An automated COVID-19 triage pipeline using artificial intelligence based on chest radiographs and clinical data

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital’s image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.

Prognostication of patients with COVID-19 using artificial intelligence based on chest x-rays and clinical data: a retrospective study

BACKGROUND

Chest x-ray is a relatively accessible, inexpensive, fast imaging modality that might be valuable in the prognostication of patients with COVID-19. We aimed to develop and evaluate an artificial intelligence system using chest x-rays and clinical data to predict disease severity and progression in patients with COVID-19.

METHODS

We did a retrospective study in multiple hospitals in the University of Pennsylvania Health System in Philadelphia, PA, USA, and Brown University affiliated hospitals in Providence, RI, USA. Patients who presented to a hospital in the University of Pennsylvania Health System via the emergency department, with a diagnosis of COVID-19 confirmed by RT-PCR and with an available chest x-ray from their initial presentation or admission, were retrospectively identified and randomly divided into training, validation, and test sets (7:1:2). Using the chest x-rays as input to an EfficientNet deep neural network and clinical data, models were trained to predict the binary outcome of disease severity (ie, critical or non-critical). The deep-learning features extracted from the model and clinical data were used to build time-to-event models to predict the risk of disease progression. The models were externally tested on patients who presented to an independent multicentre institution, Brown University affiliated hospitals, and compared with severity scores provided by radiologists.

FINDINGS

1834 patients who presented via the University of Pennsylvania Health System between March 9 and July 20, 2020, were identified and assigned to the model training (n=1285), validation (n=183), or testing (n=366) sets. 475 patients who presented via the Brown University affiliated hospitals between March 1 and July 18, 2020, were identified for external testing of the models. When chest x-rays were added to clinical data for severity prediction, area under the receiver operating characteristic curve (ROC-AUC) increased from 0·821 (95% CI 0·796-0·828) to 0·846 (0·815-0·852; p<0·0001) on internal testing and 0·731 (0·712-0·738) to 0·792 (0·780-0 ·803; p<0·0001) on external testing. When deep-learning features were added to clinical data for progression prediction, the concordance index (C-index) increased from 0·769 (0·755-0·786) to 0·805 (0·800-0·820; p<0·0001) on internal testing and 0·707 (0·695-0·729) to 0·752 (0·739-0·764; p<0·0001) on external testing. The image and clinical data combined model had significantly better prognostic performance than combined severity scores and clinical data on internal testing (C-index 0·805 vs 0·781; p=0·0002) and external testing (C-index 0·752 vs 0·715; p<0·0001).

INTERPRETATION

In patients with COVID-19, artificial intelligence based on chest x-rays had better prognostic performance than clinical data or radiologist-derived severity scores. Using artificial intelligence, chest x-rays can augment clinical data in predicting the risk of progression to critical illness in patients with COVID-19.

FUNDING

Brown University, Amazon Web Services Diagnostic Development Initiative, Radiological Society of North America, National Cancer Institute and National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health.

Reversed phase ion-pair liquid chromatographic determination of nicotine in commercial tobacco products. 1. Moist snuff

The official methods for the determination of nicotine in commercial tobacco products (AOAC, CORESTA) are based on approaches that are not selective for nicotine (colorimetric measurement, steam distillation, perchloric acid titration), and the availability of published methods based on state-of-the-art chromatographic methods is limited. Reversed phase ion-pair liquid chromatography has been established as a viable alternative for the analysis of basic analytes. A reversed phase ion-pair liquid chromatographic method for the determination of nicotine in commercial tobacco products was developed and optimized in separate experiments (Ciolino, L. A.; Turner, J. A.; McCauley, H. A.; Smallwood, A. W.; Yi, T. Y. J. Chromatogr. 1999a, 852 (2), 451-463). An extensive within-laboratory performance study of the optimized method was subsequently conducted, and results are presented here for the determination of nicotine in commercial moist snuff. Results for the determination of nicotine in commercial cigarettes are presented in a subsequent paper.

Reversed phase ion-pair liquid chromatographic determination of nicotine in commercial tobacco products. 2. Cigarettes

A reversed phase ion-pair liquid chromatographic method for the determination of nicotine in commercial tobacco products was previously developed and optimized (Ciolino, L. A.; Turner, J. A.; McCauley, H. A.; Smallwood, A. W.; Yi, T. Y. J. Chromatogr. 1999a, 852 (2), 451-463) and provided reliable results for the determination of nicotine in commercial moist snuff (Ciolino, L. A.; McCauley, H. A.; Fraser, D. B.; Barnett, D. Y.; Yi, T. Y.; Turner, J. A. J. Agric. Food Chem. 1999b, 47, 3706-3712). The method uses an aqueous-based sample extraction and provides rapid separation of nicotine from the minor tobacco alkaloids and other commercial tobacco components. In the present work, the method is evaluated for the determination of nicotine in commercial cigarettes and compared to both an official AOAC method for total alkaloids in tobacco (AOAC, AOAC Official Methods of Analysis of AOAC International, 16th ed.; AOAC International: Gaithersburg, MD, 1995; pp 30-31), and a published GC method (Lyerly, L. A.; Greene, G. H. Beitr. Tabakforsch. 1976, 8 (6), 359-361). Good agreement was obtained between the ion-pair LC method and the GC method with relative differences in determined nicotine contents of 0.6 to 5% for a series of commercial and reference cigarettes.

Optimization study for the reversed-phase ion-pair liquid chromatographic determination of nicotine in commercial tobacco products

The availability of published methods for the determination of nicotine in commercial tobacco products based on state-of-the-art chromatographic methods is limited. Nicotine is a diprotic base with pKa's of 3.12 (pyridine ring) and 8.02 (pyrrolidine ring). Other monoprotic and diprotic bases are also present in commercial tobacco including anatabine, nornicotine, anabasine, and cotinine. In this paper, the chromatography of nicotine and the minor tobacco alkaloids under reversed-phase ion-pairing conditions is thoroughly studied. The results of this study are used to understand the retention mechanisms of the tobacco alkaloids, to examine their observed elution order with respect to fundamental analyte properties (size, functionality, and acid-base strength), and to select optimum chromatographic conditions for the determination of nicotine in commercial tobacco products.