Next-Generation Scholarship: Rebranding Hematopathology Using Twitter: The MD Anderson Experience

A Reassessment of the Impact and Significance of Social Media to Pathology

CONTEXT

Social media (SM) use in pathology and medicine today is widespread, receives active advocacy, and is said to bring a host of benefits. In latter days, the harmful effects of SM have received attention, but they have yet been followed by greater encouragement of professionalized SM usage. SM use in medicine has seen adoption in parallel to its general ascendancy, even though the platforms are products with purposes misaligned with the practice of medicine.

OBJECTIVE

To (1) characterize premises and forces that propel professional SM platform adoption and use, and (2) examine wide-ranging literature, both medical and nonmedical, that substantiates the premises and to find counteracting perspectives and evidence.

DATA SOURCES

Review of the literature using relevant keyword searches in PubMed, Google Scholar, Dimensions, and Web of Science for articles that study/describe professional SM use in pathology and medicine. Additionally, we examined business, technology, and social sciences literature and high-quality gray literature (newspapers, books, blogs) that addressed questions in relation to the topic of professional SM adoption.

CONCLUSIONS

We identified 6 major premises as motivators of professional SM use and highlight significant counteracting factors. We conclude that the harms of professionalized SM use have not been fully considered in the medical literature and that a change in direction and the creation of new communication platforms would be beneficial.

Pivoting Continuing Professional Development During the COVID-19 Pandemic: A Narrative Scoping Review of Adaptations and Innovations

INTRODUCTION

Most formal continuing professional development (CPD) opportunities were offered in person until March 2020 when the COVID-19 pandemic disrupted traditional structures of CPD offerings. The authors explored the adaptations and innovations in CPD that were strengthened or newly created during the first 16 months of the pandemic.

METHODS

The objectives of the narrative review were to answer the following questions: (1) what types of adaptations to CPD innovations are described? and (2) what may shape future innovations in CPD? The following databases were searched: Medline, Embase, CINAHL, and ERIC to identify the literature published between March 2020 to July 2021. The authors conducted a comprehensive search by including all study types that described adaptations and/or innovations in CPD during the stated pandemic period.

RESULTS

Of the 8295 citations retrieved from databases, 191 satisfied the inclusion criteria. The authors found three categories to describe adaptations to CPD innovations: (1) creation of new online resources, (2) increased use of the existing online platforms/software to deliver CPD, and (3) use of simulation for teaching and learning. Reported advantages and disadvantages associated with these adaptations included logistical, interactional, and capacity building elements. The review identified five potential future CPD innovations: (1) empirical research on the effectiveness of virtual learning; (2) novel roles and ways of thinking; (3) learning from other disciplines beyond medicine; (4) formation of a global perspective; and (5) emerging wellness initiatives.

DISCUSSION

This review provided an overview of the adaptations and innovations that may shape the future of CPD beyond the pandemic.

A visual-language foundation model for pathology image analysis using medical Twitter

The lack of annotated publicly available medical images is a major barrier for computational research and education innovations. At the same time, many de-identified images and much knowledge are shared by clinicians on public forums such as medical Twitter. Here we harness these crowd platforms to curate OpenPath, a large dataset of 208,414 pathology images paired with natural language descriptions. We demonstrate the value of this resource by developing pathology language-image pretraining (PLIP), a multimodal artificial intelligence with both image and text understanding, which is trained on OpenPath. PLIP achieves state-of-the-art performances for classifying new pathology images across four external datasets: for zero-shot classification, PLIP achieves F1 scores of 0.565-0.832 compared to F1 scores of 0.030-0.481 for previous contrastive language-image pretrained model. Training a simple supervised classifier on top of PLIP embeddings also achieves 2.5% improvement in F1 scores compared to using other supervised model embeddings. Moreover, PLIP enables users to retrieve similar cases by either image or natural language search, greatly facilitating knowledge sharing. Our approach demonstrates that publicly shared medical information is a tremendous resource that can be harnessed to develop medical artificial intelligence for enhancing diagnosis, knowledge sharing and education.

Elevating Twitter-Based Journal Club Discussions by Leveraging a Voice-Based Platform: #HemepathJC Meets Clubhouse

PURPOSE OF REVIEW

Social media-based scientific journal clubs provide an opportunity to promote published literature to a broader audience and allow robust multi-disciplinary and inter-professional discussion. Hematopathology Journal Club (#HemepathJC) on Twitter has successfully conducted monthly sessions since November 2019, covering topics related to lymphoma and leukemia.

RECENT FINDINGS

To enhance connectivity, multitasking, and productivity, we present our experience of leveraging the voice-based platform Clubhouse concurrent with Twitter. The Twitter and Clubhouse partnership for #hemepathJC holds the potential to increase dissemination of scientific knowledge and further promote journal club format discussion.

Future of Education or Present Reality: MD Anderson Cancer Center Hematopathology Virtual Educational Platform under Coronavirus Disease 2019 (COVID-19) Pandemic

Context - The main focus of education in most pathology residency and subspecialty pathology fellowships is the light microscopic examination of pathology specimens. Classes with multiheaded scopes are the most popular among pathology trainees. Until recently, it was difficult to us to imagine that this educational approach could change. In the beginning of March 2020 our country faced a serious challenge, which all of us now known as coronavirus disease 2019 (COVID-19) pandemic. The rules of social distancing and work from home were applied. These types of restrictions were implemented in almost all parts of our life including work and pathology education. Objective - To share our experience in the Department of Hematopathology at The University of Texas MD Anderson Cancer Center during COVID-19 pandemic. We describe our experience in modifying our approaches to education. We show how we overcame many obstacles to learning by building one of the largest virtual hematopathology educational platforms via Cisco WebEx and using social media, in particular Twitter. These tools facilitated the learning of hematopathology by medical students, pathology trainees, and practicing pathologists from all over the world. Data Sources - During the three months of the pandemic (April, May and June 2020), we evaluated the visitors' attendance to MD Anderson Cancer Center Hematopathology Virtual Educational Platform using data collected by Cisco WebEx website. For examination of the impact of the hematopathology community on Twitter on medical education the analytic metrics obtained from Symplur LLC (www.symplur.com, 04/27/2020) were used via its Symplur Signals program. Conclusions - Our experience using the MD Anderson Hematopathology Virtual Platform showed that there is substantial, global interest and desire for virtual hematopathology education, especially during the pandemic time.

The Implementation and Effectiveness of PathElective.com

The COVID-19 pandemic put most in-person pathology electives on-hold as departments adapted to changes in education and patient care. To address the subsequent void in pathology education, we created a free, virtual, modular, and high-quality pathology elective website. Website traffic from June 1, 2020, to October 1, 2020, was monitored using the built-in analyses on Squarespace. Twitter engagement was analyzed using Twitter analytics and the Symplur Social Graph Score. A voluntary satisfaction survey was sent to all PathElective users and results were analyzed. During this time, the site saw 25 467 unique visitors, over 34 988 visits, 181 302 page views, and 4449 subscriptions from 99 countries. Countries with the highest traffic are the United States (14 682), India (5210), and the Philippines (2195). PathElective’s Twitter social graph score increased from 63.59 to 89.3 with the addition of 1637 followers. Data from surveyed users (n = 177) show most to be pathology residents (41%). Most subscribers (89%) are committed to a career in pathology. The majority heard of the website via Twitter (55%). Almost half of those surveyed engaged with the PathTwitter community on Twitter and of those who participated, 99% found that interaction useful. In all survey questions surrounding satisfaction and usefulness, a large majority of the users were either satisfied or very satisfied. PathElective is a novel pathology elective that offers a unique opportunity to educate medical students and residents from around the globe and demonstrates high effectiveness and satisfaction among users.