Data and models (updated daily) for forecasting COVID-19 severity for individual counties and hospitals in the US. The data includes confirmed cases, deaths, demographics, risk factors, social distancing data, and much more.

Table of contents

• Overview
• Quickstart
• Acknowledgements

Overview

Note: This repo is actively maintained – for any questions, please file an issue.

• Data (updated daily): We have cleaned, merged, and documented a large corpus of hospital- and county-level data from a variety of public sources to aid data science efforts to combat COVID-19.
  • At the hospital level, the data include the location of the hospital, the number of ICU beds, the total number of employees, hospital type, and contact information.
  • At the county level, our data include socioeconomic factors, social distancing scores, and COVID-19 cases/deaths from USA Facts and NYT.
  • Easily downloadable as processed csv or full pipeline.
  • Extensive documentation available here.
• Paper link: Curating a COVID-19 data repository and forecasting county-level death counts in the United States – Read here
• Project website: Visit here – see the interactive county-level map and interactive hospital-level map.
• Modeling: Using this data, we have developed a short-term (3-5 days) forecasting model for mortality at the county level. The model combines a county-specific exponential growth model and a shared exponential growth model through a weighted average, where the weights depend on past prediction accuracy.
• Severity index: The Covid pandemic severity index (CPSI) is designed to help aid the distribution of medical resources to hospitals. It takes on three values (3: High, 2: Medium, 1: Low) indicating the outbreak severity for a hospital on a certain day. It is calculated in three steps:
  1. County-level predictions for the number of deaths are modeled.
  2. County-level predictions are allocated to hospitals within counties proportionally based on their total number of employees.
  3. The final value is decided by thresholding the number of cumulative predicted deaths for a hospital (= current recorded deaths + predicted future deaths).

Quickstart with the data & models

You can download, load, and merge the data via:

python
import load_data
# first time it runs, downloads and caches the data
df = load_data.load_county_level(data_dir=path_to_data)

For more data details, see this readme or check out the quickstart notebook. We are constantly monitoring and adding new data sources (relevant data updates here).

The output from running the daily updates is stored here.

To get death predictions for our current best-performing model, the simplest way is to call the add_preds function:

python
from modeling.fit_and_predict import add_preds
df = add_preds(df, NUM_DAYS_LIST=[1, 3, 5]) # adds keys like Predicted Deaths 1-day, Predicted Deaths 3-day
# NUM_DAYS_LIST is list of number of days in the future to predict

Acknowledgements

The development of this project has been a collective effort, and we are grateful for the input from multiple teams, including:

• The UC Berkeley Departments of Statistics, EECS, and the Yu group team led by Professor Bin Yu.
• Students and summer team members.
• The Response4Life organization distribution team.
• Medical and hospital information collection teams.
• Support from Google and AWS.

Troubleshooting

If you encounter any issues while working with the datasets or models, consider the following troubleshooting ideas:

• Ensure your Python environment is set up correctly and all required libraries are installed.
• Double-check the file paths you’re using in your code to load the datasets.
• Refer to the documentation for any specific function you are using, as it may provide insights into common pitfalls.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Summary

In summary, this project offers vital data and modeling techniques to help forecast COVID-19 severity across various regions. Imagine this project as a lighthouse illuminating the stormy seas of COVID data—turning chaotic information into a navigable path for healthcare providers.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.