A Novel Machine Learning Algorithm to Predict the Lewy Body Dementias (MLDLB)

A Novel Machine Learning Algorithm to Predict the Lewy Body Dementias Using Clinical and Neuropsychological Scores

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.

Study Overview

• Status: Unknown
• Conditions: Dementia
• Intervention / Treatment: Diagnostic test: machine learning model

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 Type: Observational
• Enrollment (Anticipated): 200

Contacts and Locations

Study Locations

• Greece
  • Attiki
    • Athens, Attiki, Greece, 16674
      • Recruiting
      • Anastasia Bougea
      • Contact: EFTHYMIA EFTHYMIIOPOULOU, dr; Phone Number: 00306943061632; Email: faih.efthymiopoulou@gmail.com
      • Sub-Investigator: Christos Goumas, dr

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 50 years to 90 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

the PDD group comprised of patients fulfilling the Criteria for probable PDD and the DLB group.Patients will be enrolled from the register-based database of two clinics. The following data were collected: gender, age, education, hand dominance, Disease duration (years) and levodopa equivalent daily dose (LEDD). The burden of disease will be assess by the Movement Disorders Society-United Parkinson's Disease Rating Scale (MDS-UPDRS) part III in the Off medication state and the following six cognitive/behavioral tests: Mini-Mental State Examination (MMSE), PD- Cognitive Rating Scale (PD-CRS), Brief Visuospatial Memory test (BVMT-TR), Symbol digit written (SDMT), Trail making test (TMT A,B), Wechsler adultintelligence scale (WAIS-V). All patients will undergo brain MRI and blood test to exclude secondarycauses of dementia.

Description

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 Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Parkinson Disease Dementia; the PDD group comprised of 58 patients fulfilling the Criteria for probable PDD of the Movement Disorders Society	Diagnostic test: machine learning model; Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), were investigated for their ability to predict successfully whether patients suffered from PDD or DLB.
Dementia with Lewy Bodies; the DLB group comprised of 40 patients, according to the recent revised criteria for probable DLB	Diagnostic test: machine learning model; Two classification algorithms, logistic regression and K-Nearest Neighbors (K-NNs), were investigated for their ability to predict successfully whether patients suffered from PDD or DLB.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
MMSE predictive for dlb or PDD	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.	1 year
Parkinson's Disease - Cognitive Rating Scale (PD-CRS) predictive for DLB or PDD	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.	1 year
Brief Visuospatial Memory Test (BVMT-TR) predictive for DLB or PDD	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.	1 year
Symbol digit written predictive for DLB or PDD	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.	1 year
Wechsler adult intelligence scale,predictive for DLB or PDD	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.	1 year
trail making A and B predictive for DLB or PDD	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.	1 year

Collaborators and Investigators

• Sponsor: National and Kapodistrian University of Athens
• Investigators: Principal Investigator: ANASTASIA BOUGEA, National and Kapodistrian University of Athens

Publications and helpful links

General Publications

• Bougea A, Efthymiopoulou E, Spanou I, Zikos P. A Novel Machine Learning Algorithm Predicts Dementia With Lewy Bodies Versus Parkinson's Disease Dementia Based on Clinical and Neuropsychological Scores. J Geriatr Psychiatry Neurol. 2022 May;35(3):317-320. doi: 10.1177/0891988721993556. Epub 2021 Feb 8.

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2019
• Primary Completion (Anticipated): October 1, 2020
• Study Completion (Anticipated): March 1, 2021

Study Registration Dates

• First Submitted: June 21, 2020
• First Submitted That Met QC Criteria: June 24, 2020
• First Posted (Actual): June 25, 2020

Study Record Updates

• Last Update Posted (Actual): September 10, 2020
• Last Update Submitted That Met QC Criteria: September 8, 2020
• Last Verified: September 1, 2020

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Mental Disorders; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Neurocognitive Disorders; Parkinsonian Disorders; Basal Ganglia Diseases; Movement Disorders; Synucleinopathies; Neurodegenerative Diseases; Dementia; Lewy Body Disease
• Other Study ID Numbers: 251ATHENS HOSPITAL

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No