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.     

Can MRI differentiate between atypical cartilaginous tumors and high-grade chondrosarcoma? A systematic review

Background and purpose — Adequate staging of chondroid tumors at diagnosis is important as it determines both treatment and outcome. This systematic review provides an overview of MRI criteria used to differentiate between atypical cartilaginous tumors (ACT) and high-grade chondrosarcoma (HGCS).Patients and methods — For this systematic review PubMed and Embase were searched, from inception of the databases to July 12, 2018. All original articles describing MRI characteristics of pathologically proven primary central chondrosarcoma and ACT were included. A quality appraisal of the included papers was performed. Data on MRI characteristics and histological grade were extracted by 2 reviewers. Meta-analysis was performed if possible. The study is registered with PROSPERO, CRD42018067959.Results — Our search identified 2,132 unique records, of which 14 studies were included. 239 ACT and 140 HGCS were identified. The quality assessment showed great variability in consensus criteria used for both pathologic and radiologic diagnosis. Due to substantial heterogeneity we refrained from pooling the results in a meta-analysis and reported non-statistical syntheses. Loss of entrapped fatty marrow, cortical breakthrough, and extraosseous soft tissue expansion appeared to be present more often in HGCS compared with ACT.Interpretation — This systematic review provides an overview of MRI characteristics used to differentiate between ACT and HGCS. Future studies are needed to develop and assess more reliable imaging methods and/or features to differentiate ACT from HGCS.

The incidence of chondrosarcoma of bone appears to have been increasing during the last decade and is now reported to be the most common primary malignant bone tumor in several countries (Thorkildsen et al. 2018, van Praag et al. 2018). Conventional chondrosarcoma is the most common subtype of chondrosarcoma. Other subtypes of chondrosarcoma (e.g., juxtacortical, mesenchymal, or secondary chondrosarcoma) are rare and show different radiologic appearance and clinical behavior (Bindiganavile et al. 2015).Conventional chondrosarcoma is classified into the histological grades 1 (currently known as atypical cartilaginous tumor [ACT]), 2, and 3. The metastatic potential, and therefore the disease-specific survival, correlates with the histological grade (Fletcher et al. 2013, Laitinen et al. 2018, Thorkildsen et al. 2018). ACTs rarely metastasize and are therefore reclassified as an intermediate type of tumor, not a malignancy (Fletcher et al. 2013). Due to the increase in patients undergoing MRI examinations for joint-related complaints, the incidental detection of ACT has increased substantially (van Praag et al. 2018).With the increasing incidence of ACT, clear radiologic criteria to differentiate ACT from high-grade chondrosarcoma (i.e., grades 2 and 3) become more and more important. Adequate staging of chondroid tumors at diagnosis is important as it determines both treatment and prognosis. High-grade chondrosarcomas behave aggressively. Between 10% and 30% of grade 2 and about 70% of grade 3 chondrosarcomas metastasize (Evans et al. 1977). Hence, high-grade chondrosarcoma (HGCS) requires wide en bloc resection with free surgical margins. In contrast, ACTs are intermediate tumors and can be treated either with intralesional curettage and local adjuvant or nonoperatively with regular follow-up when located in the long bones (Deckers et al. 2016).Due to the heterogenous composition of chondroid tumors, diagnostic biopsy is unreliable in assessing the genuine histological grade and malignant potential of chondrosarcomas (Laitinen et al. 2018). Therefore, physicians need to rely on imaging and clinical findings (e.g., pain is more common in HGCS) to differentiate ACT from HGCS. Imaging evaluation of cartilaginous and other bone tumors is generally based on multimodal assessment including at least conventional radiography and MRI (Nascimento et al. 2014).During the most recent decades research has focused mainly on differentiating enchondroma from chondrosarcoma (Choi et al. 2013, Douis et al. 2014, Crim et al. 2015, Lisson et al. 2018). New insights have shown that both enchondroma and ACT located in the long bones can be observed without treatment (Deckers et al. 2016, Sampath Kumar et al. 2016, Chung et al. 2018). These insights make the differentiation between ACT and HGCS clinically relevant. Currently, literature on differentiating ACT from HGCS is sparse and clear radiologic criteria are lacking. Therefore, we performed a systematic review to provide an overview of MRI characteristics used to date to differentiate between ACT and HGCS.     

Mind the gap: Teachers’ conceptions of student-staff partnership and its potential to enhance educational quality

Abstract

Introduction: Student-staff partnerships as a concept to improve medical education have received a growing amount of attention. Such partnerships are collaborations in which students and teachers seek to improve education by each adding their unique contribution to decision-making and implementation processes. Although previous research has demonstrated that students are favourable to this concept, teachers remain hesitant. The present study investigated teachers’ conceptions of student-staff partnerships and of the prerequisites that are necessary to render such partnerships successful and enhance educational quality.

Method: We conducted semi-structured interviews with 14 course coordinators who lead course design teams and also teach in 4 bachelor health programmes, using Bovill and Bulley’s levels of student participation as sensitising concepts during data analysis.

Results: The results pointed to three different conceptions of student-staff partnerships existing among teachers: Teachers teach and students study; teachers teach and value students’ feedback; and teachers and students co-create. The prerequisites for effective co-creation teachers identified were: Teachers must be open to involve students and create dialogues; students must be motivated and have good communication skills; the organisation must be supportive; and teachers should have the final say.

Conclusion: We conclude that teachers’ conceptions are consistent with Bovill and Bulley’s levels of student participation. Under certain conditions, teachers are willing to co-create and reach the highest levels of student participation.     

Barriers and facilitators for cascade testing in genetic conditions: a systematic review

Cascade testing is the process of offering genetic counseling and testing to at-risk relatives of an individual who has been diagnosed with a genetic condition. It is critical for increasing the identification rates of individuals with these conditions and the uptake of appropriate preventive health services. The process of cascade testing is highly varied in clinical practice, and a comprehensive understanding of factors that hinder or enhance its implementation is necessary to improve this process. We conducted a systematic review to identify barriers and facilitators for cascade testing and searched PubMed, CINAHL via EBSCO, Web of Science, EMBASE, and the Cochrane Library for articles published from the databases’ inception to November 2018. Thirty articles met inclusion criteria. Barriers and facilitators identified from these studies at the individual-level were organized into the following categories: (1) demographics, (2) knowledge, (3) attitudes, beliefs, and emotional responses of the individual, and (4) perceptions of relatives, relatives’ responses, and attitudes toward relatives. At the interpersonal-level, barriers and facilitators were categorized as (1) family communication-, support- and dynamics-, and (2) provider-factors. Finally, barriers at the environmental-level relating to accessibility of genetic services were also identified. Our findings suggest that several individual, interpersonal and environmental factors may play a role in cascade testing. Future studies to further investigate these barriers and facilitators are needed to inform future interventions for improving the implementation of cascade testing for genetic conditions in clinical practice.Subject terms: Preventive medicine, Genetic services     

Building on the success of anti-vascular endothelial growth factor therapy: a vision for the next decade

This article aims to identify key opportunities for improvement in the diagnosis and treatment of retinal disease, and describe recent innovations that will potentially facilitate improved outcomes with existing intravitreal vascular endothelial growth factor (VEGF) therapies and lay the groundwork for new treatment approaches. The review begins with a summary of the key discoveries that led to the development of anti-VEGF therapies and briefly reviews their impact on clinical practice. Opportunities for improvements in diagnosis, real-world outcomes with existing therapies, long-acting therapeutics and personalised health care are discussed, as well as the need to identify new targets for therapeutic intervention. Low-cost, remote patient screening and monitoring using artificial intelligence (AI)-based technologies can help improve diagnosis rates and enable remote disease monitoring with minimal patient burden. AI-based tools can be applied to generate patient-level prognostic data and predict individual treatment needs, reducing the time needed to optimise a patient’s treatment regimen. Long-acting therapeutics can help improve visual outcomes by reducing the treatment burden. When paired with AI-generated prognoses, long-acting therapeutics enable the possibility of vision loss prevention. Dual-acting drugs may help improve efficacy and/or durability beyond what is possible with anti-VEGF agents alone. Recent developments and ongoing innovations will help build upon the success of anti-VEGF therapies to further reduce vision loss owing to retinal disease while lowering the overall burden of care.Subject terms: Retinal diseases, Quality of life     

Video observation of hand-hygiene compliance in a manufacturer of ready-to-eat pie and pastry products

ABSTRACT

Food-handler hand-hygiene can be a contributory factor for food-borne illness. Cognitive data (knowledge/attitudes/self-reported practices), while informative, are not indicative of behaviour, and are subject to biases. Consequently, observation of behaviour is superior to survey data. However, researcher presence in direct observation increases reactivity, whereas video observation gives comprehensive analysis over a longer period, furthermore, familiarity reduces reactivity. Although video observation has been used to assess food safety at retail/foodservice, this valuable method is under-utilized in food-manufacturing environments. For the study, footage (24 h) was reviewed to assess compliance in a food-manufacturing site with company protocol. Video observation of food-handlers entering production (n = 674) was assessed; upon 70 occasions no attempt to implement hand-hygiene was observed. Of attempted hand-hygiene practices (n = 604), only 2% implemented compliant practices. Although 78% of attempts utilized soap, only 42% included sanitizer. Duration ranged from 1 to 69 s (Median 17 s). The study provides hand-hygiene data in an area that observational data is seldom captured.     

Prolonged mechanical ventilation after cardiac surgery: substudy of the Transfusion Requirements in Cardiac Surgery III trial

Purpose

Prolonged mechanical ventilation (MV) is a major complication following cardiac surgery. We conducted a secondary analysis of the Transfusion Requirements in Cardiac Surgery (TRICTS) III trial to describe MV duration, identify factors associated with prolonged MV, and examine associations of prolonged MV with mortality and complications.

Methods

Four thousand, eight hundred and nine participants undergoing cardiac surgery at 71 hospitals worldwide were included. Prolonged MV was defined based on the Society of Thoracic Surgeons definition as MV lasting 24 hr or longer. Adjusted associations of patient and surgical factors with prolonged MV were examined using multivariable logistic regression. Associations of prolonged MV with complications were assessed using odds ratios, and adjusted associations between prolonged MV and mortality were evaluated using multinomial regression. Associations of shorter durations of MV with survival and complications were explored.

Results

Prolonged MV occurred in 15% (725/4,809) of participants. Prolonged MV was associated with surgical factors indicative of complexity, such as previous cardiac surgery, cardiopulmonary bypass duration, and separation attempts; and patient factors such as critical preoperative state, left ventricular impairment, renal failure, and pulmonary hypertension. Prolonged MV was associated with perioperative but not long-term complications. After risk adjustment, prolonged MV was associated with perioperative mortality; its association with long-term mortality among survivors was weaker. Shorter durations of MV were not associated with increased risk of mortality or complications.

Conclusion

In this substudy of the TRICS III trial, prolonged MV was common after cardiac surgery and was associated with patient and surgical risk factors. Although prolonged MV showed strong associations with perioperative complications and mortality, it was not associated with long-term complications and had weaker association with long-term mortality among survivors.

Study registration

www.ClinicalTrials.gov (NCT02042898); registered 23 January 2014. This is a substudy of the Transfusion Requirements in Cardiac Surgery (TRICS) III trial.

     

Effect of reverse manual wheelchair propulsion on shoulder kinematics,kinetics and muscular activity in persons with paraplegia

Objective: Shoulder pain after spinal cord injury (SCI) is attributed to increased mobility demands on the arms and negatively impacts independence and quality of life. Repetitive superior and posterior shoulder joint forces produced during traditional wheelchair (WC) locomotion can result in subacromial impingement if unopposed, as with muscular fatigue or weakness. ROWHEELS^® (RW), geared rear wheels that produce forward WC movement with backward rim pulling, could alter these forces.

Design: Cross sectional.

Setting: Research laboratory at a rehabilitation hospital.

Participants: Ten manual WC users with paraplegia.

Outcome measures: Propulsion characteristics and right upper extremity/trunk kinematics and shoulder muscle activity were collected during ergometer propulsion: (1) self-selected free speed reverse propulsion with RW, (2) matched-speed reverse (rSW), and (3) forward propulsion (fSW) with instrumented Smartwheels (SW). Inverse dynamics using right-side SW rim kinetics and kinematics compared shoulder kinetics during rSW and fSW.

Results: Free propulsion velocity, cycle distance and cadence were similar during RW, rSW and fSW. Overall shoulder motion was similar except that peak shoulder extension was significantly reduced in both RW and rSW versus fSW. Anteriorly and inferiorly directed SW rim forces were decreased during rSW versus fSW propulsion, but posteriorly and superiorly directed rim forces were significantly greater. Superior and posterior shoulder joint forces and flexor, adductor, and external rotation moments were significantly less during rSW, without a significant difference in net shoulder forces and moments. Traditional propulsive-phase muscle activity was significantly reduced and recovery-phase muscle activity was increased during reverse propulsion.

Conclusion: These results suggest that reverse propulsion may redirect shoulder demands and prevent subacromial impingement, thereby preventing injury and preserving independent mobility for individuals with paraplegia.     

A second wave of COVID-19 in Cook County: What lessons can be applied?

During the ongoing public health crisis, many agencies are reporting COVID-19 health outcome information based on the overall population. This practice can lead to misleading results and underestimation of high risk areas. To gain a better understanding of spatial and temporal distribution of COVID-19 deaths; the long term care facility (LTCF) and household population (HP) deaths must be used. This approach allows us to better discern high risk areas and provides policy makers with reliable information for community engagement and mitigation strategies. By focusing on high-risk LTCFs and residential areas, protective measures can be implemented to minimize COVID-19 spread and subsequent mortality.  These areas should be a high priority target when COVID-19 vaccines become available

During the current public health crisis, many agencies and media outlets are reporting COVID-19 health outcome information based on the overall population of Cook County. As we have demonstrated, overall COVID-19 case counts and mortality can be misleading (details in >Story Map 1). Moreover, they offer little guidance for delivering public health interventions to high risk populations, a critical need during this second and potentially more devastating wave of the pandemic. The University of Illinois Chicago School of Public Health’s Public Health Geographic Information System Program (UIC-SPH-PHGIS) and Purdue research team has been examining spatial and temporal patterns of COVID-19 mortality with a focus on the significant loss of life from COVID-19 among Long-Term Care Facility (LTCF) residents in contrast to mortality in the community among residents of private households (non-LTCF; referred to as household population, HP). The goals of the study are:

• Improve the accuracy of commonly quoted COVID-19 mortality indicators;
• Gain a better understanding of spatial and temporal distribution of COVID-19 deaths;
• Examine the role of race, ethnicity, and socioeconomic status in COVID-19 mortality;
• Identify population and organizational parameters that can inform strategies for public health interventions.

Prioritizing the allocation of resources based on reliable information is a prerequisite of a successful mitigation strategy and immunization plan. Findings from our research have significant practical implications. The state and federal government face a series of policy decisions both due to the recent surge in positive cases and, when the time comes, the need to rationalize distribution of vaccines to high priority groups beyond healthcare workers and nursing home residents in critical areas. The research team seeks to modify prevailing practices in order to derive reliable information that guides policy decisions. At this stage of the study, we identified high-risk LTCFs and residential areas (HP) of Cook County from readily available, real-time mortality data.