Sinonasal inverted papilloma (IP) is at risk of recurrence and malignancy, and early diagnosis using nasal endoscopy is essential. We thus developed a diagnostic system using artificial intelligence (AI) to identify nasal sinus papilloma. Endoscopic surgery videos of 53 patients undergoing endoscopic sinus surgery were edited to train and evaluate deep neural network models and then a diagnostic system was developed. The correct diagnosis rate based on visual examination by otolaryngologists was also evaluated using the same videos and compared with that of the AI diagnostic system patients. Main outcomes evaluated included the percentage of correct diagnosis compared to AI diagnosis and the correct diagnosis rate for otolaryngologist based on years of practice experience. The diagnostic system had an area under the curve of 0.874, accuracy of 0.843, false positive rate of 0.124, and false negative rate of 0.191. The average correct diagnosis rate among otolaryngologists was 69.4%, indicating that the AI was highly accurate. Evidently, although the number of cases was small, a highly accurate diagnostic system was created. Future studies with a larger sample size to improve the accuracy of the system and expand the range of diseases that can be detected for more clinical applications are warranted.

No abstract

Sinonasal inverted papilloma (IP) is at risk of recurrence and malignancy, and early diagnosis using nasal endoscopy is essential. We thus developed a diagnostic system using artificial intelligence (AI) to identify nasal sinus papilloma. Endoscopic surgery videos of 53 patients undergoing endoscopic sinus surgery were edited to train and evaluate deep neural network models and then a diagnostic system was developed. The correct diagnosis rate based on visual examination by otolaryngologists was also evaluated using the same videos and compared with that of the AI diagnostic system patients. Main outcomes evaluated included the percentage of correct diagnoses compared to AI diagnosis and the correct diagnosis rate for otolaryngologists based on years of practice experience. The diagnostic system had an area under the curve of 0.874, accuracy of 0.843, false positive rate of 0.124, and false negative rate of 0.191. The average correct diagnosis rate among otolaryngologists was 69.4%, indicating that the AI was highly accurate. Evidently, although the number of cases was small, a highly accurate diagnostic system was created. Future studies with larger samples to improve the accuracy of the system and expand the range of diseases that can be detected for more clinical applications are warranted.

Background: Olfaction plays an important role in our daily and social lives, both as adults and as children. This study assessed whether the ability to identify odours increases with age, as well as the ability in various age groups and the factors involved. Methods: The survey was performed in 2017 on 697 Japanese children (366 girls and 331 boys) aged 6–18 years who lived in Tsunan, Niigata Prefecture, Japan by using the ‘Open Essence’, a card-type odour identification test. We collected information regarding age, sex, and physical characteristic. We also inquired whether participants had siblings or if members of the family smoked, and whether they had conversations about odour at home. Statistical analysis was performed to evaluate the factors affecting odour identification abilities. Results: The results showed that the odour identification abilities of children increase with age, and children who have daily conversations about odours at home have better odour identification abilities. Conclusions: Odour identification ability increases with age. In addition, our findings suggest that conversation may positively affect odour identification. Hence, it is important for children to be exposed to an environment where they develop an interest in smells for better growth of their olfactory identification ability.