MétaCan
Menu
Retour à la cohorte
Enregistrement W3015945108 · doi:10.2196/17592

A Novel, Integrative Approach for Evaluating Progression in Multiple Sclerosis: Development of a Scoring Algorithm

2020· article· en· W3015945108 sur OpenAlexvenueno aff
Chloe Tolley, Daniela Piani-Meier, Sarah Bentley, Bryan Bennett, Eddie Jones, James Pike, Frank Dahlke, Davorka Tomic, Tjalf Ziemssen

Notice bibliographique

RevueJMIR Medical Informatics · 2020
Typearticle
Langueen
DomaineMedicine
ThématiqueMultiple Sclerosis Research Studies
Établissements canadiensnon disponible
Organismes subventionnairesNovartis Pharma
Mots-clésWeightingConcordanceRanking (information retrieval)Logistic regressionObservational studyMedicineMultiple sclerosisMachine learningAlgorithmPhysical therapyComputer scienceInternal medicinePsychiatry

Résumé

récupéré en direct d'OpenAlex

BACKGROUND: There is an unmet need for a tool that helps to evaluate patients who are at risk of progressing from relapsing-remitting multiple sclerosis to secondary progressive multiple sclerosis (SPMS). A new tool supporting the evaluation of early signs suggestive of progression in multiple sclerosis (MS) has been developed. In the initial stage, concepts relevant to progression were identified using a mixed method approach involving regression on data from a real-world observational study and qualitative research with patients and physicians. The tool was drafted in a questionnaire format to assess these variables. OBJECTIVE: This study aimed to develop the scoring algorithm for the tool, using both quantitative and qualitative research methods. METHODS: The draft scoring algorithm was developed using two approaches: quantitative analysis of real-world data and qualitative analysis based on physician interviews and ranking and weighting exercises. Variables that were included in the draft tool and regarded as most clinically relevant were selected for inclusion in a multiple logistic regression. The analyses were run using physician-reported data and patient-reported data. Subsequently, a ranking and weighting exercise was conducted with 8 experienced neurologists as part of semistructured interviews. Physicians were presented with the variables included in the draft tool and were asked to rank them in order of strength of contribution to progression and assign a weight by providing a percentage of the overall contribution. Physicians were also asked to explain their ranking and weighting choices. Concordance between physicians was explored. RESULTS: Multiple logistic regression identified age, MS disease activity, and Expanded Disability Status Scale score as the most significant physician-reported predictors of progression to SPMS. Patient age, mobility, and self-care were identified as the strongest patient-reported predictors of progression to SPMS. In physician interviews, the variables ranked and weighted as most important were stability or worsening of symptoms, intermittent or persistent symptoms, and presence of ambulatory and cognitive symptoms. Across all physicians, the level of concordance was 0.278 (P<.001), indicating a low to moderate, but statistically significant, level of agreement. Variables were categorized as high (n=8), moderate (n=8), or low (n=10) importance based on the findings from the different approaches described above. Accordingly, the respective questions in the tool were assigned a weight of "three," "two," or "one" to inform the draft scoring algorithm. CONCLUSIONS: This study further confirms the need for a tool to provide a consistent, comprehensive approach across physicians to support the early evaluation of signs indicative of progression to SPMS. The novel and comprehensive approach to develop the draft scoring algorithm triangulates data obtained from ranking and weighting exercises, qualitative interviews, and a real-world observational study. Variables that go beyond the clinically most obvious impairment in lower limbs have been identified as relevant subtle/sensitive signs suggestive of progressive disease.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.

Comment cette classification a été obtenuedéplier

Prédiction distillée sur la base complète

Imitation des enseignants

Ni prévalence calibrée, ni vérité terrain. Validation humaine à venir. Apprise à partir de 10 348 étiquettes directes de Codex et de 10 348 étiquettes directes de Gemma. Le mode candidate est l'union des têtes enseignantes seuillées; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont ni des étiquettes humaines ni des étiquettes directes de modèles de pointe.

score de la tête « metaresearch » (Codex)0,001
score de la tête « metaresearch » (Gemma)0,005
Version: codex-gemma-dda1882f352aStatut de validation: machine_predicted_unvalidated
Catégories candidatesaucune
Catégories consensuellesaucune
DomaineSignal candidat: aucune · Signal consensuel: aucune
Devis d'étudeSignal candidat: Simulation ou modélisation · Signal consensuel: aucune
GenreSignal candidat: Méthodes · Signal consensuel: Méthodes
Score de désaccord entre enseignants0,953
Score d'incertitude au seuil0,589

Scores Codex et Gemma par catégorie

CatégorieCodexGemma
Métarecherche0,0010,005
Méta-épidémiologie (sens strict)0,0000,000
Méta-épidémiologie (sens large)0,0010,000
Bibliométrie0,0000,000
Études des sciences et des technologies0,0000,000
Communication savante0,0000,000
Science ouverte0,0000,000
Intégrité de la recherche0,0000,000
Charge utile insuffisante (le modèle a refusé de juger)0,0000,000

Scores machine (provisoires)

Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.

Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.

Tête enseignante Opus0,231
Tête enseignante GPT0,415
Écart entre enseignants0,185 · la distance entre les deux têtes enseignantes sur ce seul travail
Statut de validationscore_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découle

Classification

machine, non validée

Prédiction automatique; un appel candidat d’une seule tête enseignante, pas un consensus.

Les modèles n’ont appliqué aucune catégorie : rien dans la taxonomie ne correspondait à ce travail.
Devis d'étudeSimulation ou modélisation
Domainenon disponible
GenreMéthodes

Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».

En bref

Citations18
Publié2020
Routes d'admission1
Résumé présentoui

Explorer davantage

Même revueJMIR Medical InformaticsMême sujetMultiple Sclerosis Research StudiesTravaux en français237 207