Related Experiment Video
Updated: Jun 23, 2025
Large-Scale Preparation of Synovial Fluid Mesenchymal Stem Cell-Derived Exosomes by 3D Bioreactor Culture
Published on: July 26, 2022
Unlocking the full potential of mesenchymal stromal cell therapy for osteoarthritis through machine learning-based in
Lu Yin1, Meiwu Ye2, Yang Qiao3
1Jiangxi Provincial Key Laboratory of Respiratory Diseases, Jiangxi Institute of Respiratory Diseases, Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, China; Jiangxi Clinical Research Center for Respiratory Diseases, Nanchang, Jiangxi, China; Jiangxi Hospital of China-Japan Friendship Hospital, Nanchang, Jiangxi, China; Agency for Science Technology and Research, Bioprocessing Technology Institute, Singapore, Singapore.
Abstract:
Despite the potential of mesenchymal stromal cells (MSCs) in osteoarthritis (OA) treatment, the challenge lies in addressing their therapeutic inconsistency. Clinical trials revealed significantly varied therapeutic outcomes among patients receiving the same allogenic MSCs but different treatment regimens. Therefore, optimizing personalized treatment strategies is crucial to fully unlock MSCs' potential and enhance therapeutic consistency. We employed the XGBoost algorithm to train a self-collected database comprising 37 published clinical reports to create a model capable of predicting the probability of effective pain relief and Western Ontario and McMaster Universities (WOMAC) index improvement in OA patients undergoing MSC therapy. Leveraging this model, extensive in silico simulations were conducted to identify optimal personalized treatment strategies and ideal patient profiles. Our in silico trials predicted that the individually optimized MSC treatment strategies would substantially increase patients' chances of recovery compared to the strategies used in reported clinical trials, thereby potentially benefiting 78.1%, 47.8%, 94.4% and 36.4% of the patients with ineffective short-term pain relief, short-term WOMAC index improvement, long-term pain relief and long-term WOMAC index improvement, respectively. We further recommended guidelines on MSC number, concentration, and the patients' appropriate physical (body mass index, age, etc.) and disease states (Kellgren-Lawrence grade, etc.) for OA treatment. Additionally, we revealed the superior efficacy of MSC in providing short-term pain relief compared to platelet-rich plasma therapy for most OA patients. This study represents the pioneering effort to enhance the efficacy and consistency of MSC therapy through machine learning applied to clinical data. The in silico trial approach holds immense potential for diverse clinical applications.
