Is cellular therapy beneficial in management of rotator cuff tears? Meta-analysis of comparative clinical studies

Evidence-based orthobiologic practice: Current evidence review and future directions

The field of orthopedic and regenerative medicine is rapidly evolving with the increasing utilization of orthobiologic. These biologically derived therapies, including platelet-rich plasma, mesenchymal stem cells, bone marrow aspirate concentrate, stromal vascular fraction (SVF), and autologous chondrocyte implantation, are gaining traction for their potential to enhance the body's natural healing processes. They offer a promising alternative to traditional surgical interventions for musculoskeletal injuries and degenerative conditions. Current evidence suggests significant benefits of orthobiologics in treating conditions like osteoarthritis, tendon injuries, and spinal disorders, yet inconsistencies in treatment protocols and outcomes persist. The global market for orthobiologics is projected to grow substantially, driven by advancements in biologic therapies such as adipose-derived stem cells and SVF, and the demand for minimally invasive treatments. Despite their promise, regulatory and ethical challenges, as well as the need for high-quality, standardized research, remain significant obstacles. Future directions in the field include advancements in delivery systems, personalized medicine approaches, and the exploration of novel sources like induced pluripotent stem cells, aiming for more targeted and effective treatments. Collaborative efforts are crucial to overcoming these challenges and ensuring the safe and effective application of orthobiologics in clinical practice.

The efficiency of machine learning-assisted platform for article screening in systematic reviews in orthopaedics

PURPOSE

With the development of machine learning and artificial intelligence, various platforms were developed to aid in the time-consuming process of article screening in systematic reviews. We aim to analyze the efficiency of a machine learning-assisted platform as an end-user to aid in the screening of the articles for selection into systematic review in orthopaedic surgery.

METHODS

We included three previously published systematic reviews in the field of orthopaedics of increasing levels of difficulty in the structure of the research question to assess the efficiency of a platform with active-learning technology for article screening. We compared the efficiency of the platform compared to the traditional screening and also across the various scenarios tested. We performed five iterations for each review analyzed. The outcome parameters analyzed were the work saved at 95% recall (WSS-95), work saved at 100% recall (WSS-100), and relevant records found after screening the first 30% of the total records (RRF-30).

RESULTS

The machine learning-assisted screening significantly improved the rate of identifying the relevant records compared to the traditional screening method (p<0.001). The WSS-95 for the easy, intermediate, and advanced screening scenarios were 78%, 59%, and 38%, respectively. The WSS-100 for the easy, intermediate, and advanced screening scenarios were 75%, 48%, and 7%, respectively. The RRF-30 for the easy, intermediate, and advanced screening scenarios were 97%, 86%, and 64%, respectively. We noted a significant reduction (p<0.001) in the efficiency with the increasing level of difficulty of the screening scenarios.

CONCLUSION

The machine learning platform is significantly better than the traditional method as an assistive technology to aid in article screening. However, the efficiency of the platform significantly decreases as the complexity of the research question increases.