What is fungalAi?
fungalAi is a platform technology with a suite of data analytics that can detect and help diagnose fungal infections from data that is readily available in clinical information systems. Natural language processing screens CT reports for the suggestion of fungal disease taking into account the variation in radiologist language; image analysis marks up suspicious features on Chest CT and the expert system integrates radiology, antifungal prescribing and microbiology to improve fungal prediction.
How does it work?
fungalAi uses artificial neural networks to analyse the language of chest CT reports and recognise features of fungal infections on chest CT scans. The expert system uses hand crafted rules and machine learning classifiers to integrate different types of data when uncertainty in fungal prediction prevails.
Why use this approach?
Diagnosis of fungal infections initially relies on chest imaging because the overwhelming majority of patients develop a pneumonia and fungal organisms are difficult to recover from sick patients. However, results of chest imaging are dictated by radiologists...so how do you sift through a deluge of reports to locate a rare disease? Our sensitive analytics can help.
fungalAi achieved a sensitivity at report level of 91%, specificity of 79%, ROC 0.92 and detected 100% of patients with fungal infections. Our deep learning based image analysis of chest CT scans has an AUC of 99.3. Our expert system combining radiology, antifungal drug prescriptions and microbiology maintains a very high sensitivity of 98%, specificity of 75% and halved false notifications.
fungalAi has helped us understand our local epidemiology, patient outcomes and improve our antifungal stewardship practice.
What about you?