Method for quantitatively predicting cartilage repair rate after mesenchymal stem cell therapy through machine learning

Abstract

The invention discloses a method for quantitatively predicting the cartilage repair rate after mesenchymal stem cell therapy through machine learning. The method comprises the following steps: S1, establishing a database; S2, preprocessing original data; S3, processing lost data; S4, developing a model; and S5, generating an MSC treatment guide for cartilage repair through machine learning. According to the invention, the treatment result of the patient receiving the MSC cartilage repair treatment can be accurately predicted according to the illness state and the treatment strategy of the patient, so that an important reference is provided for a clinician to decide whether or not and how to perform MSC treatment on the patient suffering from cartilage injury. Therefore, the method is verysuitable for popularization and application.

Description

technical field [0001] The invention relates to the technical field of regenerative medicine, in particular to a method for quantitatively predicting cartilage repair rate after mesenchymal stem cell therapy by machine learning. Background technique [0002] Stem cell (MSC) therapy is the most promising candidate in regenerative medicine, but inconsistent efficacy of MSC therapy has been reported in various clinical trials. A plausible reason is the lack of quantitative scientific guidelines for developing individualized MSC treatment strategies. Since the determination of the optimal treatment parameters depends on the individual condition of the patient, it is difficult to quantitatively obtain the treatment strategy for the best treatment outcome for the patient only by conventional biomedical research. [0003] In recent years, the use of machine learning techniques has made significant scientific progress in various biomedical fields, but few attempts have been made fo...

AI Technical Summary

Problems solved by technology

Since the determination of the optimal treatment parameters depends on the individual condition of the patient, it is difficult to quantitatively obtain the treatment strategy for the best treatment outcome for the patient only by conventional biomedical research

[0003] In recent years, the use of machine learning techniques has made significant scientific progress in various biomedical fields, but few attempts have been made for stem cell therapy. The main reason is that existing machine learning models, especially neural network models, Requires a large amount of data support. For example, Google's Tensorflow requires at least 1,000 rows of data sets to run

While clinical trial data is usually small (several to dozens of data points), if the data set is smaller than the number of variables, it cannot be processed

In addition, due to problems with experimental design and data collection, entries with incomplete input information (i.e. missing data) will be included, while existing machine learning models usually require complete data sets

Therefore, using existing machine learning techniques to predict the therapeutic efficacy of MSC cartilage repair to obtain personalized quantitative MSC optimal treatment strategies requires very high data, time and cost, and is almost impossible to achieve.