A Novel Machine Learning Algorithm to Predict the Lewy Body Dementias

• Conditions: Dementia

• Registration Number: NCT04448340
• Lead Sponsor: National and Kapodistrian University of Athens

Brief Summary

Parkinson's disease dementia (PDD) and Dementia with lewy bodies (DLB) are dementia syndromes that overlap in many clinical features, making their diagnosis difficult in clinical practice, particularly in advanced stages. We propose a machine learning algorithm, based only on non-invasively and easily in-the-clinic collectable predictors, to identify these disorders with a high prognostic performance.

Detailed Description

The algorithm will be develop using dataset from two specialized memory centers, employing a sample of PDD and DLB subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. A restricted set of information regarding clinico- demographic characteristics, 6 neuropsychological tests (mini mental, PD Cognitive Rating Scale, Brief Visuospatial Memory test, Symbol digit written, Wechsler adult intelligence scale, trail making A and B) was used as predictors. Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), will be investigated for their ability to predict successfully whether patients suffered from PDD or DLB.

Study Timeline

• Study Start: 2019-09-01
• Study First Submitted: 2020-06-21
• Study First Submitted QC: 2020-06-24
• Study First Posted: 2020-06-25
• Status Verified: 2020-09
• Last Update Submitted: 2020-09-08
• Last Update Posted: 2020-09-10
• Primary Completion: 2020-10-01
• Study Completion: 2021-03-01

Recruitment & Eligibility

• Status: UNKNOWN
• Sex: All
• Target Recruitment: 200

Inclusion Criteria

the PDD group comprised of patients fulfilling the Criteria for probable PDD of the Movement Disorders Society (b) the DLB group comprised of patients, according to the recent revised criteria for probable DLB .

Exclusion Criteria

• major psychiatrics disorders, depression

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
MMSE predictive for dlb or PDD	1 year	Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), will combine these tests in order to investigate for their ability to predict successfully whether patients suffered from PDD or DLB.
Parkinson's Disease - Cognitive Rating Scale (PD-CRS) predictive for DLB or PDD	1 year	Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), will combine these tests in order to investigate for their ability to predict successfully whether patients suffered from PDD or DLB.
Brief Visuospatial Memory Test (BVMT-TR) predictive for DLB or PDD	1 year	Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), will combine these tests in order to investigate for their ability to predict successfully whether patients suffered from PDD or DLB.
Symbol digit written predictive for DLB or PDD	1 year	Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), will combine these tests in order to investigate for their ability to predict successfully whether patients suffered from PDD or DLB.
Wechsler adult intelligence scale,predictive for DLB or PDD	1 year	Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), will combine these tests in order to investigate for their ability to predict successfully whether patients suffered from PDD or DLB.
trail making A and B predictive for DLB or PDD	1 year	Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), will combine these tests in order to investigate for their ability to predict successfully whether patients suffered from PDD or DLB.

Trial Locations

Locations (1)

Anastasia Bougea; 🇬🇷 Athens, Attiki, Greece