Measuring neuropsychiatric symptoms in early dementia patients using speech analysis

Introduction

Certain neuropsychiatric symptoms (NPS), namely apathy, depression and anxiety demonstrated great value in predicting dementia progression representing eventually an opportunity window for timely diagnosis and treatment. However, sensitive and objective markers of these symptoms are still missing.

Objectives

To investigate the association between automatically extracted speech features and NPS in early-stage dementia patients.

Methods

Speech of 141 patients aged 65 or older with neurocognitive disorder was recorded while performing two short narrative speech tasks. Presence of NPS was assessed by the Neuropsychiatric Inventory. Paralinguistic markers relating to prosodic, formant, source, and temporal qualities of speech were automatically extracted, correlated with NPS. Machine learning experiments were carried out to validate the diagnostic power of extracted markers.

Results

Different speech variables seem to be associated with specific neuropsychiatric symptoms of dementia; apathy correlates with temporal aspects, anxiety with voice quality and this was mostly consistent between male and female after correction for cognitive impairment. Machine learning regressors are able to extract information from speech features and perform above baseline in predicting anxiety, apathy and depression scores.

Conclusions

Different NPS seem to be characterized by distinct speech features which in turn were easily extractable automatically from short vocal tasks. These findings support the use of speech analysis for detecting subtypes of NPS. This could have great implications for future clinical trials.

Disclosure

No significant relationships.

Release of extracellular vesicle miR-494-3p by ARPE-19 cells with impaired mitochondria

BACKGROUND

Mitochondrial function in retinal pigmented epithelial (RPE) cells and extracellular vesicle (EV) formation/release are related through the lysosomal and exocytotic pathways that process and eliminate intracellular material, including mitochondrial fragments. We propose that RPE cells with impaired mitochondria will release EVs containing mitochondrial miRNAs that reflect the diminished capacity of mitochondria within these cells.

METHODS

We screened ARPE-19 cells for miRNAs that localize to the mitochondria, exhibit biological activity, and are present in EVs released by both untreated cells and cells treated with rotenone to induce mitochondrial injury. EVs were characterized by vesicle size, size distribution, presence of EV biomarkers: CD81, CD63, and syntenin-1, miRNA cargo, and number concentration of EVs released per cell.

RESULTS

We found that miR-494-3p was enriched in ARPE-19 mitochondria. Knockdown of miR-494-3p in ARPE-19 cells decreased ATP production and mitochondrial membrane potential in a dose-dependent manner, and decreased basal oxygen consumption rate and maximal respiratory capacity. Increased number of EVs released per cell and elevated levels of miR-494-3p in EVs released from ARPE-19 cells treated with rotenone were also measured.

CONCLUSIONS

ARPE-19 mitochondrial function is regulated by miR-494-3p. Elevated levels of miR-494-3p in EVs released by ARPE-19 cells indicate diminished capacity of the mitochondria within these cells.

GENERAL SIGNIFICANCE

EV miR-494-3p is a potential biomarker for RPE mitochondrial dysfunction, which plays a central role in non-neovascular age-related macular degeneration, and may be a diagnostic biomarker for monitoring the spread of degeneration to neighboring RPE cells in the retina.