Impact of automatic tools for detecting new lesions on therapeutic strategies offered to patients with MS by neurologists.

Computer-aided diagnosis MRI Multiple sclerosis Therapeutic decision

Journal

Multiple sclerosis and related disorders
ISSN: 2211-0356
Titre abrégé: Mult Scler Relat Disord
Pays: Netherlands
ID NLM: 101580247

Informations de publication

Date de publication:
20 Oct 2023
Historique:
received: 19 07 2023
revised: 16 09 2023
accepted: 08 10 2023
medline: 23 10 2023
pubmed: 23 10 2023
entrez: 22 10 2023
Statut: aheadofprint

Résumé

Automatic tools for detecting new lesions in patients with MS between two MRI scans are now available to clinicians. They have been assessed from the radiologist's point of view, but their impact on the therapeutic strategies that neurologists offer their patients has not yet been documented. To compare neurologist's decisions according to whether a lesion detection support system had been used and describe variability between neurologists on decision-making for the same clinical cases. We submitted 28 clinical cases associated with pairs of MRI images and radiological reports (produced by the same radiologist without vs. with the help of a system to detect new lesions) to 10 neurologists who regularly follow patients with MS. They examined each clinical case twice (without vs. with support system) in two sessions several weeks apart, and their patient management decisions were recorded. There was considerable variability between neurologists on decision-making (both with and without support system). When the support system had been used, neurologists more often made changes to patient management (75 % vs. 68 % of cases, p = 0.01) and spent significantly less time analyzing the clinical cases (249 s vs. 216 s, p == 3.10-4). The use of a lesion detection support system has an impact not only on radiologists' reports, but also on neurologists' subsequent decision-making. This observation constitutes another strong argument for promoting the wider use of such systems in clinical routine. However, despite their use, there is still considerable variability in decision-making across neurologists, which should encourage us to refine the guidelines.

Sections du résumé

BACKGROUND BACKGROUND
Automatic tools for detecting new lesions in patients with MS between two MRI scans are now available to clinicians. They have been assessed from the radiologist's point of view, but their impact on the therapeutic strategies that neurologists offer their patients has not yet been documented.
OBJECTIVES OBJECTIVE
To compare neurologist's decisions according to whether a lesion detection support system had been used and describe variability between neurologists on decision-making for the same clinical cases.
METHODS METHODS
We submitted 28 clinical cases associated with pairs of MRI images and radiological reports (produced by the same radiologist without vs. with the help of a system to detect new lesions) to 10 neurologists who regularly follow patients with MS. They examined each clinical case twice (without vs. with support system) in two sessions several weeks apart, and their patient management decisions were recorded.
RESULTS RESULTS
There was considerable variability between neurologists on decision-making (both with and without support system). When the support system had been used, neurologists more often made changes to patient management (75 % vs. 68 % of cases, p = 0.01) and spent significantly less time analyzing the clinical cases (249 s vs. 216 s, p == 3.10-4).
CONCLUSION CONCLUSIONS
The use of a lesion detection support system has an impact not only on radiologists' reports, but also on neurologists' subsequent decision-making. This observation constitutes another strong argument for promoting the wider use of such systems in clinical routine. However, despite their use, there is still considerable variability in decision-making across neurologists, which should encourage us to refine the guidelines.

Identifiants

pubmed: 37866026
pii: S2211-0348(23)00565-5
doi: 10.1016/j.msard.2023.105064
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

105064

Informations de copyright

Copyright © 2023. Published by Elsevier B.V.

Déclaration de conflit d'intérêts

Declaration of Competing Interest On behalf of all authors, the corresponding author states that there is no conflict of interest.

Auteurs

Blandine Merkler (B)

Neurology Department, Brest University Hospital, Brest, France.

Arthur Masson (A)

EMPENN research team, IRISA, CNRS‑INSERM‑INRIA, Rennes University, France.

Jean Christophe Ferré (JC)

EMPENN research team, IRISA, CNRS‑INSERM‑INRIA, Rennes University, France; Radiology Department, Rennes University Hospital, Rennes, France.

Emma Bajeux (E)

Public Health and Epidemiology Department, Rennes University Hospital, Rennes, France.

Gilles Edan (G)

EMPENN research team, IRISA, CNRS‑INSERM‑INRIA, Rennes University, France; Neurology Department, Rennes University Hospital, Rennes, France.

Laure Michel (L)

Neurology Department, Rennes University Hospital, Rennes, France.

Emmanuelle Le Page (EL)

Neurology Department, Rennes University Hospital, Rennes, France.

Marion Leclercq (M)

Neurology Department, Rennes University Hospital, Rennes, France.

Benoit Pegat (B)

Neurology Department, Vannes Hospital, Vannes, France.

Simon Lamy (S)

Neurology Department, Rennes University Hospital, Rennes, France.

Goulven Le Corre (GL)

Neurology Department, Lorient Hospital, Lorient, France.

Kevin Ahrweiler (K)

Neurology Department, Saint Malo Hospital, Saint Malo, France.

Fabien Zagnoli (F)

Private neurology office, 22 Rue d'Aiguillon Brest, France.

Denis Maréchal (D)

Neurology Department, Brest University Hospital, Brest, France.

Benoît Combès (B)

EMPENN research team, IRISA, CNRS‑INSERM‑INRIA, Rennes University, France.

Anne Kerbrat (A)

EMPENN research team, IRISA, CNRS‑INSERM‑INRIA, Rennes University, France; Neurology Department, Rennes University Hospital, Rennes, France. Electronic address: anne.kerbrat@chu-rennes.fr.

Classifications MeSH