RESUMO
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.
Assuntos
Traumatismos do Nervo Facial , Aprendizado de Máquina , Microcirurgia , Neuroma Acústico , Humanos , Neuroma Acústico/cirurgia , Masculino , Feminino , Pessoa de Meia-Idade , Microcirurgia/efeitos adversos , Microcirurgia/métodos , Prognóstico , Traumatismos do Nervo Facial/etiologia , Estudos Retrospectivos , Adulto , Idoso , AlgoritmosRESUMO
OBJECTIVE: To offer pragmatic, evidence-informed advice on administering corticosteroids in otolaryngology during the coronavirus disease 2019 (COVID-19) pandemic, considering therapeutic efficacy, potential adverse effects, susceptibility to COVID-19, and potential effects on efficacy of vaccination against SARS-CoV-2, which causes COVID-19. DATA SOURCES: PubMed, Cochrane Library, EMBASE, CINAHL, and guideline databases. REVIEW METHODS: Guideline search strategies, supplemented by database searches on sudden sensorineural hearing loss (SSNHL), idiopathic facial nerve paralysis (Bell's palsy), sinonasal polyposis, laryngotracheal disorders, head and neck oncology, and pediatric otolaryngology, prioritizing systematic reviews, randomized controlled trials, and COVID-19-specific findings. CONCLUSIONS: Systemic corticosteroids (SCSs) reduce long-term morbidity in individuals with SSNHL and Bell's palsy, reduce acute laryngotracheal edema, and have benefit in perioperative management for some procedures. Topical or locally injected corticosteroids are preferable for most other otolaryngologic indications. SCSs have not shown long-term benefit for sinonasal disorders. SCSs are not a contraindication to vaccination with COVID-19 vaccines approved by the US Food and Drug Administration. The Centers for Disease Control and Prevention noted that these vaccines are safe for immunocompromised patients. IMPLICATIONS FOR PRACTICE: SCS use for SSNHL, Bell's palsy, laryngotracheal edema, and perioperative care should follow prepandemic standards. Local or topical corticosteroids are preferable for most other otolaryngologic indications. Whether SCSs attenuate response to vaccination against COVID-19 or increase susceptibility to SARS-CoV-2 infection is unknown. Immunosuppression may lower vaccine efficacy, so immunocompromised patients should adhere to recommended infection control practices. COVID-19 vaccination with Pfizer-BioNTech, Moderna, or Johnson & Johnson vaccines is safe for immunocompromised patients.
Assuntos
Paralisia de Bell , COVID-19 , Paralisia Facial , Otolaringologia , Criança , Humanos , Paralisia de Bell/tratamento farmacológico , Vacinas contra COVID-19 , SARS-CoV-2 , Otolaringologia/métodosRESUMO
BACKGROUND AND SIGNIFICANCE: There is a high and growing prevalence of age-related hearing loss (ARHL), defined as presbycusis or bilateral, symmetric sensorineural hearing loss in older adults. Due to the increasing prevalence of ARHL, the potential delays in its diagnosis and treatment, and the significant disability associated with ARHL, the American Academy of Otolaryngology-Head and Neck Surgery Foundation (AAO-HNSF) convened a Measures Development Group (MDG) to develop quality measures (QMs) of clinical practice that could be incorporated into the AAO-HNSF's data registry Reg-ent. Although the AAO-HNSF has been engaged in robust clinical practice guideline development since 2006, the development of quality and performance measures is more recent. METHODS: We report the process, experience, and outcomes in developing a de novo QM set for ARHL in the absence of a preexisting clinical practice guideline on this topic. Steps include the MDG review of evidentiary literature on ARHL, followed by stakeholder discussions to develop measure specifications. Key considerations included discussion on the relative importance, usability, and feasibility of each measure within the Reg-ent or similar databases. RESULTS: The MDG created 4 QMs for the diagnosis and treatment of AHRL. These measures represent the AAO-HNSF's quality initiatives to develop evidence-based QMs and improve patient care and outcomes, and they are intended to assist providers in enhancing quality of care. CONCLUSION: Development of the ARHL measures is intended for clinicians to evaluate the patient perception, structure, process, and outcomes of care. This process represents a new stage in the AAO-HNSF's measure development efforts to facilitate future efforts in evidence-based QM.