Related Experiment Video
Updated: Nov 17, 2025

Drug Repurposing Hypothesis Generation Using the "RE:fine Drugs" System
Published on: December 11, 2016
From predictions to prescriptions: A data-driven response to COVID-19
Dimitris Bertsimas1,2, Leonard Boussioux3, Ryan Cory-Wright3
1Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA 02142, USA. dbertsim@mit.edu.
This study presents a data-driven approach to combat COVID-19, offering tools for clinical decisions and policy making. It integrates data to predict mortality, forecast spread, and optimize resource allocation, aiding pandemic response.
Area of Science:
- Data Science
- Epidemiology
- Health Informatics
Background:
- The COVID-19 pandemic presented significant challenges to healthcare systems and policymakers globally.
- Difficult decisions regarding patient triage, treatment, and resource allocation were necessary.
- Social distancing measures, while slowing disease spread, incurred substantial economic costs.
Purpose of the Study:
- To develop a comprehensive, data-driven analytical framework to address challenges posed by the COVID-19 pandemic.
- To understand clinical characteristics, predict mortality, forecast disease spread, and optimize resource management.
- To support clinical decision-making and inform public health policies.
Main Methods:
- Integrated four-step approach combining descriptive, predictive, and prescriptive analytics.
- Aggregated clinical studies into a comprehensive COVID-19 database.
- Developed personalized risk calculators for infection and mortality.
- Created a novel epidemiological model for pandemic spread projection.
- Designed an optimization model for resource allocation, specifically ventilators.
Main Results:
- Established the most comprehensive database on COVID-19 clinical characteristics.
- Enabled personalized prediction of infection and mortality risks.
- Provided projections for pandemic spread to inform social distancing policies.
- Developed an optimization model to address ventilator shortages.
- Results have been implemented in clinical settings for patient triage and resource management.
- Informed policy decisions, including safe back-to-work strategies and vaccine trial planning.
- Integrated into the US Centers for Disease Control's pandemic forecasting.
Conclusions:
- The proposed data-driven approach effectively supports both clinical and policy-level decision-making during the COVID-19 pandemic.
- The integrated analytical tools provide valuable insights for managing healthcare resources and mitigating the pandemic's impact.
- The framework demonstrates the power of combining diverse data sources and analytical methods for public health challenges.
More Related Videos
Related Concept Videos
Steps in Outbreak Investigation
Analysis of Population Pharmacokinetic Data
Factors Affecting Drug Response: Overview
Issues And Trends In Healthcare Delivery System
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Pharmacovigilance
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
Measurement of Bioavailability: Pharmacodynamic Methods

