Pilot study using machine learning to improve estimation of physical abuse prevalence.

BACKGROUND: International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes have been shown to underestimate physical abuse prevalence. Machine learning models are capable of efficiently processing a wide variety of data and may provide better estimates of abuse. OBJECTIVE: To achieve proof of concept applying machine learning to identify codes associated with abuse. PARTICIPANTS AND SETTING: Children <5 years, presenting to the emergency department with an injury or abuse-specific ICD-10-CM code and evaluated by the child protection team (CPT) from 2016 to 2020 at a large Midwestern children's hospital. METHODS: The Pediatric Health Information System (PHIS) and the CPT administrative databases were used to identify the study sample and injury and abuse-specific ICD-10-CM codes. Subjects were divided into abused and non-abused groups based on the CPT's evaluation. A LASSO logistic regression model was constructed using ICD-10-CM codes and patient age to identify children likely to be diagnosed by the CPT as abused. Performance was evaluated using repeated cross-validation (CV) and Reciever Operator Characteristic curve. RESULTS: We identified 2028 patients evaluated by the CPT with 512 diagnosed as abused. Using diagnosis codes and patient age, our model was able to accurately identify patients with confirmed PA (mean CV AUC = 0.87). Performance was still weaker for patients without existing ICD codes for abuse (mean CV AUC = 0.81). CONCLUSIONS: We built a model that employs injury ICD-10-CM codes and age to improve accuracy of distinguishing abusive from non-abusive injuries. This pilot modelling endeavor is a steppingstone towards improving population-level estimates of abuse.

Child maltreatment among victims of violent death: an analysis of national violent death reporting system data, 2014-2018.

BACKGROUND: Limited information is known about the impact of childhood maltreatment on lifetime risk of violent death. This study aimed to compare manner of death, demographics, age at time of death, and the presence of a mental health or substance use disorder among decedents of violent deaths with a history of child maltreatment to those without. METHODS: This cross-sectional study compared characteristics of pediatric and adult violent deaths with and without a history of child maltreatment that were captured in the National Violent Death Reporting System from 2014 through 2018. RESULTS: Decedents who were male, multiracial, and had adulthood substance or mental health disorders were more likely to have a history of maltreatment. All-age decedents with a history of maltreatment were more likely to die by homicide. Adult decedents with a history of maltreatment were more likely to die by suicide. Maltreated decedents died significantly younger than non-maltreated decedents. CONCLUSIONS: Among victims of violent deaths, an identified history of child maltreatment was associated with increased risk of homicide across the lifespan, adult suicide, and earlier death. A history of child maltreatment was also associated with mental health and substance use disorders, which may reflect one of the pathways through which the child maltreatment-to-death association functions.

The evaluation of emotional maltreatment's effect on family dynamics and suicidal behaviors.

BACKGROUND: Emotional maltreatment and poor family functioning are known risks for youth suicide, but few studies have examined these issues as prospective predictors of future attempts. OBJECTIVES: Examine family functioning and suicide risk associated with emotional maltreatment in youth with a lifetime history of major depressive disorder (MDD) and the prospective association of emotional maltreatment and family functioning with future suicide attempts. PARTICIPANTS AND SETTING: Participants included 321 youth aged 12-15 years (251 with emotional maltreatment; 70 with no emotional maltreatment) recruited from a metropolitan children's hospital from 2011 to 2018. Prospective analyses included 280 youths (221 with emotional maltreatment; 59 without emotional maltreatment). METHODS: Semi-structured interviews and self-reports assessed family functioning and suicidal thoughts and behaviors in youth with and without emotional maltreatment at baseline, 6-month, 1-year, and 2-year follow-up. Multivariate analyses examined whether emotional maltreatment predicted future suicide attempts, beyond the effect of prior suicide attempts. RESULTS: Emotionally maltreated youth reported significantly lower scores for family adaptability, cohesion, and family alliance, and higher rates of suicidal ideation and suicide attempts, compared to youth without emotional maltreatment. Youth experiencing multiple forms of abuse were significantly more likely to attempt suicide at future timepoints, however this association was attenuated after controlling for prior suicide attempts. CONCLUSION: Youth who experienced emotional maltreatment had a significantly higher percentage of past suicidal thoughts and behaviors and significantly less favorable scores for family functioning associated with an increased suicide risk. Findings support family-focused suicide prevention strategies as a promising approach to reduce youth suicide.

Characterizing child maltreatment fatalities among child victims with disabilities in the United States, 2010-2019.

BACKGROUND: There has been little research on child maltreatment-related fatalities among children with disabilities. Despite being a minority of children in the United States, children with disabilities experience higher rates of victimization. OBJECTIVE: To characterize fatalities due to child maltreatment among children with disabilities in the United States. METHODS: Data from the National Violent Death Reporting System from 2010 to 2019 were analyzed to describe child maltreatment-related deaths among children with disabilities aged birth to 17 years. RESULTS: There were 106 fatalities meeting the study criteria. The average age of the victims was 5.9 years old and 74.6 % were male. The most frequent suspected perpetrators of maltreatment-related fatalities were biological mothers (35.2 %), and most perpetrators were White (55.7 %). Analyses showed a statistically significant relationship between fatalities caused by neglect and diagnoses of attention deficit hyperactivity disorder, autism spectrum disorder, cerebral palsy, and/or traumatic brain injury. Overall, physical abuse and/or neglect resulting in a fatality among children with disabilities were significantly correlated with the relationship of the perpetrator to the victim. CONCLUSIONS: Children with disabilities who died as a result of abuse were more likely to have autism spectrum disorder, a developmental disability, or other physical impairment, with physical abuse being the most prevalent type of abuse that resulted in death. To decrease the likelihood of abuse of disabled children, healthcare practitioners and caseworkers should work together to create strategies to help caregivers cope with the financial, mental, and physical stress that comes with raising children with disabilities.

Diagnosis codes dramatically underestimate the burden of abuse.

BACKGROUND: International Classification of Diseases (ICD) billing codes are not well-suited to estimate physical abuse prevalence among hospitalized patients and may be even less accurate in emergency departments (EDs). The Centers for Disease Control and Prevention (CDC) has recently published a child abuse and neglect syndromic surveillance definition to more accurately examine national abuse trends among ED visits. OBJECTIVE: To retrospectively apply the CDC syndromic definition to a population of physically abused children and determine its sensitivity for abuse in an ED and at hospital discharge. PARTICIPANTS AND SETTING: All physically abused children <5 years seen in the ED and evaluated by the child protection team from 2016 to 2020 at a large Midwestern children's hospital. METHODS: Retrospective cross-sectional study utilizing the hospital's child protection team administrative database, the Pediatric Health Information System and the electronic health record to identify the study sample, chief complaint, and abuse-specific codes assigned in the ED and at hospital discharge. Abuse-specific codes were defined as all ICD-10-CM and Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT) codes included in the CDC syndromic definition, which was applied to the sample and its sensitivity determined. RESULTS: Among the 550 abused patients identified, most were male (58.4 %), white (65.1 %), <2 years old (80.4 %), and had public insurance (81.6 %). When applying the CDC syndromic definition, only 11.6 % were identified as abused in the ED and 65.3 % were identified at hospital discharge. CONCLUSIONS: The CDC syndrome surveillance definition lacks sensitivity in identifying abuse in the ED or at hospital discharge.

Implementation of SEEK in a Children's Advocacy Center: A Process Improvement Initiative.

Risk factors for child maltreatment are well-described, but clinicians may overlook these risk factors. The Safe Environment for Every Kid (SEEK) model is an evidence-based approach to identifying psychosocial risk factors for child maltreatment. This article describes a quality improvement initiative to implement the SEEK model in a unique pediatric setting, a Children's Advocacy Center. Methods: The objectives were to (1) describe the identification of psychosocial risk factors for child maltreatment by implementing the SEEK screening tool with each new family, (2) achieve and sustain a SEEK completion rate of greater than 85%, and (3) achieve and sustain a SEEK follow-up compliance rate of greater than 75%. Structured quality improvement methods, including several plan-do-study-act cycles, were used to implement interventions. Results: The percentage of caregivers who completed the SEEK questionnaire increased from a baseline of 76% to 86%, which was sustained for more than 2 years, resulting in a better understanding and support of families' needs. Caregivers completed 3,606 SEEK Parent Questionnaire-R. Mental health concerns and food insecurity were among the most commonly endorsed items. Follow-up compliance increased from 47% to 90%, a level that has been maintained. Conclusions: While Children's Advocacy Centers evaluate children with suspected abuse, identifying current stressors in the home and linking families with resources to address their immediate psychosocial concerns can improve short- and long-term outcomes. This initiative demonstrates the feasibility of incorporating consistent screening for psychosocial risk factors for child maltreatment in this busy environment.

Radiographic timelines for pediatric healing fractures: a systematic review.

Skeletal fractures, a common injury in physically abused children, often go undetected and untreated for significant lengths of time and are sometimes incidentally discovered radiographically. Our objective was to review current literature for scientific studies of pediatric fracture healing with associated timelines. We conducted a search of Embase, EBSCOhost, MEDLINE (PubMed), and Web of Science for literature published from the earliest available up to August 2018. We evaluated the included articles for quality, with consideration for use in clinical and forensic settings. Of a total of 313 full-text articles evaluated, 10 met study inclusion criteria. The patient age range among studies was 0-17 years, with children younger than 1 year included in the majority of studies. The fracture locations included in studies were primarily fractures of the upper limb and pectoral girdle, followed by fractures of the lower limb. The radiographic features of healing varied greatly among the studies. Timelines of common fracture healing variables differed significantly among studies. Scientific, radiographic studies of pediatric fracture healing are limited. Gaps in knowledge regarding fracture healing highlight the need for future research and validation studies. Fracture healing timelines derived from existing timelines should be used with caution.

A Retrospective Study of Cervical Spine MRI Findings in Children with Abusive Head Trauma.

BACKGROUND/AIMS: Increasing attention has been given to the possible association of cervical spine (c-spine) injuries with abusive head trauma (AHT). The aims of this study were to describe c-spine MRI findings in hospitalized AHT patients. METHODS: This is a retrospective study of children under the age of 5 years with AHT admitted to hospital in 2004-2013. Those with c-spine MRI were identified, and the images were reviewed. RESULTS: 250 AHT cases were identified, with 34 (14%) undergoing c-spine MRI. Eleven patients (32%) had 25 findings, including hematoma in 2, occiput-C1-C2 edema in 3, prevertebral edema in 6, facet edema in 2, and interspinous and/or muscular edema in 10. No patients had a clinically evident c-spine injury, a clinically unstable c-spine, or required c-spine surgery. CONCLUSIONS: C-spine MRI may identify abnormalities not apparent upon physical examination and the procedure should therefore be considered in cases of suspected AHT.

Distraction Injury of the Thoracic Spine With Spinal Cord Transection and Vascular Injury in a 5-Week-Old Infant Boy: A Case of Child Physical Abuse.

Distraction injury of the spine with spinal cord transection and adjacent vascular injury is rarely described in the setting of child physical abuse. We report a 5-week-old infant boy who sustained these injuries after an abusive event. The clinical presentation, imaging findings, and recommended evaluation modalities are discussed. An overview of pediatric spinal column and vascular injuries secondary to physical abuse is given.

Neurological Manifestations of Medical Child Abuse.

BACKGROUND: Medical child abuse occurs when a child receives unnecessary and harmful, or potentially harmful, medical care at the instigation of a caretaker through exaggeration, falsification, or induction of symptoms of illness in a child. Neurological manifestations are common with this type of maltreatment. OBJECTIVES: We sought to review common reported neurological manifestations that may alert the clinician to consider medical child abuse. In addition, the possible sequelae of this form of child maltreatment is discussed, as well as practice recommendations for establishing the diagnosis and stopping the abuse once it is identified. METHODS: A review of the medical literature was conducted regarding the reported neurological presentations of this entity. RESULTS: Neurological manifestations of medical child abuse include false reports of apparent life-threatening events and seizures and reports of induction of symptoms from poisoning. Failure to correlate objective findings with subjective complaints may lead to unnecessary and potentially harmful testing or treatment. This form of child maltreatment puts a child at significant risk of long-term morbidity and mortality. CONCLUSIONS: A wide variety of neurological manifestations have been reported in cases of medical child abuse. It is important for the practicing neurologist to include medical child abuse on the differential diagnosis.

Child advocacy center multidisciplinary team decision and its association to child protective services outcomes.

Limited studies exist evaluating the multidisciplinary team (MDT) decision-making process and its outcomes. This study evaluates the MDT determination of the likelihood of child sexual abuse (CSA) and its association to the outcome of the child protective services (CPS) disposition. A retrospective cohort study of CSA patients was conducted. The MDT utilized an a priori Likert rating scale to determine the likelihood of abuse. Subjects were dichotomized into high versus low/intermediate likelihood of CSA as determined by the MDT. Clinical and demographic characteristics were compared based upon MDT and CPS decisions. Fourteen hundred twenty-two patients were identified. A high likelihood for abuse was determined in 997 cases (70%). CPS substantiated or indicated the allegation of CSA in 789 cases (79%, Kappa 0.54). Any CSA disclosure, particularly moderate risk disclosure (AOR 59.3, 95% CI 26.50-132.80) or increasing total number of CSA disclosures (AOR 1.3, 95% CI 1.11-1.57), was independently associated with a high likelihood for abuse determination. Specific clinical features associated with discordant cases in which MDT determined high likelihood for abuse and CPS did not substantiate or indicate CSA included being white or providing a low risk CSA disclosure or other non-CSA disclosure. MDT determination regarding likelihood of abuse demonstrated moderate agreement to CPS disposition outcome. CSA disclosure is predictive of the MDT determination for high likelihood of CSA. Agreement between MDT determination and CPS protection decisions appear to be driven by the type of disclosures, highlighting the importance of the forensic interview in ensuring appropriate child protection plans.