AI for Critical Care

Modern ICUs are equipped with a large number of sensors that generate humongous amounts of data besides a large number of clinical investigations. The use of artificial intelligence (AI) and frugal open-source technologies such as low-cost noncontact thermal monitoring can be effective for shock management.

critical-care
A Prospectively Validated Generalizable Model for Outcome Prognostication Using Shock Index in Intensive Care Units

Delays in identification of critical events in intensive care contribute to irreversible organ dysfunction and mortality(1). Shock Index(SI), calculated as the ratio of heart-rate and systolic blood pressure is a validated indicator for bedside examination, risk stratification, and prognostication(2,3). SI was originally designed for the evaluation of hemodynamic stability, with values >0.7 indicating shock. Shock is one of the highest contributors to higher mortality rates and SI has been used for the assessment of Shock in ICUs(4). The mortality rate in patients who develop shock in ICU is as high as 34% in developing countries(5). While in developing countries in Europe and North America the mortality rates are at 38% due to septic shock(6) Thus, prediction and early identification of Shock Index abnormality can help in initiating early life-saving therapies to prevent shock related mortality.(7). Early identification is critical for appropriate management(1), improved patient outcomes, and reduction of mortality(8–10).

Read more

Aditya Nagori, Pradeep Singh, Sameena Firdos, Vanshika Vats, Arushi Gupta, Harsh Bandhey, Anushtha Kalia, Arjun Sharma, Prakriti Ailavadi, Raghav Awasthi, Wrik Bhadra, Ayushmaan Kaul, Rakesh Lodha, Tavpritesh Sethi

Early prediction of hypothermia in pediatric intensive care units using machine learning

Hypothermia is a life-threatening condition where the temperature of the body drops below 35°C and is a key source of concern in Intensive Care Units (ICUs). Early identification can help to nudge clinical management to initiate early interventions. Despite its importance, very few studies have focused on the early prediction of hypothermia. In this study, we aim to monitor and predict Hypothermia (30 min-4 h) ahead of its onset using machine learning (ML) models developed on physiological vitals and to prospectively validate the best performing model in the pediatric ICU. We developed and evaluated ML algorithms for the early prediction of hypothermia in a pediatric ICU. Sepsis advanced forecasting engine ICU Database (SafeICU) data resource is an in-house ICU source of data built in the Pediatric ICU at the All-India Institute of Medical Science (AIIMS), New Delhi. Each time-stamp at 1-min resolution was labeled for the presence of hypothermia to construct a retrospective cohort of pediatric patients in the SafeICU data resource. The training set consisted of windows of the length of 4.2 h with a lead time of 30 min-4 h from the onset of hypothermia. A set of 3,835 hand-engineered time-series features were calculated to capture physiological features from the time series. Features selection using the Boruta algorithm was performed to select the most important predictors of hypothermia. A battery of models such as gradient boosting machine, random forest, AdaBoost, and support vector machine (SVM) was evaluated utilizing five-fold test sets. The best-performing model was prospectively validated. A total of 148 patients with 193 ICU stays were eligible for the model development cohort. Of 3,939 features, 726 were statistically significant in the Boruta analysis for the prediction of Hypothermia. The gradient boosting model performed best with an Area Under the Receiver Operating Characteristic curve (AUROC) of 85% (SD = 1.6) and a precision of 59.2% (SD = 8.8) for a 30-min lead time before the onset of Hypothermia onset. As expected, the model showed a decline in model performance at higher lead times, such as AUROC of 77.2% (SD = 2.3) and precision of 41.34% (SD = 4.8) for 4 h ahead of Hypothermia onset. Our GBM(gradient boosting machine) model produced equal and superior results for the prospective validation, where an AUROC of 79.8% and a precision of 53% for a 30-min lead time before the onset of Hypothermia whereas an AUROC of 69.6% and a precision of 38.52% for a (30 min-4 h) lead time prospective validation of Hypothermia. Therefore, this work establishes a pipeline termed ThermoGnose for predicting hypothermia, a major complication in pediatric ICUs.

Read more

Pradeep Singh, Aditya Nagori, Tavpritesh Sethi

Early Prediction of Hemodynamic Shock in Pediatric Intensive Care Units With Deep Learning on Thermal Videos

Shock is one of the major killers in intensive care units, and early interventions can potentially reverse it. In this study, we advance a noncontact thermal imaging modality for continuous monitoring of hemodynamic shock working on 1,03,936 frames from 406 videos recorded longitudinally upon 22 pediatric patients. Deep learning was used to preprocess and extract the Center-to-Peripheral Difference (CPD) in temperature values from the videos. This time-series data along with the heart rate was finally analyzed using Long-Short Term Memory models to predict the shock status up to the next 6 h. Our models achieved the best area under the receiver operating characteristic curve of 0.81 ± 0.06 and area under the precision-recall curve of 0.78 ± 0.05 at 5 h, providing sufficient time to stabilize the patient. Our approach, thus, provides a reliable shock prediction using an automated decision pipeline that can provide better care and save lives.

Read more

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

VacSIM: Learning effective strategies for COVID-19 vaccine distribution using reinforcement learning

A COVID-19 vaccine is our best bet for mitigating the ongoing onslaught of the pandemic. However, vaccine is also expected to be a limited resource. An optimal allocation strategy, especially in countries with access inequities and temporal separation of hot-spots, might be an effective way of halting the disease spread. We approach this problem by proposing a novel pipeline VacSIM that dovetails Deep Reinforcement Learning models into a Contextual Bandits approach for optimizing the distribution of COVID-19 vaccine. Whereas the Reinforcement Learning models suggest better actions and rewards, Contextual Bandits allow online modifications that may need to be implemented on a day-to-day basis in the real world scenario. We evaluate this framework against a naive allocation approach of distributing vaccine proportional to the incidence of COVID-19 cases in five different States across India (Assam, Delhi, Jharkhand, Maharashtra and Nagaland) and demonstrate up to 9039 potential infections prevented and a significant increase in the efficacy of limiting the spread over a period of 45 days through the VacSIM approach. Our models and the platform are extensible to all states of India and potentially across the globe. We also propose novel evaluation strategies including standard compartmental model-based projections and a causality-preserving evaluation of our model. Since all models carry assumptions that may need to be tested in various contexts, we open source our model VacSIM and contribute a new reinforcement learning environment compatible with OpenAI gym to make it extensible for real-world applications across the globe.

Read more

Raghav Awasthi, Keerat Kaur Guliani, Saif Ahmad Khan, Aniket Vashishtha, Mehrab Singh Gill, Arshita Bhatt, Aditya Nagori, Aniket Gupta, Ponnurangam Kumaraguru, Tavpritesh Sethi

Generalized Prediction of Hemodynamic Shock in Intensive Care Units

Early prediction of hemodynamic shock in the ICU can save lives. Several studies have leveraged a combination of vitals, lab investigations, and clinical data to construct early warning systems for shock. However, these have a limited potential of generalization to diverse settings due to reliance on non-real-time data. Monitoring data from vitals can provide an early real-time prediction of Hemodynamic shock which can precede the clinical diagnosis to guide early therapy decisions. 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 (adult and pediatric), ICU-types, and geographies. We trained, validated, and tested a shock prediction model on the publicly available eICU dataset on 208 ICUs across the United States. Data from 156 hospitals passed the eligibility criteria for cohort building. These were split hospital-wise in a five-fold training-validation-test set. External validation of the model was done on a pediatric ICU in New Delhi and MIMIC-III database with more than 0.23 million and one million patient-hours vitals data, respectively. Our models identified 92% of all the shock events more than 8 hours in advance with AUROC of 86 %(SD= 1.4) and AUPRC of 93% (SD =1.2) on the eICU testing set. An AUROC of 87 % (SD =1.8), AUPRC 92 % (SD=1.6) were obtained in external validation on the MIMIC-III cohort. The New Delhi Pediatric SafeICU data achieved an AUROC of 87 % (SD =4) AUPRC 91% (SD=3), despite being completely different geography and age group. In this first, we demonstrate a generalizable model for predicting shock, and algorithms are publicly available as a pre-configured Docker environment at https://github.com/tavlab-iiitd/ShoQPred.

Read more

Aditya Nagori, Pradeep Singh, Sameena Firdos, Vanshika Vats, Arushi Gupta, Harsh Bandhey, Anushtha Kalia, Arjun Sharma, Prakriti Ailavadi, Raghav Awasthi, Wrik Bhadra, Ayushmaan Kaul, Rakesh Lodha, Tavpritesh Sethi

Generalized Prediction of Shock in Intensive Care Units using Deep Learning

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.

Read more

Aditya Nagori, Anushtha Kalia, Arjun Sharma, Pradeep Singh, Harsh Bandhey, Prakriti Ailavadi, Raghav Awasthi, Wrik Bhadra, Ayushmaan Kaul, Rakesh Lodha, Tavpritesh Sethi

Predicting Hemodynamic Shock from Thermal Images using Machine Learning

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.

Read more

Aditya Nagori, Lovedeep Singh Dhingra, Ambika Bhatnagar, Rakesh Lodha, Tavpritesh Sethi

Early Prediction of Hemodynamic Shock in the ICU with Deep Learning on Thermal Videos

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.

Read more

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

Target Oxygen Saturation Among Preterm Neonates on Supplemental Oxygen Therapy: A Quality Improvement Study

Excessive oxygen use or hyperoxia among preterm neonates is associated with morbidities like retinopathy of prematurity (ROP) and chronic lung disease (CLD) [1]. Delivering optimal oxygen involves maintaining the oxygen saturation (SpO2) within a narrow range by adjusting the inspired oxygen concentration. In our neonatal intensive care unit (NICU), we observed that nurses faced difficulty in maintaining SpO2 of neonates within the unit’s target range, often resulting in fluctuating SpO2 values. We planned this quality improvement (QI) study to evaluate the existing compliance with oxygen saturation targeting in our NICU, and whether implementation of a unit policy on oxygen administration would improve the compliance.

Read more

Sindhu Sivanandan, Tavpritesh Sethi, Rakesh Lodha, Anu Thukral, Jeeva M Sankar, Ramesh Agarwal

Leveraging Thermal Patterns in Children for Telemedicine: Role of Affordable Imagers, Smartphones and Data-analytics

Smartphones combined with affordable technologies has a huge potential in Telemedicine and for better delivery of healthcare. We have used an affordable thermal camera combined with intensive patient monitoring and analytics to successfully enable digitization of whole body, non-contact sensing of temperature patterns. The utility of relative and absolute temperature patterns was tested for early diagnosis of various ailments such as circulatory shock. Image analytics combined with the development of computer algorithms enabled us to validate these patterns which can be deployed for remote community based care in the absence of adequate clinical staff and scarcity of resources. The use of this approach can help health workers such as ASHA workers to visualize, record and share whole body temperature patterns with the specialists via telemedicine helping them to make an informed decision. These techniques can be extended for use in adults and we plan to validate these for early detection of severe conditions eventually saving more lives through telemedicine.

Read more

Ambika Bhatnagar, Aditya Nagori, Richard Fletcher, Rakesh Lodha, Tavpritesh Sethi

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

The potential for whole body thermal patterns in diagnosis of hemodynamic perfusion disturbances in critical care as well as community settings is unexplored. In this study we have combined an in-house digitized Big-data resource from ICU settings with Infra-red thermography to derive novel inferences about the tele-diagnostic potential of IR thermography in diagnosis of shock and perfusion disturbances. While Data-science and Big-data are expected to revolutionize the next generation medicine and healthcare, the scientific efforts towards building Big-data resources for enhancing patient safety and healthcare governance are missing, especially in developing countries. We addressed this challenge and describe our experience on deployment of Big-data warehousing and data-analytics software using lean pipelines developed using open-source technologies and their utility in deriving knowledge and high utility patterns from Affordable Infrared Thermography. These knowledge frameworks and potentially translatable technology were developed in the Pediatric Intensive Care environment through extensive cross-talk between expert clinicians and data-scientists. In this work, we first demonstrate the successful creation of a unique Pediatric ICU resource of over 60,000 hours of continuous multivariate monitoring data followed by validation of the potential of whole body IR thermography in diagnosis of hemodynamic compromise. These patterns were validated through linear mixed models, a state-of-the-art statistical method for longitudinal data. The validated technology is affordable, and can be coupled to smartphones thus providing a huge potential in tele-medicine and electronic governance in healthcare and has the potential to be deployed in a tele-medicine setting with capturing of whole body temperature patterns by Accredited Social Health Activist (ASHA) workers. Therefore, this can enable early diagnosis of critical conditions such as sepsis and shock that are commonly associated with epidemics such as Dengue hemorrhagic fever in developing countries such as India. These images can be remotely shared with expert physicians and data-analysts via telemedicine thus aiding decisions in the Critical Care as well as Community settings.

Read more

Tavpritesh Sethi, Aditya Nagori, Ambika Bhatnagar, Priyanka Gupta, Richard Fletcher, Rakesh Lodha

Immune Response to Dengue Virus Infection in Pediatric Patients in New Delhi, India—Association of Viremia, Inflammatory Mediators and Monocytes with Disease Severity

Dengue virus, a mosquito-borne flavivirus, is a causative agent for dengue infection, which manifests with symptoms ranging from mild fever to fatal dengue shock syndrome. The presence of four serotypes, against which immune cross-protection is short-lived and serotype cross-reactive antibodies that might enhance infection, pose a challenge to further investigate the role of virus and immune response in pathogenesis. We evaluated the viral and immunological factors that correlate with severe dengue disease in a cohort of pediatric dengue patients in New Delhi. Severe dengue disease was observed in both primary and secondary infections. Viral load had no association with disease severity but high viral load correlated with prolonged thrombocytopenia and delayed recovery. Severe dengue cases had low Th1 cytokines and a concurrent increase in the inflammatory mediators such as IL-6, IL-8 and IL-10. A transient increase in CD14+CD16+ intermediate monocytes was observed early in infection. Sorting of monocytes from dengue patient peripheral blood mononuclear cells revealed that it is the CD14+ cells, but not the CD16+ or the T or B cells, that were infected with dengue virus and were major producers of IL-10. Using the Boruta algorithm, reduced interferon-α levels and enhanced aforementioned pro-inflammatory cytokines were identified as some of the distinctive markers of severe dengue. Furthermore, the reduction in the levels of IL-8 and IL-10 were identified as the most significant markers of recovery from severe disease. Our results provide further insights into the immune response of children to primary and secondary dengue infection and help us to understand the complex interplay between the intrinsic factors in dengue pathogenesis.

Read more

Mohit Singla, Meenakshi Kar, Tavpritesh Sethi, Sushil K. Kabra, Rakesh Lodha, Anmol Chandele, Guruprasad R. Medigeshi