A systematic review of annotation for surgical process model analysis in minimally invasive surgery based on video.

BACKGROUND: Annotated data are foundational to applications of supervised machine learning. However, there seems to be a lack of common language used in the field of surgical data science. The aim of this study is to review the process of annotation and semantics used in the creation of SPM for minimally invasive surgery videos. METHODS: For this systematic review, we reviewed articles indexed in the MEDLINE database from January 2000 until March 2022. We selected articles using surgical video annotations to describe a surgical process model in the field of minimally invasive surgery. We excluded studies focusing on instrument detection or recognition of anatomical areas only. The risk of bias was evaluated with the Newcastle Ottawa Quality assessment tool. Data from the studies were visually presented in table using the SPIDER tool. RESULTS: Of the 2806 articles identified, 34 were selected for review. Twenty-two were in the field of digestive surgery, six in ophthalmologic surgery only, one in neurosurgery, three in gynecologic surgery, and two in mixed fields. Thirty-one studies (88.2%) were dedicated to phase, step, or action recognition and mainly relied on a very simple formalization (29, 85.2%). Clinical information in the datasets was lacking for studies using available public datasets. The process of annotation for surgical process model was lacking and poorly described, and description of the surgical procedures was highly variable between studies. CONCLUSION: Surgical video annotation lacks a rigorous and reproducible framework. This leads to difficulties in sharing videos between institutions and hospitals because of the different languages used. There is a need to develop and use common ontology to improve libraries of annotated surgical videos.

Risk factors associated with the surgical management of craniopharyngiomas in pediatric patients: analysis of 1961 patients from a national registry database.

OBJECTIVE Patient demographic characteristics, hospital volume, and admission status have been shown to impact surgical outcomes of sellar region tumors in adults; however, the data available following the resection of craniopharyngiomas in the pediatric population remain limited. The authors sought to identify potential risk factors associated with outcomes following surgical management of pediatric craniopharyngiomas. METHODS The Nationwide Inpatient Sample database and Kids' Inpatient Database were analyzed to include admissions for pediatric patients (≤ 18 years) who underwent a transcranial or transsphenoidal craniotomy for resection of a craniopharyngioma. Patient-level factors, including age, race, comorbidities, and insurance type, as well as hospital factors were collected. Outcomes analyzed included mortality rate, endocrine and nonendocrine complications, hospital charges, and length of stay. A multivariate model controlling for variables analyzed was constructed to examine significant independent risk factors. RESULTS Between 2000 and 2011, 1961 pediatric patients were identified who underwent a transcranial (71.2%) or a transsphenoidal (28.8%) craniotomy for resection of a craniopharyngioma. A major predilection for age was observed with the selection of a transcranial (23.4% in < 7-year-olds, 28.1% in 7- to 12-year-olds, and 19.7% in 13- to 18-year-olds) versus transphenoidal (2.9% in < 7-year-olds, 7.4% in 7- to 12-year-olds, and 18.4% in 13- to 18-year-olds) approach. No significant outcomes were associated with a particular surgical approach, except that 7- to 12-year-old patients had a higher risk of nonendocrine complications (relative risk [RR] 2.42, 95% CI 1.04-5.65, p = 0.04) with the transsphenoidal approach when compared with 13- to 18-year-old patients. The overall inpatient mortality rate was 0.5% and the most common postoperative complication was diabetes insipidus (64.2%). There were no independent factors associated with inpatient mortality rates and no significant differences in outcomes among groups based on sex and race. The average length of stay was 11.8 days, and the mean hospital charge was $116,5 22. Hospitals with medium and large bed capacity were protective against nonendocrine complications (RR 0.53, 95% CI 0.3-0.93, p = 0.03 [medium]; RR 0.45, 95% CI 0.25-0.8, p < 0.01 [large]) and total complications (RR 0.73, 95% CI 0.55-0.97, p = 0.03 [medium]; RR 0.68, 95% CI 0.51-0.9, p < 0.01 [large]) when compared with hospitals with small bed capacity (< 200 beds). Patients admitted to rural hospitals had an increased risk for nonendocrine complications (RR 2.56, 95% CI 1.11-5.9, p = 0.03). The presence of one or more medical comorbidities increased the risk of higher total complications (RR 1.38, 95% CI 1.14-1.68), p < 0.01 [1 comorbidity]; RR 2.37, 95% CI 1.98-2.84, p < 0.01 [≥ 2 comorbidities]) and higher total hospital charges (RR 2.9, 95% CI 1.08-7.81, p = 0.04 [1 comorbidity]; RR 9.1, 95% CI 3.74-22.12, p < 0.01 [≥ 2 comorbidities]). CONCLUSIONS This analysis identified patient age, comorbidities, insurance type, hospital bed capacity, and rural or nonteaching hospital status as independent risk factors for postoperative complications and/or increased hospital charges in pediatric patients with craniopharyngioma. Transsphenoidal surgery in younger patients with craniopharyngioma was a risk factor for nonendocrine complications.