aditya nagori

aditya nagori

PhD Student, Artificial Intelligence for Critical Care

Strainflow

We developed Strainflow for SARS-CoV-2 genome sequences, where sequences were treated as documents with words (codons) to learn the codon context of 0.9 million spike genes using the skip-gram algorithm.

Sargun Nagpal, Ridam Pal, Ashima, Ananya Tyagi, Sadhana Tripathi, Aditya Nagori, Saad Ahmad, Hara Prasad Mishra, Tavpritesh Sethi, Rintu Kutum

Visit Project
Strainflow-image
5-Year Trends and Associations of Antimicrobial Resistance in Urinary Tract Infections in India (2017-2021): A Multi-Centric, Retrospective, Longitudinal Analysis

Urinary Tract Infections (UTIs) affect nearly 150 million people worldwide annually. High antimicrobial resistance (AMR) is reported in India. However, no studies provide multicentric, nationwide data on trends and associations of AMR in UTIs. To our knowledge, this study presents the most comprehensive estimates of trends and associations of AMR across India.

Read more

Jasmine Kaur, Aditya Nagori, Balaji Veeraraghavan, Vinod Ohri, Rakesh Lodha, Kamini Walia, Harpreet Singh, Tavpritesh Sethi

Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study

Evidence from peer-reviewed literature is the cornerstone for designing responses to global threats such as COVID-19. In massive and rapidly growing corpuses, such as COVID-19 publications, assimilating and synthesizing information is challenging. Leveraging a robust computational pipeline that evaluates multiple aspects, such as network topological features, communities, and their temporal trends, can make this process more efficient.

Read more

Ridam Pal, Harshita Chopra, Raghav Awasthi, Harsh Bandhey, Aditya Nagori, Amogh Gulati, Ponnurangam Kumaraguru, Tavpritesh Sethi

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

Genomic Surveillance of COVID-19 Variants with Language Models and Machine Learning

The global efforts to control COVID-19 are threatened by the rapid emergence of novel SARS-CoV-2 variants that may display undesirable characteristics such as immune escape, increased transmissibility or pathogenicity. Early prediction for emergence of new strains with these features is critical for pandemic preparedness. We present Strainflow, a supervised and causally predictive model using unsupervised latent space features of SARS-CoV-2 genome sequences. Strainflow was trained and validated on 0.9 million sequences for the period December, 2019 to June, 2021 and the frozen model was prospectively validated from July, 2021 to December, 2021. Strainflow captured the rise in cases 2 months ahead of the Delta and Omicron surges in most countries including the prediction of a surge in India as early as beginning of November, 2021. Entropy analysis of Strainflow unsupervised embeddings clearly reveals the explore-exploit cycles in genomic feature-space, thus adding interpretability to the deep learning based model. We also conducted codon-level analysis of our model for interpretability and biological validity of our unsupervised features. Strainflow application is openly available as an interactive web-application for prospective genomic surveillance of COVID-19 across the globe.

Read more

Sargun Nagpal, Ridam Pal, Ashima, Ananya Tyagi, Sadhana Tripathi, Aditya Nagori, Saad Ahmad, Hara Prasad Mishra, Rintu Kutum, Tavpritesh Sethi

Genomic Surveillance of COVID-19 Variants with Language Models and Machine Learning

The global efforts to control COVID-19 are threatened by the rapid emergence of novel SARS-CoV-2 variants that may display undesirable characteristics such as immune escape, increased transmissibility or pathogenicity. Early prediction for emergence of new strains with these features is critical for pandemic preparedness. We present Strainflow, a supervised and causally predictive model using unsupervised latent space features of SARS-CoV-2 genome sequences. Strainflow was trained and validated on 0.9 million sequences for the period December, 2019 to June, 2021 and the frozen model was prospectively validated from July, 2021 to December, 2021. Strainflow captured the rise in cases 2 months ahead of the Delta and Omicron surges in most countries including the prediction of a surge in India as early as beginning of November, 2021. Entropy analysis of Strainflow unsupervised embeddings clearly reveals the explore-exploit cycles in genomic feature-space, thus adding interpretability to the deep learning based model. We also conducted codon-level analysis of our model for interpretability and biological validity of our unsupervised features. Strainflow application is openly available as an interactive web-application for prospective genomic surveillance of COVID-19 across the globe.

Read more

Sargun Nagpal, Ridam Pal, Ashima, Ananya Tyagi, Sadhana Tripathi, Aditya Nagori, Saad Ahmad, Hara Prasad Mishra, Rintu Kutum, Tavpritesh Sethi

Genomic Surveillance of COVID-19 Variants with Language Models and Machine Learning

The global efforts to control COVID-19 are threatened by the rapid emergence of novel SARS-CoV-2 variants that may display undesirable characteristics such as immune escape or increased pathogenicity. Early prediction of emerging strains could be vital to pandemic preparedness but remains an open challenge. Here, we developed Strainflow, to learn the latent dimensions of 0.9 million high-quality SARS-CoV-2 genome sequences, and used machine learning algorithms to predict upcoming caseloads of SARS-CoV-2. In our Strainflow model, SARS-CoV-2 genome sequences were treated as documents, and codons as words to learn unsupervised codon embeddings (latent dimensions). We discovered that codon-level changes lead to a change in the entropy of the latent dimensions. We used a machine learning algorithm to find the most relevant latent dimensions called Dimensions of Concern (DoCs) of SARS-CoV-2 spike genes, and demonstrate their potential to provide a lead time for predicting new caseloads in several countries. The DoCs capture codons associated with global Variants of Concern (VOCs) and Variants of Interest (VOIs), and may be surveilled to predict country-specific emergence and spread of SARS-CoV-2 variants.

Read more

Sargun Nagpal, Ridam Pal, Ashima, Ananya Tyagi, Sadhana Tripathi, Aditya Nagori, Saad Ahmad, Hara Prasad Mishra, Rintu Kutum, 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

Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature with Dynamic Word Embedding Networks and Machine Learning

Read more

Ridam Pal, Harshita Chopra, Raghav Awasthi, Harsh Bandhey, Aditya Nagori, Amogh Gulati, Ponnurangam Kumaraguru, Tavpritesh Sethi

Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature with Dynamic Word Embedding Networks and Machine Learning

Read more

Ridam Pal, Harshita Chopra, Raghav Awasthi, Harsh Bandhey, Aditya Nagori, Amogh Gulati, Ponnurangam Kumaraguru, 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

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. (this http URL).

Read more

Raghav Awasthi, Keerat Kaur Guliani, Arshita Bhatt, Mehrab Singh Gill, Aditya Nagori, Ponnurangam Kumaraguru, Tavpritesh Sethi

Temperature and Humidity Do Not Influence Global COVID-19 Incidence as Inferred from Causal Models

The relationship between meteorological factors such as temperature and humidity with COVID-19 incidence is still unclear after 6 months of the beginning of the pandemic. Some literature confirms the association of temperature with disease transmission while some oppose the same. This work intends to determine whether there is a causal association between temperature, humidity and Covid-19 cases. Three different causal models were used to capture stochastic, chaotic and symbolic natured time-series data and to provide a robust & unbiased analysis by constructing networks of causal relationships between the variables. Granger-Causality method, Transfer Entropy method & Convergent Cross-Mapping (CCM) was done on data from regions with different temperatures and cases greater than 50,000 as of 13th May 2020. From the Granger-Causality test we found that in only Canada, the United Kingdom, temperature and daily new infections are causally linked. The same results were obtained from Convergent Cross Mapping for India. Again using Granger-Causality test, we found that in Russia only, relative humidity is causally linked to daily new cases. Thus, a Generalized Additive Model with a smoothing spline function was fitted for these countries to understand the directionality. Using the combined results of the said models, we were able to conclude that there is no evidence of a causal association between temperature, humidity and Covid-19 cases.

Read more

Raghav Awasthi, Aditya Nagori, Pradeep Singh, Ridam Pal, Vineet Joshi, Tavpritesh Sethi

Less Wrong COVID-19 Projections With Interactive Assumptions

COVID-19 pandemic is an enigma with uncertainty caused by biological and health systems factors. Although many models have been developed all around the world, transparent models that allow interacting with the assumptions will become more important as we test various strategies for lockdown, testing and social interventions and enable effective policy decisions. In this paper we developed a suite of models to guide development of policies under different scenarios when the lockdown opens. These had been deployed to create an interactive dashboard called COVision which includes the Agent based Models (ABM) and classical compartmental models i.e. Susceptible-Infected-Recovered (SIR) and Susceptible-Exposed-Infected-Recovered (SEIR) approaches. Our tool allows simulation of scenarios by changing strength of lockdown, basic reproduction number(R0), asymptomatic spread, testing rate, contact rate (Beta), recovery rate (Gamma), incubation period and starting number of cases. We optimized ABMs and classical compartmental models to fit the actual data, both of which performed well in terms of R-squared, root mean squared error (RMSE) and mean absolute percentage error (MAPE). Out of the three models in our suite, ABM was able to capture the data better than SIR and SEIR and achieved an RSQ of 92.3% for India and 89% for Maharashtra for the next 30 days. We also computed R0 using SIR and SEIR models which were found to be decreasing over the different periods of lockdown indicating the effectiveness of policies and interventions. Finally, we formulated ICU bed requirements using our best models. Our evaluation suggests that ABM models were able to capture the dynamic nature of the epidemic for a longer duration of time while classical SIR and SEIR models performed inefficiently for longer terms. The visual interactivity and ability to simulate outcomes under different parameters will allow the policymakers to make informed decisions for estimating the strength of lockdown to be implemented and testing rates. Further, our models were able to highlight the differences at state level for the parameters such as R0 and contact rates and hence can be applied for state specific decision making. An interactive dashboard http://covision.tavlab.iiitd.edu.in have been hosted as a web-server for the war level monitoring of the covid19 pandemic in India in public domain

Read more

Aditya Nagori, Raghav Awasthi, Vineet Joshi, Suryatej Reddy Vyalla, Akhil Jarodia, Chandan Gupta, Amogh Gulati, Harsh Bandhey, Ponnurangam Kumaraguru, Tavpritesh Sethi

CovidNLP: A Web Application for Distilling Systemic Implications of COVID-19 Pandemic with Natural Language Processing

The flood of conflicting COVID-19 research has revealed that COVID-19 continues to be an enigma. Although more than 14,000 research articles on COVID-19 have been published with the disease taking a pandemic proportion, clinicians and researchers are struggling to distill knowledge for furthering clinical management and research. In this study, we address this gap for a targeted user group, i.e. clinicians, researchers, and policymakers by applying natural language processing to develop a CovidNLP dashboard in order to speed up knowledge discovery. The WHO has created a repository of about more than 5000 peer-reviewed and curated research articles on varied aspects including epidemiology, clinical features, diagnosis, treatment, social factors, and economics. We summarised all the articles in the WHO Database through an extractive summarizer followed by an exploration of the feature space using word embeddings which were then used to visualize the summarized associations of COVID-19 as found in the text. Clinicians, researchers, and policymakers will not only discover the direct effects of COVID-19 but also the systematic implications such as the anticipated rise in TB and cancer mortality due to the non-availability of drugs during the export lockdown as highlighted by our models. These demonstrate the utility of mining massive literature with natural language processing for rapid distillation and knowledge updates. This can help the users understand, synthesize, and take pre-emptive action with the available peer-reviewed evidence on COVID-19. Our models will be continuously updated with new literature and we have made our resource CovidNLP publicly available in a user-friendly fashion at http://covidnlp.tavlab.iiitd.edu.in/.

Read more

Raghav Awasthi, Ridam Pal, Harshita Chopra, Harsh Bandhey, Pradeep Singh, Aditya Nagori, Suryatej Reddy, Amogh Gulati, Ponnurangam Kumaraguru, Tavpritesh Sethi

CovidNLP: A Web Application for Distilling Systemic Implications of COVID-19 Pandemic with Natural Language Processing

The flood of conflicting COVID-19 research has revealed that COVID-19 continues to be an enigma. Although more than 14,000 research articles on COVID-19 have been published with the disease taking a pandemic proportion, clinicians and researchers are struggling to distill knowledge for furthering clinical management and research. In this study, we address this gap for a targeted user group, i.e. clinicians, researchers, and policymakers by applying natural language processing to develop a CovidNLP dashboard in order to speed up knowledge discovery. The WHO has created a repository of about more than 5000 peer-reviewed and curated research articles on varied aspects including epidemiology, clinical features, diagnosis, treatment, social factors, and economics. We summarised all the articles in the WHO Database through an extractive summarizer followed by an exploration of the feature space using word embeddings which were then used to visualize the summarized associations of COVID-19 as found in the text. Clinicians, researchers, and policymakers will not only discover the direct effects of COVID-19 but also the systematic implications such as the anticipated rise in TB and cancer mortality due to the non-availability of drugs during the export lockdown as highlighted by our models. These demonstrate the utility of mining massive literature with natural language processing for rapid distillation and knowledge updates. This can help the users understand, synthesize, and take pre-emptive action with the available peer-reviewed evidence on COVID-19. Our models will be continuously updated with new literature and we have made our resource CovidNLP publicly available in a user-friendly fashion at http://covidnlp.tavlab.iiitd.edu.in/.

Read more

Raghav Awasthi, Ridam Pal, Harshita Chopra, Harsh Bandhey, Pradeep Singh, Aditya Nagori, Suryatej Reddy, Amogh Gulati, Ponnurangam Kumaraguru, 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

Stewarding antibiotic stewardship in intensive care units with Bayesian artificial intelligence

Emerging antimicrobial resistance (AMR) is a global threat to life. Injudicious use of antibiotics is the biggest driver of resistance evolution, creating selection pressures on micro-organisms. Intensive care units (ICUs) are the strongest contributors to this pressure, owing to high infection and antibiotic usage rates. Antimicrobial stewardship programs aim to control antibiotic use; however, these are mostly limited to descriptive statistics. Genomic analyses lie at the other extreme of the value-spectrum, and together these factors predispose to siloing of knowledge arising from AMR stewardship. In this study, we bridged the value-gap at a Pediatric ICU by creating Bayesian network (BN) artificial intelligence models with potential impacts on antibiotic stewardship. Methods, actionable insights and an interactive dashboard for BN analysis upon data observed over 3 years at the PICU are described. BNs have several desirable properties for reasoning from data, including interpretability, expert knowledge injection and quantitative inference. Our pipeline leverages best practices of enforcing statistical rigor through bootstrapping, ensemble averaging and Monte Carlo simulations. Competing, shared and independent drug resistances were discovered through the presence of network motifs in BNs. Inferences guided by these visual models are also discussed, such as increasing the sensitivity testing for chloramphenicol as a potential mechanism of avoiding ertapenem overuse in the PICU. Organism, tissue and temporal influences on drug co-resistances are also discussed. While the model represents inferences that are tailored to the site, BNs are excellent tools for building upon pre-learnt structures, hence the model and inferences were wrapped into an interactive dashboard not only deployed at the site, but also made openly available to the community via GitHub. Shared repositories of such models could be a viable alternative to raw-data sharing and could promote partnering, learning across sites and charting a joint course for antimicrobial stewardship programs in the race against AMR.

Read more

Tavpritesh Sethi, Shubham Maheshwari, Aditya Nagori, Rakesh Lodha

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