AI for Public Healthcare

The COVID-19 pandemic has put immense pressure on health systems which are further strained due to the misinformation surrounding it. Under such a situation, providing the right information at the right time is crucial. There is a growing demand for the management of information spread using Artificial Intelligence. Hence, we have exploited the potential of Natural Language Processing for identifying relevant information that needs to be disseminated amongst the masses. In this work, we present a novel Cross-lingual Natural Language Processing framework to provide relevant information by matching daily news with trusted guidelines from the World Health Organization. The proposed pipeline deploys various techniques of NLP such as summarizers, word embeddings, and similarity metrics to provide users with news articles along with a corresponding healthcare guideline. A total of 36 models were evaluated and a combination of LexRank based summarizer on Word2Vec embedding with Word Mover distance metric outperformed all other models. This novel open-source approach can be used as a template for proactive dissemination of relevant healthcare information in the midst of misinformation spread associated with epidemics.

Ridam Pal, Rohan Pandey, Vaibhav Gautam, Kanav Bhagat, Tavpritesh Sethi

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).

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

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/.

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

The COVID-19 pandemic has uncovered the potential of digital misinformation in shaping the health of nations. The deluge of unverified information that spreads faster than the epidemic itself is an unprecedented phenomenon that has put millions of lives in danger. Mitigating this ‘Infodemic’ requires strong health messaging systems that are engaging, vernacular, scalable, effective and continuously learn the new patterns of misinformation.

Rohan Pandey, Vaibhav Gautam, Ridam Pal, Harsh Bandhey, Lovedeep Singh Dhingra, Himanshu Sharma, Chirag Jain, Kanav Bhagat, Arushi Arushi, Lajjaben Patel, Mudit Agarwal, Samprati Agrawal, Rishabh Jalan, Ayush Garg, Akshat Wadhwa, Vihaan Misra, Yashwin Agrawal, Bhavika Rana, Ponnurangam Kumaraguru, Tavpritesh Sethi

Life-expectancy is a complex outcome driven by genetic, socio-demographic, environmental and geographic factors. Increasing socio-economic and health disparities in the United States are propagating the longevity-gap, making it a cause for concern. Earlier studies have probed individual factors but an integrated picture to reveal quantifiable actions has been missing. There is a growing concern about a further widening of healthcare inequality caused by Artificial Intelligence (AI) due to differential access to AI-driven services. Hence, it is imperative to explore and exploit the potential of AI for illuminating biases and enabling transparent policy decisions for positive social and health impact. In this work, we reveal actionable interventions for decreasing the longevity-gap in the United States by analyzing a County-level data resource containing healthcare, socio-economic, behavioral, education and demographic features. We learn an ensemble-averaged structure, draw inferences using the joint probability distribution and extend it to a Bayesian Decision Network for identifying policy actions. We draw quantitative estimates for the impact of diversity, preventive-care quality and stable-families within the unified framework of our decision network. Finally, we make this analysis and dashboard available as an interactive web-application for enabling users and policy-makers to validate our reported findings and to explore the impact of ones beyond reported in this work.

Tavpritesh Sethi, Anant Mittal, Shubham Maheshwari, Samarth Chugh

n Ayurveda system of medicine individuals are classified into seven constitution types, “Prakriti”, for assessing disease susceptibility and drug responsiveness. Prakriti evaluation involves clinical examination including questions about physiological and behavioural traits. A need was felt to develop models for accurately predicting Prakriti classes that have been shown to exhibit molecular differences. The present study was carried out on data of phenotypic attributes in 147 healthy individuals of three extreme Prakriti types, from a genetically homogeneous population of Western India. Unsupervised and supervised machine learning approaches were used to infer inherent structure of the data, and for feature selection and building classification models for Prakriti respectively. These models were validated in a North Indian population. Unsupervised clustering led to emergence of three natural clusters corresponding to three extreme Prakriti classes. The supervised modelling approaches could classify individuals, with distinct Prakriti types, in the training and validation sets. This study is the first to demonstrate that Prakriti types are distinct verifiable clusters within a multidimensional space of multiple interrelated phenotypic traits. It also provides a computational framework for predicting Prakriti classes from phenotypic attributes. This approach may be useful in precision medicine for stratification of endophenotypes in healthy and diseased populations.

Pradeep Tiwari, Rintu Kutum, Tavpritesh Sethi, Ankita Shrivastava, Bhushan Girase, Shilpi Aggarwal, Rutuja Patil, Dhiraj Agarwal, Pramod Gautam, Anurag Agrawal, Debasis Dash, Saurabh Ghosh, Sanjay Juvekar, Mitali Mukerji, Bhavana Prasher

Knowledge of long-term outcomes following an index episode of acute severe colitis (ASC) can help informed decision-making at a time of acute exacerbation especially when colectomy is an option. We aimed to identify long-term outcomes and their predictors after a first episode of ASC in a large North Indian cohort. Methods: Hospitalized patients satisfying Truelove and Witts' criteria under follow-up at a single centre from January 2003-December 2013 were included. Patients avoiding colectomy at index admission were categorized as complete (≤3 non bloody stool per day) or incomplete responders (CR, IR), based upon response to corticosteroids at day 7. Random Forest based machine learning models were constructed to predict the long term risk of colectomy or steroid dependence following an index episode of ASC. Results: Of 1731 patients with ulcerative colitis, 179(10%) had an index episode of ASC. Nineteen(11%) patients underwent colectomy at index admission and 42(26%) over a median follow-up of 56(1-159) months. Hazard ratio for colectomy for IR was 3.6(1.7-7.5, p=0.001) compared to CR. Modeling based on four variables: response at day 7 of hospitalization, steroid use during first year of diagnosis, longer disease duration prior to ASC and number of extra-intestinal manifestations, was able to predict colectomy with an accuracy of 77%. Conclusions: Disease behavior of ASC in India is similar to the West, with a third undergoing colectomy at 10 years. Clinical features, especially response at day 7 hospitalization for index ASC, can predict both colectomy and steroid dependence with reasonable accuracy.

Saransh Jain, Saurabh Kedia, Tavpritesh Sethi, Sawan Bopanna, Dawesh Prakash Yadav, Sandeep Goyal, Rajesh Padhan, Pratap Mouli Venigalla, Peush Sahni, Nihar Ranjan Dash, Sujoy Pal, Govind Makharia, Simon P L Travis, Vineet Ahuja

Tavpritesh Sethi, Nigam H. Shah

India has one of the highest disease burdens in the world. A better understanding of what ails India will help policy makers plan appropriate health-care services and infrastructure development, design medical education curricula, and identify health research priorities that are relevant to the needs of the country. The POSEIDON study aimed to record the prevalence of symptoms and medical conditions for which patients visit a primary health-care practitioner in India.

Sundeep Salvi, Komalkirti Apte, Sapna Madas, Monica Barne, Sushmeeta Chhowala, Tavpritesh Sethi, Kunal Aggarwal, Anurag Agrawal, Jaideep Gogtay