Combining Traditional Modeling with Machine Learning for Predicting COVID-19

147 Aufrufe

Danke für die Bewertung! Teile es mit Deinen Freunden!

Danke für Deine Bewertung!

Published Jul 27, 2020

Global COVID-19 cases surpassed 10 million in late June, with the death toll exceeding half a million people. Here in the U.S., many states have rolled back reopening plans as cases shattered record highs. So what comes next? The recent surge in COVID-19 cases and deaths has prompted an even greater need to understand the disease and its spread among communities in California and throughout the nation, with health care experts, academic centers, researchers, and other agencies using models to help forecast case and death rates, and ultimately identify hot spots and the need for targeted resources in those areas. While most use either SEIR models (compartmental model), curve fitting, or machine learning to model COVID cases and deaths, Christina Ramirez, Professor of Biostatistics at the UCLA Fielding School of Public Health, and her colleagues have combined all three techniques into a single comprehensive model to forecast the total number of COVID-19 cases and deaths across the nation.

In this video, Dr. Ramirez shares her groundbreaking, comprehensive model that combined traditional SEIR models with case velocity and machine learning to get precise, reliable estimates of COVID-19 case and death rates — shining a light on whether the pandemic is gaining speed and if deaths are accelerating or stabilizing. This project also uses the UCLA Center for Health Policy Research’s California Health Interview Survey (CHIS) to obtain an accurate snapshot of California data so that morbidity and mortality rates are based on the known prevalence of sociodemographic factors such as age, race, and co-morbidities or underlying health conditions.

UCLA researchers envision this model as a helpful tool in light of the rapidly evolving knowledge of COVID-19 and its transmission. Forecasting models also help identify population needs, medical supply demands such as hospital bed availability, and may assist with the preparation for an influx of patients. The recent surge calls for an imperative need to prevent overwhelming an already overburdened health care system and the public health mission to protect vulnerable populations.

Ramirez and her team were also among a group of scientists who worked with lawmakers in Los Angeles, California, London, and even South Africa to enact masks as source control, prior to the Centers for Disease Control and Prevention and the World Health Organization recommendations.

---
This event is part of the UCLA Center for Health Policy Research's monthly Health Policy Seminar Series, which provides a platform for health policy experts to discuss timely health topics from health care reform to racial and social disparities in health care access.

Kategorien: Corona Virus aktuelle Videos

Kommentare deaktiviert.

Anmelden

Combining Traditional Modeling with Machine Learning for Predicting COVID-19

Als nächstes