2 results
106 Neurosurgery Resident Feedback through Artificial-Intelligence
- Part of
- Jose Luis Porras, Roger Soberanis-Mukul, S. Swaroop Vedula, Judy Huang, Henry Brem, Gary L. Gallia, Mathias Unberath, Masaru Ishii
-
- Journal:
- Journal of Clinical and Translational Science / Volume 7 / Issue s1 / April 2023
- Published online by Cambridge University Press:
- 24 April 2023, p. 31
-
- Article
-
- You have access Access
- Open access
- Export citation
-
OBJECTIVES/GOALS: Surgical training is constrained by duty hour limits, bias, and a trial-and-error learning process. Surgeon skill variation is a healthcare system disparity that can impact patient outcomes. Incorporating validated, standardized assessment tools and machine learning (ML) algorithms may help to standardize and reduce bias in surgeon education. METHODS/STUDY POPULATION: To support assessment tool and ML algorithm development, we are curating an annotated video registry of neurosurgical procedures. Point-of-view video of resident and attending neurosurgeons performing craniotomies is recorded via an eye-tracking headset. A Delphi panel of neurosurgeons will review the video and determine which represent expert versus trainee performance. Neurosurgery attendings will be interviewed to provide descriptions of craniotomies which will be used to develop an assessment rubric. A Delphi panel will determine what rubric components should be maintained. New craniotomy videos will be viewed by attendings in a blinded fashion while completing the assessment rubric. An online feedback platform is being developed allowing residents to prospectively track assessment data. RESULTS/ANTICIPATED RESULTS: We anticipate development of an annotated, institutional video database featuring craniotomies performed by residents and attending neurosurgeons. Using a Delphi approach, we anticipate achieving consensus on which videos reflect expert versus trainee performance. We anticipate development of a novel craniotomy assessment rubric that is both valid and reliable. Our online feedback platform will allow prospective tracking of assessment data from multiple sources and enhanced transparency in the feedback process. The video registry and assessment data will enable development of novel ML algorithms able to recognize craniotomy segments and estimate operator skill. DISCUSSION/SIGNIFICANCE: Building a video registry of procedures, validated assessment tools, and a prototype feedback platform enables a pipeline for ML algorithm development. Together these tools will help to standardize and optimize resident education translating to earlier operative independence, improved patient safety, and reduced bias during surgical training.
87 - Primary brain tumours in adults
- from PART XI - NEOPLASTIC DISORDERS
-
- By John Laterra, Department of Neurology, Johns Hopkins Medical Institutions, Baltimore, MD, USA, Henry Brem, Department of Neurosurgery, Johns Hopkins Medical Institutions, Baltimore, MD, USA
- Edited by Arthur K. Asbury, University of Pennsylvania School of Medicine, Guy M. McKhann, The Johns Hopkins University School of Medicine, W. Ian McDonald, University College London, Peter J. Goadsby, University College London, Justin C. McArthur, The Johns Hopkins University School of Medicine
-
- Book:
- Diseases of the Nervous System
- Published online:
- 05 August 2016
- Print publication:
- 11 November 2002, pp 1431-1447
-
- Chapter
- Export citation
-
Summary
Approximately 29000 primary benign and malignant central nervous system tumours are diagnosed in the United States each year (CBTRUS, 1998). Histological diagnosis, location, biological tendency to infiltrate into surrounding brain, surgical resectability, and patient age at diagnosis are strong determinants of their associated morbidity and mortality. Although primary brain tumours are generally resistant to cytotoxic therapies, recent advances in chemotherapy, radiation therapy, and drug delivery in conjunction with more novel therapeutics based upon molecular and cellular biological mechanisms have created new opportunities for prolonging life and preserving the quality of life for brain tumour patients. Even though primary tumours occur infrequently (less than 2%) relative to more common systemic neoplasms such as breast, lung and prostate, they contribute substantially to cancer morbidity because they present at early- to midadult life and can rapidly cause neurological disability.
The World Health Organization (WHO) has established a histopathological classification system that divides primary brain tumours into nine separate categories on the basis of routine histochemical and immunohistochemical criteria intended to identify the cell of tumour origin (Table 87.1) (Kleihues et al., 1993). This classification scheme is a standard for pathological diagnosis and clinical decision making. It is generally recognized that all classification schemes available to date have many limitations and need to incorporate molecular and genetic criteria that reflect cellular origins and distinct pathways of transformation. The WHO category of Tumours derived from neuroepithelial tissue consists of nine subcategories that include the most common glial tumours: astrocytoma, oligodendroglioma, ependymoma, and mixed glioma. In adults, gliomas represent the largest proportion of primary brain tumours, accounting for approximately 50% of the total. Meningiomas are the next most common comprising approximately 20–25%, followed by pituitary adenomas, nerve sheath tumours and primary CNS lymphoma that each represent less than 10% of all primary brain tumours (CBTRUS, 1998). A brief summary of the most common gliomas and meningiomas follows. A more comprehensive and detailed description of primary brain tumours can be found in Tumors of the Central Nervous System(Burger & Scheithauer, 1994).
Astrocytomas
Astrocytomas are the most common of the gliomas. These tumours have a predilection for the cerebral hemispheres and occur in a range of aggressiveness or tumour ‘grade’ that, along with patient age at diagnosis, strongly predicts the tumour's biological behaviour and patient survival (Figs. 87.1 and 87.2).