A Novel Machine Learning Algorithm to Predict the Lewy Body Dementias

NCT04448340 | Unknown

• 1 other identifier: 251ATHENS HOSPITAL
• Study Type: observational
• Target: 200
• Locations: 1 country
• Sites: 1

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.

Conditions

Dementia

Outcome Measures

Primary Outcomes (6)

• 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

Study Arms (2)

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

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

Interventions

machine learning model DIAGNOSTIC_TEST

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; Parkinson Disease Dementia

Eligibility Criteria

• Age: 50 Years - 90 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• 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.

You may qualify if:

• 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 .

You may not qualify if:

• major psychiatrics disorders, depression

Sponsors & Collaborators

• National and Kapodistrian University of Athens: lead

Study Sites (1)

Anastasia Bougea

Athens, Attica, 16674, Greece

RECRUITING

Related Publications (1)

• 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.

  PMID: 33550890 DERIVED

MeSH Terms

Conditions

Dementia

Condition Hierarchy (Ancestors)

Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Neurocognitive Disorders; Mental Disorders

Study Officials

• ANASTASIA BOUGEA

  National and Kapodistrian University of Athens

  PRINCIPAL INVESTIGATOR

Central Study Contacts

ANASTASIA BOUGEA, DR

CONTACT

+306930481046; annita139@yahoo.gr

ANASTASIA BOUGEA

CONTACT

+306930481046; annita139@yahoo.gr

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: DR

Study Record Dates

• First Submitted: June 21, 2020
• First Posted: June 25, 2020
• Study Start: September 1, 2019
• Primary Completion: October 1, 2020
• Study Completion: March 1, 2021
• Last Updated: September 10, 2020

Record last verified: 2020-09

Data Sharing

• IPD Sharing: Will not share

Locations

GR (1)