Developing a large scale population screening tool for the assessment of Parkinson's disease using telephone-quality voice

Abstract Objectives To assess the diet quality of people with Parkinson's Disease (PwPD) using two assessment tools: Healthy Eating Index (HEI)-2015 and the Dietary Screening Tool (DST). HEI-2015 and DST scores were compared for alignment to explore associations between HEI-2015 and DST total scores and sub-scores. Methods This secondary data analysis utilized a total of 28 participants from two studies examining PwPD and their informal caregivers. Dietary data was collected with two 24-hour recalls using the multiple pass method and entered into the Nutrition Data System for Research (NDSR). SAS Version 9.4 was used to compute HEI-2015 scores to assess diet quality. The HEI-2015 score is a total of 100 points and is based on the Dietary Guidelines for Americans for 2015–2020. Total HEI-2015 scores and 13 component scores were interpreted using the graded approach (grades A-F). Radar graphs provide a visual representation. Participants also completed the DST. The DST is a 25-item questionnaire used to identify dietary patterns and assess nutritional risk. Total scores were categorized into at risk <60, possibly risk 60–75, and not at risk >75. Sub-scores were calculated with point classifications for specific food categories. These sub-scores were divided into tertials of recommended intakes less than 50%, 50–80% and 80–100%, and compared for alignment between DST sub-scores and HEI-2015 sub-scores by assessing total number of pairs per category. Results The mean total score was 59.4 ± 28.6 for DST and 58.7 ± 22.2 for HEI-2015. HEI-2015 scores fell into grades of A (n = 0) B (n = 3) C (n = 3) D (n = 7) F (n = 14). PwPD who were categorized at risk from the DST scores (n = 18) received an HEI grade of D/F. PwPD who were at possible risk (n = 7) received a grade of B/C/D. PwPD who were not at risk (n = 3) received a grade of B/C/D for sub-scores, vegetable intake had a 50% alignment in scores, fat/sugar 43% alignment, whole grains and dairy 46% alignment and fruit 39% alignment. Conclusions There appeared to be partial alignment between the total HEI-2015 scores and DST nutritional risk scores. Sub-scores differ 50% of the time. Due to differences between the assessment tools, more research is needed to validate the DST in PwPD as this can be a less taxing assessment compared with 24-hour recalls. Funding Sources There was no external funding for this study.

Download Full-text

Is large-scale population screening coming to psychiatry?

The Lancet Digital Health ◽

10.1016/s2589-7500(20)30066-2 ◽

2020 ◽

Vol 2 (5) ◽

pp. e210-e211

Author(s):

Ioana Alina Cristea ◽

Florian Naudet

Keyword(s):

Large Scale ◽

Population Screening ◽

Scale Population

Download Full-text

Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity

Journal of The Royal Society Interface ◽

10.1098/rsif.2010.0456 ◽

2010 ◽

Vol 8 (59) ◽

pp. 842-855 ◽

Cited By ~ 128

Author(s):

Athanasios Tsanas ◽

Max A. Little ◽

Patrick E. McSharry ◽

Lorraine O. Ramig

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Signal Processing ◽

Symptom Severity ◽

Large Scale ◽

Rating Scale ◽

Signal Processing Algorithm ◽

Wide Range ◽

Signal Processing Algorithms ◽

Processing Algorithms

The standard reference clinical score quantifying average Parkinson's disease (PD) symptom severity is the Unified Parkinson's Disease Rating Scale (UPDRS). At present, UPDRS is determined by the subjective clinical evaluation of the patient's ability to adequately cope with a range of tasks. In this study, we extend recent findings that UPDRS can be objectively assessed to clinically useful accuracy using simple, self-administered speech tests, without requiring the patient's physical presence in the clinic. We apply a wide range of known speech signal processing algorithms to a large database (approx. 6000 recordings from 42 PD patients, recruited to a six-month, multi-centre trial) and propose a number of novel, nonlinear signal processing algorithms which reveal pathological characteristics in PD more accurately than existing approaches. Robust feature selection algorithms select the optimal subset of these algorithms, which is fed into non-parametric regression and classification algorithms, mapping the signal processing algorithm outputs to UPDRS. We demonstrate rapid, accurate replication of the UPDRS assessment with clinically useful accuracy (about 2 UPDRS points difference from the clinicians' estimates, p < 0.001). This study supports the viability of frequent, remote, cost-effective, objective, accurate UPDRS telemonitoring based on self-administered speech tests. This technology could facilitate large-scale clinical trials into novel PD treatments.

Download Full-text