A chest radiography-based artificial intelligence deep-learning model to predict severe Covid-19 patient outcomes: the CAPE (Covid-19 AI Predictive Engine) Model

BackgroundChest radiography may be used together with deep-learning models to prognosticate COVID-19 patient outcomes PurposeT o evaluate the performance of a deep-learning model for the prediction of severe patient outcomes from COVID-19 pneumonia on chest radiographs. MethodsA deep-learning model (CAPE: Covid-19 AI Predictive Engine) was trained on 2337 CXR images including 2103 used only for validation while training. The prospective test set consisted of CXR images (n=70) obtained from RT-PCR confirmed COVID-19 pneumonia patients between 1 January and 30 April 2020 in a single center. The radiographs were analyzed by the AI model. Model performance was obtained by receiver operating characteristic curve analysis. ResultsIn the prospective test set, the mean age of the patients was 46 (+/-16.2) years (84.2% male). The deep-learning model accurately predicted outcomes of ICU admission/mortality from COVID-19 pneumonia with an AUC of 0.79 (95% CI 0.79-0.96). Compared to traditional risk scoring systems for pneumonia based upon laboratory and clinical parameters, the model matched the EWS and MulBTSA risk scoring systems and outperformed CURB-65. ConclusionsA deep-learning model was able to predict severe patient outcomes (ICU admission and mortality) from COVID-19 on chest radiographs. Key ResultsA deep-learning model was able to predict severe patient outcomes (ICU admission and mortality) from COVID-19 from chest radiographs with an AUC of 0.79, which is comparable to traditional risk scoring systems for pneumonia. Summary StatementThis is a chest radiography-based AI model to prognosticate the risk of severe COVID-19 pneumonia outcomes.

Community-acquired pneumonia with Acinetobacter radioresistens bacteremia in an immunocompetent host: A case report

Rationale: Acinetobacter radioresistens is a non-fermentative Gram-negative coccobacillus that is environmentally ubiquitous and is an uncommon cause of pneumonia in an immunocompetent patient with no known chronic medical illness. Patient concerns: A middle-aged Asian male with a smoking history presented with fever and cough. Physical examination was unremarkable. Chest imaging was consistent with pulmonary parenchymal infection and blood culture grew Acinetobacter radioresistens. Diagnosis: Community acquired pneumonia with Acinetobacter radioresistens bacteremia. Interventions: The patient received a combination of intravenous and oral ampicillin-sulbactam over 2 weeks. Outcomes: Repeat blood cultures showed resolution of bacteremia. Completion of antimicrobial treatment saw resolution of respiratory symptoms and radiological pneumonic changes. Lessons: Acinetobacter radioresistens causing community-acquired pneumonia in an immunocompetent host has never been described before. It may be a novel emerging infectious agent in pulmonary infections. Its clinical course in this immunocompetent patient appears to be relatively benign.

A rare but potentially lethal complication of dengue

Severe rhabdomyolysis is an uncommon but potentially fatal complication of dengue fever that is not well characterised and may be underreported. With the resurgence and continued rise of dengue cases worldwide, physicians must be aware of the less common but serious complications of dengue. Here, we report a patient who presented with severe rhabdomyolysis secondary to dengue fever with a serum creatine kinase of 742 900 U/L.