Objective To develop and evaluate an automated system for digitizing audiograms,classifying hearing loss levels,and comparing their performance with traditional methods and otolaryngologists'interpretations.Design...Objective To develop and evaluate an automated system for digitizing audiograms,classifying hearing loss levels,and comparing their performance with traditional methods and otolaryngologists'interpretations.Designed and Methods We conducted a retrospective diagnostic study using 1,959 audiogram images from patients aged 7 years and older at the Faculty of Medicine,Vajira Hospital,Navamindradhiraj University.We employed an object detection approach to digitize audiograms and developed multiple machine learning models to classify six hearing loss levels.The dataset was split into 70%training(1,407 images)and 30%testing(352 images)sets.We compared our model's performance with classifications based on manually extracted audiogram values and otolaryngologists'interpretations.Result Our object detection-based model achieved an F1-score of 94.72%in classifying hearing loss levels,comparable to the 96.43%F1-score obtained using manually extracted values.The Light Gradient Boosting Machine(LGBM)model is used as the classifier for the manually extracted data,which achieved top performance with 94.72%accuracy,94.72%f1-score,94.72 recall,and 94.72 precision.In object detection based model,The Random Forest Classifier(RFC)model showed the highest 96.43%accuracy in predicting hearing loss level,with a F1-score of 96.43%,recall of 96.43%,and precision of 96.45%.Conclusion Our proposed automated approach for audiogram digitization and hearing loss classification performs comparably to traditional methods and otolaryngologists'interpretations.This system can potentially assist otolaryngologists in providing more timely and effective treatment by quickly and accurately classifying hearing loss.展开更多
Aim: To assess the hearing status of the study subjects in terms of degree and type of hearing loss, and establish the burden of this disability in the society. Materials and methods: This is a prospective study condu...Aim: To assess the hearing status of the study subjects in terms of degree and type of hearing loss, and establish the burden of this disability in the society. Materials and methods: This is a prospective study conducted in patients who attend our OPD. After an otorhinolaryngeal examination, all the patients were subjected to pure tone audiometry using MAICA-MA52 audiometer. Results: Our study comprises 1012 males (64%) and 563 females (36%). Out of this, about 15% have conductive deafness and 42% have sensorineural hearing loss. About 29% suffer from mild hearing loss, 26% moderate and 11% severe hearing loss. The alarming information is that about 5% have total hearing loss of Sudden Sensorineural type (SSNHL). Conclusion: Pure tone audiometry is cost effective and easy to perform. Early diagnosis and timely intervention will reduce the morbidity of deafness in our country. Hence it is necessary to identify and treat sudden sensorineural hearing loss and noise induced hearing loss at an early stage.展开更多
In this case report, we discuss a patient who presented with Tullio’s phenomenon, who also experienced bone-conduction induced seizures on two occasions. Tullio’s phenomenon refers to sound induced vestibular sympto...In this case report, we discuss a patient who presented with Tullio’s phenomenon, who also experienced bone-conduction induced seizures on two occasions. Tullio’s phenomenon refers to sound induced vestibular symptoms, including disequilibrium oscillopsia, and vertical nystagmus. We were ultimately able to rule out some of the more common pathologies associated with Tullio’s phenomenon for this patient based on imaging findings. However, given the specific nature of her chronic symptoms, as well as her seizure like activity in clinic, we performed a literature search to investigate other less common pathologies associated with Tullio’s phenomenon. Given her past medical history of mixed psychogenic non-epileptic seizures (PNES), there is likely a somatic component to her presentation. However, given the specific and unexpected nature of these events, we propose that her symptoms may also be related to a unique inner ear pathology. Specifically, we feel that she may have exhibited symptoms of vestibular atelectasis, a relatively new otologic diagnosis characterizing the pathologic collapse of the ampulla and utricle, such that the membranous labyrinth contacts the stapes. In this way, loud sounds or changes in pressure may induce vestibular symptoms. Dizzy patients can be a difficult demographic to diagnose and manage, especially when their presentation is complicated by other functional neurologic disorders. Ultimately, we believe that this case report offers helpful insights into a new disease process associated with Tullio’s phenomenon.展开更多
文摘Objective To develop and evaluate an automated system for digitizing audiograms,classifying hearing loss levels,and comparing their performance with traditional methods and otolaryngologists'interpretations.Designed and Methods We conducted a retrospective diagnostic study using 1,959 audiogram images from patients aged 7 years and older at the Faculty of Medicine,Vajira Hospital,Navamindradhiraj University.We employed an object detection approach to digitize audiograms and developed multiple machine learning models to classify six hearing loss levels.The dataset was split into 70%training(1,407 images)and 30%testing(352 images)sets.We compared our model's performance with classifications based on manually extracted audiogram values and otolaryngologists'interpretations.Result Our object detection-based model achieved an F1-score of 94.72%in classifying hearing loss levels,comparable to the 96.43%F1-score obtained using manually extracted values.The Light Gradient Boosting Machine(LGBM)model is used as the classifier for the manually extracted data,which achieved top performance with 94.72%accuracy,94.72%f1-score,94.72 recall,and 94.72 precision.In object detection based model,The Random Forest Classifier(RFC)model showed the highest 96.43%accuracy in predicting hearing loss level,with a F1-score of 96.43%,recall of 96.43%,and precision of 96.45%.Conclusion Our proposed automated approach for audiogram digitization and hearing loss classification performs comparably to traditional methods and otolaryngologists'interpretations.This system can potentially assist otolaryngologists in providing more timely and effective treatment by quickly and accurately classifying hearing loss.
文摘Aim: To assess the hearing status of the study subjects in terms of degree and type of hearing loss, and establish the burden of this disability in the society. Materials and methods: This is a prospective study conducted in patients who attend our OPD. After an otorhinolaryngeal examination, all the patients were subjected to pure tone audiometry using MAICA-MA52 audiometer. Results: Our study comprises 1012 males (64%) and 563 females (36%). Out of this, about 15% have conductive deafness and 42% have sensorineural hearing loss. About 29% suffer from mild hearing loss, 26% moderate and 11% severe hearing loss. The alarming information is that about 5% have total hearing loss of Sudden Sensorineural type (SSNHL). Conclusion: Pure tone audiometry is cost effective and easy to perform. Early diagnosis and timely intervention will reduce the morbidity of deafness in our country. Hence it is necessary to identify and treat sudden sensorineural hearing loss and noise induced hearing loss at an early stage.
文摘In this case report, we discuss a patient who presented with Tullio’s phenomenon, who also experienced bone-conduction induced seizures on two occasions. Tullio’s phenomenon refers to sound induced vestibular symptoms, including disequilibrium oscillopsia, and vertical nystagmus. We were ultimately able to rule out some of the more common pathologies associated with Tullio’s phenomenon for this patient based on imaging findings. However, given the specific nature of her chronic symptoms, as well as her seizure like activity in clinic, we performed a literature search to investigate other less common pathologies associated with Tullio’s phenomenon. Given her past medical history of mixed psychogenic non-epileptic seizures (PNES), there is likely a somatic component to her presentation. However, given the specific and unexpected nature of these events, we propose that her symptoms may also be related to a unique inner ear pathology. Specifically, we feel that she may have exhibited symptoms of vestibular atelectasis, a relatively new otologic diagnosis characterizing the pathologic collapse of the ampulla and utricle, such that the membranous labyrinth contacts the stapes. In this way, loud sounds or changes in pressure may induce vestibular symptoms. Dizzy patients can be a difficult demographic to diagnose and manage, especially when their presentation is complicated by other functional neurologic disorders. Ultimately, we believe that this case report offers helpful insights into a new disease process associated with Tullio’s phenomenon.
