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.     

Jumping in and Out of the Dirty Water… Learning from Stories while Doing Social Science

ABSTRACT

The pursuit of knowledge surrounding health-related issues during disasters, emergencies, and crises, can be delicate and challenging. Social scientists use a host of research methods to design and execute studies with the goal of making intellectual contributions. During extended field work following Hurricane Harvey in the Greater Houston area, our team collected data – interviews, observations, and private social media – from citizens, emergency responders, and volunteer rescuers. Yet sometimes the data collected, analyzed, and reported in published findings is only part of the research story. The researchers’ experiences, both in the field as well as their past, can serve as personal-sensemaking devices. Integrating these stories can help scientists build trust and collect meaningful data, well beyond what is anticipated. In this essay, I share such examples, related to dirty water: temporarily health-compromised individuals, and responders doing double duty. Below the surface, there are many more opportunities for health communication to make an impact in times of crisis.     

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.     

Shared decision-making for the management of small renal masses: Development and acceptability testing of a novel patient decision aid

IntroductionShared decision-making incorporates patients’ values and preferences to achieve high-quality decisions. The objective of this study was to develop an acceptable patient decision aid to facilitate shared decision-making for the management of small renal masses (SRMs).MethodsThe International Patient Decision Aids Standards were used to guide an evidence-based development process. Management options included active surveillance, thermal ablation, partial nephrectomy, and radical nephrectomy. A literature review was performed to provide incidence rates for outcomes of each option. Once a prototype was complete, alpha-testing was performed using a 10-question survey to assess acceptability with patients, patient advocates, urologists, and methodological experts. The primary outcome was acceptability of the decision aid.ResultsA novel patient decision aid was created to facilitate shared decision-making for the management of SRMs. Acceptability testing was performed with 20 patients, 10 urologists, two patient advocates, and one methodological expert. Responders indicated the decision aid was appropriate in length (82%, 27/33), well-balanced (82%, 27/33), and had language that was easy to follow (94%, 31/33). All patient responders felt the decision aid would have been helpful during their consultation and would recommend the decision aid for future patients (100%, 20/20). Most urologists reported they intend to use the decision aid (90%, 9/10).ConclusionsA novel patient decision aid was created to facilitate shared decision-making for management of SRMs. This clinical tool was acceptable with patients, patient advocates, and urologists and is freely available at: https://decisionaid.ohri.ca/decaids.html.     

Investigation of strategies to improve concussion reporting in American football

ABSTRACT

While research on sport-related concussion has increased dramatically over the past decade, research investigating concussion reporting is in its early stages. The purpose of this project was to assess concussion reporting and work with stakeholders to develop and assess strategies to improve reporting. We used a multi-site, repeated measures design with three NCAA Division I football programs, including 223 athlete participants. A modified community-based participatory research (CBPR) approach was used to develop intervention strategies (Fall 2017 season) with stakeholders designed to increase concussion reporting intentions. Preseason and postseason surveys were administered to determine effectiveness. Main outcome measures included concussion knowledge, intervention effectiveness, and reporting intention measures. For all three programs, concussion knowledge was unrelated to reporting intentions. Two of the three programs implemented the intervention strategies and for these programs there was evidence that the interventions were effective. Specifically, athletes from these two programs perceived more support from coaches about reporting (P< 0.05; t= 2.83), received education more frequently (P< 0.05; t= 2.67), and reported being more likely to report concussion symptoms (P< 0.05; t= 2.14). Our study demonstrates that working with stakeholders to develop site-specific strategies to improve concussion reporting is an effective approach to help improve reporting behaviours.     

Twelve tips for developing and implementing a medical education Twitter chat

Abstract

Live discussions on the social media site Twitter or Twitter chats are gaining popularity as powerful tools for engaging a broad audience in an interactive discussion. Medical education, in particular, is experiencing an increase in the use of this modality to support informal learning, as a means to encourage collaboration and share best practices, and as a platform for large-scale mentorship. Despite this growth in popularity, there are limited data to guide medical educators on the fundamentals of organizing a Twitter chat. In this Twelve Tips article, we discuss strategies relevant to potential Twitter chat organizers. We have arranged the tips chronologically, beginning with a discussion of initial considerations when planning and formulating a chat topic and publicizing the chat to potentially interested people and groups, followed by practical considerations while hosting the chat, and finally strategies for evaluating and extending a Twitter chat’s impact.     

Minority migrant men’s attitudes toward female genital mutilation: Developing strategies to engage men

Abstract

This article explores minority migrant men's attitudes towards female genital mutilation (FGM), and how these attitudes can be used to develop strategies to engage men in the eradication of FGM. Based on interviews and focus group discussions, the article finds that men's attitudes can be enabling, disabling or neutral: the identification of and variations between these need to be taken into account when developing strategies to engage men in the eradication of FGM. There is currently a window of opportunity for involving minority migrant men in the prevention of FGM and in the challenging of a minority migrant gender regime.     

Exploring the Impact of Individual UVB Radiation Levels on Serum 25-Hydroxyvitamin D in Women Living in High Versus Low Latitudes: A Cross-Sectional Analysis from the D-SOL Study

Vitamin D can be synthesized in the skin via sunlight exposure as well as ingested through diet. Vitamin D deficiency is currently a major global public health issue, with increasing prevalence in both low and high latitude locations. This cross-sectional analysis aimed to compare the intensity of individual Ultraviolet B radiation levels between women of the same ethnicity living in England and Brazil, respectively; and to investigate the association with circulating 25(OH)D concentrations. We analysed data from 135 Brazilian women (England, n = 56, 51° N; Brazil, n = 79, 16° S) recruited for the D-SOL study (Interaction between Vitamin D Supplementation and Sunlight Exposure in Women Living in Opposite Latitudes). Serum 25(OH)D concentrations were analysed by high performance liquid chromatography tandem mass spectrometry (HPLC-MS), individual UVB radiation via UVB dosimeter badges and dietary intake via 4-day diet diaries. Anthropometric, skin phototype, sociodemographic and lifestyle patterns were also assessed. Mean serum 25(OH)D concentration of England residents was significantly lower than Brazil residents. Daily individual UVB radiation level showed a strong significant positive correlation with serum 25(OH)D concentrations. The required UVB radiation to achieve 75 nmol/L was 2.2 SED and 38.8% of the total variance in 25(OH)D concentrations was explained uniquely by daily individual UVB radiation, after controlling for the influence of age and body mass index. Thus, these results highlight the strong positive association between serum 25(OH)D concentrations and individual UVB radiation and the influence of different individual characteristics and behaviours. Collectively, these factors contribute to meaningful, country-specific, public health strategies and policies for the efficient prevention and treatment of vitamin D inadequacy.     

Epidemiology of lacrosse injuries treated at the United States emergency departments between 1997 and 2015

ABSTRACT

Lacrosse has gained substantial popularity across age groups in the past few decades, but epidemiologic sex differences of lacrosse injuries in emergency settings have not been well described. We characterized and described lacrosse-related injuries presenting to United States Emergency Departments (US EDs) using data from the National Electronic Injury Surveillance System (NEISS). From 1997 to 2015, 7,587 lacrosse-related injuries were treated at US EDs (national estimate of 256,358 injuries). Males accounted for 75.5% of injuries. Average age was 16.0 ± 5.0 (range 5–71) years. Sprains/strains (25.4%), contusions/abrasions (23.9%), and fractures (18.7%) were the most common diagnoses. Females sustained a higher proportion of sprains/strains (36.0%) than males (21.9%) (p< 0.01), while males sustained a higher proportion of fractures (injury proportion ratios [IPR]; 21.3% vs. 10.8%, p< 0.01). Similar proportions of concussions were observed (IPR; 6.1% in males, 6.2% among females). Differences in injury patterns may be secondary to differences in rules and equipment between the two sports.