Early Prediction of Hemodynamic Shock in the Intensive Care Units with Deep Learning on Thermal Videos

Vats, Vanshika; Nagori, Aditya; Singh, Pradeep; Dutt, Raman; Bandhey, Harsh; Wason, Mahika; Lodha, Rakesh; Sethi, Tavpritesh

doi:10.21203/rs.3.rs-464338/v1

Cited by 2 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various studies are currently underway to quickly detect such a shock situation. Two studies [14,15] predicted hemodynamic shock by analyzing and learning image data. Even today, there are various methods for various shocks.…”

Section: Shock Treatmentmentioning

confidence: 99%

IoT-based Architecture and Implementation for Automatic Shock Treatment

2022

KSII TIIS

View full text Add to dashboard Cite

The Internet of Things (IoT) is being used in a wide variety of fields due to the recent 4th industrial revolution. In particular, research is being conducted that combines IoT with the medical field such as telemedicine. Among them, the field of shock detection is a big issue in the medical field because the causes of shock are diverse, treatments are very complex, and require a high level of medical knowledge and experience. The transmission of infectious diseases is common when treating critically ill patients, especially patients with shock. Thus, to effectively care for shock patients, we propose an architecture that continuously monitors the patient's condition, and automatically recommends a drug injection treatment according to the patient's shock condition. The patient's hemodynamic information is continuously monitored, and the patient's shock generation information is recorded periodically. With the recorded patient information, the patient's condition is determined and automatically injected with necessary medication. The medical team can find out whether the patient's condition has improved by checking the recorded information through web applications. The study can help relieve the shortage of medical personnel and help prevent transmission of infectious disease in medical staff. We look forward to playing a role in helping medical staff by making recommendations for the diagnosis and treatment of complex and difficult shocks.

show abstract

Section: Shock Treatmentmentioning

confidence: 99%

IoT-based Architecture and Implementation for Automatic Shock Treatment

2022

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Our current study includes 124 recording sessions from 65 UHID patients. The details of the data procurement procedure are described in the Supplementary methods S1 Section in Vanshika et al [5] supplementary files.…”

Section: Safeicu Frameworkmentioning

confidence: 99%

“…The thermal camera is placed at an appropriate distance from the patient in order to avoid any direct contact or disturbance during routine check-ups as stated in Vanshika et al [5]. The camera orientation is done in a way that captures the full body of the infant in a standard color-scaling.…”

Section: Thermal Imaging Setupmentioning

confidence: 99%

See 1 more Smart Citation

Heart Rate Assessment in a Pediatric ICU with Non-Contact Infrared Thermography and Machine Learning

Kaur

Prajapati

Singh

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Heart rate is one of the vital signs for monitoring health. Non-invasive, non-contact assessment of heart rate can lead to safe and potentially telemedicine based monitoring. Thermal videos as a modality for capturing heart rate has been underexplored. Regions with large vessels such as the face can capture the pulsatile change in temperature associated with the blood flow. The use of a machine learning-based approach to capture heart rate from continuous thermal videos is currently lacking. Our present clinical investigation comprises the continuous monitoring of heart rate from a smaller number of samples by using a combination of an efficient deep-learning-based segmentation followed by domain-knowledge-based feature calculation for estimating heart rate from 124 thermal imaging videos comprising 3,628,087 frames of 65 patients, admitted to the pediatric intensive care unit at AIIMS, New Delhi. We hypothesized that periodic fluctuations of thermal intensity over the face can capture heart rate. Frequency domain features for thermal time series were extracted followed by supervised learning using a battery of models. A random forest model yielded the best results with a root mean squared error of 24.54 and mean absolute percentage error of 16.129. Clinical profiling of the model showed a wide range of clinical conditions in the admitted children with acceptable model performance. Affordable and commercially available thermal cameras establish the feasibility and cost viability of exploring deployments for patient heart rate estimation in non-invasive and non-contact environments.

show abstract

Early Prediction of Hemodynamic Shock in the Intensive Care Units with Deep Learning on Thermal Videos

Cited by 2 publications

References 25 publications

IoT-based Architecture and Implementation for Automatic Shock Treatment

IoT-based Architecture and Implementation for Automatic Shock Treatment

Heart Rate Assessment in a Pediatric ICU with Non-Contact Infrared Thermography and Machine Learning

Contact Info

Product

Resources

About