-
JMIR AI May 2024The integration of artificial intelligence (AI), particularly deep learning models, has transformed the landscape of medical technology, especially in the field of...
BACKGROUND
The integration of artificial intelligence (AI), particularly deep learning models, has transformed the landscape of medical technology, especially in the field of diagnosis using imaging and physiological data. In otolaryngology, AI has shown promise in image classification for middle ear diseases. However, existing models often lack patient-specific data and clinical context, limiting their universal applicability. The emergence of GPT-4 Vision (GPT-4V) has enabled a multimodal diagnostic approach, integrating language processing with image analysis.
OBJECTIVE
In this study, we investigated the effectiveness of GPT-4V in diagnosing middle ear diseases by integrating patient-specific data with otoscopic images of the tympanic membrane.
METHODS
The design of this study was divided into two phases: (1) establishing a model with appropriate prompts and (2) validating the ability of the optimal prompt model to classify images. In total, 305 otoscopic images of 4 middle ear diseases (acute otitis media, middle ear cholesteatoma, chronic otitis media, and otitis media with effusion) were obtained from patients who visited Shinshu University or Jichi Medical University between April 2010 and December 2023. The optimized GPT-4V settings were established using prompts and patients' data, and the model created with the optimal prompt was used to verify the diagnostic accuracy of GPT-4V on 190 images. To compare the diagnostic accuracy of GPT-4V with that of physicians, 30 clinicians completed a web-based questionnaire consisting of 190 images.
RESULTS
The multimodal AI approach achieved an accuracy of 82.1%, which is superior to that of certified pediatricians at 70.6%, but trailing behind that of otolaryngologists at more than 95%. The model's disease-specific accuracy rates were 89.2% for acute otitis media, 76.5% for chronic otitis media, 79.3% for middle ear cholesteatoma, and 85.7% for otitis media with effusion, which highlights the need for disease-specific optimization. Comparisons with physicians revealed promising results, suggesting the potential of GPT-4V to augment clinical decision-making.
CONCLUSIONS
Despite its advantages, challenges such as data privacy and ethical considerations must be addressed. Overall, this study underscores the potential of multimodal AI for enhancing diagnostic accuracy and improving patient care in otolaryngology. Further research is warranted to optimize and validate this approach in diverse clinical settings.
PubMed: 38875669
DOI: 10.2196/58342 -
Laryngoscope Investigative... Jun 2024To describe findings from an otolaryngology-specific needs assessment tool in Zimbabwe.
OBJECTIVES
To describe findings from an otolaryngology-specific needs assessment tool in Zimbabwe.
METHODS
Surveys were developed and shared with Low-Middle Income Country (LMIC) hosting institutions in Zimbabwe and to High-Income Country surgical trip participants (HIC). Respondents were otolaryngologists identified online and through professional networks who had participated in a surgical trip.
RESULTS
The most common procedures Zimbabwe otolaryngologists reported treating were adenotonsillectomy (85.7%), chronic rhinosinusitis (71.4%), chronic otitis (57.1%), and head and neck tumor intervention (57.1%). The most common untreatable conditions that host physicians wanted to treat were skull base surgery (71.4%), flap reconstructions (57.1%), and laryngotracheal reconstruction (57.1%). The largest discrepancy between host desires and visiting team offerings were flap reconstruction (57.1%), nasal bone deformities (37.1%), and laryngotracheal reconstruction (17.1%). Perceptions of short-term surgical trips (STST) were recorded for host and visiting teams, and important differences between the public and private sectors of care in Zimbabwe were also identified.
CONCLUSION
The surveys utilized in this study served as a bidirectional needs assessment of the requirements and care goals of host institutions and visiting teams in Zimbabwe. Differences between public and private sectors of care, particularly regarding infrastructure, resources, and surgical goals, were revealed, and the results can be utilized as part of efforts to maximize efforts within global surgical partnerships.
LEVEL OF EVIDENCE
VI.
PubMed: 38867854
DOI: 10.1002/lio2.1278 -
Langenbeck's Archives of Surgery Jun 2024Assessing vocal cord mobility is crucial for patients undergoing thyroid surgery. We aimed to evaluate the feasibility and efficacy of surgeon-performed transcutaneous... (Observational Study)
Observational Study
PURPOSE
Assessing vocal cord mobility is crucial for patients undergoing thyroid surgery. We aimed to evaluate the feasibility and efficacy of surgeon-performed transcutaneous laryngeal ultrasound (TLUS) compared to flexible nasolaryngoscopy.
METHOD
From February 2022 to December 2022, we conducted a prospective observational study on patients scheduled for total thyroidectomy at our Institution. All patients underwent TLUS followed by flexible nasolaryngoscopy by a blinded otolaryngologist. Findings were classified as normal or vocal cord movement impairment and then compared. Patients evaluable on TLUS were included in Group A, while those not evaluable were included in Group B, and their features were compared.
RESULTS
Group A included 180 patients, while Group B included 21 patients. Male sex (p < 0.001), age (p = 0.034), BMI (p < 0.001), thyroid volume (p = 0.038), and neck circumference (p < 0.001) were associated with Group B. TLUS showed a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 100%, 99.4%, 94.4%, 100%, and 99.4%, respectively. Cohen's K value was 0.984.
CONCLUSION
TLUS is a valid, easy-to-perform, non-invasive, and painless alternative for evaluating vocal cords in selected patients. It can be used either as a first level exam and as screening tool for selecting cases for flexible nasolaryngoscopy. TLUS should be integrated into routine thyroid ultrasound examination.
Topics: Humans; Thyroidectomy; Male; Female; Prospective Studies; Middle Aged; Ultrasonography; Adult; Laryngoscopy; Vocal Cords; Aged; Feasibility Studies; Sensitivity and Specificity; Postoperative Complications; Vocal Cord Paralysis
PubMed: 38861184
DOI: 10.1007/s00423-024-03362-4 -
Nigerian Journal of Clinical Practice May 2024Tracheostomy is an important life-saving surgical procedure that could be used to secure the lower airway. It can however serve as a source of airway compromise when...
BACKGROUND
Tracheostomy is an important life-saving surgical procedure that could be used to secure the lower airway. It can however serve as a source of airway compromise when fragments from it are deposited. This condition must be diagnosed early enough, and appropriate intervention should be done to forestall potential morbidity and mortality.
CASE REPORT
A 56-year-old tracheostomized patient presented to the accident and emergency department with a 4-hour history of sudden onset choking cough and labored breathing. The shaft of his tracheostomy tube (TT) was fractured and subsequently aspirated while he was attempting to remove and clean the inner tube that morning. He has used the TT for about 6 years and lost to follow-up clinic visits. The chest radiograph showed the metallic foreign body lodged within the trachea. He had an emergency rigid bronchoscopy via the tracheostomy stoma, and the object was retrieved. All respiratory symptoms subsequently resolved, and a check radiograph showed normal findings.
CONCLUSION
Tracheostomy tube fracture and aspiration should be ruled out in every tracheostomized patient with sudden onset acute respiratory symptoms. Otolaryngologists must always emphasize the need for proper handling of TT, regular follow-up, and tube replacement when due.
Topics: Humans; Tracheostomy; Foreign Bodies; Male; Middle Aged; Bronchoscopy; Bronchi; Equipment Failure; Airway Obstruction
PubMed: 38842719
DOI: 10.4103/njcp.njcp_541_23 -
3D Printing in Medicine May 20243D-printed temporal bone models enable the training and rehearsal of complex otological procedures. To date, there has been no consolidation of the literature regarding...
INTRODUCTION
3D-printed temporal bone models enable the training and rehearsal of complex otological procedures. To date, there has been no consolidation of the literature regarding the developmental process of 3D-printed temporal bone models. A brief review of the current literature shows that many of the key surgical landmarks of the temporal bone are poorly represented in models. This study aims to propose a novel design and production workflow to produce high-fidelity 3D-printed temporal bone models for surgical simulation.
METHODS
Developmental phases for data extraction, 3D segmentation and Computer Aided Design (CAD), and fabrication are outlined. The design and fabrication considerations for key anatomical regions, such as the mastoid air cells and course of the facial nerve, are expounded on with the associated strategy and design methods employed. To validate the model, radiological measurements were compared and a senior otolaryngologist performed various surgical procedures on the model.
RESULTS
Measurements between the original scans and scans of the model demonstrate sub-millimetre accuracy of the model. Assessment by the senior otologist found that the model was satisfactory in simulating multiple surgical procedures.
CONCLUSION
This study offers a systematic method for creating accurate 3D-printed temporal bone models for surgical training. Results show high accuracy and effectiveness in simulating surgical procedures, promising improved training and patient outcomes.
PubMed: 38814431
DOI: 10.1186/s41205-024-00218-x -
Federal Practitioner : For the Health... May 2024Three-dimensional (3D) printing has emerged as a promising new technology for the development of surgical prosthetics. Research in orthopedic surgery has demonstrated...
BACKGROUND
Three-dimensional (3D) printing has emerged as a promising new technology for the development of surgical prosthetics. Research in orthopedic surgery has demonstrated that using 3D printed customized prosthetics results in more precise implant placements and better patient outcomes. However, there has been little research on implementing customized 3D printed prosthetics in otolaryngology. The program sought to determine whether computed tomography (CT) serves as feasible templates to construct 3D printed palatal obturator prosthetics for defects in patients who have been treated for head and neck cancers.
OBSERVATIONS
A retrospective review of patients with palatal defects was conducted and identified 1 patient with high quality CTs compatible with 3D modeling. CTs of the patient's craniofacial anatomy were used to develop a 3D model and a Formlabs 3B+ printer printed the palatal prosthetic. We successfully developed and produced an individualized prosthetic using CTs from a veteran with head and neck deformities caused by cancer treatment who was previously treated at the Veterans Affairs Palo Alto Health Care System. This project was successful in printing patient-specific implants using CT reproductions of the patient's craniofacial anatomy, particularly of the palate. The program was a proof of concept and the implant we created was not used on the patient.
CONCLUSIONS
Customized 3D printed implants may allow otolaryngologists to enhance the performance and efficiency of surgeries and better rehabilitate and reconstruct craniofacial deformities to restore appearance and function to patients. Additional research will strive to enhance the therapeutic potential of these prosthetics to serve as low-cost, patient-specific implants.
PubMed: 38813248
DOI: 10.12788/fp.0464 -
BMC Medical Informatics and Decision... May 2024Nasal polyps and inverted papillomas often look similar. Clinically, it is difficult to distinguish the masses by endoscopic examination. Therefore, in this study, we...
BACKGROUND
Nasal polyps and inverted papillomas often look similar. Clinically, it is difficult to distinguish the masses by endoscopic examination. Therefore, in this study, we aimed to develop a deep learning algorithm for computer-aided diagnosis of nasal endoscopic images, which may provide a more accurate clinical diagnosis before pathologic confirmation of the nasal masses.
METHODS
By performing deep learning of nasal endoscope images, we evaluated our computer-aided diagnosis system's assessment ability for nasal polyps and inverted papilloma and the feasibility of their clinical application. We used curriculum learning pre-trained with patches of nasal endoscopic images and full-sized images. The proposed model's performance for classifying nasal polyps, inverted papilloma, and normal tissue was analyzed using five-fold cross-validation.
RESULTS
The normal scores for our best-performing network were 0.9520 for recall, 0.7900 for precision, 0.8648 for F1-score, 0.97 for the area under the curve, and 0.8273 for accuracy. For nasal polyps, the best performance was 0.8162, 0.8496, 0.8409, 0.89, and 0.8273, respectively, for recall, precision, F1-score, area under the curve, and accuracy. Finally, for inverted papilloma, the best performance was obtained for recall, precision, F1-score, area under the curve, and accuracy values of 0.5172, 0.8125, 0.6122, 0.83, and 0.8273, respectively.
CONCLUSION
Although there were some misclassifications, the results of gradient-weighted class activation mapping were generally consistent with the areas under the curve determined by otolaryngologists. These results suggest that the convolutional neural network is highly reliable in resolving lesion locations in nasal endoscopic images.
Topics: Humans; Deep Learning; Endoscopy; Nasal Cavity; Nasal Polyps; Nose Neoplasms; Papilloma, Inverted; Diagnosis, Computer-Assisted; Diagnosis, Differential; Male; Middle Aged; Adult
PubMed: 38811961
DOI: 10.1186/s12911-024-02517-z -
Cureus Apr 2024We report the case of a 53-year-old female who developed tracheobronchomalacia immediately following an uncomplicated robotic hysterectomy with bilateral...
We report the case of a 53-year-old female who developed tracheobronchomalacia immediately following an uncomplicated robotic hysterectomy with bilateral salpingo-oophorectomy to treat postmenopausal bleeding. Induction of anesthesia was notable for moderately difficult intubation, managed with applied cricothyroid pressure and a small 6.5 endotracheal tube placement via GlideScope. The surgical course was uneventful. The patient remained intubated in the post-anesthesia care unit but was not providing end-tidal volumes. Attempts to replace the endotracheal tube with a larger tube were unsuccessful and the patient was temporarily unable to ventilate. Rapid troubleshooting discovered that a laryngeal mask airway (LMA) could sufficiently ventilate the patient. An otolaryngologist was able to perform direct bronchoscopy, which revealed more than 50% dynamic anterior-posterior collapse of the trachea and bronchi. The patient was subsequently awakened from anesthesia and monitored in the intensive care unit, ventilating with an LMA. After a couple of hours, it was determined that the patient's airway was protected, and the LMA was removed.
PubMed: 38800293
DOI: 10.7759/cureus.59078 -
Sleep Medicine: X Dec 2024There are significant variations in practice regarding the use of sleep studies in children with symptoms of sleep disordered breathing (SDB) prior to...
There are significant variations in practice regarding the use of sleep studies in children with symptoms of sleep disordered breathing (SDB) prior to adenotonsillectomy. Current UK guidance recommends the selective use of sleep studies to confirm a diagnosis of obstructive sleep apnoea (OSA) when there is diagnostic uncertainty, in children with comorbidities, or to assess perioperative risk when severe OSA is suspected. We have developed a novel paediatric sleep service over the past decade based on the routine use of multi-channel sleep studies (MCSS) before adenotonsillectomy. We present the results of a prospective evaluation assessing the impact of our service on treatment outcomes. We conducted a prospective service evaluation of 49 children with SDB seen between July 2021 and August 2022. We used medical records and a sleep study database to determine treatment outcomes. Otolaryngologists completed a questionnaire before each multi-channel sleep study to help evaluate the impact of sleep study findings on surgical decision making. Questionnaire responses before MCSS showed that clinicians thought 66 % of children were 'likely', 'very likely' or 'definitely' would require surgery but only 54 % of children underwent surgery following their sleep study. We estimate that the use of MCSS was associated with a 21 % reduction in children undergoing surgery in this small sample. We conclude that our use of MCSS facilitates conservative management, allowing a significant reduction in the number of children with SDB undergoing surgery, but further validation of MCSS against polysomnography is required.
PubMed: 38800098
DOI: 10.1016/j.sleepx.2024.100111 -
Children (Basel, Switzerland) May 2024Holoprosencephaly is a complex human brain malformation resulting from incomplete cleavage of the prosencephalon into both hemispheres. Congenital nasal pyriform...
Holoprosencephaly is a complex human brain malformation resulting from incomplete cleavage of the prosencephalon into both hemispheres. Congenital nasal pyriform aperture stenosis (CNPAS) is sometimes found in patients with mild forms of holoprosencephaly. Surgical treatment is required. Low-invasive surgical approaches involve balloon dilation of the pyriform opening. We present the case of an 8-day-old girl diagnosed with holoprosencephaly, CNPAS, and the presence of a solitary median maxillary central incisor. Once examined by neonatologist, geneticist, pneumologist, otolaryngologist, and pediatric dentist, a combined otolaryngological-orthodontic approach was used. The obstruction of the right nasal cavity was treated by widening the nasal cavities and stabilizing them with a balloon dilation technique. After surgery, the respiratory space was increased by applying a neonatal palatal expander plate (NPEP) considering the palatal deformity: ogival shaped, anterior vertex growth direction, reduction of transverse diameters. The NPEP promoted distraction of the median palatine suture and assisted the nasal dilation. Therefore, after the insertion of NPEP, the physiological sucking-swallowing mechanism was activated. In infants with CNPAS, NPEP can be useful to ensure the safe stability of nasal dilation. A multidisciplinary approach is fundamental. In our experience, the close collaboration between an otolaryngologist and orthodontist is essential for the management of the patient with CNPAS.
PubMed: 38790549
DOI: 10.3390/children11050554