Clinical decision support systems and computer-aided diagnosis in otology

Image-Based Artificial Intelligence Technology for Diagnosing Middle Ear Diseases: A Systematic Review

Otolaryngological diagnoses, such as otitis media, are traditionally performed using endoscopy, wherein diagnostic accuracy can be subjective and vary among clinicians. The integration of objective tools, like artificial intelligence (AI), could potentially improve the diagnostic process by minimizing the influence of subjective biases and variability. We systematically reviewed the AI techniques using medical imaging in otolaryngology. Relevant studies related to AI-assisted otitis media diagnosis were extracted from five databases: Google Scholar, PubMed, Medline, Embase, and IEEE Xplore, without date restrictions. Publications that did not relate to AI and otitis media diagnosis or did not utilize medical imaging were excluded. Of the 32identified studies, 26 used tympanic membrane images for classification, achieving an average diagnosis accuracy of 86% (range: 48.7-99.16%). Another three studies employed both segmentation and classification techniques, reporting an average diagnosis accuracy of 90.8% (range: 88.06-93.9%). These findings suggest that AI technologies hold promise for improving otitis media diagnosis, offering benefits for telemedicine and primary care settings due to their high diagnostic accuracy. However, to ensure patient safety and optimal outcomes, further improvements in diagnostic performance are necessary.

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.

An Artificial Intelligence Computer-vision Algorithm to Triage Otoscopic Images From Australian Aboriginal and Torres Strait Islander Children

OBJECTIVE

To develop an artificial intelligence image classification algorithm to triage otoscopic images from rural and remote Australian Aboriginal and Torres Strait Islander children.

STUDY DESIGN

Retrospective observational study.

SETTING

Tertiary referral center.

PATIENTS

Rural and remote Aboriginal and Torres Strait Islander children who underwent tele-otology ear health screening in the Northern Territory, Australia between 2010 and 2018.

INTERVENTIONS

Otoscopic images were labeled by otolaryngologists to classify the ground truth. Deep and transfer learning methods were used to develop an image classification algorithm.

MAIN OUTCOME MEASURES

Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, area under the curve (AUC) of the resultant algorithm compared with the ground truth.

RESULTS

Six thousand five hundred twenty seven images were used (5927 images for training and 600 for testing). The algorithm achieved an accuracy of 99.3% for acute otitis media, 96.3% for chronic otitis media, 77.8% for otitis media with effusion (OME), and 98.2% to classify wax/obstructed canal. To differentiate between multiple diagnoses, the algorithm achieved 74.4 to 92.8% accuracy and an AUC of 0.963 to 0.997. The most common incorrect classification pattern was OME misclassified as normal tympanic membranes.

CONCLUSIONS

The paucity of access to tertiary otolaryngology care for rural and remote Aboriginal and Torres Strait Islander communities may contribute to an under-identification of ear disease. Computer vision image classification algorithms can accurately classify ear disease from otoscopic images of Indigenous Australian children. In the future, a validated algorithm may integrate with existing telemedicine initiatives to support effective triage and facilitate early treatment and referral.

Predicting Common Audiological Functional Parameters (CAFPAs) as Interpretable Intermediate Representation in a Clinical Decision-Support System for Audiology

The application of machine learning for the development of clinical decision-support systems in audiology provides the potential to improve the objectivity and precision of clinical experts' diagnostic decisions. However, for successful clinical application, such a tool needs to be accurate, as well as accepted and trusted by physicians. In the field of audiology, large amounts of patients' data are being measured, but these are distributed over local clinical databases and are heterogeneous with respect to the applied assessment tools. For the purpose of integrating across different databases, the Common Audiological Functional Parameters (CAFPAs) were recently established as abstract representations of the contained audiological information describing relevant functional aspects of the human auditory system. As an intermediate layer in a clinical decision-support system for audiology, the CAFPAs aim at maintaining interpretability to the potential users. Thus far, the CAFPAs were derived by experts from audiological measures. For designing a clinical decision-support system, in a next step the CAFPAs need to be automatically derived from available data of individual patients. Therefore, the present study aims at predicting the expert generated CAFPA labels using three different machine learning models, namely the lasso regression, elastic nets, and random forests. Furthermore, the importance of different audiological measures for the prediction of specific CAFPAs is examined and interpreted. The trained models are then used to predict CAFPAs for unlabeled data not seen by experts. Prediction of unlabeled cases is evaluated by means of model-based clustering methods. Results indicate an adequate prediction of the ten distinct CAFPAs. All models perform comparably and turn out to be suitable choices for the prediction of CAFPAs. They also generalize well to unlabeled data. Additionally, the extracted relevant features are plausible for the respective CAFPAs, facilitating interpretability of the predictions. Based on the trained models, a prototype of a clinical decision-support system in audiology can be implemented and extended towards clinical databases in the future.

Clinical Decision Support Systems in Otolaryngology-Head and Neck Surgery: A State of the Art Review

OBJECTIVE

To offer practical, evidence-informed knowledge on clinical decision support systems (CDSSs) and their utility in improving care and reducing costs in otolaryngology-head and neck surgery. This primer on CDSSs introduces clinicians to both the capabilities and the limitations of this technology, reviews the literature on current state, and seeks to spur further progress in this area.

DATA SOURCES

PubMed/MEDLINE, Embase, and Web of Science.

REVIEW METHODS

Scoping review of CDSS literature applicable to otolaryngology clinical practice. Investigators identified articles that incorporated knowledge-based computerized CDSSs to aid clinicians in decision making and workflow. Data extraction included level of evidence, Osheroff classification of CDSS intervention type, otolaryngology subspecialty or domain, and impact on provider performance or patient outcomes.

CONCLUSIONS

Of 3191 studies retrieved, 11 articles met formal inclusion criteria. CDSS interventions included guideline or protocols support (n = 8), forms and templates (n = 5), data presentation aids (n = 2), and reactive alerts, reference information, or order sets (all n = 1); 4 studies had multiple interventions. CDSS studies demonstrated effectiveness across diverse domains, including antibiotic stewardship, cancer survivorship, guideline adherence, data capture, cost reduction, and workflow. Implementing CDSSs often involved collaboration with health information technologists.

IMPLICATIONS FOR PRACTICE

While the published literature on CDSSs in otolaryngology is finite, CDSS interventions are proliferating in clinical practice, with roles in preventing medical errors, streamlining workflows, and improving adherence to best practices for head and neck disorders. Clinicians may collaborate with information technologists and health systems scientists to develop, implement, and investigate the impact of CDSSs in otolaryngology.

OtoPair: Combining Right and Left Eardrum Otoscopy Images to Improve the Accuracy of Automated Image Analysis

The accurate diagnosis of otitis media (OM) and other middle ear and eardrum abnormalities is difficult, even for experienced otologists. In our earlier studies, we developed computer-aided diagnosis systems to improve the diagnostic accuracy. In this study, we investigate a novel approach, called OtoPair, which uses paired eardrum images together rather than using a single eardrum image to classify them as ‘normal’ or ‘abnormal’. This also mimics the way that otologists evaluate ears, because they diagnose eardrum abnormalities by examining both ears. Our approach creates a new feature vector, which is formed with extracted features from a pair of high-resolution otoscope images or images that are captured by digital video-otoscopes. The feature vector has two parts. The first part consists of lookup table-based values created by using deep learning techniques reported in our previous OtoMatch content-based image retrieval system. The second part consists of handcrafted features that are created by recording registration errors between paired eardrums, color-based features, such as histogram of a* and b* component of the L*a*b* color space, and statistical measurements of these color channels. The extracted features are concatenated to form a single feature vector, which is then classified by a tree bagger classifier. A total of 150-pair (300-single) of eardrum images, which are either the same category (normal-normal and abnormal-abnormal) or different category (normal-abnormal and abnormal-normal) pairs, are used to perform several experiments. The proposed approach increases the accuracy from 78.7% (±0.1%) to 85.8% (±0.2%) on a three-fold cross-validation method. These are promising results with a limited number of eardrum pairs to demonstrate the feasibility of using a pair of eardrum images instead of single eardrum images to improve the diagnostic accuracy.

Otitis media detection using tympanic membrane images with a novel multi-class machine learning algorithm

BACKGROUND

Otitis media (OM) is the infection and inflammation of the mucous membrane covering the Eustachian with the airy cavities of the middle ear and temporal bone. OM is also one of the most common ailments. In clinical practice, the diagnosis of OM is carried out by visual inspection of otoscope images. This vulnerable process is subjective and error-prone.

METHODS

In this study, a novel computer-aided decision support model based on the convolutional neural network (CNN) has been developed. To improve the generalized ability of the proposed model, a combination of the channel and spatial model (CBAM), residual blocks, and hypercolumn technique is embedded into the proposed model. All experiments were performed on an open-access tympanic membrane dataset that consists of 956 otoscopes images collected into five classes.

RESULTS

The proposed model yielded satisfactory classification achievement. The model ensured an overall accuracy of 98.26%, sensitivity of 97.68%, and specificity of 99.30%. The proposed model produced rather superior results compared to the pre-trained CNNs such as AlexNet, VGG-Nets, GoogLeNet, and ResNets. Consequently, this study points out that the CNN model equipped with the advanced image processing techniques is useful for OM diagnosis. The proposed model may help to field specialists in achieving objective and repeatable results, decreasing misdiagnosis rate, and supporting the decision-making processes.

Prediction of vestibular schwannoma recurrence using artificial neural network

OBJECTIVES

To compare two statistical models, namely logistic regression and artificial neural network (ANN), in prediction of vestibular schwannoma (VS) recurrence.

METHODS

Seven hundred eighty-nine patients with VS diagnosis completed an online survey. Potential predictors for recurrence were derived from univariate analysis by reaching the cut off P value of .05. Those nine potential predictors were years since treatment, surgeon's specialty, resection amount, and having incomplete eye closure, dry eye, double vision, facial pain, seizure, and voice/swallowing problem as a complication following treatment. Multivariate binary logistic regression model was compared with a four-layer 9-5-10-1 feedforward backpropagation ANN for prediction of recurrence.

RESULTS

The overall recurrence rate was 14.5%. Significant predictors of recurrence in the regression model were years since treatment and resection amount (both P < .001). The regression model did not show an acceptable performance (area under the curve [AUC] = 0.64; P = .27). The regression model's sensitivity and specificity were 44% and 69%, respectively and correctly classified 56% of cases. The ANN showed a superior performance compared to the regression model (AUC = 0.79; P = .001) with higher sensitivity (61%) and specificity (81%), and correctly classified 70% of cases.

CONCLUSION

The constructed ANN model was superior to logistic regression in predicting patient-answered VS recurrence in an anonymous survey with higher sensitivity and specificity. Since artificial intelligence tools such as neural networks can have higher predictive abilities compared to logistic regression models, continuous investigation into their utility as complementary clinical tools in predicting certain surgical outcomes is warranted.

Computer-aided diagnosis of external and middle ear conditions: A machine learning approach

In medicine, a misdiagnosis or the absence of specialists can affect the patient’s health, leading to unnecessary tests and increasing the costs of healthcare. In particular, the lack of specialists in otolaryngology in third world countries forces patients to seek medical attention from general practitioners, whom might not have enough training and experience for making correct diagnosis in this field. To tackle this problem, we propose and test a computer-aided system based on machine learning models and image processing techniques for otoscopic examination, as a support for a more accurate diagnosis of ear conditions at primary care before specialist referral; in particular, for myringosclerosis, earwax plug, and chronic otitis media. To characterize the tympanic membrane and ear canal for each condition, we implemented three different feature extraction methods: color coherence vector, discrete cosine transform, and filter bank. We also considered three machine learning algorithms: support vector machine (SVM), k-nearest neighbor (k-NN) and decision trees to develop the ear condition predictor model. To conduct the research, our database included 160 images as testing set and 720 images as training and validation sets of 180 patients. We repeatedly trained the learning models using the training dataset and evaluated them using the validation dataset to thus obtain the best feature extraction method and learning model that produce the highest validation accuracy. The results showed that the SVM and k-NN presented the best performance followed by decision trees model. Finally, we performed a classification stage –i.e., diagnosis– using testing data, where the SVM model achieved an average classification accuracy of 93.9%, average sensitivity of 87.8%, average specificity of 95.9%, and average positive predictive value of 87.7%. The results show that this system might be used for general practitioners as a reference to make better decisions in the ear pathologies diagnosis.

Design of a Clinical Decision Support System for Predicting Erectile Dysfunction in Men Using NHIRD Dataset

Erectile dysfunction (ED) affects millions of men worldwide. Men with ED generally complain failure to attain or maintain an adequate erection during sexual activity. The prevalence of ED is strongly correlated with age, affecting about 40% of men at age 40 and nearly 70% at age 70. A variety of chronic diseases, including diabetes, ischemic heart disease, congestive heart failure, hypertension, depression, chronic renal failure, obstructive sleep apnea, prostate disease, gout, and sleep disorder, were reported to be associated with ED. In this study, data retrieved from a subset of the National Health Insurance Research Database of Taiwan were used for designing the clinical decision support system (CDSS) for predicting ED incidences in men. The positive cases were male patients aged 20-65 who were diagnosed with ED between January 2000 and December 2010 confirmed by at least three outpatient visits or at least one inpatient visit, while the negative cases were randomly selected from the database without a history of ED and were frequency (1:1), age, and index year matched with the ED patients. Data of a total of 2832 ED patients and 2832 non-ED patients, each consisting of 41 features including index age, 10 comorbidities, and 30 other comorbidity-related variables, were retrieved for designing the predictive models. Integrated genetic algorithm and support vector machine was adopted to design the CDSSs with two experiments of independent training and testing (ITT) conducted to verify their effectiveness. In the 1st ITT experiment, data extracted from January 2000 till December 2005 (61.51%, 1742 positive cases and 1742 negative cases) were used for training and validating and the data retrieved from January 2006 till December 2010 were used for testing (38.49%), whereas in the 2nd ITT experiment, data in the training set (77.78%) were extracted from January 2000 till Deceber 2007 and those in the testing set (22.22%) were retrieved afterward. Tenfold cross validation and three different objective functions were adopted for obtaining the optimal models with best predictive performance in the training phase. The testing results show that the CDSSs achieved a predictive performance with accuracy, sensitivity, specificity, g-mean, and area under ROC curve of 74.72%-76.65%, 72.33%-83.76%, 69.54%-77.10%, 0.7468-0.7632, and 0.766-0.817, respectively. In conclusion, the CDSSs designed based on cost-sensitive objective functions as well as salient comorbidity-related features achieve satisfactory predictive performance for predicting ED incidences.

Clinical verification of a clinical decision support system for ventilator weaning

Background

Weaning is typically regarded as a process of discontinuing mechanical ventilation in the daily practice of an intensive care unit (ICU). Among the ICU patients, 39%-40% need mechanical ventilator for sustaining their lives. The predictive rate of successful weaning achieved only 35-60% for decisions made by physicians. Clinical decision support systems (CDSSs) are promising in enhancing diagnostic performance and improve healthcare quality in clinical setting. To our knowledge, a prospective study has never been conducted to verify the effectiveness of the CDSS in ventilator weaning before. In this study, the CDSS capable of predicting weaning outcome and reducing duration of ventilator support for patients has been verified.

Methods

A total of 380 patients admitted to the respiratory care center of the hospital were randomly assigned to either control or study group. In the control group, patients were weaned with traditional weaning method, while in the study group, patients were weaned with CDSS monitored by physicians. After excluding the patients who transferred to other hospitals, refused further treatments, or expired the admission period, data of 168 and 144 patients in the study and control groups, respectively, were used for analysis.

Results

The results show that a sensitivity of 87.7% has been achieved, which is significantly higher (p<0.01) than the weaning determined by physicians (sensitivity: 61.4%). Furthermore, the days using mechanical ventilator for the study group (38.41 ± 3.35) is significantly (p<0.001) shorter than the control group (43.69 ± 14.89), with a decrease of 5.2 days in average, resulting in a saving of healthcare cost of NT$45,000 (US$1,500) per patient in the current Taiwanese National Health Insurance setting.

Conclusions

The CDSS is demonstrated to be effective in identifying the earliest time of ventilator weaning for patients to resume and sustain spontaneous breathing, thereby avoiding unnecessary prolonged ventilator use and decreasing healthcare cost.

The methodology of Dynamic Uncertain Causality Graph for intelligent diagnosis of vertigo

Vertigo is a common complaint with many potential causes involving otology, neurology and general medicine, and it is fairly difficult to distinguish the vertiginous disorders from each other accurately even for experienced physicians. Based on comprehensive investigations to relevant characteristics of vertigo, we propose a diagnostic modeling and reasoning methodology using Dynamic Uncertain Causality Graph. The symptoms, signs, findings of examinations, medical histories, etiology and pathogenesis, and so on, are incorporated in the diagnostic model. A modularized modeling scheme is presented to reduce the difficulty in model construction, providing multiple perspectives and arbitrary granularity for disease causality representations. We resort to the "chaining" inference algorithm and weighted logic operation mechanism, which guarantee the exactness and efficiency of diagnostic reasoning under situations of incomplete and uncertain information. Moreover, the causal insights into underlying interactions among diseases and symptoms intuitively demonstrate the reasoning process in a graphical manner. These solutions make the conclusions and advices more explicable and convincing, further increasing the objectivity of clinical decision-making. Verification experiments and empirical evaluations are performed with clinical vertigo cases. The results reveal that, even with incomplete observations, this methodology achieves encouraging diagnostic accuracy and effectiveness. This study provides a promising assistance tool for physicians in diagnosis of vertigo.

A cooperative approach for the diagnosis of the melanoma

In this work we present a decision support system for the melanoma diagnosis using individual methods and the collaboration between these methods. The system designed uses a photograph of the lesion and it makes a preprocessing task to extract the region of interest. Then, several characteristics of the image are analyzed, studying with different methods the degree of malignity; the methods used are based in Bayesian rules and in neural networks. Finally, each individual decision from each method contributes in some way to the final decision. The classification rate obtained with the cooperative approach is above 92%.