Incorporation of a biparietal narrowing metric to improve the ability of machine learning models to detect sagittal craniosynostosis with 2D photographs.

OBJECTIVE: Sagittal craniosynostosis is the most common form of craniosynostosis and typically results in scaphocephaly, which is characterized by biparietal narrowing, compensatory frontal bossing, and an occipital prominence. The cephalic index (CI) is a simple metric for quantifying the degree of cranial narrowing and is often used to diagnose sagittal craniosynostosis. However, patients with variant forms of sagittal craniosynostosis may present with a "normal" CI, depending on the part of the suture that is closed. As machine learning (ML) algorithms are developed to assist in the diagnosis of cranial deformities, metrics that reflect the other phenotypic features of sagittal craniosynostosis are needed. In this study the authors sought to describe the posterior arc angle (PAA), a measurement of biparietal narrowing that is obtained with 2D photographs, and elucidate the role of PAA as an adjuvant to the CI in characterizing scaphocephaly and the potential relevance of PAA in new ML model development. METHODS: The authors retrospectively reviewed 1013 craniofacial patients treated during the period from 2006 to 2021. Orthogonal top-down photographs were used to calculate the CI and PAA. Distribution densities, receiver operating characteristic (ROC) curves, and chi-square analyses were used to describe the relative predictive utility of each method for sagittal craniosynostosis. RESULTS: In total, 1001 patients underwent paired CI and PAA measurements and a clinical head shape diagnosis (sagittal craniosynostosis, n = 122; other cranial deformity, n = 565; normocephalic, n = 314). The area under the ROC curve (AUC) for the CI was 98.5% (95% confidence interval 97.8%-99.2%, p < 0.001), with an optimum specificity of 92.6% and sensitivity of 93.4%. The PAA had an AUC of 97.4% (95% confidence interval 96.0%-98.8%, p < 0.001) with an optimum specificity of 94.9% and sensitivity of 90.2%. In 6 of 122 (4.9%) cases of sagittal craniosynostosis, the PAA was abnormal while the CI was normal. This means that adding a PAA cutoff branch to a partition model increases the detection of sagittal craniosynostosis. CONCLUSIONS: Both CI and PAA are excellent discriminators for sagittal craniosynostosis. Using an accuracy-optimized partition model, the addition of the PAA to the CI increased model sensitivity compared to using the CI alone. Using a model that incorporates both CI and PAA could assist in the early identification and treatment of sagittal craniosynostosis via automated and semiautomated algorithms that utilize tree-based ML models.

Esophageal Surveillance Practices in Esophageal Atresia Patients: A Survey by the Eastern Pediatric Surgery Network.

INTRODUCTION: Endoscopic surveillance guidelines for patients with repaired esophageal atresia (EA) rely primarily on expert opinion. Prior to embarking on a prospective EA surveillance registry, we sought to understand EA surveillance practices within the Eastern Pediatric Surgery Network (EPSN). METHODS: An anonymous, 23-question Qualtrics survey was emailed to 181 physicians (surgeons and gastroenterologists) at 19 member institutions. Likert scale questions gauged agreement with international EA surveillance guideline-derived statements. Multiple-choice questions assessed individual and institutional practices. RESULTS: The response rate was 77%. Most respondents (80%) strongly agree or agree that EA surveillance endoscopy should follow a set schedule, while only 36% claimed to perform routine upper GI endoscopy regardless of symptoms. Many institutions (77%) have an aerodigestive clinic, even if some lack a multi-disciplinary EA team. Most physicians (72%) expressed strong interest in helping develop evidence-based guidelines. CONCLUSIONS: Our survey reveals physician agreement with current guidelines but weak adherence. Surveillance methods vary greatly, underscoring the lack of evidence-based data to guide EA care. Aerodigestive clinics may help implement surveillance schedules. Respondents support evidence-based protocols, which bodes well for care standardization. Results will inform the first multi-institutional EA databases in the United States (US), which will be essential for evidence-based care. LEVEL OF EVIDENCE: This is a prognosis study with level 4 evidence.

Perceptions and Attitudes toward Community Health and Interprofessional Education in Students with and without an Additional Community Medicine-Focused Program.

The Rural Medical Education (RMED) Program at the University of Illinois College of Medicine Rockford campus, and part of the National Center for Rural Health Professions, strives to recruit students from rural areas, who, after completing residency, return to rural Illinois as primary care physicians. RMED students meet monthly to learn about the community and public health in rural communities. Furthermore, they complete a 16-week rural preceptorship during their fourth year. During the fourth year of medical school, all RMED students, as well as the students following the regular curriculum, are asked to complete a survey, related to the understanding of medical students' views of community and interprofessional education. We aimed to identify how the community-based curriculum affects the students' understanding and appreciation of community as they go into rural health practice. The results showed that students in the RMED Program are more aware of the community they are part of, as well as being more interested in becoming part of their community. RMED students reported a statistically significantly higher rating of feeling appreciated and accepted by their community and rated their confidence in their abilities in the community statistically significantly higher. Interestingly, RMED students were not more likely to be more familiar with several health professions and programs within their community, compared to non-RMED students. Results comparing self-rated capabilities for RMED students within the community both before and after adding components of an interprofessional education curriculum showed no statistically significant changes. These results support previous research, while also providing more support for the development of successful interprofessional education courses.