1
|
Austad B, Nilsen AH, Thorstensen WM, Helvik AS. Postoperative care for children after ventilation tube surgery: A qualitative study of parents' experiences over time in Norway. Am J Otolaryngol 2024; 45:104457. [PMID: 39154491 DOI: 10.1016/j.amjoto.2024.104457] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2024] [Accepted: 07/30/2024] [Indexed: 08/20/2024]
Abstract
OBJECTIVE To explore the parents' experience of postoperative care during the first two years after ventilation tube (VT) surgery in a setting where the check-ups were conducted either by otolaryngologists or their regular general practitioner (GP). METHODS 55 individual interviews of parents at up to three different time points (<1, 6, and 24 months) after their child received VT-surgery, analyzed with reflexive thematic analysis. RESULTS 1. Parents' trust in the healthcare system and responsibility for booking check-ups. Nearly all parents seemed to maintain trust in the healthcare system and felt safeguarded regardless of where they had their check-ups. Still, they would prefer otolaryngologist-led care if they could choose from the top shelf. They took responsibility for seeking healthcare when needed and experienced that their GP referred their child if necessary. 2. As time goes by, parental worries are reduced. Most experienced that their child stayed healthy after surgery, and their demand for postoperative check-ups decreased. For the children who faced ongoing issues, most parents experienced that their child's challenges had been handled professionally, and they became less worried. Some parents attribute other diagnoses to their child's behavior or speech delays, refining their understanding of their child's condition. 3. The desire for closure. Parents sought reassurance about their child's recovery and desired professional evaluation for closure. While some advocated for audiometry, others trusted their own assessments about hearing. The transition to school marked a pivotal time, prompting concerns about social inclusion. CONCLUSION Overall, the parents experienced that their child was safeguarded irrespective of whether postoperative care was provided by otolaryngologists or GPs. Still, many preferred check-ups by an otolaryngologist. The parental worries and focus on the VTs were reduced as time went by after surgery, but even so many wanted a 'closure' to be sure that the hearing was as good as it could be and the VTs rejected. We advocate for an individualized approach to postoperative care that addresses specific medical needs without imposing unnecessary check-ups.
Collapse
Affiliation(s)
- Bjarne Austad
- General Practice Research Unit, Department of Public Health and Nursing, Norwegian University of Science and Technology (NTNU), Postbox 8905, 7491 Trondheim, Norway; Øya Medical Centre, Prinsensgate 1 A, 7013 Trondheim, Norway.
| | - Ann Helen Nilsen
- Department of Otolaryngology, Head and Neck Surgery, St. Olavs University Hospital, Postbox 3250, 7006 Trondheim, Norway.
| | - Wenche Moe Thorstensen
- Department of Otolaryngology, Head and Neck Surgery, St. Olavs University Hospital, Postbox 3250, 7006 Trondheim, Norway; Department of Neuromedicine and Movement Science, NTNU, Postbox 8900, 7491 Trondheim, Norway.
| | - Anne-Sofie Helvik
- General Practice Research Unit, Department of Public Health and Nursing, Norwegian University of Science and Technology (NTNU), Postbox 8905, 7491 Trondheim, Norway.
| |
Collapse
|
2
|
Rosenfeld RM, Tunkel DE, Schwartz SR, Anne S, Bishop CE, Chelius DC, Hackell J, Hunter LL, Keppel KL, Kim AH, Kim TW, Levine JM, Maksimoski MT, Moore DJ, Preciado DA, Raol NP, Vaughan WK, Walker EA, Monjur TM. Clinical Practice Guideline: Tympanostomy Tubes in Children (Update). Otolaryngol Head Neck Surg 2022; 166:S1-S55. [PMID: 35138954 DOI: 10.1177/01945998211065662] [Citation(s) in RCA: 30] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
OBJECTIVE Insertion of tympanostomy tubes is the most common ambulatory surgery performed on children in the United States. Tympanostomy tubes are most often inserted because of persistent middle ear fluid, frequent ear infections, or ear infections that persist after antibiotic therapy. All these conditions are encompassed by the term otitis media (middle ear inflammation). This guideline update provides evidence-based recommendations for patient selection and surgical indications for managing tympanostomy tubes in children. The guideline is intended for any clinician involved in managing children aged 6 months to 12 years with tympanostomy tubes or children being considered for tympanostomy tubes in any care setting as an intervention for otitis media of any type. The target audience includes specialists, primary care clinicians, and allied health professionals. PURPOSE The purpose of this clinical practice guideline update is to reassess and update recommendations in the prior guideline from 2013 and to provide clinicians with trustworthy, evidence-based recommendations on patient selection and surgical indications for managing tympanostomy tubes in children. In planning the content of the updated guideline, the guideline update group (GUG) affirmed and included all the original key action statements (KASs), based on external review and GUG assessment of the original recommendations. The guideline update was supplemented with new research evidence and expanded profiles that addressed quality improvement and implementation issues. The group also discussed and prioritized the need for new recommendations based on gaps in the initial guideline or new evidence that would warrant and support KASs. The GUG further sought to bring greater coherence to the guideline recommendations by displaying relationships in a new flowchart to facilitate clinical decision making. Last, knowledge gaps were identified to guide future research. METHODS In developing this update, the methods outlined in the American Academy of Otolaryngology-Head and Neck Surgery Foundation's "Clinical Practice Guideline Development Manual, Third Edition: A Quality-Driven Approach for Translating Evidence Into Action" were followed explicitly. The GUG was convened with representation from the disciplines of otolaryngology-head and neck surgery, otology, pediatrics, audiology, anesthesiology, family medicine, advanced practice nursing, speech-language pathology, and consumer advocacy. ACTION STATEMENTS The GUG made strong recommendations for the following KASs: (14) clinicians should prescribe topical antibiotic ear drops only, without oral antibiotics, for children with uncomplicated acute tympanostomy tube otorrhea; (16) the surgeon or designee should examine the ears of a child within 3 months of tympanostomy tube insertion AND should educate families regarding the need for routine, periodic follow-up to examine the ears until the tubes extrude.The GUG made recommendations for the following KASs: (1) clinicians should not perform tympanostomy tube insertion in children with a single episode of otitis media with effusion (OME) of less than 3 months' duration, from the date of onset (if known) or from the date of diagnosis (if onset is unknown); (2) clinicians should obtain a hearing evaluation if OME persists for 3 months or longer OR prior to surgery when a child becomes a candidate for tympanostomy tube insertion; (3) clinicians should offer bilateral tympanostomy tube insertion to children with bilateral OME for 3 months or longer AND documented hearing difficulties; (5) clinicians should reevaluate, at 3- to 6-month intervals, children with chronic OME who do not receive tympanostomy tubes, until the effusion is no longer present, significant hearing loss is detected, or structural abnormalities of the tympanic membrane or middle ear are suspected; (6) clinicians should not perform tympanostomy tube insertion in children with recurrent acute otitis media who do not have middle ear effusion in either ear at the time of assessment for tube candidacy; (7) clinicians should offer bilateral tympanostomy tube insertion in children with recurrent acute otitis media who have unilateral or bilateral middle ear effusion at the time of assessment for tube candidacy; (8) clinicians should determine if a child with recurrent acute otitis media or with OME of any duration is at increased risk for speech, language, or learning problems from otitis media because of baseline sensory, physical, cognitive, or behavioral factors; (10) the clinician should not place long-term tubes as initial surgery for children who meet criteria for tube insertion unless there is a specific reason based on an anticipated need for prolonged middle ear ventilation beyond that of a short-term tube; (12) in the perioperative period, clinicians should educate caregivers of children with tympanostomy tubes regarding the expected duration of tube function, recommended follow-up schedule, and detection of complications; (13) clinicians should not routinely prescribe postoperative antibiotic ear drops after tympanostomy tube placement; (15) clinicians should not encourage routine, prophylactic water precautions (use of earplugs or headbands, avoidance of swimming or water sports) for children with tympanostomy tubes.The GUG offered the following KASs as options: (4) clinicians may perform tympanostomy tube insertion in children with unilateral or bilateral OME for 3 months or longer (chronic OME) AND symptoms that are likely attributable, all or in part, to OME that include, but are not limited to, balance (vestibular) problems, poor school performance, behavioral problems, ear discomfort, or reduced quality of life; (9) clinicians may perform tympanostomy tube insertion in at-risk children with unilateral or bilateral OME that is likely to persist as reflected by a type B (flat) tympanogram or a documented effusion for 3 months or longer; (11) clinicians may perform adenoidectomy as an adjunct to tympanostomy tube insertion for children with symptoms directly related to the adenoids (adenoid infection or nasal obstruction) OR in children aged 4 years or older to potentially reduce future incidence of recurrent otitis media or the need for repeat tube insertion.
Collapse
Affiliation(s)
| | - David E Tunkel
- School of Medicine, Johns Hopkins University, Baltimore, Maryland, USA
| | | | | | - Charles E Bishop
- University of Mississippi Medical Center, Jackson, Mississippi, USA
| | - Daniel C Chelius
- Baylor College of Medicine-Texas Children's Hospital, Houston, Texas, USA
| | - Jesse Hackell
- Pomona Pediatrics, Boston Children's Health Physicians, Pomona, New York, USA.,New York Medical College, Valhalla, New York, USA
| | - Lisa L Hunter
- Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA
| | | | - Ana H Kim
- Columbia University Medical Center, New York, New York, USA
| | - Tae W Kim
- University of Minnesota School of Medicine/Masonic Children's Hospital, Minneapolis, Minnesota, USA
| | - Jack M Levine
- Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, New York, USA
| | | | - Denee J Moore
- School of Medicine, Virginia Commonwealth University, Richmond, Virginia, USA
| | | | | | - William K Vaughan
- Consumers United for Evidence-Based Healthcare, Falls Church, Virginia, USA
| | | | - Taskin M Monjur
- American Academy of Otolaryngology-Head and Neck Surgery Foundation, Alexandria, Virginia, USA
| |
Collapse
|
3
|
Patel TA, McCoy JL, Belsky MA, Sim ES, Konanur A, Yan A, Jabbour N, Padia R. Effect of Insurance Type on Postoperative Tympanostomy Tube Follow-up. Otolaryngol Head Neck Surg 2021; 166:1078-1084. [PMID: 34962848 DOI: 10.1177/01945998211067504] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
OBJECTIVE Bilateral myringotomy with tube insertion (BMT) is a common procedure performed in children. Appropriate follow-up is necessary to ensure management of postoperative sequalae. The objectives are to investigate (1) the relationship between insurance type and postoperative follow-up attendance and (2) the effect of follow-up on need for further care after BMT. STUDY DESIGN Retrospective cohort study. SETTING The study included patients <3 years of age undergoing BMT for recurrent acute otitis media at a tertiary care children's hospital within a single year and followed for 3 years. Patients were excluded if they had received a prior BMT; underwent a concurrent otolaryngologic procedure; or had a syndromic diagnosis, craniofacial abnormality, or any significant cardiac or respiratory comorbidity. METHODS Number of follow-up appointments, demographics, socioeconomic status, and postoperative outcomes were analyzed. RESULTS A total of 734 patients were included with mean (SD) age of 1.4 years (0.50). The majority of patients had private insurance (520/734, 70.8%). Patients with public insurance attended fewer postoperative appointments (1.5 vs 1.8, P < .001) and had a higher incidence of BMT-related emergency department (ED) visits (10.3% vs 3.8%, P = .001). There was no significance found when different insurance providers were compared. An adjusted multivariate regression analysis showed that patients with private insurance were more likely to attend postoperative appointments (odds ratio, 3.52 [95% CI, 2.12-5.82]; P < .001) and less likely to have a BMT-related ED visit (odds ratio, 0.42 [95% CI, 0.20-0.89]; P = .024). CONCLUSION Insurance type is related to outcomes after the treatment of recurrent acute otitis media with BMT. Future studies that survey individuals will help identify barriers that contribute to patient absence at follow-ups and need for subsequent ED visits.
Collapse
Affiliation(s)
- Terral A Patel
- Department of Otolaryngology-Head and Neck Surgery, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania, USA
| | - Jennifer L McCoy
- Division of Pediatric Otolaryngology, UPMC Children's Hospital of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Michael A Belsky
- School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Edward S Sim
- School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Anisha Konanur
- School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Annie Yan
- School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Noel Jabbour
- Division of Pediatric Otolaryngology, UPMC Children's Hospital of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Reema Padia
- Division of Pediatric Otolaryngology, UPMC Children's Hospital of Pittsburgh, Pittsburgh, Pennsylvania, USA
| |
Collapse
|
4
|
Monroy GL, Pande P, Nolan RM, Shelton RL, Porter RG, Novak MA, Spillman DR, Chaney EJ, McCormick DT, Boppart SA. Noninvasive in vivo optical coherence tomography tracking of chronic otitis media in pediatric subjects after surgical intervention. JOURNAL OF BIOMEDICAL OPTICS 2017; 22:1-11. [PMID: 29275547 PMCID: PMC5745859 DOI: 10.1117/1.jbo.22.12.121614] [Citation(s) in RCA: 29] [Impact Index Per Article: 4.1] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/21/2017] [Accepted: 12/15/2017] [Indexed: 05/12/2023]
Abstract
In an institutional review board-approved study, 25 pediatric subjects diagnosed with chronic or recurrent otitis media were observed over a period of six months with optical coherence tomography (OCT). Subjects were followed throughout their treatment at the initial patient evaluation and preoperative consultation, surgery (intraoperative imaging), and postoperative follow-up, followed by an additional six months of records-based observation. At each time point, the tympanic membrane (at the light reflex region) and directly adjacent middle-ear cavity were observed in vivo with a handheld OCT probe and portable system. Imaging results were compared with clinical outcomes to correlate the clearance of symptoms in relation to changes in the image-based features of infection. OCT images of most all participants showed the presence of additional infection-related biofilm structures during their initial consultation visit and similarly for subjects imaged intraoperatively before myringotomy. Subjects with successful treatment (no recurrence of infectious symptoms) had no additional structures visible in OCT images during the postoperative visit. OCT image findings suggest surgical intervention consisting of myringotomy and tympanostomy tube placement provides a means to clear the middle ear of infection-related components, including middle-ear fluid and biofilms. Furthermore, OCT was demonstrated as a rapid diagnostic tool to prospectively monitor patients in both outpatient and surgical settings.
Collapse
Affiliation(s)
- Guillermo L. Monroy
- University of Illinois at Urbana-Champaign, Department of Bioengineering, Urbana, Illinois, United States
- Beckman Institute for Advanced Science and Technology, Urbana, Illinois, United States
| | - Paritosh Pande
- Beckman Institute for Advanced Science and Technology, Urbana, Illinois, United States
| | - Ryan M. Nolan
- Beckman Institute for Advanced Science and Technology, Urbana, Illinois, United States
| | - Ryan L. Shelton
- Beckman Institute for Advanced Science and Technology, Urbana, Illinois, United States
- University of Illinois at Urbana-Champaign, Department of Electrical and Computer Engineering, Urbana, Illinois, United States
| | - Ryan G. Porter
- Carle Foundation Hospital, Department of Otolaryngology, Urbana, Illinois, United States
- University of Illinois at Urbana-Champaign, Carle–Illinois College of Medicine, Urbana, Illinois, United States
| | - Michael A. Novak
- Carle Foundation Hospital, Department of Otolaryngology, Urbana, Illinois, United States
- University of Illinois at Urbana-Champaign, Carle–Illinois College of Medicine, Urbana, Illinois, United States
| | - Darold R. Spillman
- Beckman Institute for Advanced Science and Technology, Urbana, Illinois, United States
| | - Eric J. Chaney
- Beckman Institute for Advanced Science and Technology, Urbana, Illinois, United States
| | | | - Stephen A. Boppart
- University of Illinois at Urbana-Champaign, Department of Bioengineering, Urbana, Illinois, United States
- Beckman Institute for Advanced Science and Technology, Urbana, Illinois, United States
- University of Illinois at Urbana-Champaign, Department of Electrical and Computer Engineering, Urbana, Illinois, United States
- University of Illinois at Urbana-Champaign, Carle–Illinois College of Medicine, Urbana, Illinois, United States
- Address all correspondence to: Stephen A. Boppart, E-mail:
| |
Collapse
|
5
|
Homøe P, Kværner K, Casey JR, Damoiseaux RAMJ, van Dongen TMA, Gunasekera H, Jensen RG, Kvestad E, Morris PS, Weinreich HM. Panel 1: Epidemiology and Diagnosis. Otolaryngol Head Neck Surg 2017; 156:S1-S21. [DOI: 10.1177/0194599816643510] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
Abstract
Objective To create a literature review between 2011 and June 1, 2015, on advances in otitis media (OM) epidemiology and diagnosis (including relevant audiology studies). Data Sources Electronic search engines (PubMed, EMBASE, and Cochrane Library) with a predefined search strategy. Review Methods Articles with appropriate epidemiologic methodology for OM, including acute mastoiditis and eustachian tube dysfunction. Items included OM worldwide and in high-risk populations, OM-related hearing loss, news in OM diagnostics, prenatal risk factors and comorbidities, postnatal risk factors, genetics, microbiological epidemiology, guidelines, and quality of life. Conclusions Diagnostic evidence and genetic studies are increasing; guidelines are introduced worldwide; and there is evidence of benefit of pneumococcal conjugate vaccines. New risk factors and comordities are identified in the study period, and quality of life is affected in children and their families. Implications for Practice Chronic suppurative OM occurs worldwide and contributes to lifelong hearing loss. Uniform definitions are still lacking and should be provided. An association between HIV and chronic suppurative OM has been found. Tympanometry is recommended for diagnosis, with or without pneumatic otoscopy. Video otoscopy, algorithms, and validated questionnaires may assist clinicians. Childhood obesity is associated with OM. Heritability accounts for 20% to 50% of OM diagnoses. OM-prone children seem to produce weaker immunologic responses to pneumococcal conjugate vaccines. Clinicians tend to individualize treatment without adhering to guidelines.
Collapse
Affiliation(s)
- Preben Homøe
- Department of Otorhinolaryngology and Maxillofacial Surgery, Zealand University Hospital, University of Copenhagen, Køge, Denmark
| | - Kari Kværner
- Centre for Connected Care, Oslo University Hospital, Oslo, Norway
- BI Norwegian Business School, Oslo, Norway
| | | | - Roger A. M. J. Damoiseaux
- Julius Centre for Health Sciences and Primary Care, University Medical Centre, Utrecht, The Netherlands
| | - Thijs M. A. van Dongen
- Julius Centre for Health Sciences and Primary Care, University Medical Centre, Utrecht, The Netherlands
| | - Hasantha Gunasekera
- Discipline of Paediatrics and Child Health, University of Sydney, Sydney, Australia
| | - Ramon G. Jensen
- Department of Otorhinolaryngology and Maxillofacial Surgery, Zealand University Hospital, University of Copenhagen, Køge, Denmark
| | - Ellen Kvestad
- ENT Department, Oslo University Hospital and Division of Mental Health, Norwegian Institute of Public Health, Oslo, Norway
| | - Peter S. Morris
- Department of Paediatrics, Royal Darwin Hospital and Menzies School of Health Research, Darwin, Australia
| | - Heather M. Weinreich
- Department of Otolaryngology–Head and Neck Surgery, Johns Hopkins University, Baltimore, Maryland, USA
| |
Collapse
|
6
|
Mughal Z, Thirunavukarasu V, Darr A, Jindal M. Follow-up care after grommet insertion in children: Review article. Int J Pediatr Otorhinolaryngol 2016; 88:25-9. [PMID: 27497381 DOI: 10.1016/j.ijporl.2016.06.040] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/27/2016] [Revised: 06/09/2016] [Accepted: 06/18/2016] [Indexed: 10/21/2022]
Abstract
BACKGROUND Grommet insertion is a common procedure in children. A lengthy otolaryngology follow-up can have an adverse impact on clinic waiting times, new patient appointment availability, and pecuniary disadvantage for the hospital. OBJECTIVE OF REVIEW To consolidate research and opinion concerning follow-up care following grommet insertion in a pediatric population. SEARCH STRATEGY The literature between January 1990 and September 2015 was searched on MEDLINE (Ovid), Google Scholar, PubMed and Web of Science databases. RESULTS Guidelines and consensus of opinion from the United States advocate that an initial post-operative review should take place within 4 weeks, and subsequent appointments every 6 months until grommet extrusion. Recent audit reports from the United Kingdom have shown that some groups arrange their first post-operative review at 3 months, and subsequent appointments vary considerably from no further follow-up to up to 24 months. Up to 75% of follow-up appointments were scheduled despite normal audiometry and clinical findings after grommet insertion, suggesting a large cohort of patients may undergo unnecessary specialist clinic reviews. General practioners (GP), audiologists or specialist nurses are potential alternative providers of regular reviews to ensure normal hearing thresholds and an adequate tympanic membrane healing course. CONCLUSION Follow-up schedules are largely driven by consensus of opinion. A significant number of follow-up appointments in otolaryngology clinic appear to be redundant. Recently attention has been drawn to earlier discharge from otolaryngology clinic with subsequent follow-up in less resource and cost intensive clinics coordinated by GPs, audiologist or nurses, which may help alleviate some outpatient workload on acute hospital trusts.
Collapse
Affiliation(s)
- Zahir Mughal
- Department of Otorhinolaryngology, Russells Hall Hospital, Pensnett Rd, Dudley, DY1 2HQ, UK.
| | - Vijay Thirunavukarasu
- Department of Otorhinolaryngology, Russells Hall Hospital, Pensnett Rd, Dudley, DY1 2HQ, UK.
| | - Adnan Darr
- Department of Otorhinolaryngology, Walsall Manor Hospital, Moat Road, Walsall, WS2 9PS, UK.
| | - Mudit Jindal
- Department of Otorhinolaryngology, Russells Hall Hospital, Pensnett Rd, Dudley, DY1 2HQ, UK.
| |
Collapse
|
7
|
Detecting tympanostomy tubes from otoscopic images via offline and online training. Comput Biol Med 2015; 61:107-18. [PMID: 25889718 DOI: 10.1016/j.compbiomed.2015.03.025] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2014] [Revised: 03/22/2015] [Accepted: 03/23/2015] [Indexed: 01/10/2023]
Abstract
Tympanostomy tube placement has been commonly used nowadays as a surgical treatment for otitis media. Following the placement, regular scheduled follow-ups for checking the status of the tympanostomy tubes are important during the treatment. The complexity of performing the follow up care mainly lies on identifying the presence and patency of the tympanostomy tube. An automated tube detection program will largely reduce the care costs and enhance the clinical efficiency of the ear nose and throat specialists and general practitioners. In this paper, we develop a computer vision system that is able to automatically detect a tympanostomy tube in an otoscopic image of the ear drum. The system comprises an offline classifier training process followed by a real-time refinement stage performed at the point of care. The offline training process constructs a three-layer cascaded classifier with each layer reflecting specific characteristics of the tube. The real-time refinement process enables the end users to interact and adjust the system over time based on their otoscopic images and patient care. The support vector machine (SVM) algorithm has been applied to train all of the classifiers. Empirical evaluation of the proposed system on both high quality hospital images and low quality internet images demonstrates the effectiveness of the system. The offline classifier trained using 215 images could achieve a 90% accuracy in terms of classifying otoscopic images with and without a tympanostomy tube, and then the real-time refinement process could improve the classification accuracy by 3-5% based on additional 20 images.
Collapse
|