Correction: Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered, Web-Based Clinical Decision Support System for the Treatment of Depression in Adults: Longitudinal Feasibility Study.

[This corrects the article DOI: 10.2196/31862.].

Optimizing resource utilization: palliative care consultations in critically ill pediatric trauma patients.

Objectives: The American College of Surgeons Trauma Quality Improvement Program (TQIP) and Committee on Trauma released a best practice guideline for palliative care in trauma patients in 2017. Utilization of pediatric palliative care services for pediatric trauma patients has not been studied. We sought to identify patients who received the consultation and develop criteria for patients who would benefit from these resources at our institution. Methods: The institutional pediatric trauma registry was queried to identify all admissions age 0-17 years old to the pediatric intensive care unit (PICU) or trauma ICU (TICU) from 2014 to 2021. Demographic and clinical features were obtained from the registry. Electronic medical records were reviewed to identify and review consultations to the ComPASS team. A clinical practice guideline (CPG) for palliative care consultations was developed based on the TQIP guideline and applied retrospectively to patients admitted 2014-2021. The CPG was then prospectively applied to patients admitted from March through November 2022. Results: A total of 399 patients were admitted to the PICU/TICU. There were 30 (7.5%) deaths, 20 (66.7%) within 24 hours of admission. Palliative care consultations were obtained in 21 (5.3%). Of these, 10 (47.6%) patients were infants/toddlers

The EPIC procedure (Endoscopic-assisted Pilonidal Irrigation and Cleaning): a simple and effective treatment for pilonidal disease.

BACKGROUND: Pilonidal disease (PD) is a common condition of the sacrococcygeal region leading to inflammation and abscess formation. PD is a topic of renewed interest due to the lack of satisfactory management options. Minimally invasive techniques have recently been investigated, with promising results in adult and pediatric populations. Our technique, the "EPIC procedure," Endoscopic-assisted Pilonidal Irrigation and Cleaning, involves removal of hair under direct visualization using a small endoscope while flushing saline through the cavity via an angiocatheter. We aim to show that the EPIC procedure is a safe and effective operation for the treatment of pilonidal disease in the pediatric population. MATERIALS AND METHODS: We performed a retrospective chart review including 20 consecutive patients. All had a primary sacrococcygeal pilonidal sinus; all underwent the EPIC procedure. Post-operative care instructions included daily bathing and weekly depilatory application. We evaluated gender, age, weight, disease severity, operative duration, recurrence of PD, and other complications. RESULTS: In the 20 patients studied, 22 EPIC procedures were performed. The median follow-up duration was 27.95 (range 0.63-45.27) months. The mean operative duration was 28.8 (SD 10.2) min. There was a 15% recurrence rate (95% CI 0.00%, 30.65%). CONCLUSIONS: The EPIC procedure is an endoscopic-assisted operation that simplifies previously published techniques in pursuit of reduced operative complexity, cost, and time, with comparable recurrence and complication rates. All three recurrences occurred in patients that did not follow instructions for post-operative depilatory care. Two of these patients underwent repeat EPIC procedure and had no further complications. The third was lost to follow-up. The EPIC procedure provides a simple, effective, and minimally invasive approach to the treatment of pilonidal disease.

Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered, Web-Based Clinical Decision Support System for the Treatment of Depression in Adults: Longitudinal Feasibility Study.

BACKGROUND: Approximately two-thirds of patients with major depressive disorder do not achieve remission during their first treatment. There has been increasing interest in the use of digital, artificial intelligence-powered clinical decision support systems (CDSSs) to assist physicians in their treatment selection and management, improving the personalization and use of best practices such as measurement-based care. Previous literature shows that for digital mental health tools to be successful, the tool must be easy for patients and physicians to use and feasible within existing clinical workflows. OBJECTIVE: This study aims to examine the feasibility of an artificial intelligence-powered CDSS, which combines the operationalized 2016 Canadian Network for Mood and Anxiety Treatments guidelines with a neural network-based individualized treatment remission prediction. METHODS: Owing to the COVID-19 pandemic, the study was adapted to be completed entirely remotely. A total of 7 physicians recruited outpatients diagnosed with major depressive disorder according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition criteria. Patients completed a minimum of one visit without the CDSS (baseline) and 2 subsequent visits where the CDSS was used by the physician (visits 1 and 2). The primary outcome of interest was change in appointment length after the introduction of the CDSS as a proxy for feasibility. Feasibility and acceptability data were collected through self-report questionnaires and semistructured interviews. RESULTS: Data were collected between January and November 2020. A total of 17 patients were enrolled in the study; of the 17 patients, 14 (82%) completed the study. There was no significant difference in appointment length between visits (introduction of the tool did not increase appointment length; F2,24=0.805; mean squared error 58.08; P=.46). In total, 92% (12/13) of patients and 71% (5/7) of physicians felt that the tool was easy to use; 62% (8/13) of patients and 71% (5/7) of physicians rated that they trusted the CDSS. Of the 13 patients, 6 (46%) felt that the patient-clinician relationship significantly or somewhat improved, whereas 7 (54%) felt that it did not change. CONCLUSIONS: Our findings confirm that the integration of the tool does not significantly increase appointment length and suggest that the CDSS is easy to use and may have positive effects on the patient-physician relationship for some patients. The CDSS is feasible and ready for effectiveness studies. TRIAL REGISTRATION: ClinicalTrials.gov NCT04061642; http://clinicaltrials.gov/ct2/show/NCT04061642.

SCORE-Based Simulated ABSITE Exam Performance as a Predictor of Performance on the ABSITE.

INTRODUCTION: The American Board of Surgery In-Training Examination (ABSITE) is a crucial, objective assessment of surgical knowledge during training. In 2014, the American Board of Surgery (ABS) announced the alignment of the ABSITE to the SCORE® (Surgical Council on Resident Education) Curriculum Outline for General Surgery Residency. We hypothesized that implementing a pre-ABSITE SCORE-based exam would help identify underperforming residents and provide early guidance to improve performance on the ABSITE. METHODS: In October 2014, our university-based surgical residency program began administering a yearly comprehensive pre-ABSITE SCORE-based exam consisting of 225 to 250 multiple-choice questions selected from the SCORE question bank to all our general surgery residents, preliminary and categorical. The 4-hour exam addresses both clinical management (80%) and applied sciences (20%). Residents receive reports with their scores (percentage correct). Residents performing at less than 60% meet with the Program Director for discussion and formulation of a study plan. Correlational analysis was performed between resident ABSITE scores, pre-ABSITE SCORE-based exam scores, gender, resident status (preliminary vs. categorical), postgraduate year (PGY), and the United States Medical Licensing Examination (USMLE) Step 1 and Step 2 scores. RESULTS: A total of 244 exam scores (122 pre-ABSITE SCORE-based exams and 122 matched ABSITE) were completed by 51 residents at different PGY levels (32 PGY1, 32 PGY2, 20 PGY3, 19 PGY4, and 18 PGY5). Fifty-seven percent were males, 62% were categorical residents, and 38% were preliminary residents. October pre-ABSITE SCORE-based exam scores were compared to the subsequent January ABSITE scores. Categorical residents completed 101 (83%) of the January exams, while preliminary residents completed 21 (17%) of these paired exams. We found strong correlations between the correct percentage on ABSITE and pre-ABSITE SCORE-based scores (r = 0.637, p < 0.001), between the correct percentage on ABSITE and PGY (r = 0.688, p < 0.001), and between ABSITE and resident status (r = 0.462, p < 0.001). Additionally, there was a weak to negligible correlation between the correct percentage on ABSITE and resident gender (r = 0.274, p = 0.001), USMLE-2 (r = 0.12, p = 0.16), and USMLE-1 (r = 0.04, p = 0.653). Multiple regression analysis, with all predictors, was performed to predict the percentage score on the ABSITE and produced R2 0.58, with an adjusted R2 of 0.57, with a large size effect, p < 0.001. After controlling for the other variables, three factors reached statistical significance (p < 0.05): pre-ABSITE SCORE-based exam scores, PGY, and resident gender. CONCLUSION: We found a strong correlation between performance on the pre-ABSITE SCORE-based exam and performance on the ABSITE exam. Surgery residents are encouraged to start studying earlier and to utilize SCORE contents as outlined by the ABS in their study plan.

The relationship of sociodemographic and psychological variables with chronic pain variables in a low-income population.

Chronic pain is a pervasive condition that is complicated by economic, educational, and racial disparities. This study analyzes key factors associated with chronic pain within an understudied and underserved population. The sample is characterized by a triple disparity with respect to income, education/literacy, and racial barriers that substantially increase the vulnerability to the negative consequences of chronic pain. The study examined the pretreatment data of 290 participants enrolled in the Learning About My Pain trial, a randomized controlled comparative effectiveness trial of psychosocial interventions (B.E.T., Principal Investigator, Patient-Centered Outcomes Research Institute Contract No. 941; clinicaltrials.gov identifier NCT01967342) for chronic pain. Hierarchical multiple regression analyses evaluated the relationships among sociodemographic (sex, age, race, poverty status, literacy, and education level) and psychological (depressive symptoms and pain catastrophizing) variables and pain interference, pain severity, and disability. The indirect effects of depressive symptoms and pain catastrophizing on the sociodemographic and pain variables were investigated using bootstrap resampling. Reversed mediation models were also examined. Results suggested that the experience of chronic pain within this low-income sample is better accounted for by psychological factors than sex, age, race, poverty status, literacy, and education level. Depressive symptoms and pain catastrophizing mediated the relationships between age and pain variables, whereas pain catastrophizing mediated the effects of primary literacy and poverty status. Some reversed models were equivalent to the hypothesized models, suggesting the possibility of bidirectionality. Although cross-sectional findings cannot establish causality, our results highlight the critical role psychological factors play in individuals with chronic pain and multiple health disparities.