Attitudes on Artificial Intelligence use in Pediatric Care From Parents of Hospitalized Children.

INTRODUCTION: Artificial intelligence (AI) may benefit pediatric healthcare, but it also raises ethical and pragmatic questions. Parental support is important for the advancement of AI in pediatric medicine. However, there is little literature describing parental attitudes toward AI in pediatric healthcare, and existing studies do not represent parents of hospitalized children well. METHODS: We administered the Attitudes toward Artificial Intelligence in Pediatric Healthcare, a validated survey, to parents of hospitalized children in a single tertiary children's hospital. Surveys were administered by trained study personnel (11/2/2021-5/1/2022). Demographic data were collected. An Attitudes toward Artificial Intelligence in Pediatric Healthcare score, assessing openness toward AI-assisted medicine, was calculated for seven areas of concern. Subgroup analyses were conducted using Mann-Whitney U tests to assess the effect of race, gender, education, insurance, length of stay, and intensive care unit (ICU) admission on AI use. RESULTS: We approached 90 parents and conducted 76 surveys for a response rate of 84%. Overall, parents were open to the use of AI in pediatric medicine. Social justice, convenience, privacy, and shared decision-making were important concerns. Parents of children admitted to an ICU expressed the most significantly different attitudes compared to parents of children not admitted to an ICU. CONCLUSIONS: Parents were overall supportive of AI-assisted healthcare decision-making. In particular, parents of children admitted to ICU have significantly different attitudes, and further study is needed to characterize these differences. Parents value transparency and disclosure pathways should be developed to support this expectation.

Technical/Algorithm, Stakeholder, and Society (TASS) barriers to the application of artificial intelligence in medicine: A systematic review.

INTRODUCTION: The use of artificial intelligence (AI), particularly machine learning and predictive analytics, has shown great promise in health care. Despite its strong potential, there has been limited use in health care settings. In this systematic review, we aim to determine the main barriers to successful implementation of AI in healthcare and discuss potential ways to overcome these challenges. METHODS: We conducted a literature search in PubMed (1/1/2001-1/1/2023). The search was restricted to publications in the English language, and human study subjects. We excluded articles that did not discuss AI, machine learning, predictive analytics, and barriers to the use of these techniques in health care. Using grounded theory methodology, we abstracted concepts to identify major barriers to AI use in medicine. RESULTS: We identified a total of 2,382 articles. After reviewing the 306 included papers, we developed 19 major themes, which we categorized into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). These themes included: Lack of Explainability, Need for Validation Protocols, Need for Standards for Interoperability, Need for Reporting Guidelines, Need for Standardization of Performance Metrics, Lack of Plan for Updating Algorithm, Job Loss, Skills Loss, Workflow Challenges, Loss of Patient Autonomy and Consent, Disturbing the Patient-Clinician Relationship, Lack of Trust in AI, Logistical Challenges, Lack of strategic plan, Lack of Cost-effectiveness Analysis and Proof of Efficacy, Privacy, Liability, Bias and Social Justice, and Education. CONCLUSION: We identified 19 major barriers to the use of AI in healthcare and categorized them into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). Future studies should expand on barriers in pediatric care and focus on developing clearly defined protocols to overcome these barriers.

Validation and Comparison of Common Thoracolumbar Injury Classification Treatment Algorithms and a Novel Modification.

BACKGROUND AND OBJECTIVES: The most common thoracolumbar trauma classification systems are the Thoracolumbar Injury Classification and Severity Score (TLICS) and the Thoracolumbar AO Spine Injury Score (TL AOSIS). Predictive accuracy of treatment recommendations is a historical limitation. Our objective was to validate and compare TLICS, TL AOSIS, and a modified TLICS (mTLICS) that awards 2 points for the presence of fractured vertebral body height loss >50% and/or spinal canal stenosis >50% at the fracture site. METHODS: The medical records of adult patients with acute, traumatic thoracolumbar injuries at an urban, Level 1 trauma center were retrospectively reviewed. TLICS, mTLICS, and TL AOSIS scores were calculated for 476 patients using computed tomography, MRI, and the documented neurological examination. Treatment recommendations were compared with treatment received. Standard validity measures were calculated. RESULTS: Treatment recommendations matched actual treatments in 95.6% (455/476) of patients for mTLICS, 91.3% (435/476) for TLICS, and 92.6% (441/476) for TL AOSIS. The differences between the accuracy of mTLICS and TLICS (95.6% vs 91.3%, P < .001) and between mTLICS and TL AOSIS (95.6% vs 91.3%, P = .003) were significant. The sensitivity of mTLICS was higher than that of TLICS (96.3% vs 81.3%, P < .001), and the sensitivity of TL AOSIS was higher than that of TLICS (92.5% vs 81.3%, P < .001). The specificity of mTLICS was equal to that of TLICS (95.3%) and higher than that of TL AOSIS (95.3% vs 92.7%, P = .02). The modifier led to substantial outperformance of mTLICS over TLICS due to 38 patients (20 of whom received surgery) moving from a TLICS score of <4 to a mTLICS score equal to 4. CONCLUSION: All systems performed well. The mTLICS had improved sensitivity and accuracy compared with TLICS and higher accuracy and specificity than TL AOSIS. The sensitivity of TL AOSIS was higher than that of TLICS. Prospective, multi-institutional reliability and validity studies of this mTLICS are needed for adoption.

Characterization of the influence of spinopelvic parameters on thoracolumbar trauma.

OBJECTIVE: The current Roussouly classification identifies four groups of "normal" sagittal spine morphology, which has greatly expanded the understanding of normal heterogeneity of the spine. While there has been extensive characterization of the influence of spinopelvic parameters on outcomes after degenerative spine surgery, the influence of spinopelvic parameters on thoracolumbar trauma has yet to be described. The goal of this study was to determine if spinopelvic parameters and global spine morphology influence fracture location, fracture morphology, and rate of neurological deficit in the setting of thoracolumbar trauma. METHODS: Of 2896 patients reviewed in the authors' institutional spine database between January 2014 and April 2020 with an ICD-9/10 diagnosis of thoracolumbar trauma, 514 met the inclusion criteria of acute thoracolumbar fracture on CT and visible femoral heads on sagittal CT. Pelvic incidence (PI) was calculated on sagittal CT. Demographic and clinical data including age, sex, BMI, smoking status, concomitant cervical fracture, mechanism of injury, major fracture location, neurological deficit, AO Spine thoracolumbar injury classification, and management type (operative vs nonoperative) were collected. Patients were stratified into high-PI (≥ 50°) and low-PI (< 50°) groups. RESULTS: Patients with high PI had a lower incidence of fractures in the lower lumbar spine (below L2) compared with patients with low PI (16% vs 8%, p < 0.01). The last lordotic vertebrae were observed between T10 and L4, and of fractures that occurred at these levels, 75% were at the last lordotic vertebrae. Fall from height was the most common cause of neurological deficit, accounting for 47%. Of the patients presenting with a fall from height, AO Spine type B distraction injuries were more common in the high-PI group (41% vs 18%, p = 0.01). Similarly, within the same subgroup, AO Spine type A compression injuries were more common in the low-PI group (73% vs 53%, p = 0.01). CONCLUSIONS: Spinopelvic parameters and sagittal balance influence the location and morphology of thoracolumbar fractures. Fractures of the thoracolumbar junction are strongly associated with the inflection point, which is defined by sagittal alignment. While the importance of considering sagittal balance is known for decision-making in degenerative spinal pathology, further studies are required to determine if spinopelvic parameters and sagittal balance should play a role in the decision-making for management of thoracolumbar fractures.

The Impact of Traumatic Brain Injury on Microbiome Composition: A Systematic Review.

Traumatic brain injuries (TBIs) are a significant health problem, impacting millions of people every year. Although emerging evidence suggests that the composition of the gut microbiome is altered after TBI, no systematic review has been published on this topic. The objective of the present systematic review is to analyze publications that evaluate the impact of TBI on gut microbiome composition. Research articles were pulled from seven databases. The systematic review was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. In order for publications to be eligible for this review, they had to (1) report on original human- or animal-subjects research, (2) evaluate the impact of TBI on the microbiome, and (3) be written in English and (4) be published in a peer-reviewed journal. Of the seven articles that met these criteria, one involved human participants, while the other six reported on experimental animal studies. All studies found changes in the gut microbiome following TBI, with similar changes in bacterial populations observed across studies. The limitations of these studies included the use of primarily male animals, limitations of 16 S rRNA gene sequencing, and small sample sizes. This review was also limited by the small pool of studies conducted in this area. In summary, changes in bacterial populations of the gut microbiome, specifically increases in proteobacteria and firmicutes, were observed across the studies. By evaluating the changes in the microbiome resulting from TBI, potential therapeutic interventions could be explored.

The management of diabetes in everyday life study: Design and methods for a pragmatic randomized controlled trial comparing the effectiveness of text messaging versus health coaching.

Background African American patients with uncontrolled diabetes living in medically underserved areas need effective clinic-based interventions to improve self-care behaviors. Text messaging (TM) and health coaching (HC) are among the most promising low-cost population-based approaches, but little is known about their comparative effectiveness in real-world clinical settings. Objective Use a pragmatic randomized controlled trial design to determine the comparative effectiveness of TM and HC with enhanced usual care (EC) in African American adults with uncontrolled diabetes and multiple chronic health conditions. Methods/design The Management of Diabetes in Everyday Life (MODEL) study is randomizing 646 patients (n = 581with anticipated 90% retention) to 3 intervention arms: TM, HC, and EC. Participants are African American adults living in medically underserved areas of the Mid-South, age ≥ 18, with uncontrolled diabetes (A1c ≥ 8), one or more additional chronic conditions, and who have a phone with texting and voicemail capability. Primary outcome measures: the general diet, exercise, and medication adherence subscales of the revised Summary of Diabetes Self-Care Activities questionnaire assessed at one year. Secondary outcomes: diabetes-specific quality of life, primary care engagement, and average blood sugar (A1c). The study will also assess heterogeneity of treatment effects by six key baseline participant characteristics. Conclusions We describe the design and methods of the MODEL study along with design revisions required during implementation in a pragmatic setting. This trial, upon its conclusion, will allow us to compare the effectiveness of two promising low-cost primary care-based strategies for supporting self-care behaviors among African Americans individuals with uncontrolled diabetes. ClinicalTrials.gov registration number: NCT02957513.

Cosmetics as a feature of the extended human phenotype: modulation of the perception of biologically important facial signals.

Research on the perception of faces has focused on the size, shape, and configuration of inherited features or the biological phenotype, and largely ignored the effects of adornment, or the extended phenotype. Research on the evolution of signaling has shown that animals frequently alter visual features, including color cues, to attract, intimidate or protect themselves from conspecifics. Humans engage in conscious manipulation of visual signals using cultural tools in real time rather than genetic changes over evolutionary time. Here, we investigate one tool, the use of color cosmetics. In two studies, we asked viewers to rate the same female faces with or without color cosmetics, and we varied the style of makeup from minimal (natural), to moderate (professional), to dramatic (glamorous). Each look provided increasing luminance contrast between the facial features and surrounding skin. Faces were shown for 250 ms or for unlimited inspection time, and subjects rated them for attractiveness, competence, likeability and trustworthiness. At 250 ms, cosmetics had significant positive effects on all outcomes. Length of inspection time did not change the effect for competence or attractiveness. However, with longer inspection time, the effect of cosmetics on likability and trust varied by specific makeup looks, indicating that cosmetics could impact automatic and deliberative judgments differently. The results suggest that cosmetics can create supernormal facial stimuli, and that one way they may do so is by exaggerating cues to sexual dimorphism. Our results provide evidence that judgments of facial trustworthiness and attractiveness are at least partially separable, that beauty has a significant positive effect on judgment of competence, a universal dimension of social cognition, but has a more nuanced effect on the other universal dimension of social warmth, and that the extended phenotype significantly influences perception of biologically important signals at first glance and at longer inspection.