Analysis of Stroke Detection during the COVID-19 Pandemic Using Natural Language Processing of Radiology Reports

BACKGROUND AND PURPOSE:The coronavirus disease 2019 (COVID-19) pandemic has led to decreases in neuroimaging volume. Our aim was to quantify the change in acute or subacute ischemic strokes detected on CT or MR imaging during the pandemic using natural language processing of radiology reports.MATERIALS AND METHODS:We retrospectively analyzed 32,555 radiology reports from brain CTs and MRIs from a comprehensive stroke center, performed from March 1 to April 30 each year from 2017 to 2020, involving 20,414 unique patients. To detect acute or subacute ischemic stroke in free-text reports, we trained a random forest natural language processing classifier using 1987 randomly sampled radiology reports with manual annotation. Natural language processing classifier generalizability was evaluated using 1974 imaging reports from an external dataset.RESULTS:The natural language processing classifier achieved a 5-fold cross-validation classification accuracy of 0.97 and an F1 score of 0.74, with a slight underestimation (−5%) of actual numbers of acute or subacute ischemic strokes in cross-validation. Importantly, cross-validation performance stratified by year was similar. Applying the classifier to the complete study cohort, we found an estimated 24% decrease in patients with acute or subacute ischemic strokes reported on CT or MR imaging from March to April 2020 compared with the average from those months in 2017–2019. Among patients with stroke-related order indications, the estimated proportion who underwent neuroimaging with acute or subacute ischemic stroke detection significantly increased from 16% during 2017–2019 to 21% in 2020 (P = .01). The natural language processing classifier performed worse on external data.CONCLUSIONS:Acute or subacute ischemic stroke cases detected by neuroimaging decreased during the COVID-19 pandemic, though a higher proportion of studies ordered for stroke were positive for acute or subacute ischemic strokes. Natural language processing approaches can help automatically track acute or subacute ischemic stroke numbers for epidemiologic studies, though local classifier training is important due to radiologist reporting style differences.

There is much concern regarding the impact of the coronavirus disease 2019 (COVID-19) pandemic on the quality of stroke care, including issues with hospital capacity, clinical resource re-allocation, and the safety of patients and clinicians.^1,2 Previous reports have shown that there have been substantial decreases in stroke neuroimaging volume during the pandemic.^3,4 In addition, acute ischemic infarcts have been found on neuroimaging studies in many hospitalized patients with COVID-19, though the causal relationship is unclear.^5,6 Studies like these and other epidemiologic analyses usually rely on the creation of manually curated databases, in which identification of cases can be time-consuming and difficult to update in real-time. One way to facilitate such research is to use natural language processing (NLP), which has shown utility for automated analysis of radiology report data.⁷ NLP algorithms have been developed previously for the classification of neuroradiology reports for the presence of ischemic stroke findings and acute ischemic stroke subtypes.^8,9 Thus, NLP has the potential to facilitate COVID-19 research.In this study, we developed an NLP machine learning model that classifies radiology reports for the presence or absence of acute or subacute ischemic stroke (ASIS), as opposed to chronic stroke. We used this model to quantify the change in ASIS detected on all CT or MR imaging studies performed at a large comprehensive stroke center during the COVID-19 pandemic in the United States. We also evaluated NLP model generalizability and different training strategies using a sample of radiology reports from a second stroke center.     

Novel Risk Factors for Progression of Diabetic and Nondiabetic CKD: Findings From the Chronic Renal Insufficiency Cohort (CRIC) Study

1. Download : Download high-res image (451KB)
2. Download : Download full-size image

     

Evaluation of DISORDER: Retrospective Image Motion Correction for Volumetric Brain MRI in a Pediatric Setting

BACKGROUND AND PURPOSE:Head motion causes image degradation in brain MR imaging examinations, negatively impacting image quality, especially in pediatric populations. Here, we used a retrospective motion correction technique in children and assessed image quality improvement for 3D MR imaging acquisitions.MATERIALS AND METHODS:We prospectively acquired brain MR imaging at 3T using 3D sequences, T1-weighted MPRAGE, T2-weighted TSE, and FLAIR in 32 unsedated children, including 7 with epilepsy (age range, 2–18 years). We implemented a novel motion correction technique through a modification of k-space data acquisition: Distributed and Incoherent Sample Orders for Reconstruction Deblurring by using Encoding Redundancy (DISORDER). For each participant and technique, we obtained 3 reconstructions as acquired (Aq), after DISORDER motion correction (Di), and Di with additional outlier rejection (DiOut). We analyzed 288 images quantitatively, measuring 2 objective no-reference image quality metrics: gradient entropy (GE) and MPRAGE white matter (WM) homogeneity. As a qualitative metric, we presented blinded and randomized images to 2 expert neuroradiologists who scored them for clinical readability.RESULTS:Both image quality metrics improved after motion correction for all modalities, and improvement correlated with the amount of intrascan motion. Neuroradiologists also considered the motion corrected images as of higher quality (Wilcoxon z = −3.164 for MPRAGE; z = −2.066 for TSE; z = −2.645 for FLAIR; all P < .05).CONCLUSIONS:Retrospective image motion correction with DISORDER increased image quality both from an objective and qualitative perspective. In 75% of sessions, at least 1 sequence was improved by this approach, indicating the benefit of this technique in unsedated children for both clinical and research environments.

Head motion is a common cause of image degradation in brain MR imaging. Motion artifacts negatively impact MR image quality and therefore radiologists’ capacity to read the images, ultimately affecting patient clinical care.¹ Motion artifacts are more common in noncompliant patients,² but even in compliant adults, intrascan movement is reported in at least 10% of cases.³ For children who require high-resolution MR images, obtaining optimal image quality can be challenging, owing to the requirement to stay still over long durations needed for acquisition.⁴ Sedation can be an option, but it carries higher risks, costs, and preparation and recovery time.⁵In conditions such as intractable focal epilepsy, identification of an epileptogenic lesion is clinically important to guide surgical treatment. However, these lesions can be visually subtle, particularly in children in whom subtle cortical dysplasias are more common.⁶ Dedicated epilepsy MR imaging protocols use high-resolution 3D sequences to allow better cortical definition and free reformatting of orientation but involve acquisition times in the order of minutes, so data collection becomes more sensitive to motion.⁷For children in particular, multiple strategies are available for minimizing motion during MR examinations. Collaboration with play specialists using mock scanners and training or projecting a cartoon are good approaches to reduce anxiety.^8,9 These tools are not always available in clinical radiology and, even with these strategies, motion can still be an issue.¹⁰ Different scanning approaches to correct for intrascan motion have been proposed. Broadly, prospective methods track head motion in real time and modify the acquisition directions accordingly.¹¹ These approaches are applicable to a wide range of sequences but require optical systems with external tracking markers, sometimes uncomfortable or impractical, and extra setup can ultimately result in longer examinations. Furthermore, these approaches may also not be robust to continuous motion.^11-13 Retrospective techniques have also been proposed, in some cases relying on imaging navigators that are not compatible with all standard sequences or contrasts.¹²Here, we use a more general retrospective motion correction technique: Distributed and Incoherent Sample Orders for Reconstruction Deblurring by using Encoding Redundancy (DISORDER). In this method, k-space samples are reordered to enable retrospective motion correction during image reconstruction.¹⁴ Our hypothesis is that DISORDER improves clinical MR imaging quality and readability. To assess its use for clinical sequences, we acquired a dedicated epilepsy MR imaging protocol in 32 children across a wide age range. We used both objective image quality metrics and expert neuroradiologist ratings to evaluate the outcome after motion correction.     

Impact on Health-Related Quality of Life of Induction Chemotherapy Compared With Concurrent Cisplatin and Radiation Therapy in Patients With Head and Neck Cancer

AimsOrgan preservation, an important goal in the treatment of head and neck squamous cell carcinoma (HNSCC), may include induction chemotherapy and cisplatin with radiation therapy (CRT). To our knowledge, no reports have directly compared the impact of induction chemotherapy with that of CRT on health-related quality of life (HRQOL).Materials and methodsIn a phase II trial, we assessed the HRQOL of patients treated with induction chemotherapy followed by CRT. Eligible patients had stage III–IV HNSCC. HRQOL questionnaires were administered at baseline, the end of induction (EOI), the end of CRT (EOCRT) and after CRT. Functional Assessment of Cancer Therapy (FACT version 4) assessed HRQOL. We carried out a comparison of changes in HRQOL from baseline to EOI and from EOI to EOCRT. This trial is registered with ClinicalTrials.gov (NCT01566435).ResultsThirty patients were enrolled in the study. Most HRQOL questionnaires were completed (88%). The mean total FACT scores did not differ from baseline to EOI (general: 83.8 versus 79.1, P = 0.08; head and neck: 109.7 versus 105.8, P = 0.33; Total Outcome Index: 69.7 versus 62.3, P = 0.03; respectively, using P ≤ 0.01 to adjust for multiple simultaneous tests of differences). However, total FACT scores significantly worsened from EOI to EOCRT (79.1 versus 62.3, P = 0.01; 105.8 versus 74.2, P < 0.01; 62.3 versus 34.2, P = 0.01; respectively). Within domains, the head and neck cancer subscale score did not differ from baseline to EOI (median 28.5 versus 27.0, P = 0.69), but significantly worsened from EOI to EOCRT (27.0 versus 9.5, P < 0.01). Swallowing, oral pain and voice quality improved from baseline to EOI, but worsened from EOI to EOCRT. Physical and functional scores worsened from baseline to EOI and from EOI to EOCRT. The emotional well-being score improved from baseline to EOI but worsened from EOI to EOCRT.ConclusionsOverall, HRQOL did not significantly change from baseline to EOI but dramatically worsened from EOI to EOCRT.     

Routine diagnostics for neural antibodies,clinical correlates,treatment and functional outcome

Objective

To determine frequencies, interlaboratory reproducibility, clinical ratings, and prognostic implications of neural antibodies in a routine laboratory setting in patients with suspected neuropsychiatric autoimmune conditions.

Methods

Earliest available samples from 10,919 patients were tested for a broad panel of neural antibodies. Sera that reacted with leucine-rich glioma-inactivated protein 1 (LGI1), contactin-associated protein-2 (CASPR2), or the voltage-gated potassium channel (VGKC) complex were retested for LGI1 and CASPR2 antibodies by another laboratory. Physicians in charge of patients with positive antibody results retrospectively reported on clinical, treatment, and outcome parameters.

Results

Positive results were obtained for 576 patients (5.3%). Median disease duration was 6 months (interquartile range 0.6–46 months). In most patients, antibodies were detected both in CSF and serum. However, in 16 (28%) patients with N-methyl-d-aspartate receptor (NMDAR) antibodies, this diagnosis could be made only in cerebrospinal fluid (CSF). The two laboratories agreed largely on LGI1 and CASPR2 antibody diagnoses (κ = 0.95). The clinicians (413 responses, 71.7%) rated two-thirds of the antibody-positive patients as autoimmune. Antibodies against the α-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid receptor (AMPAR), NMDAR (CSF or high serum titer), γ-aminobutyric acid-B receptor (GABABR), and LGI1 had ≥ 90% positive ratings, whereas antibodies against the glycine receptor, VGKC complex, or otherwise unspecified neuropil had ≤ 40% positive ratings. Of the patients with surface antibodies, 64% improved after ≥ 3 months, mostly with ≥ 1 immunotherapy intervention.

Conclusions

This novel approach starting from routine diagnostics in a dedicated laboratory provides reliable and useful results with therapeutic implications. Counseling should consider clinical presentation, demographic features, and antibody titers of the individual patient.

     

Dose optimization of moxifloxacin and linezolid against tuberculosis using mathematical modeling and simulation

Introduction

There is an urgent need for new anti-tuberculosis (TB) drugs and optimization of current TB treatment. Moxifloxacin and linezolid are valuable options for the treatment of drug-resistant TB; however, it is crucial to find a dose at which these drugs not only show high efficacy but also suppress the development of further drug resistance.

Midterm Outcomes of the Dissected Aorta Repair Through Stent Implantation Trial

1. Download : Download high-res image (134KB)
2. Download : Download full-size image