Harnessing the Power of Machine Learning and Electronic Health Records to Support Child Abuse and Neglect Identification in Emergency Department Settings.

Emergency departments (EDs) are pivotal in detecting child abuse and neglect, but this task is often complex. Our study developed a machine learning model using structured and unstructured electronic health record (EHR) data to predict when children in EDs might need intervention from child protective services. We used a case-control study design, analyzing data from a pediatric ED. Clinical notes were processed with natural language processing (NLP) techniques to identify suspected cases and matched in a 1:9 ratio to ensure dataset balance. The features from these notes were combined with structured EHR data to construct a model using the XGBoost algorithm. The model achieved a precision of 0.95, recall of 0.88, and F1-score of 0.92, with improvements seen from integrating NLP-derived data. Key indicators for abuse included hospital admissions, extended ED stays, and specific clinical orders. The model's accuracy and the utility of NLP suggest the potential for EDs to better identify at-risk children. Future work should validate the model further and explore additional features while considering ethical implications to aid healthcare providers in safeguarding children.

Evidence From the USPSTF and New Approaches to Evaluate Interventions to Prevent Child Maltreatment.

Importance: The United States Preventive Services Task Force (USPSTF) has considered the topic of prevention of child maltreatment multiple times over its nearly 40-year history, each time reaching the conclusion that the evidence is insufficient to recommend for or against interventions aimed at preventing this important health problem with significant negative sequelae before it occurs. In the most recent evidence review, which was conducted from August 2021 to November 2023 and published in March 2024, the USPSTF considered contextual questions on the evidence for bias in reporting and diagnosis of maltreatment in addition to key questions regarding effectiveness of interventions to prevent child maltreatment. Observations: A comprehensive literature review found evidence of inaccuracies in risk assessment and racial and ethnic bias in the reporting of child maltreatment and in the evaluation of injuries concerning for maltreatment, such as skull fractures. When children are incorrectly identified as being maltreated, harms, such as unnecessary family separation, may occur. Conversely, when children who are being maltreated are missed, harms, such as ongoing injury to the child, continue. Interventions focusing primarily on preventing child maltreatment did not demonstrate consistent benefit or information was insufficient. Additionally, the interventions may expose children to the risk of harm as a result of these inaccuracies and biases in reporting and evaluation. These inaccuracies and biases also complicate assessment of the evidence for making clinical prevention guidelines. Conclusions and Relevance: There are several potential strategies for consideration in future efforts to evaluate interventions aimed at the prevention of child maltreatment while minimizing the risk of exposing children to known biases in reporting and diagnosis. Promising strategies to explore might include a broader array of outcome measures for addressing child well-being, using population-level metrics for child maltreatment, and assessments of policy-level interventions aimed at improving child and family well-being. These future considerations for research in addressing child maltreatment complement the USPSTF's research considerations on this topic. Both can serve as guides to researchers seeking to study the ways in which we can help all children thrive.

Identifying inflicted injuries in infants and young children.

Child physical abuse is a common cause of pediatric morbidity and mortality. Up to half of all children presenting with abusive injuries have a history of a prior suspicious injury, suggesting a pattern of repeated physical abuse. Medical providers are responsible for identifying children with suspicious injuries, completing mandated reporting to child protective services for investigation, and screening for occult injuries and underlying medical conditions that can predispose to injuries. Early identification of inflicted injuries appropriate evaluations may serve as an opportunity for life-saving intervention and prevent further escalation of abuse. However, identification of abuse can be challenging. This article will review both physical exam findings and injuries that suggest abuse as well as the evaluation and management of physical abuse.

Acute presentation of abusive head trauma.

Child abuse is a major cause of morbidity and mortality in the United States. The leading cause of child physical abuse related deaths is abusive head trauma, formerly known as shaken baby syndrome, making the rapid identification and assessment of these children critical. The clinical presentation of cases of abusive head trauma ranges from neurological complaints, such as seizures, to vague or subtle symptoms, such as vomiting. This results in frequent missed diagnoses of abusive head trauma. The identification of abusive head trauma relies on a thorough medical history and physical examination, followed by lab evaluation and imaging. The goal of the evaluation is to discover further injury and identify possible underlying non-traumatic etiologies of the patient's symptoms. In this article we present a framework for the assessment of abusive head trauma and provide information on common presentations and injuries, as well as differential diagnoses. A strong foundational knowledge of abusive head trauma will lead to greater recognition and improved safety planning for victims of this unfortunate diagnosis.

Neuroimaging considerations in abusive head trauma.

This focused review on abusive head trauma describes the injuries to the head, brain and/or spine of an infant or young child from inflicted trauma and their neuroimaging correlates. Accurate recognition and diagnosis of abusive head trauma is paramount to prevent repeated injury, provide timely treatment, and ensure that accidental or underlying medical contributors have been considered. In this article, we aim to discuss the various findings on neuroimaging that have been associated with AHT, compared to those that are more consistent with accidental injuries or with underlying medical causes that may also be on the differential.

Ophthalmologic findings in abusive head trauma.

A leading cause of death and disability in infancy is abusive head trauma (AHT) and there are common clinical signs that help to establish this diagnosis. Children diagnosed with AHT can have many ophthalmologic findings, including retinal hemorrhages, retinoschisis, subconjunctival hemorrhages, corneal injury, and globe rupture. If any such injuries are suspected, an ophthalmologic consultation, with indirect ophthalmoscopy, should be completed. In addition to a complete physical exam, a thorough history imaging, and lab work, should be obtained to investigate the etiology of ophthalmic pathology including accidental and systemic causes. In general, studies show that retinal hemorrhages that are multilayered, too numerous to count, and located from the posterior pole to the ora serrata are highly suspicious for abusive head trauma.

Evaluation of a Child Abuse Screen Performed by Nurses Among Young Children with Fractures Seen in a Pediatric Emergency Department.

AIMS: To assess institutional compliance with, and test characteristics of, a child abuse screen performed by emergency department (ED) nurses for children <5 years old who were diagnosed with fractures. METHODS: A secondary analysis of a retrospective observational study of children 0-5 years old with fractures seen at a pediatric ED between January 2018 and April 2023 was performed. We analyzed demographics, ED visit data, and results of the nurse-completed abuse screen. Screen results were compared to ED clinician concern for abuse to calculate test characteristics. RESULTS: The mean age of the 2,705 children identified was 38.4 months (SD 19.8). Out of the total patient cohort, 2,449 (90.5%) had a nurse-completed screen. Among these, 65 patients (2.4%) screened positive for possible abuse. We found no statistically significant difference in screen completion by age group, race, ethnicity, language, or insurance type. Of 312 (11.5%) encounters with clinician concern for abuse, 17.6% screened positive, 76.0% screened negative, and 6.4% had an incomplete screen. The sensitivity and specificity among screened children aged 0-5 were 19.2% [95% CI 14.7-23.8%] and 99.5% [95% CI 99.3-99.8%]. The PPV and NPV were 84.6% [95% CI 75.8-93.4%] and 90.3% [95% CI 89.1-91.5%]. Comparatively, among children <12 months, the sensitivity was 24.4% [95% CI 18.0-30.8%], specificity was 98.1% [95% CI 95.4-100%], PPV was 95.5% [95% CI 89.3-100%], and NPV was 43.7% [95% CI 37.3-50.1%]. CONCLUSIONS: Although there was high compliance with this nurse-completed abuse screen, it is an inadequate sole modality for screening young children with fractures, with a low probability of a positive screen given clinician concern for potential abuse for the entire cohort and among high-risk infants.

Medical assessments for abuse and neglect in contacts of maltreated children.

AIM: Identifying abuse or neglect in one child (index) implicates risk to other children residing in the same home (contacts). While child protection investigators may interview and visually examine contacts, there is lack of consensus regarding when contacts should have a medical assessment. Our goal was to describe the prevalence, characteristics and predictors of abuse and neglect among contacts medically assessed by a child maltreatment evaluation centre over a 5-year period. METHODS: Records of 381 maltreated index children and their 588 contacts were reviewed. Abuse or neglect was diagnosed in 15% of contact children. RESULTS: When index children had more than one type of maltreatment or more than three risk factors, their contacts were more likely to be neglected or abused, respectively. Failure to thrive, patterned injuries, and unmet medical needs were the most common findings among maltreated contacts, and most were diagnosed with injuries or conditions that would not be evident to a child protection investigator. CONCLUSIONS: Clinicians should consider evaluating contacts of maltreated children who have multiple risk factors or maltreatment types. These evaluations should include a careful assessment for injuries, growth and unmet medical needs.

Are you a cop?: Identifying suspicion in online chat operations with online groomers.

BACKGROUND: The increase in online enticement has led to law enforcement agencies engaging in more proactive policing through undercover chat sting operations. OBJECTIVE: We aimed to identify the topics and communication strategies triggering suspicion in chats between law enforcement officers and offenders and why those topics do not result in suspicion in victim-offender conversations. METHODS: We conducted a thematic analysis identifying: (1) how LEOs trigger suspicion, (2) how offenders communicate suspicion, (3) how LEOs attempt recovery from suspicion, and (4) how these triggers were present but did not trigger suspicion in victim-offender chats. We examined 20 LEO-offender chats and 20 victim-offender chats from US ICAC task forces. RESULTS: We identified four themes that triggered suspicion: risk assessment by the LEO's persona, LEO avoidance measures, details related to the offense and evidence, and proof of identity of chat participants. Offender responses to triggers revealed three themes: discomfort navigating boundaries and uncertainty, risk identification, and risk mitigation. Themes for the LEO's responses to suspicion included: risk assessment for chatters, issues with technology, appeasement, and negative emotional reactions. Finally, juxtaposing triggers onto minor-offender chats yielded four themes: explicit boundary setting, victim risk assessment, deep relationship forming and disclosures, and technology issues. CONCLUSION: This study has implications for law enforcement agencies seeking to reduce suspicion and risk assessment by offenders during internet sting operations.

Atypical localized Mongolian spots in dark pigmented skin - a challenge for forensic medical examination.

The assessment of skin changes in the context of possible child abuse is an important task in forensic medicine. This requires knowledge of pigmentation variants and pigmentation disorders such as congenital dermal melanocytosis, which includes Mongolian spots. Particularly in the case of atypical localization and dark pigmented skin, the differentiation from hematomas can be challenging. A case of two Nigerian siblings with extensive and atypically localized Mongolian spots is reported. The 1.5-year-old girl showed Mongolian spots on her back and the right side of her trunk. The 8-year-old boy showed Mongolian spots only on the back of his thighs. The authors are not aware of any case in which so called Mongolian spots were present exclusively on the back of the thighs and this case is all the more noteworthy as the back of the thigh is a common localization of blunt force trauma.

Iron contact burns and the path to the diagnosis of child abuse.

Burns are a common injury in both abused and non-abused children, and the accurate diagnosis of abusive burns is important to ensure protection. In the particular case of a three year old child with a second degree burn on her face and neck caused by an alleged contact with a hot iron, the correct analysis of the injury and the dynamics of what was reported as a domestic accident allowed the recognition of a different scenario and a diagnosis of child abuse due to the pressure of the flat part of the iron on the skin, thus uniformly involving the cheek and the upper part of the neck. The involvement of parts of the body placed on different anatomical planes (thus indicating pressure and not mere contact) should be considered as a further element of differential diagnosis. This demonstrates and underlines the importance of a thorough multidisciplinary assessment for this type of injury which is described as an accidental event but rarely as an outcome of child abuse.

Detecting and preventing child maltreatment in primary care and PHNs' role-a cross-sectional study.

BACKGROUND: Child maltreatment is a global problem that puts children at risk of mental illness, substance abuse, and premature death. Interdisciplinary collaboration is important in preventing and detecting child maltreatment. In Norway, children undergo universal preventive health assessments and receive complimentary follow-up care from specialized public health nurses in child and family health clinics. These nurses conduct regular check-ups and home visits to monitor children for signs of maltreatment. OBJECTIVE: The objective of this study is to describe how public health nurses at child and family health clinics follow the National Clinical Guidelines to prevent and detect child maltreatment, with a particular focus on clinical procedures and interdisciplinary collaboration. Furthermore, we aim to determine factors that are associated with identification of child maltreatment. DESIGN: A cross-sectional online survey was conducted among public health nurses working in primary care between October 24th and December 31st, 2022. Public health nurses who worked with children aged 0-5 years and had consultations with families were eligible to participate, resulting in 554 responses. The study employed descriptive analysis, including frequency, percentage and mean, as well as a two-step logistic regression analysis. The study was approved by the relevant authority, and informed consent was obtained through questionnaire completion. RESULTS: The public health nurses in this study displayed strong adherence to the guidelines and utilized various comprehensive assessment procedures to monitor child well-being, growth, and development. However, there was limited and infrequent collaboration with other professionals, such as child protection services, general practitioners, and hospitals. Most public health nurses reported occasional suspicion of child maltreatment, with age and years of experience in child and family clinics influencing these suspicions. Older public health nurses were more likely to suspect physical violence, while those with less than two years of experience reported less experience in suspecting maltreatment. Additional education increased the probability of suspecting sexual violence. CONCLUSIONS: This study provides insights into the practices of public health nurses in Norway regarding the detection and prevention of child maltreatment in child and family clinics. While adherence to guidelines is strong, suspicion of maltreatment is relatively rare. Collaboration across agencies is crucial in addressing child maltreatment. Age and experience may influence the detection of maltreatment. Improved collaboration, targeted guidelines, and ongoing professional development are needed to enhance child protection.

Fractura craneal deprimida congénita ("fractura ping-pong") en neonatos como diagnóstico diferencial de maltrato físico / Congenital depressed skull fracture ("ping-pong" fracture) in newborn infants as a differential diagnosis of physical abuse

Las fracturas con hundimiento de cráneo sin una explicación clara sobre su origen orientan al traumatismo con un objeto romo y a la sospecha de maltrato infantil. En el caso de los bebés recién nacidos, su corta edad es un factor de vulnerabilidad y obliga a una exhaustiva evaluación. Ante la sospecha de maltrato infantil, resulta importante evaluar los diagnósticos diferenciales para realizar la intervención más adecuada posible. Es necesario evitar tanto intervenciones excesivas como omitir la intervención que sea necesaria. Las fracturas craneales deprimidas congénitas, descritas como "fracturas pingpong", son raras (0,3 a 2/10 000 partos). Pueden aparecer sin antecedentes traumáticos o en partos instrumentalizados. Se describe en este artículo el caso de un recién nacido con una fractura ping-pong como ejemplo de una fractura no intencional.

Depressed skull fractures without a clear explanation as to their origin point to trauma with a blunt object and suspected child abuse. In the case of newborn infants, their young age is a vulnerability factor and requires an exhaustive assessment. When child abuse is suspected, an assessment of the differential diagnoses is required to make the most appropriate intervention possible. Both an excessive intervention and an omission of a necessary intervention should be avoided. Congenital depressed skull fractures, described as "ping-pong fractures", are rare (0.3 to 2/10 000 births). They may appear without any trauma history or in instrumentalized childbirth. Here we describe the case of a newborn infant with a ping-pong fracture as an example of an accidental fracture.

Early identification and awareness of child abuse and neglect among physicians and teachers.

BACKGROUND: Child abuse and neglect (CAN) causes enormous suffering for those affected. OBJECTIVE: The study investigated the current state of knowledge concerning the recognition of CAN and protocols for suspected cases amongst physicians and teachers. METHODS: In a pilot study conducted in Mecklenburg-Western Pomerania from May 2020 to June 2021, we invited teachers and physicians working with children to complete an online questionnaire containing mainly multiple-choice-questions. RESULTS: In total, 45 physicians and 57 teachers responded. Altogether, 84% of physicians and 44% of teachers were aware of cases in which CAN had occurred in the context of their professional activity. Further, 31% of physicians and 23% of teachers stated that specific instructions on CAN did not exist in their professional institution or that they were not aware of them. All physicians and 98% of teachers were in favor of mandatory training on CAN for pediatric residents and trainee teachers. Although 13% of physicians and 49% of teachers considered a discussion of a suspected case of CAN to constitute a breach of confidentiality, 87% of physicians and 60% of teachers stated that they would discuss a suspected case with colleagues. CONCLUSION: Despite the fact that a large proportion of respondents had already been confronted with suspected cases of CAN, further guidelines for reporting procedures and training seem necessary. There is still uncertainty in both professions on dealing with cases of suspected CAN.

Emergency Department Triage Chief Complaints Among Children Evaluated for Physical Abuse Concerns.

OBJECTIVES: The aims of this study were to describe chief complaints provided at emergency department triage for young children ultimately given a diagnosed with injuries concerning for physical abuse and compare chief complaints by hospital child protection team assessment (abuse most likely, accident most likely, undetermined) among children younger than 2 years who were the subject of a report to child protective services. METHODS: This is a retrospective review of children evaluated by the child protection team at an urban children's hospital over a 5-year period. Children younger than 2 years who were the subject of a report to child protective services for suspected physical abuse were included. Chief complaints noted in emergency department triage notes were categorized as follows: 1, medical sign or symptom; 2, accidental trauma incident; 3, identified injury; 4, concern for abuse; or 5, multiple unrelated complaints. Child protection team assessments were categorized as follows: 1, abuse most likely; 2, accident most likely; or 3, undetermined. We used descriptive statistics and tests of association (χ 2 , Fisher exact, Kruskal-Wallis). RESULTS: Median age of the 422 children included was 4.9 months. Child protection team assessment was abuse most likely in 44%, accident most likely in 23%, and undetermined in 34%. Chief complaints in the overall sample were 39% medical, 29% trauma incident, 16% injury, 10% abuse concern, and 6% multiple unrelated. When the abuse most likely and accident most likely groups were compared, medical chief complaints were more common in the former (47% vs 19%, P < 0.001), whereas trauma incident chief complaints were more common in the latter (19% vs 64%, P < 0.001). Most common medical complaints in the abuse most likely group were altered mental status, abnormal limb use, swelling, pain, apnea, and vomiting. CONCLUSION: Many children found to have injuries concerning for abuse (47%) present without mention of trauma, injury, or abuse concern as part of the chief complaint. Our findings suggest important topics to include in training physicians about recognition of abuse.

Urinalysis in Suspected Child Abuse Evaluation in the Emergency Department.

BACKGROUND: Intra-abdominal injury (IAI) is the second leading cause of mortality in abused children. It is challenging to identify in young patients due to their limited verbal skills, delayed symptoms, less muscular abdominal wall, and limited bruising. METHODS: We conducted a retrospective cohort study of children aged 0 to 12 months who were evaluated in the emergency department for suspected child abuse with a skeletal survey and urinalysis between January 1, 2015, and December 31, 2017. Our primary objective was to identify the proportion of IAI cases identified by urinalysis alone (>10 RBC/HPF) and not by examination findings or other laboratory results. A secondary objective was to quantify potential delay in disposition while waiting for urinalysis results, calculated as the length of time between receiving skeletal survey and laboratory results and receiving urinalysis results. RESULTS: Six hundred thirteen subjects met our inclusion criteria; two subjects had hematuria, one of whom had a urinary tract infection. The other was determined to have blood from a catheterized urine specimen. One subject was found to have an IAI. We further found that urinalysis was delayed for 78% of subjects and took a median of 93 [interquartile range, 46-153] minutes longer than imaging and/or laboratories. CONCLUSIONS: No subjects were diagnosed with abdominal trauma based on urinalysis during evaluation in the emergency department who would not have been identified by other standard testing. In addition, patients' disposition was delayed while waiting for urinalysis.

Effect of Routine Child Physical Abuse Screening Tool on Emergency Department Efficiency.

OBJECTIVES: Physical abuse is a significant cause of morbidity and mortality for children. Routine screening by emergency nurses has been proposed to improve recognition, but the effect on emergency department (ED) workflow has not yet been assessed. We sought to evaluate the feasibility of routine screening and its effect on length of stay in a network of general EDs. METHODS: A 2-question child physical abuse screening tool was deployed for children <6 years old who presented for care in a system of 27 general EDs. Data were compared for the 6 months before and after screening was deployed (4/1/2019-10/2/2019 vs 10/3/2019-3/31/2020). The main outcome was ED length of stay in minutes. RESULTS: There were 14,133 eligible visits in the prescreening period and 16,993 in the screening period. Screening was completed for 13,404 visits (78.9%), with 116 (0.7%) screening positive. The mean ED length of stay was not significantly different in the prescreening (95.9 minutes) and screening periods (95.2 minutes; difference, 0.7 minutes; 95% CI, -1.5, 2.8). Among those who screened positive, 29% were reported to child protective services. On multivariable analysis, implementation of the screening tool did not impact overall ED length of stay. There were no significant differences in resource utilization between the prescreening and screening periods. CONCLUSIONS: Routine screening identifies children at high risk of physical abuse without increasing ED length of stay or resource utilization. Next steps will include determining rates of subsequent serious physical abuse in children with or without routine screening.

Micro-CT in a forensic examination of a fatal child abuse case: A case report.

Child abuse is a serious concern that can cause the death of a child. In such cases the medico-legal evidence is often pivotal but complex, drawing across multiple medical disciplines and techniques. One key specialism is histopathology, which is considered the gold standard for estimating the age of individual fractures. Another is micro-CT imaging, which can visualise the location of trauma across the body. This case report demonstrates how micro-CT was used to contextualise the histological evidence in the Criminal Justice Proceedings of a fatal child abuse case. This was achieved by overlaying the aged fracture evidence from histopathology onto the visuals rendered from micro-CT imaging. The case was a suspected child abuse of a deceased 1-month old infant who was reported unresponsive by their parents. The child was taken to hospital where they were pronounced dead. Suspicion was raised and post-mortem imaging confirmed head trauma and rib fractures, and the case was escalated for a forensic investigation. This case report details how the micro-CT imaging was merged with the gold standard of histopathology for visualisation of trauma, and how the court presentation was planned alongside Senior Investigating Officers and various medical experts. The presentation was used in court by the histopathologist to present the evidence. The resulting presentation provided additional clarity to jury members regarding the location, severity, frequency, and timings of the injuries. From the perspective of the investigating police force, the resulting presentation was crucial in ensuring understanding of the medico-legal evidence of how the infant died. The prosecuting lawyer noted that combining the histological and micro-CT evidence in this way allowed the evidence to be presented in a sensitive, clear, and impactful manner.

Impacts on paediatricians testifying in cases of child maltreatment: protocol for a systematic review.

INTRODUCTION: Paediatricians perform medical assessments for children in cases of suspected child maltreatment. Due to their role with statutory child protection agencies and police, paediatricians may be asked to testify in court about child protection and criminal justice matters. To the authors' knowledge, there has been no previous systematic review of the literature synthesising the evidence on the impacts on paediatricians testifying in cases of child maltreatment. METHODS AND ANALYSIS: A search strategy comprising indexed and key terms will be applied to six electronic reference databases from inception to May 2023: Medline, EMBASE, PsycINFO, CINAHL, Criminal Justice Abstracts and Cochrane Library. Two reviewers will independently screen titles and abstracts and full-text articles against predefined eligibility criteria to identify studies of interest. Conflicts will be independently adjudicated by a third reviewer. ETHICS AND DISSEMINATION: Since the systematic review methodology aims at synthesising information from available publications, this study does not require ethical approval. An article reporting the results of the systematic review will be submitted for publication in a scientific journal, presented at relevant conferences and used in subsequent stakeholder consultations.