Detecting Parkinson’s disease and its cognitive phenotypes via automated semantic analyses of action stories
García, A. M., Escobar Grisales, D., Vásquez Correa, J. C., Bocanegra, Y., Moreno, L., Carmona, J. & Orozco-Arroyave, J. R. (2022). Detecting Parkinson’s disease and its cognitive phenotypes via automated semantic analyses of action stories. npj Parkinson’s Disease 8, 163.
En este trabajo mostramos que el peso de conceptos de acción en la narración de historias permite discriminar distintos fenotipos cognitivos de la enfermedad de Parkinson. Esta medida, captada de modo automático, supera a otras métricas estándar en el campo del análisis automatizado del lenguaje. Así surgen nuevas avenidas para identificar marcadores de la enfermedad en un entorno objetivo y naturalista.
Para acceder al artículo, hacé click aquí.
Detecting Parkinson’s disease and its cognitive phenotypes via automated semantic analyses of action stories
García, A. M., Escobar Grisales, D., Vásquez Correa, J. C., Bocanegra, Y., Moreno, L., Carmona, J. & Orozco-Arroyave, J. R. (2022). Detecting Parkinson’s disease and its cognitive phenotypes via automated semantic analyses of action stories. npj Parkinson’s Disease 8, 163.
Action-concept outcomes are useful targets to identify Parkinson’s disease (PD) patients and differentiate between those with and without mild cognitive impairment (PD-MCI, PD-nMCI). Yet, most approaches employ burdensome examiner-dependent tasks, limiting their utility. We introduce a framework capturing action-concept markers automatically in natural speech. Patients from both subgroups and controls retold an action-laden and a non-action-laden text (AT, nAT). In each retelling, we weighed action and non-action concepts through our automated Proximity-to-Reference-Semantic-Field (P-RSF) metric, for analysis via ANCOVAs (controlling for cognitive dysfunction) and support vector machines. Patients were differentiated from controls based on AT (but not nAT) P-RSF scores. The same occurred in PD-nMCI patients. Conversely, PD-MCI patients exhibited reduced P-RSF scores for both texts. Direct discrimination between patient subgroups was not systematic, but it yielded best outcomes via AT scores. Our approach outperformed classifiers based on corpus-derived embeddings. This framework opens scalable avenues to support PD diagnosis and phenotyping.
To access the full paper, please click here.
