AI-based algorithm relying on facial picture of patient may help diagnose facial nerve palsy
Facial palsy is a facial nerve disease. It occurs on one side of the face, leading to a loss of voluntary muscle control. Patients may experience various symptoms, such as taste and hearing problems, facial pain, sagging eyelids, and dry eyes. The disease affects approximately one in every 60 people, with pregnant women, diabetics, and those with a family history being at the highest risk...
Facial palsy is a facial nerve disease. It occurs on one side of the face, leading to a loss of voluntary muscle control. Patients may experience various symptoms, such as taste and hearing problems, facial pain, sagging eyelids, and dry eyes. The disease affects approximately one in every 60 people, with pregnant women, diabetics, and those with a family history being at the highest risk of developing it. The incidence of FP is around 10%. Traditional diagnosis methods rely on the doctor's judgment and can be time-consuming and expensive. FP can be uncomfortable and disfiguring, making it necessary to develop an automatic system to detect FP accurately and fast.
In a paper published in BioMedInformatics, researchers proposed a diagnostic system based on CNN, which is highly accurate and modern. It can diagnose FP with an accuracy of 98% and detect the patient's gender and age. It is recommended as an auxiliary tool for doctors, nursing staff, and patients. The patient can use this system at home, reducing embarrassment, effort, time, and cost. Further work is being done to expand its diagnostic potential and diagnose more conditions.
FP is a neurological disorder affecting facial nerve (seventh nerve). The patient loses control of the facial muscles on one side of the face. It can occur in children and adults, regardless of gender. Diagnosis by visual examination is based on differences in the sides of the face. It can be prone to errors and inaccuracies. Detecting FP using artificial intelligence has become increasingly important and deep learning is the best solution for detecting this condition in real-time with high accuracy, saving patients time, effort, and cost.
This study used a dataset of 20,600 images. It had 19,000 normal images and 1600 FP images, to achieve an accuracy of 98%.
The present work proposes a real-time detection system for FP and for determining the patient's gender and age using a Raspberry Pi device with a digital camera and a deep learning algorithm.It effectively recognizes FP, pinpoints the affected facial side, and determines the patient's gender. Furthermore, it diagnoses the healthy person's condition and predicts their gender and age; multiple individuals simultaneously identify their gender and age, they explained.
The solution facilitates the diagnosis process for both the doctor and the patient. It could be part of a medical assessment activity, they added.
The proposed system has several advantages, such as a large amount of training data, real-time diagnosis and age/gender detection, and the use of a practical Raspberry Pi device. However, it has limitations in accurately diagnosing FP and detecting age due to variations in people's shapes (same age), difficulties in diagnosing when patients are moving, and challenges in distinguishing between facial deviations caused by accidents or deviations in the nose. Collecting data for disease cases can also be difficult due to patient embarrassment.
Reference:
Amsalam, A.S.; Al-Naji, A.; Daeef, A.Y.; Chahl, J. Automatic Facial Palsy, Age and Gender Detection Using a Raspberry Pi. BioMedInformatics 2023, 3, 455-466. https://doi.org/10.3390/biomedinformatics3020031
Disclaimer: This site is primarily intended for healthcare professionals. Any content/information on this website does not replace the advice of medical and/or health professionals and should not be construed as medical/diagnostic advice/endorsement/treatment or prescription. Use of this site is subject to our terms of use, privacy policy, advertisement policy. © 2024 Minerva Medical Treatment Pvt Ltd