Takeaway
- Artificial intelligence (AI) potentially boosts rapidity and screening accuracy for COVID-19 patients who test positive by RT-PCR but have normal CT findings.
Why this matters
- Augmenting chest CT and clinical information with AI may accelerate COVID-19 screening and diagnosis, especially when testing modalities are unavailable.
Key results
- 905 patients had chest CT scans.
- 46.3% (419) tested SARS-CoV-2-positive and 53.7% (486) tested negative by RT-PCR/next-generation sequencing.
- Negatives confirmed by 2+ RT-PCR tests and clinical observation.
- Clinical factors: age, exposure history, fever/cough/cough with sputum/white blood cell counts.
- Joint AI model using clinical data and CT imaging outperformed models using either alone.
- Joint model vs a senior thoracic radiologist using CT+clinical data (95% CIs):
- Sensitivity: 84.3% (77.1%-90.0%) AI vs 74.6% (66.4%-81.7%) human.
- Specificity: 82.8% (75.6%-88.5%) AI vs 93.8% (88.5%-97.1%) human.
- Area under the curve: 0.92 (0.887-0.948) vs 0.84 (0.800-0.884) human.
- Test set: 25 patients with COVID-19 and normal chest CT per radiologists at presentation.
- Deep-learning AI model identified 52% (13/25) scans as COVID-19-positive.
- Clinical model classified 64% (16/25) as COVID-19-positive.
- Joint model identified 68% (17/25) as COVID-19-positive.
- Senior thoracic radiologist, radiologist fellow identified 0% (0/25) as positive.
Study design
- Evaluation of AI model to augment early detection of SARS-CoV-2 infection.
- Funding: None disclosed.
Limitations
- Small numbers.
- Bias toward patients with COVID-19.
Desafortunadamente este artículo no esta disponible para usuarios no logados
Has alcanzdo el límite de artículos por usuario
Acceso gratuito Un servicio exclusivo para profesionales sanitarios