A contemporary review of machine learning in otolaryngology-head and neck surgery

Automated Detection of Pediatric Foreign Body Aspiration from Chest X-rays Using Machine Learning

OBJECTIVE/HYPOTHESIS

Standard chest radiographs are a poor diagnostic tool for pediatric foreign body aspiration. Machine learning may improve upon the diagnostic capabilities of chest radiographs. The objective is to develop a machine learning algorithm that improves the diagnostic capabilities of chest radiographs in pediatric foreign body aspiration.

METHOD

This retrospective, diagnostic study included a retrospective chart review of patients with a potential diagnosis of FBA from 2010 to 2020. Frontal view chest radiographs were extracted, processed, and uploaded to Google AutoML Vision. The developed algorithm was then evaluated against a pediatric radiologist.

RESULTS

The study selected 566 patients who were presented with a suspected diagnosis of foreign body aspiration. One thousand six hundred and eighty eight chest radiograph images were collected. The sensitivity and specificity of the radiologist interpretation were 50.6% (43.1-58.0) and 88.7% (85.3-91.5), respectively. The sensitivity and specificity of the algorithm were 66.7% (43.0-85.4) and 95.3% (90.6-98.1), respectively. The precision and recall of the algorithm were both 91.8% with an AuPRC of 98.3%.

CONCLUSION

Chest radiograph analysis augmented with machine learning can diagnose foreign body aspiration in pediatric patients at a level similar to a read performed by a pediatric radiologist despite only using single-view, fixed images. Overall, this study highlights the potential and capabilities of machine learning in diagnosing conditions with a wide range of clinical presentations.

LEVEL OF EVIDENCE

3 Laryngoscope, 134:3807-3814, 2024.

Predicting reoperation and readmission for head and neck free flap patients using machine learning

BACKGROUND

To develop machine learning (ML) models predicting unplanned readmission and reoperation among patients undergoing free flap reconstruction for head and neck (HN) surgery.

METHODS

Data were extracted from the 2012-2019 NSQIP database. eXtreme Gradient Boosting (XGBoost) was used to develop ML models predicting 30-day readmission and reoperation based on demographic and perioperative factors. Models were validated using 2019 data and evaluated.

RESULTS

Four-hundred and sixty-six (10.7%) of 4333 included patients were readmitted within 30 days of initial surgery. The ML model demonstrated 82% accuracy, 63% sensitivity, 85% specificity, and AUC of 0.78. Nine-hundred and four (18.3%) of 4931 patients underwent reoperation within 30 days of index surgery. The ML model demonstrated 62% accuracy, 51% sensitivity, 64% specificity, and AUC of 0.58.

CONCLUSION

XGBoost was used to predict 30-day readmission and reoperation for HN free flap patients. Findings may be used to assist clinicians and patients in shared decision-making and improve data collection in future database iterations.

Artificial intelligence based diagnosis of sulcus: assesment of videostroboscopy via deep learning

PURPOSE

To develop a convolutional neural network (CNN)-based model for classifying videostroboscopic images of patients with sulcus, benign vocal fold (VF) lesions, and healthy VFs to improve clinicians' accuracy in diagnosis during videostroboscopies when evaluating sulcus.

MATERIALS AND METHODS

Videostroboscopies of 433 individuals who were diagnosed with sulcus (91), who were diagnosed with benign VF diseases (i.e., polyp, nodule, papilloma, cyst, or pseudocyst [311]), or who were healthy (33) were analyzed. After extracting 91,159 frames from videostroboscopies, a CNN-based model was created and tested. The healthy and sulcus groups underwent binary classification. In the second phase of the study, benign VF lesions were added to the training set, and multiclassification was executed across all groups. The proposed CNN-based model results were compared with five laryngology experts' assessments.

RESULTS

In the binary classification phase, the CNN-based model achieved 98% accuracy, 98% recall, 97% precision, and a 97% F1 score for classifying sulcus and healthy VFs. During the multiclassification phase, when evaluated on a subset of frames encompassing all included groups, the CNN-based model demonstrated greater accuracy when compared with that of the five laryngologists (%76 versus 72%, 68%, 72%, 63%, and 72%).

CONCLUSION

The utilization of a CNN-based model serves as a significant aid in the diagnosis of sulcus, a VF disease that presents notable challenges in the diagnostic process. Further research could be undertaken to assess the practicality of implementing this approach in real-time application in clinical practice.

Can GPT-4 revolutionize otolaryngology? Navigating opportunities and ethical considerations

Otolaryngologists can enhance workflow efficiency, provide better patient care, and advance medical research and education by integrating artificial intelligence (AI) into their practices. GPT-4 technology is a revolutionary and contemporary example of AI that may apply to otolaryngology. The knowledge of otolaryngologists should be supplemented, not replaced when using GPT-4 to make critical medical decisions and provide individualized patient care. In our thorough examination, we explore the potential uses of the groundbreaking GPT-4 technology in the field of otolaryngology, covering aspects such as potential outcomes and technical boundaries. Additionally, we delve into the intricate and intellectually challenging dilemmas that emerge when incorporating GPT-4 into otolaryngology, considering the ethical considerations inherent in its implementation. Our stance is that GPT-4 has the potential to be very helpful. Its capabilities, which include aid in clinical decision-making, patient care, and administrative job automation, present exciting possibilities for enhancing patient outcomes, boosting the efficiency of healthcare delivery, and enhancing patient experiences. Even though there are still certain obstacles and limitations, the progress made so far shows that GPT-4 can be a valuable tool for modern medicine. GPT-4 may play a more significant role in clinical practice as technology develops, helping medical professionals deliver high-quality care tailored to every patient's unique needs.

Computer Vision-Radiomics & Pathognomics

The role of computer vision in extracting radiographic (radiomics) and histopathologic (pathognomics) features is an extension of molecular biomarkers that have been foundational to our understanding across the spectrum of head and neck disorders. Especially within head and neck cancers, machine learning and deep learning applications have yielded advances in the characterization of tumor features, nodal features, and various outcomes. This review aims to overview the landscape of radiomic and pathognomic applications, informing future work to address gaps. Novel methodologies will be needed to potentially engineer ways of integrating multidimensional data inputs to examine disease features to guide prognosis comprehensively and ultimately clinical management.

AI Detection of Glottic Neoplasm Using Voice Signals, Demographics, and Structured Medical Records

OBJECTIVE

This study investigated whether artificial intelligence (AI) models combining voice signals, demographics, and structured medical records can detect glottic neoplasm from benign voice disorders.

METHODS

We used a primary dataset containing 2-3 s of vowel "ah", demographics, and 26 items of structured medical records (e.g., symptoms, comorbidity, smoking and alcohol consumption, vocal demand) from 60 patients with pathology-proved glottic neoplasm (i.e., squamous cell carcinoma, carcinoma in situ, and dysplasia) and 1940 patients with benign voice disorders. The validation dataset comprised data from 23 patients with glottic neoplasm and 1331 patients with benign disorders. The AI model combined convolutional neural networks, gated recurrent units, and attention layers. We used 10-fold cross-validation (training-validation-testing: 8-1-1) and preserved the percentage between neoplasm and benign disorders in each fold.

RESULTS

Results from the AI model using voice signals reached an area under the ROC curve (AUC) value of 0.631, and additional demographics increased this to 0.807. The highest AUC of 0.878 was achieved when combining voice, demographics, and medical records (sensitivity: 0.783, specificity: 0.816, accuracy: 0.815). External validation yielded an AUC value of 0.785 (voice plus demographics; sensitivity: 0.739, specificity: 0.745, accuracy: 0.745). Subanalysis showed that AI had higher sensitivity but lower specificity than human assessment (p < 0.01). The accuracy of AI detection with additional medical records was comparable with human assessment (82% vs. 83%, p = 0.78).

CONCLUSIONS

Voice signal alone was insufficient for AI differentiation between glottic neoplasm and benign voice disorders, but additional demographics and medical records notably improved AI performance and approximated the prediction accuracy of humans.

LEVEL OF EVIDENCE

NA Laryngoscope, 2024.

Trust in Machine Learning Driven Clinical Decision Support Tools Among Otolaryngologists

BACKGROUND

Machine learning driven clinical decision support tools (ML-CDST) are on the verge of being integrated into clinical settings, including in Otolaryngology-Head & Neck Surgery. In this study, we investigated whether such CDST may influence otolaryngologists' diagnostic judgement.

METHODS

Otolaryngologists were recruited virtually across the United States for this experiment on human-AI interaction. Participants were shown 12 different video-stroboscopic exams from patients with previously diagnosed laryngopharyngeal reflux or vocal fold paresis and asked to determine the presence of disease. They were then exposed to a random diagnosis purportedly resulting from an ML-CDST and given the opportunity to revise their diagnosis. The ML-CDST output was presented with no explanation, a general explanation, or a specific explanation of its logic. The ML-CDST impact on diagnostic judgement was assessed with McNemar's test.

RESULTS

Forty-five participants were recruited. When participants reported less confidence (268 observations), they were significantly (p = 0.001) more likely to change their diagnostic judgement after exposure to ML-CDST output compared to when they reported more confidence (238 observations). Participants were more likely to change their diagnostic judgement when presented with a specific explanation of the CDST logic (p = 0.048).

CONCLUSIONS

Our study suggests that otolaryngologists are susceptible to accepting ML-CDST diagnostic recommendations, especially when less confident. Otolaryngologists' trust in ML-CDST output is increased when accompanied with a specific explanation of its logic.

LEVEL OF EVIDENCE

2 Laryngoscope, 134:2799-2804, 2024.

The future of maxillofacial prosthodontics in North America: The role of advanced digital technology and artificial intelligence - A discussion document

STATEMENT OF PROBLEM

Maxillofacial prosthodontists were advanced digital technology (ADT) adopters early in the new Millennium. The past two decades saw a range of digital enablers emerge including digital imaging (internal and surface), digital surgical planning, digital functional assessment, subtractive and additive manufacturing, navigation, and robotics among others. Artificial Intelligence (AI) is the latest ADT arrival that will be a challenging disruptive technology. ADT has served as a profound change agent in maxillofacial prosthodontics. The intent was to explore the process and level of ADT engagement in maxillofacial prosthodontics.

PURPOSE

The purpose was twofold. Firstly, to explore maxillofacial prosthodontic engagement of ADT. Secondly, to develop a discussion document to assist the American Academy of Maxillofacial Prosthetics (AAMP) with establishing a collective awareness and considered opinion on the future of maxillofacial prosthodontics in the digital era.

MATERIAL AND METHODS

AAMP member interest in ADT was assessed through analysis of AAMP annual congress programs and publications in the Journal of Prosthetic Dentistry (JPD). The history of the maxillofacial prosthodontic journey to the digital era was undertaken with a selective literature review. The perceptions maxillofacial prosthodontists hold on ADT engagement was assessed through a survey of AAMP members. Developing an understanding of the influence AI was conducted with a review of pertinent literature.

RESULTS

From 2011-2020, an annual mean of 38% of papers published in the JPD involved clinical use of ADT. From 2017-2019, 44% of invited presentations at AAMP annual congresses included clinical use of ADT. The journey to the digital era distinguished three periods with formative and consolidation periods influencing the innovation digital era. The AAMP member survey had a 59% response rate and studied 10 domains through 31 questions. Of the respondents, 89% thought ADT important to the future of maxillofacial prosthodontics.

CONCLUSIONS

The discussion document will assist the AAMP in developing a collective consciousness and considered opinion on ADT in the future of maxillofacial prosthodontics. Members of the AAMP have a developed interest in clinical applications of ADT. A great challenge is that no formal education, training, or clinical competency requirements for ADT could be identified. Clinical competency requirements are important to prepare maxillofacial prosthodontics for the inevitability of a digital era future. The discussion document poses the fundamental question of whether maxillofacial prosthodontists will remain as passive end users of ADT and AI or will they become engaged knowledge workers that have determined clinical competency in ADT and AI in patient care. Without this knowledge worker role, maxillofacial prosthodontists may experience difficulty being part of the inevitable ADT-AI driven future.

The Integration and Impact of Artificial Intelligence in Otolaryngology-Head and Neck Surgery: Navigating the Last Mile

Incorporating artificial Intelligence and machine learning into otolaryngology requires careful data handling, security, and ethical considerations. Success depends on interdisciplinary cooperation, consistent innovation, and regulatory compliance to improve clinical outcomes, provider experience, and operational effectiveness.

Machine learning in the evaluation of voice and swallowing in the head and neck cancer patient

PURPOSE OF REVIEW

The purpose of this review is to present recent advances and limitations in machine learning applied to the evaluation of speech, voice, and swallowing in head and neck cancer.

RECENT FINDINGS

Novel machine learning models incorporating diverse data modalities with improved discriminatory capabilities have been developed for predicting toxicities following head and neck cancer therapy, including dysphagia, dysphonia, xerostomia, and weight loss as well as guiding treatment planning. Machine learning has been applied to the care of posttreatment voice and swallowing dysfunction by offering objective and standardized assessments and aiding innovative technologies for functional restoration. Voice and speech are also being utilized in machine learning algorithms to screen laryngeal cancer.

SUMMARY

Machine learning has the potential to help optimize, assess, predict, and rehabilitate voice and swallowing function in head and neck cancer patients as well as aid in cancer screening. However, existing studies are limited by the lack of sufficient external validation and generalizability, insufficient transparency and reproducibility, and no clear superior predictive modeling strategies. Algorithms and applications will need to be trained on large multiinstitutional data sets, incorporate sociodemographic data to reduce bias, and achieve validation through clinical trials for optimal performance and utility.

The Use of Artificial Intelligence in Head and Neck Cancers: A Multidisciplinary Survey

Artificial intelligence (AI) approaches have been introduced in various disciplines but remain rather unused in head and neck (H&N) cancers. This survey aimed to infer the current applications of and attitudes toward AI in the multidisciplinary care of H&N cancers. From November 2020 to June 2022, a web-based questionnaire examining the relationship between AI usage and professionals' demographics and attitudes was delivered to different professionals involved in H&N cancers through social media and mailing lists. A total of 139 professionals completed the questionnaire. Only 49.7% of the respondents reported having experience with AI. The most frequent AI users were radiologists (66.2%). Significant predictors of AI use were primary specialty (V = 0.455; p < 0.001), academic qualification and age. AI's potential was seen in the improvement of diagnostic accuracy (72%), surgical planning (64.7%), treatment selection (57.6%), risk assessment (50.4%) and the prediction of complications (45.3%). Among participants, 42.7% had significant concerns over AI use, with the most frequent being the 'loss of control' (27.6%) and 'diagnostic errors' (57.0%). This survey reveals limited engagement with AI in multidisciplinary H&N cancer care, highlighting the need for broader implementation and further studies to explore its acceptance and benefits.

Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches

Eosinophilic chronic rhinosinusitis (ECRS) is a distinct subset of chronic rhinosinusitis characterized by heightened eosinophilic infiltration and increased symptom severity, often resisting standard treatments. Traditional diagnosis requires invasive histological evaluation. This study aims to develop predictive models for ECRS based on patient clinical parameters, eliminating the need for invasive biopsy. Utilizing logistic regression with lasso regularization, random forest (RF), gradient-boosted decision tree (GBDT), and deep neural network (DNN), we trained models on common clinical data. The predictive performance was evaluated using metrics such as area under the curve (AUC) for receiver operator characteristics, decision curves, and feature ranking analysis. In a cohort of 437 eligible patients, the models identified peripheral blood eosinophil ratio, absolute peripheral blood eosinophil, and the ethmoidal/maxillary sinus density ratio (E/M) on computed tomography as crucial predictors for ECRS. This predictive model offers a valuable tool for identifying ECRS without resorting to histological biopsy, enhancing clinical decision-making.

Predicting Acoustic Hearing Preservation Following Cochlear Implant Surgery Using Machine Learning

OBJECTIVES

The aim of the study was to train and test supervised machine-learning classifiers to predict acoustic hearing preservation after CI using preoperative clinical data.

STUDY DESIGN

Retrospective predictive modeling study of prospectively collected single-institution CI dataset.

METHODS

One hundred and seventy-five patients from a REDCap database including 761 patients >18 years who underwent CI and had audiometric testing preoperatively and one month after surgery were included. The primary outcome variable was the lowest quartile change in acoustic hearing at one month after CI using various formulae (standard pure tone average, SPTA; low-frequency PTA, LFPTA). Analysis involved applying multivariate logistic regression to detect statistical associations and training and testing supervised learning classifiers. Classifier performance was assessed with numerous metrics including area under the receiver operating characteristic curve (AUC) and Matthews correlation coefficient (MCC).

RESULTS

Lowest quartile change (indicating hearing preservation) in SPTA was positively associated with a history of meningitis, preoperative LFPTA, and preoperative SPTA. Lowest quartile change in SPTA was negatively associated with sudden hearing loss, noise exposure, aural fullness, and abnormal anatomy. Lowest quartile change in LFPTA was positively associated with preoperative LFPTA. Lowest quartile change in LFPTA was negatively associated with tobacco use. Random forest demonstrated the highest mean classification performance on the validation dataset when predicting each of the outcome variables.

CONCLUSIONS

Machine learning demonstrated utility for predicting preservation of residual acoustic hearing in patients undergoing CI surgery, and the detected associations facilitated the interpretation of our machine-learning models. The models and statistical associations together may be used to facilitate improvements in shared clinical decision-making and patient outcomes.

LEVEL OF EVIDENCE

3 Laryngoscope, 134:926-936, 2024.

Label-Free Optical Technologies for Middle-Ear Diseases

Medical applications of optical technology have increased tremendously in recent decades. Label-free techniques have the unique advantage of investigating biological samples in vivo without introducing exogenous agents. This is especially beneficial for a rapid clinical translation as it reduces the need for toxicity studies and regulatory approval for exogenous labels. Emerging applications have utilized label-free optical technology for screening, diagnosis, and surgical guidance. Advancements in detection technology and rapid improvements in artificial intelligence have expedited the clinical implementation of some optical technologies. Among numerous biomedical application areas, middle-ear disease is a unique space where label-free technology has great potential. The middle ear has a unique anatomical location that can be accessed through a dark channel, the external auditory canal; it can be sampled through a tympanic membrane of approximately 100 microns in thickness. The tympanic membrane is the only membrane in the body that is surrounded by air on both sides, under normal conditions. Despite these favorable characteristics, current examination modalities for middle-ear space utilize century-old technology such as white-light otoscopy. This paper reviews existing label-free imaging technologies and their current progress in visualizing middle-ear diseases. We discuss potential opportunities, barriers, and practical considerations when transitioning label-free technology to clinical applications.

Development of machine learning models for the prediction of long-term feeding tube dependence after oral and oropharyngeal cancer surgery

PURPOSE

To predict the necessity of enteral nutrition at 28 days after surgery in patients undergoing major head and neck oncologic procedures for oral and oropharyngeal cancers.

MATERIAL AND METHODS

Data from 193 patients with oral cavity and oropharyngeal squamous cell carcinoma were retrospectively collected at two tertiary referral centers to train (n = 135) and validate (n = 58) six supervised machine learning (ML) models for binary prediction employing 29 clinical variables available pre-operatively.

RESULTS

The accuracy of the six ML models ranged between 0.74 and 0.88, while the measured area under the curve (AUC) between 0.75 and 0.87. The ML algorithms showed high specificity (range 0.87-0.96) and moderate sensitivity (range: 0.31-0.77) in detecting patients with ≥28 days feeding tube dependence. Negative predictive value was higher (range: 0.81-0.93) compared to positive predictive value (range: 0.40-0.71). Finally, the F1 score ranged between 0.35 and 0.74.

CONCLUSIONS

Classification performance of the ML algorithms showed optimistic accuracy in the prediction of enteral nutrition at 28 days after surgery. Prospective studies are mandatory to define the clinical benefit of a ML-based pre-operative prediction of a personalized nutrition protocol.

Artificial Intelligence Governance and Otolaryngology-Head and Neck Surgery

This rapid communication highlights components of artificial intelligence governance in healthcare and suggests adopting key governance approaches in otolaryngology – head and neck surgery.

Advances in Image-Based Artificial Intelligence in Otorhinolaryngology-Head and Neck Surgery: A Systematic Review

OBJECTIVE

To update the literature and provide a systematic review of image-based artificial intelligence (AI) applications in otolaryngology, highlight its advances, and propose future challenges.

DATA SOURCES

Web of Science, Embase, PubMed, and Cochrane Library.

REVIEW METHODS

Studies written in English, published between January 2020 and December 2022. Two independent authors screened the search results, extracted data, and assessed studies.

RESULTS

Overall, 686 studies were identified. After screening titles and abstracts, 325 full-text studies were assessed for eligibility, and 78 studies were included in this systematic review. The studies originated from 16 countries. Among these countries, the top 3 were China (n = 29), Korea (n = 8), the United States, and Japan (n = 7 each). The most common area was otology (n = 35), followed by rhinology (n = 20), pharyngology (n = 18), and head and neck surgery (n = 5). Most applications of AI in otology, rhinology, pharyngology, and head and neck surgery mainly included chronic otitis media (n = 9), nasal polyps (n = 4), laryngeal cancer (n = 12), and head and neck squamous cell carcinoma (n = 3), respectively. The overall performance of AI in accuracy, the area under the curve, sensitivity, and specificity were 88.39 ± 9.78%, 91.91 ± 6.70%, 86.93 ± 11.59%, and 88.62 ± 14.03%, respectively.

CONCLUSION

This state-of-the-art review aimed to highlight the increasing applications of image-based AI in otorhinolaryngology head and neck surgery. The following steps will entail multicentre collaboration to ensure data reliability, ongoing optimization of AI algorithms, and integration into real-world clinical practice. Future studies should consider 3-dimensional (3D)-based AI, such as 3D surgical AI.

Current role of artificial intelligence in head and neck cancer surgery: a systematic review of literature

Aim

Artificial intelligence (AI) is a new field of science in which computers will provide decisions-supporting tools to help doctors make difficult clinical choices. Recent AI applications in otolaryngology include head and neck oncology, rhinology, neurotology, and laryngology. The aim of this systematic review is to describe the potential uses of AI in head and neck oncology with a special focus on the surgical field.

Methods

The authors performed a systematic review, in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines, in the main medical databases, including PubMed, Scopus, and Cochrane Library, considering all original studies published until February 2023 about the role of AI in head and neck cancer surgery. The search strategy included a combination of the following terms: "artificial intelligence" or "machine learning" and "head and neck cancer".

Results

Overall, 303 papers were identified and after duplicate removal (12 papers) and excluding papers not written in English (1 paper) and off-topic (4 papers), papers were assessed for eligibility; finally, only 12 papers were included. Three main fields of clinical interest were identified: the most widely investigated included the role of AI in surgical margins assessment (7 papers); the second most frequently evaluated topic was complications assessment (4 papers); finally, only one paper dealt with the indication of salvage laryngectomy after primary radiotherapy.

Conclusions

The authors report the first systematic review in the literature concerning the role of AI in head and neck cancer surgery. An increasing influx of AI applications to clinical problems in otolaryngology is expected, so specialists should be increasingly prepared to manage the constant changes. It will always remain critical for clinicians to use their skills and knowledge to critically evaluate the additional information provided by AI and make the final decisions on each patient.

End-to-end deep learning classification of vocal pathology using stacked vowels

Objectives

Advances in artificial intelligence (AI) technology have increased the feasibility of classifying voice disorders using voice recordings as a screening tool. This work develops upon previous models that take in single vowel recordings by analyzing multiple vowel recordings simultaneously to enhance prediction of vocal pathology.

Methods

Voice samples from the Saarbruecken Voice Database, including three sustained vowels (/a/, /i/, /u/) from 687 healthy human participants and 334 dysphonic patients, were used to train 1-dimensional convolutional neural network models for multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings. Three models were trained: (1) a baseline model that analyzed individual vowels in isolation, (2) a stacked vowel model that analyzed three vowels (/a/, /i/, /u/) in the neutral pitch simultaneously, and (3) a stacked pitch model that analyzed the /a/ vowel in three pitches (low, neutral, and high) simultaneously.

Results

For multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings, the stacked vowel model demonstrated higher performance compared with the baseline and stacked pitch models (F1 score 0.81 vs. 0.77 and 0.78, respectively). Specifically, the stacked vowel model achieved higher performance for class-specific classification of hyperfunctional dysphonia voice samples compared with the baseline and stacked pitch models (F1 score 0.56 vs. 0.49 and 0.50, respectively).

Conclusions

This study demonstrates the feasibility and potential of analyzing multiple sustained vowel recordings simultaneously to improve AI-driven screening and classification of vocal pathology. The stacked vowel model architecture in particular offers promise to enhance such an approach.

Lay Summary

AI analysis of multiple vowel recordings can improve classification of voice pathologies compared with models using a single sustained vowel and offer a strategy to enhance AI-driven screening of voice disorders.

Level of Evidence

3.

Development of machine learning models to predict lymph node metastases in major salivary gland cancers

INTRODUCTION

Indications for elective treatment of the neck in patients with major salivary gland cancers are still debated. Our purpose was to develop a machine learning (ML) model able to generate a predictive algorithm to identify lymph node metastases (LNM) in patients with major salivary gland cancer (SGC).

METHODS

A Retrospective study was performed with data obtained from the Surveillance, Epidemiology, and End Results (SEER) program. Patients diagnosed with a major SGC between 1988 and 2019 were included. Two 2-class supervised ML decision models (random forest, RF; extreme gradient boosting, XGB) were used to predict the presence of LNM, implementing thirteen demographics and clinical variables collected from the SEER database. A permutation feature importance (PFI) score was computed using the testing dataset to identify the most important variables used in model prediction.

RESULTS

A total of 10 350 patients (males: 52%; mean age: 59.9 ± 17.2 years) were included in the study. The RF and the XGB prediction models showed an overall accuracy of 0.68. Both models showed a high specificity (RF: 0.90; XGB: 0.83) and low sensitivity (RF: 0.27; XGB: 0.38) in identifying LNM. According, a high negative predictive value (RF: 0.70; XGB: 0.72) and a low positive predictive value (RF: 0.58; XGB: 0.56) were measured. T classification and tumor size were the most important features in the construction of the prediction algorithms.

CONCLUSIONS

Classification performance of the ML algorithms showed high specificity and negative predictive value that allow to preoperatively identify patients with a lower risk of LNM.

LAY SUMMARY

Based on data from the Surveillance, Epidemiology, and End Results (SEER) program, our study showed that machine learning algorithms owns a high specificity and negative predictive value, allowing to preoperatively identify patients with a lower risk of lymph node metastasis.

LEVEL OF EVIDENCE: 3

A Machine Learning Approach to Assess Patients with Deep Neck Infection Progression to Descending Mediastinitis: Preliminary Results

BACKGROUND

Deep neck infection (DNI) is a serious infectious disease, and descending mediastinitis is a fatal infection of the mediastinum. However, no study has applied artificial intelligence to assess progression to descending mediastinitis in DNI patients. Thus, we developed a model to assess the possible progression of DNI to descending mediastinitis.

METHODS

Between August 2017 and December 2022, 380 patients with DNI were enrolled; 75% of patients (n = 285) were assigned to the training group for validation, whereas the remaining 25% (n = 95) were assigned to the test group to determine the accuracy. The patients' clinical and computed tomography (CT) parameters were analyzed via the k-nearest neighbor method. The predicted and actual progression of DNI patients to descending mediastinitis were compared.

RESULTS

In the training and test groups, there was no statistical significance (all p > 0.05) noted at clinical variables (age, gender, chief complaint period, white blood cells, C-reactive protein, diabetes mellitus, and blood sugar), deep neck space (parapharyngeal, submandibular, retropharyngeal, and multiple spaces involved, ≥3), tracheostomy performance, imaging parameters (maximum diameter of abscess and nearest distance from abscess to level of sternum notch), or progression to mediastinitis. The model had a predictive accuracy of 82.11% (78/95 patients), with sensitivity and specificity of 41.67% and 87.95%, respectively.

CONCLUSIONS

Our model can assess the progression of DNI to descending mediastinitis depending on clinical and imaging parameters. It can be used to identify DNI patients who will benefit from prompt treatment.

The Evolution and Application of Artificial Intelligence in Rhinology: A State of the Art Review

OBJECTIVE

To provide a comprehensive overview on the applications of artificial intelligence (AI) in rhinology, highlight its limitations, and propose strategies for its integration into surgical practice.

DATA SOURCES

Medline, Embase, CENTRAL, Ei Compendex, IEEE, and Web of Science.

REVIEW METHODS

English studies from inception until January 2022 and those focusing on any application of AI in rhinology were included. Study selection was independently performed by 2 authors; discrepancies were resolved by the senior author. Studies were categorized by rhinology theme, and data collection comprised type of AI utilized, sample size, and outcomes, including accuracy and precision among others.

CONCLUSIONS

An overall 5435 articles were identified. Following abstract and title screening, 130 articles underwent full-text review, and 59 articles were selected for analysis. Eleven studies were from the gray literature. Articles were stratified into image processing, segmentation, and diagnostics (n = 27); rhinosinusitis classification (n = 14); treatment and disease outcome prediction (n = 8); optimizing surgical navigation and phase assessment (n = 3); robotic surgery (n = 2); olfactory dysfunction (n = 2); and diagnosis of allergic rhinitis (n = 3). Most AI studies were published from 2016 onward (n = 45).

IMPLICATIONS FOR PRACTICE

This state of the art review aimed to highlight the increasing applications of AI in rhinology. Next steps will entail multidisciplinary collaboration to ensure data integrity, ongoing validation of AI algorithms, and integration into clinical practice. Future research should be tailored at the interplay of AI with robotics and surgical education.

Automatic Measuring of Finger Joint Space Width on Hand Radiograph using Deep Learning and Conventional Computer Vision Methods

Hand osteoarthritis (OA) severity can be assessed visually through radiographs using semi-quantitative grading systems. However, these grading systems are subjective and cannot distinguish minor differences. Joint space width (JSW) compensates for these disadvantages, as it quantifies the severity of OA by accurately measuring the distances between joint bones. Current methods used to assess JSW require users' interaction to identify the joints and delineate initial joint boundary, which is time-consuming. To automate this process and offer a more efficient and robust measurement for JSW, we proposed two novel methods to measure JSW: 1) The segmentation-based (SEG) method, which uses traditional computer vision techniques to calculate JSW; 2) The regression-based (REG) method, which is a deep learning approach employing a modified VGG-19 network to predict JSW. On a dataset with 3,591 hand radiographs, 10,845 DIP joints were cut as regions of interest and served as input to the SEG and REG methods. The bone masks of the ROI images generated by a U-Net model were sent as input in addition to the ROIs. The ground truth of JSW was labeled by a trained research assistant using a semi-automatic tool. Compared with the ground truth, the REG method achieved a correlation coefficient of 0.88 and mean square error (MSE) of 0.02 mm on the testing set; the SEG method achieved a correlation coefficient of 0.42 and MSE of 0.15 mm. Results show the REG method has promising performance in automatic JSW measurement and in general, Deep Learning approaches can facilitate the automatic quantification of distance features in medical images.

Nanocatalysts as fast and powerful medical intervention: Bridging cochlear implant therapies and advanced modelling using Hidden Markov Models (HMMs) for effective treatment of infections

As human population growth and waste from technologically advanced industries threaten to destabilise our delicate ecological equilibrium, the global spotlight intensifies on environmental contamination and climate-related changes. These challenges extend beyond our external environment and have significant effects on our internal ecosystems. The inner ear, which is responsible for balance and auditory perception, is a prime example. When these sensory mechanisms are impaired, disorders such as deafness can develop. Traditional treatment methods, including systemic antibiotics, are frequently ineffective due to inadequate inner ear penetration. Conventional techniques for administering substances to the inner ear fail to obtain adequate concentrations as well. In this context, cochlear implants laden with nanocatalysts emerge as a promising strategy for the targeted treatment of inner ear infections. Coated with biocompatible nanoparticles containing specific nanocatalysts, these implants can degrade or neutralise contaminants linked to inner ear infections. This method enables the controlled release of nanocatalysts directly at the infection site, thereby maximising therapeutic efficacy and minimising adverse effects. In vivo and in vitro studies have demonstrated that these implants are effective at eliminating infections, reducing inflammation, and fostering tissue regeneration in the ear. This study investigates the application of hidden Markov models (HMMs) to nanocatalyst-loaded cochlear implants. The HMM is trained on surgical phases in order to accurately identify the various phases associated with implant utilisation. This facilitates the precision placement of surgical instruments within the ear, with a location accuracy between 91% and 95% and a standard deviation between 1% and 5% for both sites. In conclusion, nanocatalysts serve as potent medicinal instruments, bridging cochlear implant therapies and advanced modelling utilising hidden Markov models for the effective treatment of inner ear infections. Cochlear implants loaded with nanocatalysts offer a promising method to combat inner ear infections and enhance patient outcomes by addressing the limitations of conventional treatments.

Advances in Artificial Intelligence to Diagnose Otitis Media: State of the Art Review

OBJECTIVE

Otitis media (OM) is a model disease for developing, validating, and implementing artificial intelligence (AI) techniques. We aim to review the state of the art applications of AI used to diagnose OM in pediatric and adult populations.

DATA SOURCES

Several comprehensive databases were searched to identify all articles that applied AI technologies to diagnose OM.

REVIEW METHODS

Relevant articles from January 2010 through May 2021 were identified by title and abstract. Articles were excluded if they did not discuss AI in conjunction with diagnosing OM. References of included studies and relevant review articles were cross-referenced to identify any additional studies.

CONCLUSION

Title and abstract screening resulted in full-text retrieval of 40 articles that met initial screening parameters. Of this total, secondary review articles (n = 7) and commentary-based articles (n = 2) were removed, as were articles that did not specifically discuss AI and OM diagnosis (n = 5), leaving 25 articles for review. Applications of AI technologies specific to diagnosing OM included machine learning and natural language processing (n = 23) and prototype approaches (n = 2).

IMPLICATIONS FOR PRACTICE

This review emphasizes the utility of AI techniques to automate and aid in diagnosing OM. Although these techniques are still in the development and testing stages, AI has the potential to improve the practice of otolaryngologists and primary care clinicians by increasing the efficiency and accuracy of diagnoses.

Artificial Intelligence and Laryngeal Cancer: From Screening to Prognosis: A State of the Art Review

OBJECTIVE

This state of the art review aims to examine contemporary advances in applications of artificial intelligence (AI) to the screening, detection, management, and prognostication of laryngeal cancer (LC).

DATA SOURCES

Four bibliographic databases were searched: PubMed, EMBASE, Cochrane, and IEEE.

REVIEW METHODS

A structured review of the current literature (up to January 2022) was performed. Search terms related to topics of AI in LC were identified and queried by 2 independent reviewers. Citations of selected studies and review articles were also evaluated to ensure comprehensiveness.

CONCLUSIONS

AI applications in LC have encompassed a variety of data modalities, including radiomics, genomics, acoustics, clinical data, and videomics, to support screening, diagnosis, therapeutic decision making, and prognosis. However, most studies remain at the proof-of-concept level, as AI algorithms are trained on single-institution databases with limited data sets and a single data modality.

IMPLICATIONS FOR PRACTICE

AI algorithms in LC will need to be trained on large multi-institutional data sets and integrate multimodal data for optimal performance and clinical utility from screening to prognosis. Out of the data types reviewed, genomics has the most potential to provide generalizable models thanks to available large multi-institutional open access genomic data sets. Voice acoustic data represent an inexpensive and accurate biomarker, which is easy and noninvasive to capture, offering a unique opportunity for screening and monitoring of LA, especially in low-resource settings.

Development of machine learning models for the prediction of positive surgical margins in transoral robotic surgery (TORS)

PURPOSE

To develop machine learning (ML) models for predicting positive margins in patients undergoing transoral robotic surgery (TORS).

METHODS

Data from 453 patients with laryngeal, hypopharyngeal, and oropharyngeal squamous cell carcinoma were retrospectively collected at a tertiary referral center to train (n = 316) and validate (n = 137) six two-class supervised ML models employing 14 variables available pre-operatively.

RESULTS

The accuracy of the six ML models ranged between 0.67 and 0.75, while the measured AUC between 0.68 and 0.75. The ML algorithms showed high specificity (range: 0.75-0.89) and low sensitivity (range: 0.26-0.64) in detecting patients with positive margins after TORS. NPV was higher (range: 0.73-0.83) compared to PPV (range: 0.45-0.63). T classification and tumor site were the most important predictors of positive surgical margins.

CONCLUSIONS

ML algorithms can identify patients with low risk of positive margins and therefore amenable to TORS.

Artificial Neural Network-Assisted Classification of Hearing Prognosis of Sudden Sensorineural Hearing Loss With Vertigo

This study aimed to determine the impact on hearing prognosis of the coherent frequency with high magnitude-squared wavelet coherence (MSWC) in video head impulse test (vHIT) among patients with sudden sensorineural hearing loss with vertigo (SSNHLV) undergoing high-dose steroid treatment. This study was a retrospective cohort study. SSNHLV patients treated at our referral center from December 2016 to December 2020 were examined. The cohort comprised 64 patients with SSNHLV undergoing high-dose steroid treatment. MSWC was measured by calculating the wavelet coherence analysis (WCA) at various frequencies from a vHIT. The hearing prognosis were analyzed using a multivariable Cox regression model and convolution neural network (CNN) of WCA. There were 64 patients with a male-to-female ratio of 1:1.67. The greater highest coherent frequency of the posterior semicircular canal (SCC) was associated with the complete recovery (CR) of hearing. After adjustment for other factors, the result remained robust (hazard ratio [HR] 2.11, 95% confidence interval [CI] 1.86-2.35). In the feature extraction with Resnet-50 and proceeding SVM in the horizontal image cropping style, the classification accuracy [STD] for (CR vs. partial + no recovery [PR + NR]), (over-sampling of CR vs. PR + NR), (extensive data extraction of CR vs. PR + NR), and (interpolation of time series of CR vs. PR + NR) were 83.6% [7.4], 92.1% [6.8], 88.9% [7.5], and 91.6% [6.4], respectively. The high coherent frequency of the posterior SCC was a significantly independent factor that was associated with good hearing prognosis in the patients who have SSNHLV. WCA may be provided with comprehensive ability in vestibulo-ocular reflex (VOR) evaluation. CNN could be utilized to classify WCA, predict treatment outcomes, and facilitate vHIT interpretation. Feature extraction in CNN with proceeding SVM and horizontal cropping style of wavelet coherence plot performed better accuracy and offered more stable model for hearing outcomes in patients with SSNHLV than pure CNN classification. Clinical and Translational Impact Statement-High coherent frequency in vHIT results in good hearing outcomes in SSNHLV and facilitates AI classification.

Localization and quantification of glottal gaps on deep learning segmentation of vocal folds

The entire glottis has mostly been the focus in the tracking of the vocal folds, both manually and automatically. From a treatment point of view, the various regions of the glottis are of specific interest. The aim of the study was to test if it was possible to supplement an existing convolutional neural network (CNN) with post-network calculations for the localization and quantification of posterior glottal gaps during phonation, usable for vocal fold function analysis of e.g. laryngopharyngeal reflux findings. 30 subjects/videos with insufficient closure in the rear glottal area and 20 normal subjects/videos were selected from our database, recorded with a commercial high-speed video setup (HSV with 4000 frames per second), and segmented with an open-source CNN for validating voice function. We made post-network calculations to localize and quantify the 10% and 50% distance lines from the rear part of the glottis. The results showed a significant difference using the algorithm at the 10% line distance between the two groups of p < 0.0001 and no difference at 50%. These novel results show that it is possible to use post-network calculations on CNNs for the localization and quantification of posterior glottal gaps.

Development, Validation and Comparison of Artificial Neural Network and Logistic Regression Models Predicting Eosinophilic Chronic Rhinosinusitis With Nasal Polyps

PURPOSE

Chronic rhinosinusitis with nasal polyps (CRSwNP) can be classified into eosinophilic CRSwNP (eCRSwNP) and non-eosinophilic CRSwNP (non-eCRSwNP) by tissue biopsy, which is difficult to perform preoperatively. Clinical biomarkers have predictive value for the classification of CRSwNP. We aimed to evaluate the application of artificial neural network (ANN) modeling in distinguishing different endotypes of CRSwNP based on clinical biomarkers.

METHODS

Clinical parameters were collected from 109 CRSwNP patients, and their predictive ability was analyzed. ANN and logistic regression (LR) models were developed in the training group (72 patients) and further tested in the test group (37 patients). The output variable was the diagnosis of eCRSwNP, defined as tissue eosinophil count > 10 per high-power field. The receiver operating characteristics curve was used to assess model performance.

RESULTS

A total of 15 clinical features from 60 healthy controls, 60 eCRSwNP and 49 non-eCRSwNP were selected as candidate predictors. Nasal nitric oxide levels, peripheral eosinophil absolute count, total immunoglobulin E, and ratio of bilateral computed tomography scores for the ethmoid sinus and maxillary sinus were identified as important features for modeling. Two ANN models based on 4 and 15 clinical features were developed to predict eCRSwNP, which showed better performance, with the area under the receiver operator characteristics significantly higher than those from the respective LR models (0.976 vs. 0.902, P = 0.048; 0.970 vs. 0.845, P = 0.011). All ANN models had better fits than single variable prediction models (all P < 0.05), and ANN model 1 had the best predictive performance among all models.

CONCLUSIONS

Machine learning models assist clinicians in predicting endotypes of nasal polyps before invasive detection. The ANN model has the potential to predict eCRSwNP with high sensitivity and specificity, and is superior to the LR model. ANNs are valuable for optimizing personalized patient management.

Comparison of convolutional neural networks for classification of vocal fold nodules from high-speed video images

OBJECTIVES

Deep learning is in this study used through convolutional neural networks (CNN) to the determination of vocal fold nodules. Through high-speed video (HSV) images and computer-assisted tools, a comparison of convolutional neural network models and their accuracy will be presented.

METHODS

The data have been collected by an Ear Nose Throat (ENT) specialist with a 90° rigid scope in the years from 2007 to 2019, where 15.732 high-speed videos have been collected from 7909 patients. A total of 4000 images have been carefully selected, 2000 images were of normal vocal folds and 2000 images were of vocal folds with varying degrees of vocal fold nodules. These images were then split into training-, validation-, and testing-data set, for use with a CNN model with 5 layers (CNN5) and compared to other models: VGG19, MobileNetV2, and Inception-ResNetV2. To compare the neural network models, the following evaluation metrics have been calculated: accuracy, sensitivity, specificity, precision, and negative predictive values.

RESULTS

All the trained CNN models have shown high accuracy when applied to the test set. The accuracy is 97.75%, 83.5%, 91.5%, and 89.75%, for CNN5, VGG19, MobileNetV2, and InceptionResNetV2, respectively.

CONCLUSIONS

Precision was identified as the most relevant performance metric for a study that focuses on the classification of vocal fold nodules. The highest performing model was MobilNetV2 with a precision of 97.7%. The average accuracy across all 4 neural networks was 90.63% showing that neural networks can be used for classifying vocal fold nodules in a clinical setting.

Developing an Artificial Intelligence Tool to Predict Vocal Cord Pathology in Primary Care Settings

OBJECTIVES

Diagnostic tools for voice disorders are lacking for primary care physicians. Artificial intelligence (AI) tools may add to the armamentarium for physicians, decreasing the time to diagnosis and limiting the burden of dysphonia.

METHODS

Voice recordings of patients were collected from 2019 to 2021 using smartphones. The Saarbruecken dataset was included for comparison. Audio files were converted to mel-spectrograms using TensorFlow. Diagnostic categories were created to group pathology, including neurological and muscular disorders, inflammatory, mass lesions, and normal. The samples were further separated into sustained/a/and the rainbow passage.

RESULTS

Two hundred three prospective samples and 1131 samples were used from the Saarbruecken database. The AI detected abnormal pathology with an F1-score of 98%. The artificial neural network (ANN) differentiated key pathologies, including unilateral paralysis, laryngitis, adductor spasmodic dysphonia (ADSD), mass lesions, and normal samples with 39%-87% F-1 scores. The Calgary database models had higher F-1 scores in a head-to-head comparison to the Saarbruecken and combined datasets (87% vs. 58% and 50%). The AI outperformed otolaryngologists using a standardized test set of recordings (83% compared to 55% ± 15%).

CONCLUSION

An AI tool was created to differentiate pathology by individual or categorical diagnosis with high evaluation metrics. Prospective data should be collected in a controlled fashion to reduce intrinsic variability between recordings. Multi-center data collaborations are imperative to increase the prediction capability of AI tools for detecting vocal cord pathology. We provide proof-of-concept for an AI tool to assist primary care physicians in managing dysphonic patients.

LEVEL OF EVIDENCE

3 Laryngoscope, 2022.

Machine Learning in the Management of Lateral Skull Base Tumors: A Systematic Review

The application of machine learning (ML) techniques to otolaryngology remains a topic of interest and prevalence in the literature, though no previous articles have summarized the current state of ML application to management and the diagnosis of lateral skull base (LSB) tumors. Subsequently, we present a systematic overview of previous applications of ML techniques to the management of LSB tumors. Independent searches were conducted on PubMed and Web of Science between August 2020 and February 2021 to identify the literature pertaining to the use of ML techniques in LSB tumor surgery written in the English language. All articles were assessed in regard to their application task, ML methodology, and their outcomes. A total of 32 articles were examined. The number of articles involving applications of ML techniques to LSB tumor surgeries has significantly increased since the first article relevant to this field was published in 1994. The most commonly employed ML category was tree-based algorithms. Most articles were included in the category of surgical management (13; 40.6%), followed by those in disease classification (8; 25%). Overall, the application of ML techniques to the management of LSB tumor has evolved rapidly over the past two decades, and the anticipated growth in the future could significantly augment the surgical outcomes and management of LSB tumors.

Artificial intelligence and tele-otoscopy: A window into the future of pediatric otology

Telehealth in otolaryngology is gaining popularity as a potential tool for increased access for rural populations, decreased specialist wait times, and overall savings to the healthcare system. The adoption of telehealth has been dramatically increased by the COVID-19 pandemic limiting patients' physical access to hospitals and clinics. One of the key challenges to telehealth in general otolaryngology and otology specifically is the limited physical examination possible on the ear canal and middle ear. This is compounded in pediatric populations who commonly present with middle ear pathologies which can be challenging to diagnose even in the clinic. To address this need, various otoscopes have been designed to allow patients, their parents, or primary care providers to image the tympanic membrane and middle ear, and send data to otolaryngologists for review. Furthermore, the ability of these devices to capture images in digital format has opened the possibility of using artificial intelligence for quick and reliable diagnostic workup. In this manuscript, we provide a concise review of the literature regarding the efficacy of remote otoscopy, as well as recent efforts on the use of artificial intelligence in aiding otologic diagnoses.

Smartphone-based artificial intelligence using a transfer learning algorithm for the detection and diagnosis of middle ear diseases: A retrospective deep learning study

BACKGROUND

Middle ear diseases such as otitis media and middle ear effusion, for which diagnoses are often delayed or misdiagnosed, are among the most common issues faced by clinicians providing primary care for children and adolescents. Artificial intelligence (AI) has the potential to assist clinicians in the detection and diagnosis of middle ear diseases through imaging.

METHODS

Otoendoscopic images obtained by otolaryngologists from Taipei Veterans General Hospital in Taiwan between Jany 1, 2011 to Dec 31, 2019 were collected retrospectively and de-identified. The images were entered into convolutional neural network (CNN) training models after data pre-processing, augmentation and splitting. To differentiate sophisticated middle ear diseases, nine CNN-based models were constructed to recognize middle ear diseases. The best-performing models were chosen and ensembled in a small CNN for mobile device use. The pretrained model was converted into the smartphone-based program, and the utility was evaluated in terms of detecting and classifying ten middle ear diseases based on otoendoscopic images. A class activation map (CAM) was also used to identify key features for CNN classification. The performance of each classifier was determined by its accuracy, precision, recall, and F1-score.

FINDINGS

A total of 2820 clinical eardrum images were collected for model training. The programme achieved a high detection accuracy for binary outcomes (pass/refer) of otoendoscopic images and ten different disease categories, with an accuracy reaching 98.0% after model optimisation. Furthermore, the application presented a smooth recognition process and a user-friendly interface and demonstrated excellent performance, with an accuracy of 97.6%. A fifty-question questionnaire related to middle ear diseases was designed for practitioners with different levels of clinical experience. The AI-empowered mobile algorithm's detection accuracy was generally superior to that of general physicians, resident doctors, and otolaryngology specialists (36.0%, 80.0% and 90.0%, respectively). Our results show that the proposed method provides sufficient treatment recommendations that are comparable to those of specialists.

INTERPRETATION

We developed a deep learning model that can detect and classify middle ear diseases. The use of smartphone-based point-of-care diagnostic devices with AI-empowered automated classification can provide real-world smart medical solutions for the diagnosis of middle ear diseases and telemedicine.

FUNDING

This study was supported by grants from the Ministry of Science and Technology (MOST110-2622-8-075-001, MOST110-2320-B-075-004-MY3, MOST-110-2634-F-A49 -005, MOST110-2745-B-075A-001A and MOST110-2221-E-075-005), Veterans General Hospitals and University System of Taiwan Joint Research Program (VGHUST111-G6-11-2, VGHUST111c-140), and Taipei Veterans General Hospital (V111E-002-3).

Initial experience of a deep learning application for the differentiation of Kikuchi-Fujimoto’s disease from tuberculous lymphadenitis on neck CECT

Neck contrast-enhanced CT (CECT) is a routine tool used to evaluate patients with cervical lymphadenopathy. This study aimed to evaluate the ability of convolutional neural networks (CNNs) to classify Kikuchi-Fujimoto’s disease (KD) and cervical tuberculous lymphadenitis (CTL) on neck CECT in patients with benign cervical lymphadenopathy. A retrospective analysis of consecutive patients with biopsy-confirmed KD and CTL in a single center, from January 2012 to June 2020 was performed. This study included 198 patients of whom 125 patients (mean age, 25.1 years ± 8.7, 31 men) had KD and 73 patients (mean age, 41.0 years ± 16.8, 34 men) had CTL. A neuroradiologist manually labelled the enlarged lymph nodes on the CECT images. Using these labels as the reference standard, a CNNs was developed to classify the findings as KD or CTL. The CT images were divided into training (70%), validation (10%), and test (20%) subsets. As a supervised augmentation method, the Cut&Remain method was applied to improve performance. The best area under the receiver operating characteristic curve for classifying KD from CTL for the test set was 0.91. This study shows that the differentiation of KD from CTL on neck CECT using a CNNs is feasible with high diagnostic performance.

Deep Learning Artificial Intelligence to Predict the Need for Tracheostomy in Patients of Deep Neck Infection Based on Clinical and Computed Tomography Findings—Preliminary Data and a Pilot Study

Background: Deep neck infection (DNI) can lead to airway obstruction. Rather than intubation, some patients need tracheostomy to secure the airway. However, no study has used deep learning (DL) artificial intelligence (AI) to predict the need for tracheostomy in DNI patients. Thus, the purpose of this study was to develop a DL framework to predict the need for tracheostomy in DNI patients. Methods: 392 patients with DNI were enrolled in this study between August 2016 and April 2022; 80% of the patients (n = 317) were randomly assigned to a training group for model validation, and the remaining 20% (n = 75) were assigned to the test group to determine model accuracy. The k-nearest neighbor method was applied to analyze the clinical and computed tomography (CT) data of the patients. The predictions of the model with regard to the need for tracheostomy were compared with actual decisions made by clinical experts. Results: No significant differences were observed in clinical or CT parameters between the training group and test groups. The DL model yielded a prediction accuracy of 78.66% (59/75 cases). The sensitivity and specificity values were 62.50% and 80.60%, respectively. Conclusions: We demonstrated a DL framework to predict the need for tracheostomy in DNI patients based on clinical and CT data. The model has potential for clinical application; in particular, it may assist less experienced clinicians to determine whether tracheostomy is necessary in cases of DNI.

The state of the art for artificial intelligence in lung digital pathology

Lung diseases carry a significant burden of morbidity and mortality worldwide. The advent of digital pathology (DP) and an increase in computational power have led to the development of artificial intelligence (AI)-based tools that can assist pathologists and pulmonologists in improving clinical workflow and patient management. While previous works have explored the advances in computational approaches for breast, prostate, and head and neck cancers, there has been a growing interest in applying these technologies to lung diseases as well. The application of AI tools on radiology images for better characterization of indeterminate lung nodules, fibrotic lung disease, and lung cancer risk stratification has been well documented. In this article, we discuss methodologies used to build AI tools in lung DP, describing the various hand-crafted and deep learning-based unsupervised feature approaches. Next, we review AI tools across a wide spectrum of lung diseases including cancer, tuberculosis, idiopathic pulmonary fibrosis, and COVID-19. We discuss the utility of novel imaging biomarkers for different types of clinical problems including quantification of biomarkers like PD-L1, lung disease diagnosis, risk stratification, and prediction of response to treatments such as immune checkpoint inhibitors. We also look briefly at some emerging applications of AI tools in lung DP such as multimodal data analysis, 3D pathology, and transplant rejection. Lastly, we discuss the future of DP-based AI tools, describing the challenges with regulatory approval, developing reimbursement models, planning clinical deployment, and addressing AI biases. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Deep learning model developed by multiparametric MRI in differential diagnosis of parotid gland tumors

PURPOSE

To create a new artificial intelligence approach based on deep learning (DL) from multiparametric MRI in the differential diagnosis of common parotid tumors.

METHODS

Parotid tumors were classified using the InceptionResNetV2 DL model and majority voting approach with MRI images of 123 patients. The study was conducted in three stages. At stage I, the classification of the control, pleomorphic adenoma, Warthin tumor and malignant tumor (MT) groups was examined, and two approaches in which MRI sequences were given in combined and non-combined forms were established. At stage II, the classification of the benign tumor, MT and control groups was made. At stage III, patients with a tumor in the parotid gland and those with a healthy parotid gland were classified.

RESULTS

A stage I, the accuracy value for classification in the non-combined and combined approaches was 86.43% and 92.86%, respectively. This value at stage II and stage III was found respectively as 92.14% and 99.29%.

CONCLUSIONS

The approach presented in this study classifies parotid tumors automatically and with high accuracy using DL models.

Development of a machine-learning based voice disorder screening tool

OBJECTIVE

Early recognition and referral are crucial for voice disorder management. Limited availability of subspecialists, poor primary care awareness, and the need for specialized equipment impede effective care. Thus, there is a need for a tool to improve voice pathology screening. Machine learning algorithms (MLAs) have shown promise in analyzing acoustic characteristics of phonation. However, few studies report clinical applications of MLAs for voice pathology detection. The objective of this study was to design and validate a MLA for detecting pathological voices.

METHODS

A MLA was developed for voice analysis. Audio samples converted into spectrograms were inputted into a pre-existing VGG19 convolutional neural network (CNN) and image-classifier. The resulting feature map was classified as either pathological or healthy using a Support Vector Machine (SVM) binary linear classifier. This combined MLA was "trained" with 950 sustained "/i/" vowel audio samples from the Saarbrucken Voice Database (SVD), which contains subjects with and without voice disorders. The trained MLA was "tested" with 406 SVD samples to determine sensitivity, specificity, and overall accuracy. External validation of the MLA was performed using clinical voice samples collected from patients attending a subspecialty voice clinic.

RESULTS

The MLA detected pathologies in SVD samples with 98.5% sensitivity, 97.1% specificity and 97.8% overall accuracy. In 30 samples obtained prospectively from voice clinic patients, the MLA detected pathologies with 100% sensitivity, 96.3% specificity and 96.7% overall accuracy.

CONCLUSIONS

This study demonstrates that a MLA using a simple audio input can detect diverse vocal pathologies with high sensitivity and specificity. Thus, this algorithm shows promise as a potential screening tool.

Predicting speech discrimination scores from pure-tone thresholds-A machine learning-based approach using data from 12,697 subjects

Diagnostic tests for hearing impairment not only determines the presence (or absence) of hearing loss, but also evaluates its degree and type, and provides physicians with essential data for future treatment and rehabilitation. Therefore, accurately measuring hearing loss conditions is very important for proper patient understanding and treatment. In current-day practice, to quantify the level of hearing loss, physicians exploit specialized test scores such as the pure-tone audiometry (PTA) thresholds and speech discrimination scores (SDS) as quantitative metrics in examining a patient’s auditory function. However, given that these metrics can be easily affected by various human factors, which includes intentional (or accidental) patient intervention, there are needs to cross validate the accuracy of each metric. By understanding a “normal” relationship between the SDS and PTA, physicians can reveal the need for re-testing, additional testing in different dimensions, and also potential malingering cases. For this purpose, in this work, we propose a prediction model for estimating the SDS of a patient by using PTA thresholds via a Random Forest-based machine learning approach to overcome the limitations of the conventional statistical (or even manual) methods. For designing and evaluating the Random Forest-based prediction model, we collected a large-scale dataset from 12,697 subjects, and report a SDS level prediction accuracy of 95.05% and 96.64% for the left and right ears, respectively. We also present comparisons with other widely-used machine learning algorithms (e.g., Support Vector Machine, Multi-layer Perceptron) to show the effectiveness of our proposed Random Forest-based approach. Results obtained from this study provides implications and potential feasibility in providing a practically-applicable screening tool for identifying patient-intended malingering in hearing loss-related tests.

Artificial intelligence, machine learning, and deep learning for clinical outcome prediction

AI is a broad concept, grouping initiatives that use a computer to perform tasks that would usually require a human to complete. AI methods are well suited to predict clinical outcomes. In practice, AI methods can be thought of as functions that learn the outcomes accompanying standardized input data to produce accurate outcome predictions when trialed with new data. Current methods for cleaning, creating, accessing, extracting, augmenting, and representing data for training AI clinical prediction models are well defined. The use of AI to predict clinical outcomes is a dynamic and rapidly evolving arena, with new methods and applications emerging. Extraction or accession of electronic health care records and combining these with patient genetic data is an area of present attention, with tremendous potential for future growth. Machine learning approaches, including decision tree methods of Random Forest and XGBoost, and deep learning techniques including deep multi-layer and recurrent neural networks, afford unique capabilities to accurately create predictions from high dimensional, multimodal data. Furthermore, AI methods are increasing our ability to accurately predict clinical outcomes that previously were difficult to model, including time-dependent and multi-class outcomes. Barriers to robust AI-based clinical outcome model deployment include changing AI product development interfaces, the specificity of regulation requirements, and limitations in ensuring model interpretability, generalizability, and adaptability over time.

Predictive models for cochlear implant outcomes: Performance, generalizability, and the impact of cohort size

While cochlear implants have helped hundreds of thousands of individuals, it remains difficult to predict the extent to which an individual’s hearing will benefit from implantation. Several publications indicate that machine learning may improve predictive accuracy of cochlear implant outcomes compared to classical statistical methods. However, existing studies are limited in terms of model validation and evaluating factors like sample size on predictive performance. We conduct a thorough examination of machine learning approaches to predict word recognition scores (WRS) measured approximately 12 months after implantation in adults with post-lingual hearing loss. This is the largest retrospective study of cochlear implant outcomes to date, evaluating 2,489 cochlear implant recipients from three clinics. We demonstrate that while machine learning models significantly outperform linear models in prediction of WRS, their overall accuracy remains limited (mean absolute error: 17.9-21.8). The models are robust across clinical cohorts, with predictive error increasing by at most 16% when evaluated on a clinic excluded from the training set. We show that predictive improvement is unlikely to be improved by increasing sample size alone, with doubling of sample size estimated to only increasing performance by 3% on the combined dataset. Finally, we demonstrate how the current models could support clinical decision making, highlighting that subsets of individuals can be identified that have a 94% chance of improving WRS by at least 10% points after implantation, which is likely to be clinically meaningful. We discuss several implications of this analysis, focusing on the need to improve and standardize data collection.

Radiomics and deep learning approach to the differential diagnosis of parotid gland tumors

PURPOSE OF REVIEW

Advances in computer technology and growing expectations from computer-aided systems have led to the evolution of artificial intelligence into subsets, such as deep learning and radiomics, and the use of these systems is revolutionizing modern radiological diagnosis. In this review, artificial intelligence applications developed with radiomics and deep learning methods in the differential diagnosis of parotid gland tumors (PGTs) will be overviewed.

RECENT FINDINGS

The development of artificial intelligence models has opened new scenarios owing to the possibility of assessing features of medical images that usually are not evaluated by physicians. Radiomics and deep learning models come to the forefront in computer-aided diagnosis of medical images, even though their applications in the differential diagnosis of PGTs have been limited because of the scarcity of data sets related to these rare neoplasms. Nevertheless, recent studies have shown that artificial intelligence tools can classify common PGTs with reasonable accuracy.

SUMMARY

All studies aimed at the differential diagnosis of benign vs. malignant PGTs or the identification of the commonest PGT subtypes were identified, and five studies were found that focused on deep learning-based differential diagnosis of PGTs. Data sets were created in three of these studies with MRI and in two with computed tomography (CT). Additional seven studies were related to radiomics. Of these, four were on MRI-based radiomics, two on CT-based radiomics, and one compared MRI and CT-based radiomics in the same patients.

Applications of Artificial Intelligence to Office Laryngoscopy: A Scoping Review

OBJECTIVES/HYPOTHESIS

This scoping review aims to provide a broad overview of the applications of artificial intelligence (AI) to office laryngoscopy to identify gaps in knowledge and guide future research.

STUDY DESIGN

Scoping Review.

METHODS

Searches for studies on AI and office laryngoscopy were conducted in five databases. Title and abstract and then full-text screening were performed. Primary research studies published in English of any date were included. Studies were summarized by: AI applications, targeted conditions, imaging modalities, author affiliations, and dataset characteristics.

RESULTS

Studies focused on vocal fold vibration analysis (43%), lesion recognition (24%), and vocal fold movement determination (19%). The most frequently automated tasks were recognition of vocal fold nodules (19%), polyp (14%), paralysis (11%), paresis (8%), and cyst (7%). Imaging modalities included high-speed laryngeal videos (45%), stroboscopy (29%), and narrow band imaging endoscopy (7%). The body of literature was primarily authored by science, technology, engineering, and math (STEM) specialists (76%) with only 30 studies (31%) involving co-authorship by STEM specialists and otolaryngologists. Datasets were mostly from single institution (84%) and most commonly originated from Germany (23%), USA (16%), Spain (9%), Italy (8%), and China (8%). Demographic information was only reported in 39 studies (40%), with age and sex being the most commonly reported, whereas race/ethnicity and gender were not reported in any studies.

CONCLUSION

More interdisciplinary collaboration between STEM and otolaryngology research teams improved demographic reporting especially of race and ethnicity to ensure broad representation, and larger and more geographically diverse datasets will be crucial to future research on AI in office laryngoscopy.

LEVEL OF EVIDENCE

N/A Laryngoscope, 2021.

A MultiCenter Analysis of Factors Associated with Hearing Outcome for 2,735 Adults with Cochlear Implants

While the majority of cochlear implant recipients benefit from the device, it remains difficult to estimate the degree of benefit for a specific patient prior to implantation. Using data from 2,735 cochlear-implant recipients from across three clinics, the largest retrospective study of cochlear-implant outcomes to date, we investigate the association between 21 preoperative factors and speech recognition approximately one year after implantation and explore the consistency of their effects across the three constituent datasets. We provide evidence of 17 statistically significant associations, in either univariate or multivariate analysis, including confirmation of associations for several predictive factors, which have only been examined in prior smaller studies. Despite the large sample size, a multivariate analysis shows that the variance explained by our models remains modest across the datasets (R2=0.12–0.21). Finally, we report a novel statistical interaction indicating that the duration of deafness in the implanted ear has a stronger impact on hearing outcome when considered relative to a candidate’s age. Our multicenter study highlights several real-world complexities that impact the clinical translation of predictive factors for cochlear implantation outcome. We suggest several directions to overcome these challenges and further improve our ability to model patient outcomes with increased accuracy.

Towards Providing an Automated Approach to Differentiating the Nystagmus of Ménière's Disease, Vestibular Migraine, and Benign Paroxysmal Positional Vertigo

OBJECTIVE

The diagnosis of vertigo is challenging, particularly as patients usually present while asymptomatic. We have developed an ambulatory medical device that allows vestibular telemetry to record eye movements over a 30-day period to aid the diagnosis of vertigo. We have undertaken proof-of-concept work to identify unique properties of nystagmus that could be used to differentiate between three of the most common causes of vertigo: Ménière's disease, vestibular migraine, and Benign Paroxysmal Positional Vertigo.

PATIENTS

We analyze the nystagmus from patients with a diagnosis of Ménière's disease, vestibular migraine, and Benign Paroxysmal Positional Vertigo.

INTERVENTIONS

Our vestibular telemetry system includes a wearable, ambulatory monitor which continuously records horizontal and vertical eye-movements, as well as three-axis movements of the head.

MAIN OUTCOME MEASURES

Horizontal and vertical eye-movement data, and three-axis head positioning data.

RESULTS

Sixteen participants were enrolled onto the study and three reported experiencing rotatory vertigo during their 30-day trial, confirmed by the presence of nystagmus in their eye-movement traces. Vestibular telemetry revealed distinct differences between the nystagmus produced during an acute Ménière's attack, and attacks of vestibular migraine and Benign Paroxysmal Positional Vertigo. Attack frequency, nystagmus duration, whether the nystagmus onset was motion provoked, nystagmus direction, slow phase velocity, and slow phase duration were found to be discriminatory features that could be exploited to allow an automated diagnosis to be made.

CONCLUSIONS

The data provided by vestibular telemetry can be used to differentiate between different inner-ear causes of dizziness.