Rheumatoid Arthritis Diagnosis: Deep Learning vs. Humane
Rheumatoid arthritis (RA) is a systemic autoimmune disease that preferably affects small joints. As the well-timed diagnosis of the disease is essential for the treatment of the patient, several works have been conducted in the field of deep learning to develop fast and accurate automatic methods fo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/1/10 |
| _version_ | 1797499714618261504 |
|---|---|
| author | George P. Avramidis Maria P. Avramidou George A. Papakostas |
| author_facet | George P. Avramidis Maria P. Avramidou George A. Papakostas |
| author_sort | George P. Avramidis |
| collection | DOAJ |
| description | Rheumatoid arthritis (RA) is a systemic autoimmune disease that preferably affects small joints. As the well-timed diagnosis of the disease is essential for the treatment of the patient, several works have been conducted in the field of deep learning to develop fast and accurate automatic methods for RA diagnosis. These works mainly focus on medical images as they use X-ray and ultrasound images as input for their models. In this study, we review the conducted works and compare the methods that use deep learning with the procedure that is commonly followed by a medical doctor for the RA diagnosis. The results show that 93% of the works use only image modalities as input for the models as distinct from the medical procedure where more patient medical data are taken into account. Moreover, only 15% of the works use direct explainability methods, meaning that the efforts for solving the trustworthiness issue of deep learning models were limited. In this context, this work reveals the gap between the deep learning approaches and the medical doctors’ practices traditionally applied and brings to light the weaknesses of the current deep learning technology to be integrated into a trustworthy context inside the existed medical infrastructures. |
| first_indexed | 2024-03-10T03:51:23Z |
| format | Article |
| id | doaj.art-8a5b69588ebf44d281e67fd129936d01 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:51:23Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-8a5b69588ebf44d281e67fd129936d012023-11-23T11:06:15ZengMDPI AGApplied Sciences2076-34172021-12-011211010.3390/app12010010Rheumatoid Arthritis Diagnosis: Deep Learning vs. HumaneGeorge P. Avramidis0Maria P. Avramidou1George A. Papakostas2MLV Research Group, Department of Computer Science, International Hellenic University, 65404 Kavala, GreeceConsultant in Rheumatology, Schmerzklinik Basel, 4010 Basel, SwitzerlandMLV Research Group, Department of Computer Science, International Hellenic University, 65404 Kavala, GreeceRheumatoid arthritis (RA) is a systemic autoimmune disease that preferably affects small joints. As the well-timed diagnosis of the disease is essential for the treatment of the patient, several works have been conducted in the field of deep learning to develop fast and accurate automatic methods for RA diagnosis. These works mainly focus on medical images as they use X-ray and ultrasound images as input for their models. In this study, we review the conducted works and compare the methods that use deep learning with the procedure that is commonly followed by a medical doctor for the RA diagnosis. The results show that 93% of the works use only image modalities as input for the models as distinct from the medical procedure where more patient medical data are taken into account. Moreover, only 15% of the works use direct explainability methods, meaning that the efforts for solving the trustworthiness issue of deep learning models were limited. In this context, this work reveals the gap between the deep learning approaches and the medical doctors’ practices traditionally applied and brings to light the weaknesses of the current deep learning technology to be integrated into a trustworthy context inside the existed medical infrastructures.https://www.mdpi.com/2076-3417/12/1/10deep learningrheumatoid arthritis (RA)trustworthinessexplainable AIartificial intelligencemedical imaging |
| spellingShingle | George P. Avramidis Maria P. Avramidou George A. Papakostas Rheumatoid Arthritis Diagnosis: Deep Learning vs. Humane Applied Sciences deep learning rheumatoid arthritis (RA) trustworthiness explainable AI artificial intelligence medical imaging |
| title | Rheumatoid Arthritis Diagnosis: Deep Learning vs. Humane |
| title_full | Rheumatoid Arthritis Diagnosis: Deep Learning vs. Humane |
| title_fullStr | Rheumatoid Arthritis Diagnosis: Deep Learning vs. Humane |
| title_full_unstemmed | Rheumatoid Arthritis Diagnosis: Deep Learning vs. Humane |
| title_short | Rheumatoid Arthritis Diagnosis: Deep Learning vs. Humane |
| title_sort | rheumatoid arthritis diagnosis deep learning vs humane |
| topic | deep learning rheumatoid arthritis (RA) trustworthiness explainable AI artificial intelligence medical imaging |
| url | https://www.mdpi.com/2076-3417/12/1/10 |
| work_keys_str_mv | AT georgepavramidis rheumatoidarthritisdiagnosisdeeplearningvshumane AT mariapavramidou rheumatoidarthritisdiagnosisdeeplearningvshumane AT georgeapapakostas rheumatoidarthritisdiagnosisdeeplearningvshumane |