Search

Summary: 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

Despite largely unproven clinical effectiveness, incentive spirometry (IS) is widely used in an effort to reduce postoperative pulmonary complications. The objective of the study is to evaluate the financial impact of implementing IS. The amount of time nurses and RTs spend each day doing IS-related activities was assessed utilizing an online survey distributed to the relevant national nursing and respiratory therapists (RT) societies along with questionnaire that was prospectively collected every day for 4 weeks at a single 10-bed cardiothoracic surgery step-down unit. Cost of RT time to teach IS use to patients and cost of nurse time spent reeducating and reminding patients to use IS were used to calculate IS implementation cost estimates per patient. Per-patient cost of IS implementation ranged from $65.30 to $240.96 for a mean 9-day step-down stay. For the 566 patients who stayed in the 10-bed step-down in 2016, the total estimated cost of implementing IS ranged from $36 959.80 to $136 383.36. Using national survey workload data, per-patient cost of IS implementation costed $107.36 (95% confidence interval [CI], $97.88-$116.98) for a hospital stay of 4.5 days. For the 9.7 million inpatient surgeries performed annually in the United States, the total annual cost of implementing postoperative IS is estimated to be $1.04 billion (95% CI, $949.4 million-$1.13 billion). The cost of implementing IS is substantial. Further efficacy studies are necessary to determine whether the cost is justifiable.