Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review.

This scoping review of randomised controlled trials on artificial intelligence (AI) in clinical practice reveals an expanding interest in AI across clinical specialties and locations. The USA and China are leading in the number of trials, with a focus on deep learning systems for medical imaging, particularly in gastroenterology and radiology. A majority of trials (70 [81%] of 86) report positive primary endpoints, primarily related to diagnostic yield or performance; however, the predominance of single-centre trials, little demographic reporting, and varying reports of operational efficiency raise concerns about the generalisability and practicality of these results. Despite the promising outcomes, considering the likelihood of publication bias and the need for more comprehensive research including multicentre trials, diverse outcome measures, and improved reporting standards is crucial. Future AI trials should prioritise patient-relevant outcomes to fully understand AI's true effects and limitations in health care.

Critical evaluation of artificial intelligence as a digital twin of pathologists for prostate cancer pathology.

Prostate cancer pathology plays a crucial role in clinical management but is time-consuming. Artificial intelligence (AI) shows promise in detecting prostate cancer and grading patterns. We tested an AI-based digital twin of a pathologist, vPatho, on 2603 histological images of prostate tissue stained with hematoxylin and eosin. We analyzed various factors influencing tumor grade discordance between the vPatho system and six human pathologists. Our results demonstrated that vPatho achieved comparable performance in prostate cancer detection and tumor volume estimation, as reported in the literature. The concordance levels between vPatho and human pathologists were examined. Notably, moderate to substantial agreement was observed in identifying complementary histological features such as ductal, cribriform, nerve, blood vessel, and lymphocyte infiltration. However, concordance in tumor grading decreased when applied to prostatectomy specimens (κ = 0.44) compared to biopsy cores (κ = 0.70). Adjusting the decision threshold for the secondary Gleason pattern from 5 to 10% improved the concordance level between pathologists and vPatho for tumor grading on prostatectomy specimens (κ from 0.44 to 0.64). Potential causes of grade discordance included the vertical extent of tumors toward the prostate boundary and the proportions of slides with prostate cancer. Gleason pattern 4 was particularly associated with this population. Notably, the grade according to vPatho was not specific to any of the six pathologists involved in routine clinical grading. In conclusion, our study highlights the potential utility of AI in developing a digital twin for a pathologist. This approach can help uncover limitations in AI adoption and the practical application of the current grading system for prostate cancer pathology.

Disparities in detection of suspected child abuse.

BACKGROUND: Child abuse is a significant cause of injury and death among children, but accurate identification is often challenging. This study aims to assess whether racial disparities exist in the identification of child abuse. METHODS: The 2010-2014 and 2016-2017 National Trauma Data Bank was queried for trauma patients ages 1-17. Using ICD-9CM and ICD-10CM codes, children with injuries consistent with child abuse were identified and analyzed by race. RESULTS: Between 2010-2014 and 2016-2017, 798,353 patients were included in NTDB. Suspected child abuse victims (SCA) accounted for 7903 (1%) patients. Of these, 51% were White, 33% Black, 1% Asian, 0.3% Native Hawaiian/Other Pacific Islander, 2% American Indian, and 12% other race. Black patients were disproportionately overrepresented, composing 12% of the US population, but 33% of SCA patients (p < 0.001). Although White SCA patients were more severely injured (ISS 16-24: 20% vs 16%, p < 0.01) and had higher in-hospital mortality (9% vs. 6%, p = 0.01), Black SCA patients were hospitalized longer (7.2 ± 31.4 vs. 6.2 ± 9.9 days, p < 0.01) despite controlling for ISS (1-15: 4. 5.7 ± 35.7 vs. 4.2 ± 6.2 days, p < 0.01). In multivariate regression, Black children continued to have longer lengths of stay despite controlling for ISS and insurance type. CONCLUSIONS: Utilizing a nationally representative dataset, Black children were disproportionately identified as potential victims of abuse. They were also subjected to longer hospitalizations, despite milder injuries. Further studies are needed to better understand the etiology of the observed trends and whether they reflect potential underlying unconscious or conscious biases of mandated reporters. TYPE OF STUDY: Treatment study. LEVEL OF EVIDENCE: III.

Mental health outcomes in pediatric trauma patients: A 10 year real world analysis using a large database approach.

INTRODUCTION: Traumatic injury is the leading cause of morbidity and mortality among children in the United States. Single institution studies suggest an increased risk of poor mental health outcomes among these patients, but there are few population-based studies assessing this risk. METHODS: The IBMⓇ MarketScanⓇ private insurance claims database was used to identify children (6-17yo) with traumatic injuries between 2007 and 2016. Time-to-event analysis was performed to compare rates of PTSD, depression, anxiety, and adjustment disorder among children admitted to the hospital compared to children treated in the emergency department (ED), urgent care (UC), or in the outpatient setting, and to children admitted with uncomplicated appendicitis. RESULTS: Among children admitted for traumatic injury, 3.3% developed a subsequent mental health diagnosis, and 1.6% developed PTSD. Children admitted for traumatic injury were at increased risk of developing a mental health condition (HR 1.34, p < 0.001) compared to those admitted for appendicitis. Children treated in the ED or UC for traumatic injury and those treated in the outpatient setting were also at increased risk (HR 1.20 and 1.18, p = 0.006 and p = 0.012, respectively). Among those admitted to the hospital, the risk of subsequent mental health diagnosis increased by 1.5% per day; in the first 31 days of hospitalization, the risk of PTSD diagnosis increased by 13% per day. CONCLUSION: Children who sustain a traumatic injury are at increased risk of developing a mental health condition. PTSD rates found in our real world analysis are lower than those found in prospective studies, raising the possibility of under-recognition of PTSD in this population. LEVEL OF EVIDENCE: Level II.

Epidemiology of pediatric trauma during the COVID-19 pandemic shelter in place.

INTRODUCTION: The first COVID-19 cases occurred in the US in January of 2020, leading to the implementation of shelter in place. This study seeks to define the impact of shelter in place on the epidemiology of pediatric trauma. METHODS: We examined pediatric trauma admissions at 5 Level 1 and 1 Level 2 US pediatric trauma centers between January 1 and June 30, 2017-2020. Demographic and injury data were compared between pre- and post-shelter in place patient cohorts. RESULTS: A total of 8772 pediatric trauma activations were reviewed. There was a 13% decrease in trauma volume in 2020, with a nadir at 16 days following implementation of shelter in place. Injury severity scores were higher in the post-shelter in place cohort. The incidence of nonmotorized vehicle accidents and gunshot wounds increased in the post-shelter in place cohort. CONCLUSION: We found an overall decrease in pediatric trauma volume following shelter in place. However, injuries tended to be more severe. Our findings help inform targeted injury prevention campaigns during future pandemics.

Financial burden of pediatric firearm-related injury admissions in the United States.

Pediatric firearm-related injuries pose a significant public health problem in the United States, yet the associated financial burden has not been well described. This is the first study examining national data on the cost of initial hospitalization for pediatric firearm-related injuries. In this retrospective review, the Healthcare Cost and Utilization Project Kids' Inpatient Database from the years 2003, 2006, 2009, and 2012 was used to identify all patients 18 years of age and under who were admitted with firearm-related injuries. We compared demographic and discharge-level data including injury severity score, hospital length of stay, income quartile, injury intent, and inflation-adjusted hospital costs across age groups (0-5, 6-9, 10-15, 16-18 years). There were approximately 4,753 pediatric firearm-related admissions each year, with a median hospitalization cost of $12,984 per patient. Annual initial hospitalization costs for pediatric firearm injuries were approximately $109 million during the study period. Pediatric firearm-related injuries predominately occured among older teenagers (74%, 16-18 years), males (89%), black individuals (55%), and those from the lowest income quartile (53%). We found significant cost variation based on patient race, income quartile, injury severity score, intent, hospital length of stay, disposition, and hospital region. Inflation-adjusted hospitalization costs have increased significantly over the study period (p < 0.001). Pediatric firearm-related injuries are a large financial burden to the United States healthcare system. There are significant variations in cost based on predictable factors like hospital length of stay and injury severity score; however, there are also substantial discrepancies based on hospital region, patient race, and income quartile that require further investigation.

Heterogeneous, three-dimensional texturing of graphene.

We report a single-step strategy to achieve heterogeneous, three-dimensional (3D) texturing of graphene and graphite by using a thermally activated shape-memory polymer substrate. Uniform arrays of graphene crumples can be created on the centimeter scale by controlling simple thermal processing parameters without compromising the electrical properties of graphene. In addition, we show the capability to selectively pattern crumples from otherwise flat graphene and graphene/graphite in a localized manner, which has not been previously achievable using other methods. Finally, we demonstrate 3D crumpled graphene field-effect transistor arrays in a solution-gated configuration. The presented approach has the capability to conform onto arbitrary 3D surfaces, a necessary prerequisite for adaptive electronics, and will enable facile large-scale topography engineering of not only graphene but also other thin-film and 2D materials in the future.