Polyembolokoilamania in Child Sexual Abuse: Physical Examination Findings After Abusive Foreign Body Insertion and Literature Summary.

OBJECTIVE: To characterize the physical examination findings in children and adolescents who disclosed insertion of an object into their bodies as part of their sexual abuse history and to identify how this population compares to similar cases described in the published literature. METHODS: This is a 15-year retrospective review of children younger than 18 years seen at a large urban children's assessment center. In addition, we reviewed and summarized the last two decades of literature characterizing pediatric anogenital foreign bodies to better understand previously described findings in similar populations. RESULTS: Sixty-eight children whose abuse histories included anal or genital insertion of a foreign body still presented with normal examination findings in the vast majority (89.7%) of cases, despite the diversity of items described. The literature on anogenital foreign bodies was sparse, offered a variety of approaches to the overall evaluation of such cases, and demonstrated inconsistent consideration of child sexual abuse in response to the diagnosis. CONCLUSIONS: This article further supports the literature reflecting the overall rarity of abnormal anogenital findings in the clinical assessment for sexual abuse.

3 Cases of Inflicted Skull Crush Injuries in Infants.

ABSTRACT: We describe 3 infants with skull fractures that involved more than 1 skull bone. On further evaluation, 2 of the 3 infants had additional fractures at other sites of the body and the third infant had concerning bruising of the face. Although an accidental mechanism of injury was initially given as the history in each case, law enforcement investigations led all 3 fathers to confess to crushing their infants' skulls out of frustration. These crushes were caused by their arms or hands. Bilateral skull fractures or those involving more than 1 skull bone can be seen in falls as well as in crush injuries. A crush-like pattern of injury, in the absence of a clear and plausible accidental mechanism, should raise concerns for possible physical abuse especially in nonambulatory infants.

A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records.

Child physical abuse is a leading cause of traumatic injury and death in children. In 2017, child abuse was responsible for 1688 fatalities in the United States, of 3.5 million children referred to Child Protection Services and 674,000 substantiated victims. While large referral hospitals maintain teams trained in Child Abuse Pediatrics, smaller community hospitals often do not have such dedicated resources to evaluate patients for potential abuse. Moreover, identification of abuse has a low margin of error, as false positive identifications lead to unwarranted separations, while false negatives allow dangerous situations to continue. This context makes the consistent detection of and response to abuse difficult, particularly given subtle signs in young, non-verbal patients. Here, we describe the development of artificial intelligence algorithms that use unstructured free-text in the electronic medical record-including notes from physicians, nurses, and social workers-to identify children who are suspected victims of physical abuse. Importantly, only the notes from time of first encounter (e.g.: birth, routine visit, sickness) to the last record before child protection team involvement were used. This allowed us to develop an algorithm using only information available prior to referral to the specialized child protection team. The study was performed in a multi-center referral pediatric hospital on patients screened for abuse within five different locations between 2015 and 2019. Of 1123 patients, 867 records were available after data cleaning and processing, and 55% were abuse-positive as determined by a multi-disciplinary team of clinical professionals. These electronic medical records were encoded with three natural language processing (NLP) algorithms-Bag of Words (BOW), Word Embeddings (WE), and Rules-Based (RB)-and used to train multiple neural network architectures. The BOW and WE encodings utilize the full free-text, while RB selects crucial phrases as identified by physicians. The best architecture was selected by average classification accuracy for the best performing model from each train-test split of a cross-validation experiment. Natural language processing coupled with neural networks detected cases of likely child abuse using only information available to clinicians prior to child protection team referral with average accuracy of 0.90±0.02 and average area under the receiver operator characteristic curve (ROC-AUC) 0.93±0.02 for the best performing Bag of Words models. The best performing rules-based models achieved average accuracy of 0.77±0.04 and average ROC-AUC 0.81±0.05, while a Word Embeddings strategy was severely limited by lack of representative embeddings. Importantly, the best performing model had a false positive rate of 8%, as compared to rates of 20% or higher in previously reported studies. This artificial intelligence approach can help screen patients for whom an abuse concern exists and streamline the identification of patients who may benefit from referral to a child protection team. Furthermore, this approach could be applied to develop computer-aided-diagnosis platforms for the challenging and often intractable problem of reliably identifying pediatric patients suffering from physical abuse.

Do pediatric chief residents recognize details of prepubertal male genital anatomy.

This study evaluates how well pediatric chief residents can label anatomic structures, recognize circumcision, and discern abnormal anatomy on three photographs of male pre-pubertal genitalia. Additionally, this study explored aspects of pediatric training in sexual abuse and clinical practice issues regarding routine genital examination of a male patient. We asked respondents to identify anatomic structures, recognize circumcision, and assign a Tanner stage to pre-pubertal male genitalia and to recognize an abnormal finding. 92.7% of chief residents were able to correctly identify basic structures on the photo of a circumcised pre-pubertal male. Only 22% correctly recognized the abnormal example as hypospadias. Basic recognition of anatomic structures and circumcision did not achieve 100% accuracy, while an abnormal condition was missed by the majority of respondents. These data suggest a need to address education about the male genital exam in greater detail during pediatric residency training.