Predicting COVID-19 and pneumonia complications from admission texts
This work addresses risk assessment for hospitalized patients with pneumonia or COVID-19, representing an incremental improvement in medical text analysis.
The paper tackled predicting complications for COVID-19 and pneumonia patients using admission texts, applying a Longformer neural network to outperform Transformer baselines and demonstrating generalization across institutions and diagnoses.
In this paper we present a novel approach to risk assessment for patients hospitalized with pneumonia or COVID-19 based on their admission reports. We applied a Longformer neural network to admission reports and other textual data available shortly after admission to compute risk scores for the patients. We used patient data of multiple European hospitals to demonstrate that our approach outperforms the Transformer baselines. Our experiments show that the proposed model generalises across institutions and diagnoses. Also, our method has several other advantages described in the paper.