A multi-institutional machine learning algorithm for prognosticating facial nerve injury following microsurgical resection of vestibular schwannoma.

Vestibular schwannomas (VS) are the most common tumor of the skull base with available treatment options that carry a risk of iatrogenic injury to the facial nerve, which can significantly impact patients' quality of life. As facial nerve outcomes remain challenging to prognosticate, we endeavored to utilize machine learning to decipher predictive factors relevant to facial nerve outcomes following microsurgical resection of VS. A database of patient-, tumor- and surgery-specific features was constructed via retrospective chart review of 242 consecutive patients who underwent microsurgical resection of VS over a 7-year study period. This database was then used to train non-linear supervised machine learning classifiers to predict facial nerve preservation, defined as House-Brackmann (HB) I vs. facial nerve injury, defined as HB II-VI, as determined at 6-month outpatient follow-up. A random forest algorithm demonstrated 90.5% accuracy, 90% sensitivity and 90% specificity in facial nerve injury prognostication. A random variable (rv) was generated by randomly sampling a Gaussian distribution and used as a benchmark to compare the predictiveness of other features. This analysis revealed age, body mass index (BMI), case length and the tumor dimension representing tumor growth towards the brainstem as prognosticators of facial nerve injury. When validated via prospective assessment of facial nerve injury risk, this model demonstrated 84% accuracy. Here, we describe the development of a machine learning algorithm to predict the likelihood of facial nerve injury following microsurgical resection of VS. In addition to serving as a clinically applicable tool, this highlights the potential of machine learning to reveal non-linear relationships between variables which may have clinical value in prognostication of outcomes for high-risk surgical procedures.

Atypical Schwannoma: A 10-year experience.

OBJECTIVE: The goal of this study was to describe the clinical presentation associated with atypical schwannoma of the cerebellopontine angle, characterize the pathologic findings and describe the long-term outcome. MATERIALS AND METHODS: The study design was retrospective case review of patients with the histopathologic diagnosis of atypical and benign schwannoma of the cerebellopontine angle diagnosed at the study institution over a 10-year period. SETTING: Tertiary referral center. MAIN OUTCOMES MEASURE: Demographic data of the cohort were recorded. Findings on pathology were evaluated. Initial treatment and post-operative course was recorded. Main outcome measures were clinical presentation, including cranial nerve deficits at the time of presentation, complication and recurrence rates. RESULTS: At presentation, a somewhat accelerated course of cranial nerve deficit was noted among patients with atypical schwannoma as compared to benign schwannoma. In the immediate post-operative period, there were no differences noted in the complication rate. Atypical schwannomas appear to have higher recurrence rate compared to benign schwannomas. CONCLUSIONS: Atypical schwannoma is an intermediate disease process with an accelerated clinical course and higher recurrence rate as compared to vestibular schwannoma. Traditional operative approaches may be employed without increased concern for post-operative complications. Thorough counseling and close follow-up should be offered to these patients given the higher recurrence rate. Larger studies are required to determine if these patients need more frequent MRIs for long-term surveillance.

MHC class II epitope nesting modulates dendritic cell function and improves generation of antigen-specific CD4 helper T cells.

CD4 Th cells are critical to the development of coordinated immune responses to infections and tumors. Th cells are activated through interactions of the TCR with MHC class II complexed with peptide. T cell activation is dependent on the density of MHC peptide complexes as well as the duration of interaction of the TCR with APCs. In this study, we sought to determine whether MHC class II peptides could be modified with amino acid sequences that facilitated uptake and presentation with the goal of improving Th cell activation in vitro and in vivo. A model epitope derived from the murine folate receptor α, a self- and tumor Ag, was modified at its carboxyl terminus with the invariant chain-derived Ii-Key peptide and at its N terminus with a peptide that enhances uptake of Ag by APC. Modification of a peptide resulted in enhanced generation of high-avidity murine folate receptor α T cells that persisted in vivo and homed to sites of Ag deposition. The nesting approach was epitope and species independent and specifically excluded expansion of CD4 regulatory T cells. The resulting Th cells were therapeutic, enhanced in vivo helper activity and had an increased ability to resist tolerizing immune microenvironments. In addition to improved immunoadjuvants, this epitope modification strategy may be useful for enhancing ex vivo and in vivo generation of Th cells for preventing and treating diseases.