A research paper by Anna Anttalainen on the prediction of lecithin concentrations from DMS measurements was published on Talanta!
Mass spectrometry studies of surgical smoke have revealed phospholipids as the key compounds enabling this discrimination. Lecithin is a mixture of phospholipids encountered in tissues.
In the study, different lecithin concentrations in a biologically relevant range considering healthy and cancerous tissues were measured with DMS and trained regression models to predict the analyte concentration. The best cross-validation results were obtained with convolutional neural networks, with root mean square error (RMSE) = 0.38 mg/ml. The best external validation results were acquired with sparse linear regression methods, with RMSE varying from 0.40 mg/ml to 0.41 mg/ml.
This is the first demonstration of estimation of analyte concentration from DMS measurements with neural networks. The results demonstrate that DMS is sufficiently sensitive to detect biologically relevant changes in phospholipid concentration. Predicting concentration with neural networks lays the foundation for wider analytical usage of DMS, and for the identification of lecithin from surgical smoke medium.
Read the full article on ScienceDirect