Cargando…

Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor?

INTRODUCTION: Machine learning (ML) is an established technique that uses sets of training data to develop algorithms and perform data classification without using human intervention/supervision. This study aims to determine how functional and anatomical brain connectivity (FC and SC) data can be us...

Descripción completa

Detalles Bibliográficos
Autores principales: Tran, Khue, Salazar, Betsy H., Boone, Timothy B., Khavari, Rose, Karmonik, Christof
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10071087/
https://www.ncbi.nlm.nih.gov/pubmed/37025479
http://dx.doi.org/10.1002/bco2.217
_version_ 1785019126631104512
author Tran, Khue
Salazar, Betsy H.
Boone, Timothy B.
Khavari, Rose
Karmonik, Christof
author_facet Tran, Khue
Salazar, Betsy H.
Boone, Timothy B.
Khavari, Rose
Karmonik, Christof
author_sort Tran, Khue
collection PubMed
description INTRODUCTION: Machine learning (ML) is an established technique that uses sets of training data to develop algorithms and perform data classification without using human intervention/supervision. This study aims to determine how functional and anatomical brain connectivity (FC and SC) data can be used to classify voiding dysfunction (VD) in female MS patients using ML. METHODS: Twenty‐seven ambulatory MS individuals with lower urinary tract dysfunction were recruited and divided into two groups (Group 1: voiders [V, n = 14]; Group 2: VD [n = 13]). All patients underwent concurrent functional MRI/urodynamics testing. RESULTS: Best‐performing ML algorithms, with highest area under the curve (AUC), were partial least squares (PLS, AUC = 0.86) using FC alone and random forest (RF) when using SC alone (AUC = 0.93) and combined (AUC = 0.96) as inputs. Our results show 10 predictors with the highest AUC values were associated with FC, indicating that although white matter was affected, new connections may have formed to preserve voiding initiation. CONCLUSIONS: MS patients with and without VD exhibit distinct brain connectivity patterns when performing a voiding task. Our results demonstrate FC (grey matter) is of higher importance than SC (white matter) for this classification. Knowledge of these centres may help us further phenotype patients to appropriate centrally focused treatments in the future.
format Online
Article
Text
id pubmed-10071087
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-100710872023-04-05 Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor? Tran, Khue Salazar, Betsy H. Boone, Timothy B. Khavari, Rose Karmonik, Christof BJUI Compass Original Articles INTRODUCTION: Machine learning (ML) is an established technique that uses sets of training data to develop algorithms and perform data classification without using human intervention/supervision. This study aims to determine how functional and anatomical brain connectivity (FC and SC) data can be used to classify voiding dysfunction (VD) in female MS patients using ML. METHODS: Twenty‐seven ambulatory MS individuals with lower urinary tract dysfunction were recruited and divided into two groups (Group 1: voiders [V, n = 14]; Group 2: VD [n = 13]). All patients underwent concurrent functional MRI/urodynamics testing. RESULTS: Best‐performing ML algorithms, with highest area under the curve (AUC), were partial least squares (PLS, AUC = 0.86) using FC alone and random forest (RF) when using SC alone (AUC = 0.93) and combined (AUC = 0.96) as inputs. Our results show 10 predictors with the highest AUC values were associated with FC, indicating that although white matter was affected, new connections may have formed to preserve voiding initiation. CONCLUSIONS: MS patients with and without VD exhibit distinct brain connectivity patterns when performing a voiding task. Our results demonstrate FC (grey matter) is of higher importance than SC (white matter) for this classification. Knowledge of these centres may help us further phenotype patients to appropriate centrally focused treatments in the future. John Wiley and Sons Inc. 2023-01-28 /pmc/articles/PMC10071087/ /pubmed/37025479 http://dx.doi.org/10.1002/bco2.217 Text en © 2023 The Authors. BJUI Compass published by John Wiley & Sons Ltd on behalf of BJU International Company. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Articles
Tran, Khue
Salazar, Betsy H.
Boone, Timothy B.
Khavari, Rose
Karmonik, Christof
Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor?
title Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor?
title_full Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor?
title_fullStr Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor?
title_full_unstemmed Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor?
title_short Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor?
title_sort classification of multiple sclerosis women with voiding dysfunction using machine learning: is functional connectivity or structural connectivity a better predictor?
topic Original Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10071087/
https://www.ncbi.nlm.nih.gov/pubmed/37025479
http://dx.doi.org/10.1002/bco2.217
work_keys_str_mv AT trankhue classificationofmultiplesclerosiswomenwithvoidingdysfunctionusingmachinelearningisfunctionalconnectivityorstructuralconnectivityabetterpredictor
AT salazarbetsyh classificationofmultiplesclerosiswomenwithvoidingdysfunctionusingmachinelearningisfunctionalconnectivityorstructuralconnectivityabetterpredictor
AT boonetimothyb classificationofmultiplesclerosiswomenwithvoidingdysfunctionusingmachinelearningisfunctionalconnectivityorstructuralconnectivityabetterpredictor
AT khavarirose classificationofmultiplesclerosiswomenwithvoidingdysfunctionusingmachinelearningisfunctionalconnectivityorstructuralconnectivityabetterpredictor
AT karmonikchristof classificationofmultiplesclerosiswomenwithvoidingdysfunctionusingmachinelearningisfunctionalconnectivityorstructuralconnectivityabetterpredictor