Comparative assessment of glucose prediction models for patients with type 1 diabetes mellitus applying sensors for glucose and physical activity monitoring.

The present work presents the comparative assessment of four glucose prediction models for patients with type 1 diabetes mellitus (T1DM) using data from sensors monitoring blood glucose concentration. The four models are based on a feedforward neural network (FNN), a self-organizing map (SOM), a neuro-fuzzy network with wavelets as activation functions (WFNN), and a linear regression model (LRM), respectively. For the development and evaluation of the models, data from 10 patients with T1DM for a 6-day observation period have been used. The models' predictive performance is evaluated considering a 30-, 60- and 120-min prediction horizon, using both mathematical and clinical criteria. Furthermore, the addition of input data from sensors monitoring physical activity is considered and its effect on the models' predictive performance is investigated. The continuous glucose-error grid analysis indicates that the models' predictive performance benefits mainly in the hypoglycemic range when additional information related to physical activity is fed into the models. The obtained results demonstrate the superiority of SOM over FNN, WFNN, and LRM with SOM leading to better predictive performance in terms of both mathematical and clinical evaluation criteria.

Transthyretin interacts with the lysosome-associated membrane protein (LAMP-1) in circulation.

LAMP-1 (lysosome-associated membrane protein), a major glycoprotein present in the lysosomal membrane, constitutes up to 50% of total membrane proteins. LAMP-1, expressed at the plasma membrane, is reported to be the major molecule expressing the sialyl-Lewis X antigen. Two forms of LAMP-1 exist; the full-length LAMP-1 [LAMP-1 (+Tail)] has a highly glycosylated lumenal domain, a membrane-spanning domain and a short cytoplasmic tail, and the truncated LAMP-1 [LAMP-1 (-Tail)] contains only the lumenal domain. Soluble LAMP-1 (+/-Tail) has been reported in circulation. LAMP-1 at the cell surface has been shown to interact with E-selectin and galectin and is proposed to function in cell-cell interactions. However, the functional role(s) of soluble LAMP-1 in circulation is unclear. To investigate the functional role of soluble LAMP-1 in circulation, recombinant LAMP-1 (-Tail) and LAMP-1 (+Tail) were produced in HT1080 cells. Two immune-quantification assays were developed to distinguish between the LAMP-1 forms. The interaction and aggregation properties of the different LAMP-1 forms were investigated using the immune-quantification assays. Only LAMP-1 (+Tail) was found to aggregate and interact with plasma proteins. Plasma proteins that interact with LAMP-1 were isolated by affinity chromatography with either the recombinant LAMP-1 (-Tail) or a synthesized peptide consisting of the 14 amino acids of the LAMP-1 cytoplasmic tail. Transthyretin was found to interact with the cytoplasmic tail of LAMP-1. Transthyretin exists as a homotetramer in plasma, as such may play a role in the aggregation of LAMP-1 in circulation.