Application of Machine Learning Method in Validation of Screening Cognitive Test for Parkinsonisms

Completed

• Conditions: Supranuclear Palsy, Progressive; Secondary Vascular Parkinson Disease; Multiple System Atrophy; Primary Parkinsonism
• Interventions: Diagnostic Test: CoMDA associated with Neural Net 91 classificator

• Registration Number: NCT04858893
• Lead Sponsor: Ospedale Generale Di Zona Moriggia-Pelascini

Brief Summary

Based on a prospectively collected data analysis, a new tool, namely CoMDA (Cognition in Movement Disorders Assessment) is developed by merging each item of Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA) and Frontal Assessment Battery (FAB). A machine learning, able to classify the cognitive profile and predict patients' at risk of dementia, is created.

Detailed Description

A prospectively data-base was setting up, collecting CoMDA and in-depht-neuropsychologocal-battery scores, obtained from the evaluation of 500 patients with parkinsonisms. Data were analyzed to compare the classification of patient cognition profile, obtained with CoMDA, MMSE, MoC and FAB, with that obtained from in-depth neuropsychological evaluation. A very high percentage of false negative emerged, for MMSE, MoCA and FAB. Conversely, the CoMDA score significantly reduces the rate of false negative.

This new tool, namely "CoMDA" (Cognition in Movement Disorders Assessment), was composed, by merging each item of Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA) and Frontal Assessment Battery (FAB). Moreover, we created a machine learning, namely "Neural Net 91classification" able to classify the cognitive profile and predict patients' at risk of dementia, providing a prediction of the findings resulting from a in-depht neuropsychological evaluation.

CoMDA and the related Neural Net 91classification represent a reliable, time-sparing screening instrument, which is much more powerful of other common, widely-adopted tools.

Study Timeline

• Study Start: 2017-01-01
• Primary Completion: 2020-02-01
• Study Completion: 2020-08-31
• Study First Submitted: 2021-04-21
• Study First Submitted QC: 2021-04-23
• Study First Posted: 2021-04-26
• Status Verified: 2021-05
• Last Update Submitted: 2021-05-11
• Last Update Posted: 2021-05-12

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 562

Inclusion Criteria

diagnosis of idiopathic PD according to the MDS clinical diagnostic criteria (Postuma et al. 2015); b) diagnosis of PSP according to the MDS clinical diagnostic criteria (Höglinger et al. 2017); c) diagnosis of MSA according to the second diagnostic consensus statement (Gilman et al. 2008); d) diagnosis of VP according to Zijlmans et al (Zijlmans et al. 2004).

Exclusion Criteria

a) any focal brain lesion detected with brain imaging studies (CT or MRI); b) diagnosis of clinically relevant psychiatric disorders, psychosis (evaluated with Neuropsychiatric Inventory) and/or delirium; c) diagnosis of dementia or MCI; d) diagnosis of neurological diseases other than PD or atypical parkinsonian syndromes; e) other medical conditions negatively affecting the cognitive status; f) disturbing resting and/or action tremor, corresponding to scores 2-4 in the specific items of MDS Unified Parkinson's Disease Rating Scale (MDS-UPDRS) III, such as to affect the psychometric evaluation; g) disturbing dyskinesia, corresponding to scores 2-4 in the specific items of MDS-UPDRS III, such as to affect the psychometric evaluation; h) auditory and/or visual dysfunctions impairing the patient´s ability to perform cognitive tests.

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Subjects affected from Parkinsonims	CoMDA associated with Neural Net 91 classificator	Scores of MMSE, FAB MoCA were summarized to calculate the CoMDA scores, than they were used to develop the Neural Net 91 classificator
Health Controls	CoMDA associated with Neural Net 91 classificator	CoMDA was administered and total score was calculate to develop the Neural Net 91 classificator

Primary Outcome Measures

Name	Time	Method
Neural Net 91 classificator from CoMDA score	30 minuts	prediction of cognitive level obtained from the application of Neural Net 91 classificator at CoMDA score

Trial Locations

Locations (1)

"Moriggia Pelascini" Hospital; 🇮🇹 Gravedona E Uniti, Como, Italy