Cochrane Colloquium 2023 - Laser AI & Evidence Prime Overview

The Cochrane Colloquium 2023 in London was a remarkable gathering that brought together healthcare professionals, researchers, and experts worldwide. The theme for this event was "Forward together for trusted evidence," and it provided a platform to delve into the critical issue of ensuring healthcare data and information trustworthiness in the future of healthcare.

Our team attended the event from September 4th to 6th, 2023, at the Queen Elizabeth II (QEII) Centre in London. We were thrilled by the many thought-provoking discussions and the new connections that we made.

‍

Exploring Trustworthiness in Healthcare Data

Evidence Prime commends the theme for this year's event. Trust is paramount in today's rapidly evolving healthcare landscape, where information and misinformation are abundant. As an AI software tool that aids the process of completing systematic reviews, trust is a crucial foundation that we build on. The future of AI in healthcare is exciting and inspiring, but not without its concerns, and we wanted to be at the forefront of groundbreaking thoughts and discussions around data security and trustworthiness in evidence-based healthcare. 

The Cochrane Colloquium 2023 event addressed several of these challenges head-on, fostering a deeper understanding of how we can ensure the reliability and credibility of healthcare evidence. 

Particular presentations stood out to us from the event that we wanted to share:

1. The Norwegian Institute of Public Health gave a compelling talk on "Building Acceptance for Machine Learning in Study Selection within a Systematic Review Institution." The speakers, Heather Ames, Patricia Sofia Jacobsen Jardim, and Christine Hestevik, shared their practical experiences implementing machine learning and automation, focusing on crucial aspects such as building trust and effective training. Their presentation offered a unique perspective, highlighting the overlooked human factor in technology and emphasizing the critical elements required to integrate new technology successfully within an organization.
2. Rocío Fuentes, representing Universidad de La Frontera, tackled the subject of "Rapid Reviews and Their Alignment with Cochrane Recommendations for Reliable Evidence." During the COVID-19 pandemic, the surge in rapid reviews (RRs) emerged as a rapid-response approach to pressing issues. RRs, which simplify or omit specific steps from systematic reviews, were examined for their adherence to Cochrane's recommendations. In the presentation, Fuentes analyzed published RRs, and it turns out that they were not following the guidance set out by Cochrane.
3. "Integrating Machine Learning into a Living Systematic Review of Baseline Risks for Venous Thromboembolism Complications in Hospitalized COVID-19 Patients" was an insightful presentation by Tamara Lotfi, representing McMaster University. The talk emphasized the efficiency and relevance of combining manual and machine learning-driven screening into living systematic reviews for prognostic studies, offering valuable insights for enhancing research methodologies.
4. Elie Akl and Joanne Khabsa from the American University of Beirut each had separate presentations that discussed the development of "Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) Extension for Living Systematic Reviews (LSRs)" and the "Conceptualizing the Reporting of Living Systematic Reviews." The discussions emphasized the unique challenges in:
   Reporting LSRs, 
   The need for standardized reporting and 
   They highlighted the efforts to extend PRISMA 2020 for LSRs. 

These presentations underscored the importance of transparent and timely reporting, addressing the evolving nature of evidence synthesis.

A Glimpse into the Future

As we left the event, we were proud to be attendees and actively contribute to a brighter future for healthcare. The event reinforced the importance of forging ahead together to ensure that the evidence we rely on is trustworthy and reliable. We are excited to take the lessons learned and the connections made at the Colloquium back to our respective roles, where we will continue to advance the cause of evidence-based healthcare.

Evidence Prime and Laser AI attended the Cochrane Colloquium 2023 in London from the 4th to the 6th of September 2023.

The Cochrane Colloquium 2023 is an annual conference organized by the Cochrane Collaboration, focusing on evidence-based medicine. It brings together researchers, healthcare professionals, and other stakeholders to discuss the latest systematic reviews and meta-analysis developments. The colloquium offers networking, learning, and collaboration opportunities for attendees from various disciplines and organizations interested in evidence-based healthcare.

Our team demonstrated how our tool helps develop systematic reviews, the backbone of evidence-based medicine. Laser AI is an AI-based systematic review tool that revolutionizes systematic reviews by accelerating data extraction, reducing workload, and ensuring adherence to rigorous standards. Its user-friendly interface and time-saving features make it a valuable tool for researchers across disciplines.

Tamara Lotfi demonstrated laser AI in an oral session in which Tamara explored the "Integration of Machine Learning in a living systematic review of baseline risks of Venous Thromboembolism complications in hospitalized patients with COVID-19."

This study focused on using a machine learning (ML) algorithm integrated into Laser AI to aid in the screening process of a Living Systematic Review (LSR) for venous thromboembolism (VTE) outcomes and baseline risks in patients with COVID-19. 

The goal was to assess Laser AI's algorithm's performance compared to manual screening and determine its impact on the review's efficiency and relevance.

The study concluded that combining manual screening with ML-directed screening can enhance the efficiency and relevance of LSRs for prognostic studies.

This work is a direct follow-up to the project that ‍Laser AI's CEO, Artur Nowak, presented during the Information Retrieval Meeting (IRM 2022), "Drinking from a firehose: living systematic review with 15,000 new references every month," where Laser AI helped a team at McMaster University maintain a living systematic review with 15,000 monthly search results.

This study showcased implementing a living review process using machine learning to manage the influx of research data and provide accurate and timely guidance for healthcare practitioners dealing with COVID-19 patients' thromboembolic risks.