Predicting outcomes of expectant and medical management in early pregnancy miscarriage using machine learning to develop and validate multivariable clinical prediction models.

Objective: To determine whether readily available patient, ultrasound and treatment outcome data can be used to develop, validate and externally test two machine learning (ML) models for predicting the success of expectant and medical management of miscarriage respectively.

Methods: A retrospective, multi-site study of patients opting for expectant or medical management of miscarriage was undertaken. A total of 1075 patients across two hospital early pregnancy units were eligible for inclusion.

Perception Versus Comprehension of Bound Morphemes in Children Who Are Deaf and Hard of Hearing: The Pivotal Role of Form-Meaning Mapping.

Purpose: Bound morphemes are challenging for children who are deaf and hard of hearing (DHH) to acquire and to use successfully. The challenge arises in part from limited access to spoken word forms as a result of reduced audibility during perception, but successful comprehension requires access to the morphological forms and the mapping between these forms and their meanings. This study investigated the relationship between perception and comprehension of bound morphemes in order to assess the impact of form-meaning mapping on performance.

Clinical utility of ultrasonography in pediatric and adolescent gynecology: retrospective review of 1313 ultrasound examinations.

Objectives: Ultrasound is the first-line imaging modality of the pelvis in the pediatric and adolescent gynecology (PAG) population. Ultrasound findings in pre- and postpubertal PAG patients differ from those in adults. Diagnostic models for adnexal pathology have not been validated in this cohort.