Over 400,000 deaths per year are the result of preventable harm,1 with medication errors contributing to a large proportion of these errors.2 Specifically, errors at the ordering are particularly at risk for causing serious patient harm.3-5
In this project we’ll be expanding on an existing family of supervised topic models. These models extend LDA to document collections where for each document we observe additional labels or values of interest. More specifically, one of the goals of this project is to use additional document level data, such as regulatory discretion, to develop better data modelling tools.
This project will generate polygenic risk score for obesity for ~ 250 subjects using 2 different datasets using existing R and python based tools. The student will also need to be familiar with unix platform. An association of polygenic risk score with eating behaviors will be tested.
I’m currently working, on loan, for NTIA (ntia.gov) on the BEAD (Broadband Equity, Access and Deployment), a roughly $40 billion project to deploy high-speed internet to all or most locations that currently lack access. We have a public and semi-public data set that lists every home and business in the United States, as well as broadband deployments and government grants.The project will answer questions such as: What will it cost to deploy fiber? Where are community anchor institutions located? What locations are already being subsidized? Which locations without service are in high-poverty areas?
Prediction Markets have been used to forecast outcomes of research interest using market mechanisms (See https://www.nature.com/news/the-power-of-prediction-markets-1.20820). A decentralized prediction market, Auger, has been created on blockchain for betting purposes (See, https://www.augur.net/). An alternative approach to prediction market has been proposed in Dalal et al (https://www.sciencedirect.com/science/article/abs/pii/S0040162511000734). This project develops a new hybrid model for centralized and decentralized collaborative prediction market that can be used to elicit opinions of university researchers on socially important issues. Specifically, the project uses Django and Ethereum based platform to develop a smart contract and an ERC-20 compliant token for researchers to participate in the new market. The smart contract is being developed in Solidity and Javascript. The corresponding frontend and backend uses Django and python on AWS cloud. The project will require developing and experimenting with new innovative Automated Market Makers used in DeFi.
We will leverage and extend large language models and ChatGPT or GPT-3 technologies to retrieve, appraise and synthesize clinical evidence for patients and clinicians. Students with strong background in large language models and natural language processing will be preferred. We will be working closely with clinicians to fine tune the methods.
Global sea level rise has been accelerating at an alarming rate for the last couple of decades, endangering and displacing millions of people. The majority of this sea level rise can be attributed to ice mass loss processes. In particular, ice mass loss from the Greenland ice sheet (GrIS) is a major contributor to sea level rise. Every year, about half of the ice that is lost from Greenland, and added to the oceans, comes from melting ice from the surface of the ice sheet. A large driver of ice surface melting is solar radiation. The amount of solar radiation that is absorbed vs reflected is strongly controlled by the ice albedo, with dark surfaces having a lower albedo (and absorbing more solar radiation) than light surfaces.