Advances in Artificial Intelligence to Diagnose Otitis Media: State of the Art Review.

OBJECTIVE: Otitis media (OM) is a model disease for developing, validating, and implementing artificial intelligence (AI) techniques. We aim to review the state of the art applications of AI used to diagnose OM in pediatric and adult populations. DATA SOURCES: Several comprehensive databases were searched to identify all articles that applied AI technologies to diagnose OM. REVIEW METHODS: Relevant articles from January 2010 through May 2021 were identified by title and abstract. Articles were excluded if they did not discuss AI in conjunction with diagnosing OM. References of included studies and relevant review articles were cross-referenced to identify any additional studies. CONCLUSION: Title and abstract screening resulted in full-text retrieval of 40 articles that met initial screening parameters. Of this total, secondary review articles (n = 7) and commentary-based articles (n = 2) were removed, as were articles that did not specifically discuss AI and OM diagnosis (n = 5), leaving 25 articles for review. Applications of AI technologies specific to diagnosing OM included machine learning and natural language processing (n = 23) and prototype approaches (n = 2). IMPLICATIONS FOR PRACTICE: This review emphasizes the utility of AI techniques to automate and aid in diagnosing OM. Although these techniques are still in the development and testing stages, AI has the potential to improve the practice of otolaryngologists and primary care clinicians by increasing the efficiency and accuracy of diagnoses.

Development of a novel screening tool for predicting Cochlear implant candidacy.

OBJECTIVES: Cochlear implantation (CI) is a well-established treatment for sensorineural hearing loss. Due in part to a lack of referral guidelines, CI technology remains underutilized, and many patients who could benefit from CI may not be referred for evaluation. This study aimed to develop a model for predicting CI candidacy using routine audiometric measures, with the goal of providing guidance to clinicians regarding when to refer a patient for CI evaluation. METHODS: Unaided three-frequency pure tone average (PTA), unaided speech discrimination score (SDS), and best-aided sentence recognition testing with AZBio sentence lists were collected from 252 subjects undergoing CIE. Candidacy was defined by meeting traditional (AZBio score ≤ 60%), or Medicare criteria (≤40%). A logistic regression model was developed to predict candidacy. Confusion matrices were plotted to determine the sensitivity and specificity at various probability thresholds. RESULTS: Logistic regression models were capable of predicting probability of candidacy for traditional criteria (P < .001) and Medicare criteria (P < .001). PTA and SDS were significant predictors (P < .001). Using a probability cutoff of .5, the models yielded a sensitivity rate of 91% and 78% for traditional and Medicare criteria, respectively. CONCLUSION: Probability of CI candidacy may be determined using a novel screening tool for referral. This tool supports individualized counseling, serves as a proof of concept for candidacy prediction, and could be modified based on an institution's philosophy regarding an acceptable false positive rate of referral. LEVEL OF EVIDENCE: 4.

Endoscopic transorbital ligation of the maxillary artery through the inferior orbital fissure.

OBJECTIVE: Determine the feasibility of accessing the internal maxillary artery (IMA) through a transorbital endoscopic assisted approach through the inferior orbital fissure (IOF). MATERIALS AND METHODS: Six adult cadaveric specimens were injected intravascularly with colored latex and dissected on 12 sides. A transorbital endoscopic approach was used to expose the IOF and reach the IMA. RESULTS: The average length and width of the anterolateral segment of the IOF were 7.3 and 4 mm, respectively, on the right side and 6.7 and 3.8 mm, respectively, on the left side. Surgical exposure and modification of the IOF allowed the exposure and control of the IMA in all 12 sides. CONCLUSIONS: The IOF is a feasible portal to the IMA. The benefits of this approach include vascular control of the distal segment of the maxillary artery. It may provide access in clinical scenarios where endonasal access is not possible (e.g., extensive tumors) or serve as an alternative or complementary surgical route (e.g., control during a total or radical maxillectomy).

The "Frankentower:" A clinician-driven approach to enhancing endoscopic data technology.

OBJECTIVE: To develop a more efficient endoscopy tower and evaluate its capability to improve retrieval and storage of videos across 6 clinical sites. METHODS: Descriptive study that took place at tertiary care Pediatric Otolaryngology Department over a 2 year period. In collaboration with our Information Services Department and Otolaryngology endoscopy vendors, we assembled our "Frankentower" endoscopy cart using components from 3 medical device manufacturers. RESULTS: It is feasible to create a functional composite endoscopic tower. Implementation of "Frankentower" improved overall management and retrieval of endoscopy video and images in our department which lead to better patient care and facilitated education for medical students, residents and faculty. CONCLUSIONS: The "Frankentower" is a feasible, cost-effective solution to streamline the capture, access and storage of patient endoscopy exams across our operating rooms, inpatient consult service, Emergency Department and outpatient clinics.

Comparison of Opioid Prescription Patterns and Consumption Following Otologic Surgery.

OBJECTIVE: To examine opioid prescribing patterns and consumption among patients undergoing common otologic surgeries. STUDY DESIGN: Retrospective cohort study with chart review and telephone survey. SETTING: Tertiary academic medical center. METHODS: Retrospective chart review and telephone survey of those undergoing tympanoplasty, tympanomastoidectomy, stapedectomy, and cochlear implantation in 2018. The survey consisted of questions regarding the details of the number of pills taken, duration of opioid use, subjective pain control, the use of over-the-counter pain medications, opioid disposal, and their history of substance abuse. RESULTS: Sixty-one patients were able to be contacted and agreed to participate in the study. Fifty-nine (96.7%) stated that their pain was controlled, and 10 (16.4%) did not take any opioids postoperatively despite their prescription. The mean morphine milligram equivalent (MME) prescribed was 99.9 (44.3) and MME taken was 45.2 (SD 46.3) (p < 0.001). Similarly, the mean number of pills prescribed was 17.8 (SD 8.6) and mean taken was 7.9 (SD 8.3) (p < 0.001). Comparison between males and females regarding MME and pills prescribed and taken were not statistically significantly different (p > 0.05). Analysis of the MME and pills prescribed and taken among the different surgeries (tympanoplasty, stapes surgery, tympanomastoidectomy, and cochlear implantation) revealed no statistically significant interactions (p > 0.05). Pain control was achieved for 50% of patients with 5 pills (MME = 25 mg), for 75% with 12 pills (MME = 60 mg), and for 90% with 24 pills (MME = 135 mg). CONCLUSION: The opioid epidemic continues to be an ongoing issue in the United States, and prescription opioid abuse is a large contributor. There is increasing literature to suggest a practice of overprescribing in multiple surgical specialties. This same finding appears to be present in common otologic surgeries, where on average patients took less than half of the prescribed MME/pills, and 75% of patients had their pain controlled with 12 pills or fewer. Otolaryngologists performing otologic surgery should strongly consider adjusting their postoperative regimens to reflect these findings. LEVEL OF EVIDENCE: 2b.