Validating the Tele-diagnostic Potential of Affordable Thermography in a Big-data Data-enabled ICU

Singh

Firdos

et al. 2021

Preprint

Self Cite

Shock is a major killer in the ICU and Deep learning based early predictions can potentially save lives. Generalization across age and geographical context is an unaddressed challenge. In this retrospective observational study, we built real-time shock prediction models generalized across age groups and continents. More than 1.5 million patient-hours of novel data from a pediatric ICU in New Delhi and 5 million patient-hours from the adult ICU MIMIC database were used to build models. We achieved model generalization through a novel fractal deep-learning approach and predicted shock up to 12 hours in advance. Our deep learning models showed a receiver operating curve (AUROC) drop from 78% (95%CI, 73-83) on MIMIC data to 66% (95%CI, 54-78) on New Delhi data, outperforming standard machine learning by nearly a 10% gap. Therefore, better representations and deep learning can partly address the generalizability-gap of ICU prediction models trained across geographies. Our data and algorithms are publicly available as a pre-configured docker environment at https://github.com/SAFE-ICU/ShoQPred.

Section: Dataset Description and Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Generalized Prediction of Hemodynamic Shock in Intensive Care Units

Singh

Firdos

et al. 2021

Preprint

Self Cite

“…The most recent minimally invasive way to get sufficient data is to work on the thermal images [6] . The studies have found out that the possibility of shock can be determined using the temperature difference observed between the abdomen and foot of the patient (Centre-to-Peripheral Difference) [7][8] .…”

Section: Introductionmentioning

confidence: 99%

“…Percentage difference of segmented body parts, identified as abdomen and foot were taken, termed as Centre to Peripheral Difference (CPD). These segmentation models were trained on the images collected during May-September 2016 and February-April 2017 [6,9] . The extracted CPD time-series along with vitals time-series were used to predict the future (1-12 hr) hemodynamic shock using sequence models called Long-Short Term Memory (LSTM).…”

mentioning

confidence: 99%

“…The copyright holder for this this version posted November 15, 2020. ; https://doi.org/10.1101/2020.11.12.20230441 doi: medRxiv preprint extracted from the data warehouse at 15s intervals (SAFE ICU) [6] . A comparison was made between the shock and non-shock groups using either Wilcoxon rank sum test or two-tailed Student's t-test, after testing for normality by D'Agostino-Pearson normality test using GraphPad Prism version 6.00, GraphPad Software, La Jolla California USA, www.graphpad.com.…”

mentioning

confidence: 99%

See 1 more Smart Citation

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

Vats

Singh

et al. 2020

Preprint

Self Cite

Shock is one of the major killers in ICUs and early interventions can potentially reverse it. In this study, we advance a non-contact thermal imaging modality to continuous monitoring of hemodynamic shock working on 406 patient videos of 256 seconds length for 22 patients longitudinally. Deep learning was performed upon these videos to extract Center-to-Peripheral Difference (CPD) in temperature values. CPD along with heart rate, was finally analysed to predict the shock status up to next 12 hours using Long-Short Term Memory models. Our models achieved best area under the receiver-operating-characteristics curve of 0.81 ± 0.06 and area under precision-recall curve of 0.78 ± 0.05 at 5 hours, providing sufficient time to stabilize the patient. Our approach, thus, provides a reliable prediction using an automated decision pipeline, that can save lives and provide better care.

Predicting Hemodynamic Shock from Thermal Images using Machine Learning

Dhingra

Bhatnagar

et al. 2019

Sci Rep

Self Cite

Proactive detection of hemodynamic shock can prevent organ failure and save lives. Thermal imaging is a non-invasive, non-contact modality to capture body surface temperature with the potential to reveal underlying perfusion disturbance in shock. In this study, we automate early detection and prediction of shock using machine learning upon thermal images obtained in a pediatric intensive care unit of a tertiary care hospital. 539 images were recorded out of which 253 had concomitant measurement of continuous intra-arterial blood pressure, the gold standard for shock monitoring. Histogram of oriented gradient features were used for machine learning based region-of-interest segmentation that achieved 96% agreement with a human expert. The segmented center-to-periphery difference along with pulse rate was used in longitudinal prediction of shock at 0, 3, 6 and 12 hours using a generalized linear mixed-effects model. The model achieved a mean area under the receiver operating characteristic curve of 75% at 0 hours (classification), 77% at 3 hours (prediction) and 69% at 12 hours (prediction) respectively. Since hemodynamic shock associated with critical illness and infectious epidemics such as Dengue is often fatal, our model demonstrates an affordable, non-invasive, non-contact and tele-diagnostic decision support system for its reliable detection and prediction.