PREDICTING THE EFFECTIVENESS OF MYOPIA CONTROL WHEN USING ORTHOKERATOLOGICAL LENSES BASED ON INDIVIDUAL EYE PARAMETERS
Notice bibliographique
Résumé
Introduction. The prevalence and progressive course of myopia is one of the most important medical and social problems worldwide. In recent years, in our country and abroad there is a tendency to increase the incidence of myopia, becoming in some countries an epidemic. In recent years, the most common method of effective control of myopia is the method of refractive therapy with orthokeratological lenses. Objective: To develop criteria for predicting the effectiveness of myopia control using orthokeratological lenses based on individual eye parameters. Object and methods of research. A total of 60 children (117 eyes) were included in the clinical study, who were selected by OKL of combined design, SkyOptix, licensed by KATT Design Group (Canada). The average age was 11 [10; 13], from 7 to 14 years, of which 37 were females (61.7%), 23 males (38.3%). Ophthalmological examination consisted of visometry without correction and with optical correction, autorefractometry on the narrow pupil and in the state of drug cycloplegia, biomicroscopy, biometry, ophthalmoscopy of the central and peripheral fundus, keratotopography of the horns, pupilometry. The results of the research: Among the studied people, the average refractive index at the beginning of the study was -2.25 [-3; -1.5] diopters. The initial diameter of the pupils was determined from 2.78 to 6.30 mm according to the pupilometry performed on the topograph. The average values of eccentricity (Ex) studied in the flat meridian averaged 0.51 [0.47; 0.58], in the steep - 0.53 [0.43; 0.59] at the beginning of the study. In our study, the keratometry of the cornea averaged 43.5 at the beginning of the study [42.7; 44.4]. As a result of probability analysis (increase in APS for two years), the method of construction of logistic regression models was used. We selected five factor features (X): Initial refraction, Pupil diameter (X2), Keratometry (X3), Peripheral corneal force on the reverse zone ring (X4 and X5), Corneal diameter, and Axial length of the eye (APS) at the time of treatment (initial). The equation of logistic regression of the model for predicting the probability of progression of myopia on the background of the use of OKL had the form: The classification ability of the model was determined according to the training sample and amounted to 79.5%. The probability of a true positive result (increase in APS less than 0.3) when using this model was 91.9%, and the probability of a true negative result - 38.5%. Evaluation of the quality of the model using ROC-analysis showed the following: the area under the ROC-curve (AUC) was equal to 0.86 (p <0.001), which characterizes the good quality of the classification of traits. The sensitivity of the model was 82.6%, specificity - 73.1%. As part of the research and mathematical calculations, an interactive WEB application was also developed, which can be accessed from various types of devices connected to the World Wide Web. Modern solutions and approaches used in IT (Information Technology) were used for development. Conclusions. It is determined that when examining a child with progressive myopia, it is important to pay attention to the diameter of the pupil in photographic conditions, because it can be a predictor of progression and influence the choice of correction individually. The smaller the value of keratometry before the appointment of refractive therapy, the greater the value of the size of the APS, so this factor can be indicated as prognostic. The differential topographic force of the cornea along the peripheral ring corresponding to the reverse zone of the lens is a prognostic practical factor. Taking into account the primary parameters of the eye allows you to customize the approach to each child with myopia, improving the individual design of orthokeratological lenses.
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 machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,001 | 0,006 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,000 |
| Méta-épidémiologie (sens large) | 0,000 | 0,000 |
| Bibliométrie | 0,001 | 0,000 |
| Études des sciences et des technologies | 0,000 | 0,000 |
| Communication savante | 0,001 | 0,000 |
| Science ouverte | 0,000 | 0,000 |
| Intégrité de la recherche | 0,001 | 0,000 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,002 | 0,000 |
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.
score_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 découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».