Conversion d'un poids statistique en sensibilité / spécificité (Gestion:Tâches/Liste/258/13/1)
Type | Tâche |
---|---|
Création | Antoine Mercier-Linteau |
Responsable(s) | Michaël St-Gelais, Jean-Philippe Pialasse |
État | En cours |
Date de création | 2019/12/09 |
Échéance | aucune |
Priorité | Urgente |
Projet(s) |
Les auteurs de la base de données de connaissances médicales Doknosis ont utilisé un poids d'association déduit selon leurs recherches sur des textes:
For a given ICD-10 diagnosis or common medication (A) we described the associated observations (B) as weighted numerical probabilities based upon the frequency of association of B given A.
P(A avec B) = [ P(B avec A)P(A) ] / P(B)
For instance, if a given disease always presents an associated observation we would weight that with 1.0, if it was associated 10% of the time we would use 0.1, and if that association never occurred, it was encoded with 0. Negating findings, e.g. gender and specific conditions or rash and Malaria were encoded as − 1. When only written descriptions were available we translated them to a numerical value as per Additional file 1. Initial mappings will be refined as public curation is enabled (see Additional file 2). Prior probabilities P(A) were encoded for infectious syndromes and preliminarily assigned binary values based on presence or absence in broad geographic areas. Other binary relations such as sex, required conditions or related diseases were encoded similarly. We encoded age distributions by broad groups; infant (0–6 months), child (6 months-12 years), adult (13–60 years), elderly (> 60).
Il s'agit maintenant de voir comment ces valeurs pourraient être converties en spécificité/sensibilité, likelyhood ratio, hazard ration, valeur prédictive positive, etc. Il est possible qu'elles ne soient pas convertibles et doivent être utilisées telles quelles.
Tableau d'association
Code | Descriptors | Percentage |
---|---|---|
1.0 | Always, all | 100% |
0.75 | Commonly, often | 75% |
0.5 | Probable | 50% |
0.25 | Infrequently, uncommonly | 25% |
0.1 | Rarely | 10% |
0.0 | Never | 0% |
Discussion
Références
- ↑ (en) Lars Müller, Rashmi Gangadharaiah, Simone C. Klein et James Perry, « An open access medical knowledge base for community driven diagnostic decision support system development », BMC Medical Informatics and Decision Making, vol. 19, no 1, (ISSN 1472-6947, PMID 31029130, Central PMCID PMC6486985, DOI 10.1186/s12911-019-0804-1, lire en ligne)
- ↑ Appendice A de l'étude