automated postoperative triage classification system to generating an actionable, explainable decision support system.Study designThis longitudinal cohort study included adults undergoing inpatient surgery at two university hospitals. Triage classifications were generated by an explainable deep learning model using preoperative and intraoperative electronic health record features. Nearest neighbor algorithms identified risk-matched controls. Primary outcomes were mortality, morbidity, and value of care (inverted risk-adjusted mortality/total direct costs).ResultsAmong 4,669 ICU admissions, 237 (5.1%) were overtriaged. Compared with 1,021 control ward admissions, overtriaged admissions had similar outcomes but higher costs ($15.9K [interquartile range $9.8K to $22.3K] vs $10.7K [$7.0K to $17.6K], p < 0.001) and lower value of care (0.2 [0.1 to 0.3] vs 1.5 [0.9 to 2.2], p < 0.001). Among 8,594 ward admissions, 1,029 (12.0%) were undertriaged. Compared with 2,498 control ICU admissions, undertriaged admissions had longer hospital length-of-stays (6.4 [3.4 to 12.4] vs 5.4 [2.6 to 10.4] days, p < 0.001); greater incidence of hospital mortality (1.7% vs 0.7%, p = 0.03), cardiac arrest (1.4% vs 0.5%, p = 0.04), and persistent acute kidney injury without renal recovery (5.2% vs 2.8%, p = 0.002); similar costs ($21.8K [$13.3K to $34.9K] vs $21.9K [$13.1K to $36.3K]); and lower value of care (0.8 [0.5 to 1.3] vs 1.2 [0.7 to 2.0], p < 0.001).ConclusionsOvertriage was associated with low value of care; undertriage was associated with both low value of care and increased mortality and morbidity. The proposed framework for generating automated postoperative triage classifications is reproducible.

Project description:The COVID-19 pandemic has caused a worldwide catastrophe and widespread devastation that reeled almost all countries. The pandemic has mounted pressure on the existing healthcare system and caused panic and desperation. The gold testing standard for COVID-19 detection, reverse transcription-polymerase chain reaction (RT-PCR), has shown its limitations with 70% accuracy, contributing to the incorrect diagnosis that exaggerated the complexities and increased the fatalities. The new variations further pose unseen challenges in terms of their diagnosis and subsequent treatment. The COVID-19 virus heavily impacts the lungs and fills the air sacs with fluid causing pneumonia. Thus, chest X-ray inspection is a viable option if the inspection detects COVID-19-induced pneumonia, hence confirming the exposure of COVID-19. Artificial intelligence and machine learning techniques are capable of examining chest X-rays in order to detect patterns that can confirm the presence of COVID-19-induced pneumonia. This research used CNN and deep learning techniques to detect COVID-19-induced pneumonia from chest X-rays. Transfer learning with fine-tuning ensures that the proposed work successfully classifies COVID-19-induced pneumonia, regular pneumonia, and normal conditions. Xception, Visual Geometry Group 16, and Visual Geometry Group 19 are used to realize transfer learning. The experimental results were promising in terms of precision, recall, F1 score, specificity, false omission rate, false negative rate, false positive rate, and false discovery rate with a COVID-19-induced pneumonia detection accuracy of 98%. Experimental results also revealed that the proposed work has not only correctly identified COVID-19 exposure but also made a distinction between COVID-19-induced pneumonia and regular pneumonia, as the latter is a very common disease, while COVID-19 is more lethal. These results mitigated the concern and overlap in the diagnosis of COVID-19-induced pneumonia and regular pneumonia. With further integrations, it can be employed as a potential standard model in differentiating the various lung-related infections, including COVID-19.

Dataset Information

An automated ICU agitation monitoring system for video streaming using deep learning classification.

Objective

Methods

Results

Conclusion

Publications

An automated ICU agitation monitoring system for video streaming using deep learning classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets