ALS Predictive model

Amyotrophic lateral sclerosis (ALS) diagnosis: A predictive model.


The clinical diagnosis of amyotrophic lateral sclerosis (ALS) usually takes several months and this delay adversely affects the therapeutic interventions. Hence, earlier and effective diagnosis of ALS for better management of ALS patients needs the development of a statistical model. Therefore, we have developed a statistical model for predicting the risk of ALS at earlier stages. The study recruited 44 sporadic ALS patients along with 29 normal controls. Demographic details (e.g. age, sex, cigarette smoking status, alcohol consumption, diet and bodymass index) of patients at the age of onset of disease was collected using a questionnaire. Thirteen independent variables (predictors) which may be associated with ALS were included in the study. Forward stepwise (likelihood ratio) binary logistic regression was used to find significant variables and probability of disease prediction.

The Serum chemokine ligand-2, chemokine ligand-2 mRNA, vascular endothelial growth factor-A mRNA, smoking and alcohol consumption are the independent variables found significant to predict risk of ALS.  The current model yielded 93.2% sensitivity and 86.2% specificity with 90.4% overall validity of correct ALS prediction. The study suggest the Forward stepwise (likelihood ratio) binary logistic regression model is an accurate method to predict ALS in the presence of serum CCL2, CCL2 mRNA, VEGFA mRNA, smoking and alcohol consumption with high sensitivity and specificity.

Gupta P K,  Prabhakar S, SharmaS and Anand A. A predictive model for amyotrophic lateral sclerosis (ALS) diagnosis. Journal of the Neurological Sciences. 2012;  312:68–72


<<< Back to Research Area