Optimizing resource utilization during proficiency-based training of suturing skills in medical students: a randomized controlled trial of faculty-led, peer tutor-led, and holography-augmented methods of teaching.

BACKGROUND: Suturing is a fundamental skill in undergraduate medical education. It can be taught by faculty-led, peer tutor-led, and holography-augmented methods; however, the most educationally effective and cost-efficient method for proficiency-based teaching of suturing is yet to be determined. METHODS: We conducted a randomized controlled trial comparing faculty-led, peer tutor-led, and holography-augmented proficiency-based suturing training in pre-clerkship medical students. Holography-augmented training provided holographic, voice-controlled instructional material. Technical skill was assessed using hand motion analysis every ten sutures and used to construct learning curves. Proficiency was defined by one standard deviation within average faculty surgeon performance. Intervention arms were compared using one-way ANOVA of the number of sutures placed, full-length sutures used, time to proficiency, and incremental costs incurred. Surveys were used to evaluate participant preferences. RESULTS: Forty-four students were randomized to the faculty-led (n = 16), peer tutor-led (n = 14), and holography-augmented (n = 14) intervention arms. At proficiency, there were no differences between groups in the number of sutures placed, full-length sutures used, and time to achieve proficiency. The incremental costs of the holography-augmented method were greater than faculty-led and peer tutor-led instruction ($247.00 ± $12.05, p < 0.001) due to the high cost of the equipment. Faculty-led teaching was the most preferred method (78.0%), while holography-augmented was the least preferred (0%). 90.6% of students reported high confidence in performing simple interrupted sutures, which did not differ between intervention arms (faculty-led 100.0%, peer tutor-led 90.0%, holography-augmented 83.3%, p = 0.409). 93.8% of students felt the program should be offered in the future. CONCLUSION: Faculty-led and peer tutor-led instructional methods of proficiency-based suturing teaching were superior to holography-augmented method with respect to costs and participants' preferences despite being educationally equivalent.

Length of Stay Prediction Models for Oral Cancer Surgery: Machine Learning, Statistical and ACS-NSQIP.

OBJECTIVE: Accurate prediction of hospital length of stay (LOS) following surgical management of oral cavity cancer (OCC) may be associated with improved patient counseling, hospital resource utilization and cost. The objective of this study was to compare the performance of statistical models, a machine learning (ML) model, and The American College of Surgeons National Surgical Quality Improvement Program's (ACS-NSQIP) calculator in predicting LOS following surgery for OCC. MATERIALS AND METHODS: A retrospective multicenter database study was performed at two major academic head and neck cancer centers. Patients with OCC who underwent major free flap reconstructive surgery between January 2008 and June 2019 surgery were selected. Data were pooled and split into training and validation datasets. Statistical and ML models were developed, and performance was evaluated by comparing predicted and actual LOS using correlation coefficient values and percent accuracy. RESULTS: Totally 837 patients were selected with mean patient age being 62.5 ± 11.7 [SD] years and 67% being male. The ML model demonstrated the best accuracy (validation correlation 0.48, 4-day accuracy 70%), compared with the statistical models: multivariate analysis (0.45, 67%) and least absolute shrinkage and selection operator (0.42, 70%). All were superior to the ACS-NSQIP calculator's performance (0.23, 59%). CONCLUSION: We developed statistical and ML models that predicted LOS following major free flap reconstructive surgery for OCC. Our models demonstrated superior predictive performance to the ACS-NSQIP calculator. The ML model identified several novel predictors of LOS. These models must be validated in other institutions before being used in clinical practice. LEVEL OF EVIDENCE: 3 Laryngoscope, 134:3664-3672, 2024.