Harnessing topological machine learning in Raman spectroscopy: perspectives for Alzheimer’s disease detection via cerebrospinal fluid analysis

Conti F., Banchelli M., Bessi V., Cecchi C., Chiti F., Colantonio S., D'Andrea C., De Angelis M., Moroni D., Nacmias B., Pascali M. A., Sorbi S., Matteini P.

Persistent homology  Topological machine learning  Raman spectroscopy  Alzheimer's disease 

The cerebrospinal fluid of 21 subjects who received a clinical diagnosis of Alzheimer’s disease (AD) as well as of 22 pathological controls has been collected and analysed by Raman spectroscopy (RS). We investigated whether the Raman spectra could be used to distinguish AD from controls, after a preprocessing procedure. We applied machine learning to a set of topological descriptors extracted from the spectra, achieving a high classification accuracy of 86%. Our experimentation indicates that RS and topological analysis may be a reliable and effective combination to confirm or disprove a clinical diagnosis of Alzheimer’s disease. The following steps will aim at leveraging the intrinsic interpretability of the topological data analysis to characterize the AD subtypes, e.g. by identifying the bands of the Raman spectrum relevant for AD detection, possibly increasing and/or confirming the knowledge about the precise molecular events and biological pathways behind the Alzheimer’s disease.

Source: JOURNAL OF THE FRANKLIN INSTITUTE, vol. 361 (issue 18)

Metrics