1
|
Shaikh N, Conway SJ, Kovačević J, Condessa F, Shope TR, Haralam MA, Campese C, Lee MC, Larsson T, Cavdar Z, Hoberman A. Development and Validation of an Automated Classifier to Diagnose Acute Otitis Media in Children. JAMA Pediatr 2024; 178:401-407. [PMID: 38436941 PMCID: PMC10985552 DOI: 10.1001/jamapediatrics.2024.0011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Accepted: 11/17/2023] [Indexed: 03/05/2024]
Abstract
Importance Acute otitis media (AOM) is a frequently diagnosed illness in children, yet the accuracy of diagnosis has been consistently low. Multiple neural networks have been developed to recognize the presence of AOM with limited clinical application. Objective To develop and internally validate an artificial intelligence decision-support tool to interpret videos of the tympanic membrane and enhance accuracy in the diagnosis of AOM. Design, Setting, and Participants This diagnostic study analyzed otoscopic videos of the tympanic membrane captured using a smartphone during outpatient clinic visits at 2 sites in Pennsylvania between 2018 and 2023. Eligible participants included children who presented for sick visits or wellness visits. Exposure Otoscopic examination. Main Outcomes and Measures Using the otoscopic videos that were annotated by validated otoscopists, a deep residual-recurrent neural network was trained to predict both features of the tympanic membrane and the diagnosis of AOM vs no AOM. The accuracy of this network was compared with a second network trained using a decision tree approach. A noise quality filter was also trained to prompt users that the video segment acquired may not be adequate for diagnostic purposes. Results Using 1151 videos from 635 children (majority younger than 3 years of age), the deep residual-recurrent neural network had almost identical diagnostic accuracy as the decision tree network. The finalized deep residual-recurrent neural network algorithm classified tympanic membrane videos into AOM vs no AOM categories with a sensitivity of 93.8% (95% CI, 92.6%-95.0%) and specificity of 93.5% (95% CI, 92.8%-94.3%) and the decision tree model had a sensitivity of 93.7% (95% CI, 92.4%-94.9%) and specificity of 93.3% (92.5%-94.1%). Of the tympanic membrane features outputted, bulging of the TM most closely aligned with the predicted diagnosis; bulging was present in 230 of 230 cases (100%) in which the diagnosis was predicted to be AOM in the test set. Conclusions and Relevance These findings suggest that given its high accuracy, the algorithm and medical-grade application that facilitates image acquisition and quality filtering could reasonably be used in primary care or acute care settings to aid with automated diagnosis of AOM and decisions regarding treatment.
Collapse
Affiliation(s)
- Nader Shaikh
- Department of Pediatrics, Division of General Academic Pediatrics, University of Pittsburgh School of Medicine, University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh, Pennsylvania
| | - Shannon J. Conway
- Department of Pediatrics, Division of General Academic Pediatrics, University of Pittsburgh School of Medicine, University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh, Pennsylvania
| | - Jelena Kovačević
- Tandon School of Engineering, New York University, New York, New York
| | - Filipe Condessa
- Bosch Center for Artificial Intelligence, Pittsburgh, Pennsylvania
| | - Timothy R. Shope
- Department of Pediatrics, Division of General Academic Pediatrics, University of Pittsburgh School of Medicine, University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh, Pennsylvania
| | - Mary Ann Haralam
- Department of Pediatrics, Division of General Academic Pediatrics, University of Pittsburgh School of Medicine, University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh, Pennsylvania
| | - Catherine Campese
- Department of Pediatrics, Division of General Academic Pediatrics, University of Pittsburgh School of Medicine, University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh, Pennsylvania
| | - Matthew C. Lee
- Department of Pediatrics, Division of General Academic Pediatrics, University of Pittsburgh School of Medicine, University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh, Pennsylvania
| | | | | | - Alejandro Hoberman
- Department of Pediatrics, Division of General Academic Pediatrics, University of Pittsburgh School of Medicine, University of Pittsburgh Medical Center Children’s Hospital of Pittsburgh, Pennsylvania
| |
Collapse
|
2
|
Byun H, Lee SH, Kim TH, Oh J, Chung JH. Feasibility of the Machine Learning Network to Diagnose Tympanic Membrane Lesions without Coding Experience. J Pers Med 2022; 12:jpm12111855. [PMID: 36579584 PMCID: PMC9697619 DOI: 10.3390/jpm12111855] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 09/29/2022] [Accepted: 10/31/2022] [Indexed: 11/10/2022] Open
Abstract
A machine learning platform operated without coding knowledge (Teachable machine®) has been introduced. The aims of the present study were to assess the performance of the Teachable machine® for diagnosing tympanic membrane lesions. A total of 3024 tympanic membrane images were used to train and validate the diagnostic performance of the network. Tympanic membrane images were labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), and cholesteatoma. According to the complexity of the categorization, Level I refers to normal versus abnormal tympanic membrane; Level II was defined as normal, OME, or COM + cholesteatoma; and Level III distinguishes between all four pathologies. In addition, eighty representative test images were used to assess the performance. Teachable machine® automatically creates a classification network and presents diagnostic performance when images are uploaded. The mean accuracy of the Teachable machine® for classifying tympanic membranes as normal or abnormal (Level I) was 90.1%. For Level II, the mean accuracy was 89.0% and for Level III it was 86.2%. The overall accuracy of the classification of the 80 representative tympanic membrane images was 78.75%, and the hit rates for normal, OME, COM, and cholesteatoma were 95.0%, 70.0%, 90.0%, and 60.0%, respectively. Teachable machine® could successfully generate the diagnostic network for classifying tympanic membrane.
Collapse
Affiliation(s)
- Hayoung Byun
- Department of Otolaryngology & Head and Neck Surgery, College of Medicine, Hanyang University, Seoul 04763, Korea
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04763, Korea
| | - Seung Hwan Lee
- Department of Otolaryngology & Head and Neck Surgery, College of Medicine, Hanyang University, Seoul 04763, Korea
| | - Tae Hyun Kim
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04763, Korea
- Department of Computer Science, Hanyang University, Seoul 04763, Korea
| | - Jaehoon Oh
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04763, Korea
- Department of Emergency Medicine, College of Medicine, Hanyang University, Seoul 04763, Korea
| | - Jae Ho Chung
- Department of Otolaryngology & Head and Neck Surgery, College of Medicine, Hanyang University, Seoul 04763, Korea
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04763, Korea
- Department of HY-KIST Bio-Convergence, College of Medicine, Hanyang University, Seoul 04763, Korea
- Correspondence:
| |
Collapse
|
3
|
Habib AR, Kajbafzadeh M, Hasan Z, Wong E, Gunasekera H, Perry C, Sacks R, Kumar A, Singh N. Artificial intelligence to classify ear disease from otoscopy: A systematic review and meta-analysis. Clin Otolaryngol 2022; 47:401-413. [PMID: 35253378 PMCID: PMC9310803 DOI: 10.1111/coa.13925] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Revised: 01/08/2022] [Accepted: 02/27/2022] [Indexed: 11/29/2022]
Abstract
Objectives To summarise the accuracy of artificial intelligence (AI) computer vision algorithms to classify ear disease from otoscopy. Design Systematic review and meta‐analysis. Methods Using the PRISMA guidelines, nine online databases were searched for articles that used AI computer vision algorithms developed from various methods (convolutional neural networks, artificial neural networks, support vector machines, decision trees and k‐nearest neighbours) to classify otoscopic images. Diagnostic classes of interest: normal tympanic membrane, acute otitis media (AOM), otitis media with effusion (OME), chronic otitis media (COM) with or without perforation, cholesteatoma and canal obstruction. Main outcome measures Accuracy to correctly classify otoscopic images compared to otolaryngologists (ground truth). The Quality Assessment of Diagnostic Accuracy Studies Version 2 tool was used to assess the quality of methodology and risk of bias. Results Thirty‐nine articles were included. Algorithms achieved 90.7% (95%CI: 90.1–91.3%) accuracy to difference between normal or abnormal otoscopy images in 14 studies. The most common multiclassification algorithm (3 or more diagnostic classes) achieved 97.6% (95%CI: 97.3–97.9%) accuracy to differentiate between normal, AOM and OME in three studies. AI algorithms outperformed human assessors to classify otoscopy images achieving 93.4% (95%CI: 90.5–96.4%) versus 73.2% (95%CI: 67.9–78.5%) accuracy in three studies. Convolutional neural networks achieved the highest accuracy compared to other classification methods. Conclusion AI can classify ear disease from otoscopy. A concerted effort is required to establish a comprehensive and reliable otoscopy database for algorithm training. An AI‐supported otoscopy system may assist health care workers, trainees and primary care practitioners with less otology experience identify ear disease.
Collapse
Affiliation(s)
- Al-Rahim Habib
- Faculty of Medicine and Health, University of Sydney, New South Wales, Australia.,Department of Otolaryngology - Head and Neck Surgery, Princess Alexandra Hospital, Queensland, Australia.,Department of Otolaryngology - Head and Neck Surgery, Westmead Hospital, New South Wales, Australia
| | - Majid Kajbafzadeh
- Faculty of Medicine and Health, University of Sydney, New South Wales, Australia
| | - Zubair Hasan
- Department of Otolaryngology - Head and Neck Surgery, Westmead Hospital, New South Wales, Australia
| | - Eugene Wong
- Department of Otolaryngology - Head and Neck Surgery, Westmead Hospital, New South Wales, Australia
| | - Hasantha Gunasekera
- Faculty of Medicine and Health, University of Sydney, New South Wales, Australia.,The Children's Hospital at Westmead, New South Wales, Australia
| | - Chris Perry
- Department of Otolaryngology - Head and Neck Surgery, Princess Alexandra Hospital, Queensland, Australia.,University of Queensland Medical School, Queensland, Australia
| | - Raymond Sacks
- Faculty of Medicine and Health, University of Sydney, New South Wales, Australia
| | - Ashnil Kumar
- School of Biomedical Engineering, Faculty of Engineering, University of Sydney, New South Wales, Australia
| | - Narinder Singh
- Faculty of Medicine and Health, University of Sydney, New South Wales, Australia.,Department of Otolaryngology - Head and Neck Surgery, Westmead Hospital, New South Wales, Australia
| |
Collapse
|
4
|
Canares TL, Wang W, Unberath M, Clark JH. Artificial intelligence to diagnose ear disease using otoscopic image analysis: a review. J Investig Med 2021; 70:354-362. [PMID: 34521730 DOI: 10.1136/jim-2021-001870] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/27/2021] [Indexed: 12/22/2022]
Abstract
AI relates broadly to the science of developing computer systems to imitate human intelligence, thus allowing for the automation of tasks that would otherwise necessitate human cognition. Such technology has increasingly demonstrated capacity to outperform humans for functions relating to image recognition. Given the current lack of cost-effective confirmatory testing, accurate diagnosis and subsequent management depend on visual detection of characteristic findings during otoscope examination. The aim of this manuscript is to perform a comprehensive literature review and evaluate the potential application of artificial intelligence for the diagnosis of ear disease from otoscopic image analysis.
Collapse
Affiliation(s)
- Therese L Canares
- Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Weiyao Wang
- Johns Hopkins University Whiting School of Engineering, Baltimore, Maryland, USA
| | - Mathias Unberath
- Johns Hopkins University Whiting School of Engineering, Baltimore, Maryland, USA
| | - James H Clark
- Otolaryngology-HNS, Johns Hopkins Medicine School of Medicine, Baltimore, Maryland, USA
| |
Collapse
|
5
|
Kerbl R. [Pediatrics up to date-Brief notes on research]. Monatsschr Kinderheilkd 2021; 169:681-683. [PMID: 34305179 PMCID: PMC8287283 DOI: 10.1007/s00112-021-01240-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/14/2021] [Indexed: 12/02/2022]
Affiliation(s)
- Reinhold Kerbl
- Abteilung für Kinder und Jugendliche, LKH Hochsteiermark/Leoben, Vordernbergerstraße 42, 8700 Leoben, Österreich
| |
Collapse
|
6
|
Won J, Monroy GL, Dsouza RI, Spillman DR, McJunkin J, Porter RG, Shi J, Aksamitiene E, Sherwood M, Stiger L, Boppart SA. Handheld Briefcase Optical Coherence Tomography with Real-Time Machine Learning Classifier for Middle Ear Infections. BIOSENSORS-BASEL 2021; 11:bios11050143. [PMID: 34063695 PMCID: PMC8147830 DOI: 10.3390/bios11050143] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Revised: 04/29/2021] [Accepted: 04/30/2021] [Indexed: 12/13/2022]
Abstract
A middle ear infection is a prevalent inflammatory disease most common in the pediatric population, and its financial burden remains substantial. Current diagnostic methods are highly subjective, relying on visual cues gathered by an otoscope. To address this shortcoming, optical coherence tomography (OCT) has been integrated into a handheld imaging probe. This system can non-invasively and quantitatively assess middle ear effusions and identify the presence of bacterial biofilms in the middle ear cavity during ear infections. Furthermore, the complete OCT system is housed in a standard briefcase to maximize its portability as a diagnostic device. Nonetheless, interpreting OCT images of the middle ear more often requires expertise in OCT as well as middle ear infections, making it difficult for an untrained user to operate the system as an accurate stand-alone diagnostic tool in clinical settings. Here, we present a briefcase OCT system implemented with a real-time machine learning platform for middle ear infections. A random forest-based classifier can categorize images based on the presence of middle ear effusions and biofilms. This study demonstrates that our briefcase OCT system coupled with machine learning can provide user-invariant classification results of middle ear conditions, which may greatly improve the utility of this technology for the diagnosis and management of middle ear infections.
Collapse
Affiliation(s)
- Jungeun Won
- Department of Bioengineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA;
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA; (G.L.M.); (R.I.D.); (D.R.S.J.); (J.S.); (E.A.)
| | - Guillermo L. Monroy
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA; (G.L.M.); (R.I.D.); (D.R.S.J.); (J.S.); (E.A.)
| | - Roshan I. Dsouza
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA; (G.L.M.); (R.I.D.); (D.R.S.J.); (J.S.); (E.A.)
| | - Darold R. Spillman
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA; (G.L.M.); (R.I.D.); (D.R.S.J.); (J.S.); (E.A.)
| | - Jonathan McJunkin
- Department of Otolaryngology, Carle Foundation Hospital, Champaign, IL 61822, USA; (J.M.); (R.G.P.)
- Carle Illinois College of Medicine, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USA
| | - Ryan G. Porter
- Department of Otolaryngology, Carle Foundation Hospital, Champaign, IL 61822, USA; (J.M.); (R.G.P.)
- Carle Illinois College of Medicine, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USA
| | - Jindou Shi
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA; (G.L.M.); (R.I.D.); (D.R.S.J.); (J.S.); (E.A.)
- Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
| | - Edita Aksamitiene
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA; (G.L.M.); (R.I.D.); (D.R.S.J.); (J.S.); (E.A.)
| | - MaryEllen Sherwood
- Stephens Family Clinical Research Institute, Carle Foundation Hospital, Urbana, IL 61801, USA; (M.S.); (L.S.)
| | - Lindsay Stiger
- Stephens Family Clinical Research Institute, Carle Foundation Hospital, Urbana, IL 61801, USA; (M.S.); (L.S.)
| | - Stephen A. Boppart
- Department of Bioengineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA;
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA; (G.L.M.); (R.I.D.); (D.R.S.J.); (J.S.); (E.A.)
- Carle Illinois College of Medicine, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USA
- Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
- Correspondence:
| |
Collapse
|