AI and Health/ COVID19
AI and Health
Surjodeep Sarkar, Manas Gaur, Lujie, Muskan Garg, Biplav Srivastava, Bhaktee Dongaonkar, Towards Explainable and Safe Conversational Agents for Mental Health: A Survey, 2023. On Arxiv at: https://arxiv.org/abs/2304.13191, 2023 [Mental Health, Chatbot Survey]
Biplav Srivastava, Did Chatbots Miss Their 'Apollo Moment'? A Survey of the Potential, Gaps and Lessons from Using Collaboration Assistants During COVID-19, Cell PATTERNS, Aug 2021. [Chatbots, COVID]
Sahoo, P.K., Malhotra, N., Kokane, S.S., Srivastava, B., Tiwari, H.N., Sawant, S. (2022). Utilizing Predictive Analysis to Aid Emergency Medical Services. In: Shaban-Nejad, A., Michalowski, M., Bianco, S. (eds) AI for Disease Surveillance and Pandemic Intelligence. W3PHAI 2021. Studies in Computational Intelligence, vol 1013, 2022. Springer, Cham. https://doi.org/10.1007/978-3-030-93080-6_17
Srivastava, V., Srivastava, B. Towards Timely Public Health Decisions to Tackle Seasonal Diseases With Open Government Data. AAAI Workshops, 2014. Available at: https://www.aaai.org/ocs/index.php/WS/AAAIW14/paper/view/8728/8221
COVID19 Resources
Wiki collating information on GitHub
COVID19 Mask Analysis Program (CMAP)
COVID19 is a global pandemic whose impact in regions around the world has varied widely, as measured by the number of cases and deaths, depending on the local demographics as well as public health policies implemented in response, e.g., mask coverings. In this work, we present a tool called COVID Mask Analyzer Program (CMAP) that can be used to understand the impact of mask policies at local and national scale. Internally, the tool uses the well established techniques of robust synthetic control and New York Times' data about mask adherence and cases to answer counter-factual questions.
CMAP was developed in partnership between Tantiv4 and me at the AI Institute. It uses advanced data cleaning and normalization methods, and covers counties around the United States. As an example of output, CMAP shows that for Richland county, SC, intervention by June 1, 2020 would have been most consequential in saving lives compared to July 1 or Aug 1. This work opens up new avenues of research in human-machine collaboration to foster data-driven public health policies.
See the video to see the tool in action and read the demonstration paper for details.
Press
The Conversation and 30+ media outlets around the world (Nov 2020) - A new data-driven model shows that wearing masks saves lives – and the earlier you start, the better
Post & Courier (10 Oct 2020) - USC researchers build model showing how many coronavirus infections masks prevent.
The reporter highlights for Charleston, SC.
Paper
Sparsh Johri, Kartikaya Srivastava, Chinmayi Appajigowda, Lokesh Johri and Biplav Srivastava, A Nation-Wide Tool To Understand Impact of COVID19 Related Mask Policies Using Robust Synthetic Control, Oct 2020. On ResearchGate at: https://tinyurl.com/y4qarglw [Machine Learning, Health]
COVID19 Mask Adherance Estimation Tool (CAET)
COVID-19 is a global health crisis during which mask-wearing has emerged as an effective tool to combat the spread of disease. During this time, non-technical users like health officials and school administrators need tools to know how widely people are wearing masks in public. We present a robust and efficient Mask Adherence Estimation Tool (MAET) based on the pre-trained YOLOv5s object detection model, CSPNet feature extractor, PANet as neck and combine it with LIME explanation method to help the user understand the mask adherence at an individual and aggregate level.
See the video to see the tool in action and read the demonstration paper for details.
Paper
Gupta, A., Srivastava, B. (2023). A Robust System to Detect and Explain Public Mask Wearing Behavior. In: Shaban-Nejad, A., Michalowski, M., Bianco, S. (eds) Multimodal AI in Healthcare. Studies in Computational Intelligence, vol 1060. Springer, Cham. https://doi.org/10.1007/978-3-031-14771-5_11 Preprin on ResearchGate [Vision, Health]