Neurodegenerative diseases like Alzheimer's disease or Parkinson's disease are caused by folding errors (misfolding) in proteins or peptides, i.e. by changes in their spatial structure. This is the result of minute deviations in the chemical composition of the biomolecules. Researchers at the Karlsruhe Institute of Technology (KIT) have developed a simple and effective method for detecting such misfolding at an early stage of the disease. Misfolding is revealed by the structure of dried residue from protein and peptide solutions. The method involves analyzing micrographs with neural networks and has a predictive accuracy of more than 99%. The results have been published in Advanced Materials.