ABSTRACT
The coronavirus disease 2019 (COVID-19) pandemic had a major impact on global health and was associated with millions of deaths worldwide. During the pandemic, imaging characteristics of chest X-ray (CXR) and chest computed tomography (CT) played an important role in the screening, diagnosis and monitoring the disease progression. Various studies suggested that quantitative image analysis methods including artificial intelligence and radiomics can greatly boost the value of imaging in the management of COVID-19. However, few studies have explored the use of longitudinal multi-modal medical images with varying visit intervals for outcome prediction in COVID-19 patients. This study aims to explore the potential of longitudinal multimodal radiomics in predicting the outcome of COVID-19 patients by integrating both CXR and CT images with variable visit intervals through deep learning. 2274 patients who underwent CXR and/or CT scans during disease progression were selected for this study. Of these, 946 patients were treated at the University of Pennsylvania Health System (UPHS) and the remaining 1328 patients were acquired at Stony Brook University (SBU) and curated by the Medical Imaging and Data Resource Center (MIDRC). 532 radiomic features were extracted with the Cancer Imaging Phenomics Toolkit (CaPTk) from the lung regions in CXR and CT images at all visits. We employed two commonly used deep learning algorithms to analyze the longitudinal multimodal features, and evaluated the prediction results based on the area under the receiver operating characteristic curve (AUC). Our models achieved testing AUC scores of 0.816 and 0.836, respectively, for the prediction of mortality. © 2023 SPIE.
ABSTRACT
Introduction: Ocrelizumab is administered every 6 months due to expectations that this is necessary to control new disease activity. This dosing schedule is difficult in some settings, such as during the SARS-CoV-2 pandemic, which can lead to anxiety for patients and care teams. There is clinical evidence and mechanistic rationale that ocrelizumab may have a more durable treatment effect beyond the 6-month dosing interval;however, it is unclear whether infusion delays contribute to relapses. Objectives/Aims: To explore whether infusion delay, length of delay, and repeated delays are associated with radiologic relapse in patients on ocrelizumab, as part of a quality improvement project to improve departmental practices. Methods: Retrospective, single site (University of Pennsylvania) cohort study, that included 86 patients with relapsing-remitting multiple sclerosis (MS) treated with ocrelizumab for at least 2 years. Demographics and infusion dates were obtained through chart review. Routine clinical MRIs that included a 1mm3 isotropic T2/FLAIR sequence obtained at baseline (3-9 months after starting ocrelizumab) and follow-up (at least 2 years after starting ocrelizumab) were compared using in-house developed software that aids in detection of new lesions by registration and subtraction of MR images from two time points. New MS lesions were adjudicated by two neurologists. Statistical analysis was performed using Fisher's exact test. Results: Due to logistics of arranging infusions, 33 (38.4%) patients had at least 1 infusion interval longer than 7 months (210 days). Five patients (5.8%) had a radiologic relapse during two years of observation. Presence of an infusion interval longer than 7 months or 8 months (240 days) was not associated with radiologic relapse (p=1.00, p=0.43, respectively). Length of maximum infusion interval was not associated with radiologic relapse (p=0.52). Patients with multiple infusion delays had no increased risk of relapse (p=0.47). Conclusions: While underpowered to exclude a relationship between ocrelizumab infusion delays and new disease activity, our study is reassuring that a delay of up to 2 months is not associated with relapse. Prospective studies could confirm these findings and identify characteristics of patients who will have more prolonged disease control with ocrelizumab beyond the currently prescribed 6-month dosing interval.