Dataset Information

Abstracts 2022 North American Meeting for the Society of Medical Decision Making, October 23-26, 2022

ABSTRACT:

SUBMITTER:

PROVIDER: S-EPMC9969228 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:After two years of conferences on a virtual platform due to the COVID-19 pandemic, finally, the 19th annual meeting of the Interuniversity Institute of Myology (IIM) has returned to the heart of central Italy, in Assisi, an important cultural hub, which boasts a wide range of historic buildings and museums. This event brought together scientists from around the world providing a valuable opportunity to discuss scientific issues in the field of myology. Traditionally, the meeting particularly encourages the participation of young trainees, and the panel discussions were moderated by leading international scientists, making this a special event where young researchers had the opportunity to talk to prestigious scientists in a friendly and informal environment. Furthermore, the IIM young researchers' winners for the best oral and poster presentations, became part of the IIM Young Committee, involved in the scientific organization of sessions and roundtables and for the invitation of a main speaker for the IIM 2023 meeting. The four keynote speakers for the IIM Conference 2022 presented new insights into the role of multinucleation during muscle growth and disease, the long-range distribution of giant mRNAs in skeletal muscle, human skeletal muscle remodelling from type 2 diabetic patients and the genome integrity and cell identity in adult muscle stem cells. The congress hosted young PhD students and trainees and included 6 research sessions, two poster sessions, round tables and socio-cultural events, promoting science outreach and interdisciplinary works that are advancing new directions in the field of myology. All other attendees had the opportunity to showcase their work through poster presentations. The IIM meeting 2022 was also part of an advanced training event, which included dedicated round tables and a training session of Advanced Myology on the morning of 23 October, reserved for students under 35 enrolled in the training school, receiving a certificate of attendance. This course proposed lectures and roundtable discussions coordinated by internationally outstanding speakers on muscle metabolism, pathophysiological regeneration and emerging therapeutic approaches for muscle degenerations. As in past editions, all participants shared their results, opinions, and perspectives in understanding developmental and adult myogenesis with novel insights into muscle biology in pathophysiological conditions. We report here the abstracts of the meeting that describe the basic, translational, and clinical research and certainly contribute to the vast field of myology in an innovative and original way.

Project description:Background contextAcademic meetings serve as an opportunity to present and discuss novel ideas. Previous studies have identified factors predictive of publication without generating predictive models. Machine learning (ML) presents a novel tool capable of generating these models. As such, the objective of this study was to use ML models to predict subsequent publication of abstracts presented at a major surgical conference.Study design/settingDatabase study.MethodsAll abstracts from the North American Spine Society (NASS) annual general meetings (AGM) from 2013-2015 were reviewed. The following information was extracted: number of authors, institution, location, conference category, subject category, study type, data collection methodology, human subject research, and FDA approval. Abstracts were then searched on the PubMed, Google Scholar, and Scopus databases for publication. ML models were trained to predict whether the abstract would be published or not. Quality of models was determined by using the area under the receiver operator curve (AUC). The top ten most important factors were extracted from the most successful model during testing.ResultsA total of 1119 abstracts were presented, with 553 (49%) abstracts published. During training, the model with the highest AUC and accuracy metrics was the partial least squares (AUC of 0.77±0.05, accuracy of 75.5%±4.7%). During testing, the model with the highest AUC and accuracy was the random forest (AUC of 0.69, accuracy of 67%). The top ten features for the random forest model were (descending order): number of authors, year, conference category, subject category, human subjects research, continent, and data collection methodology.ConclusionsThis was the first study attempting to use ML to predict the publication of complete articles after abstract presentation at a major academic conference. Future studies should incorporate deep learning frameworks, cognitive/results-based variables and aim to apply this methodology to larger conferences across other fields of medicine to improve the quality of works presented.

Dataset Information

Abstracts 2022 North American Meeting for the Society of Medical Decision Making, October 23-26, 2022

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets