Comparative analysis of traditional machine learning and automated machine learning: advancing inverted papilloma versus associated squamous cell carcinoma diagnosis

Farideh Hosseinzadeh; S Saeed Mohammadi; James N Palmer; Michael A Kohanski; Nithin D Adappa; Michael T Chang; Peter H Hwang; Jayakar V Nayak; Zara M Patel

doi:10.1002/alr.23438

Comparative analysis of traditional machine learning and automated machine learning: advancing inverted papilloma versus associated squamous cell carcinoma diagnosis

Int Forum Allergy Rhinol. 2024 Dec;14(12):1957-1960. doi: 10.1002/alr.23438. Epub 2024 Aug 26.

Authors

Farideh Hosseinzadeh¹, S Saeed Mohammadi², James N Palmer³, Michael A Kohanski³, Nithin D Adappa³, Michael T Chang¹, Peter H Hwang¹, Jayakar V Nayak¹, Zara M Patel¹

Affiliations

¹ Department of Otolaryngology-Head & Neck Surgery, Stanford University School of Medicine, Stanford, California, USA.
² Byers Eye Institute, Department of Ophthalmology, Stanford University, Palo Alto, California, USA.
³ University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA.

PMID: 39186252
DOI: 10.1002/alr.23438

Abstract

Inverted papilloma conversion to squamous cell carcinoma is not always easy to predict. AutoML requires much less technical knowledge and skill to use than traditional ML. AutoML surpassed the traditional ML algorithm in differentiating IP from IP-SCC.

Keywords: artificial intelligence; deep learning; generative pretrained transformer; image classification; inverted papilloma; machine learning; sinonasal cancer; sinus cancer; sinus malignancy; sinus tumor.

Publication types

Comparative Study

MeSH terms

Algorithms
Carcinoma, Squamous Cell* / diagnosis
Carcinoma, Squamous Cell* / pathology
Diagnosis, Differential
Female
Humans
Machine Learning*
Male
Papilloma, Inverted* / diagnosis
Papilloma, Inverted* / pathology