Artificial Intelligence and COVID-19 Using Chest CT Scan and Chest X-ray Images: Machine Learning and Deep Learning Approaches for Diagnosis and Treatment
Problem
Fast, reliable diagnosis of COVID-19 from chest CT scans and X-ray images was needed during the pandemic.
Why it matters
Timely accurate diagnosis affects treatment decisions and patient outcomes during a global health crisis.
What the AI did
Systematic review of 22 studies where machine learning and deep learning models analyzed CXR and CT images for COVID-19 diagnosis.
Results
CXR mean accuracy 93.7% ± 10.0% (range 68.4–99.9%), mean precision 95.7% ± 7.1%; CT results truncated in abstract.
Impact
Summarized evidence that AI can diagnose COVID-19 from imaging with high reported accuracy across studies.
Record
| Venue | Journal of Personalized Medicine |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Roberta Fusco, Roberta Grassi, Vincenza Granata, Sergio Venanzio Setola, Francesca Grassi, Diletta Cozzi, Biagio Pecori, Francesco Izzo et al. |
| Citations | 96 (OpenAlex, at import time) |
| References | 112 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/jpm11100993 |
| Open access | gold |
| Keywords | COVID-19, chest X-ray, CT scan, deep learning, diagnosis, systematic review |
Importance rating
major — millions of lives, an industry or a field
COVID-19 diagnosis during a global health crisis affects millions of patients; abstract reports high summarized accuracy across 22 studies but states no pandemic-scale figures itself.