Finger-aware Artificial Neural Network for predicting arthritis in Patients with hand pain.

Journal: Artificial intelligence in medicine
PMID:

Abstract

Arthritis is an inflammatory condition associated with joint damage, the incidence of which is increasing worldwide. In severe cases, arthritis can result in the restriction of joint movement, thereby affecting daily activities; as such, early and accurate diagnosis crucial to ensure effective treatment and management. Advances in imaging technologies used for arthritis diagnosis, particularly Single Photon Emission Computed Tomography/Computed Tomography (SPECT/CT), have enabled the quantitative measurement of joint inflammation using SUV. To the best of our knowledge, this is the first study to apply deep learning to SUV to predict the development of hand arthritis. We developed a transformer-based Finger-aware Artificial Neural Network (FANN) to predict arthritis in patients experiencing hand pain, including finger embedding, and to share unique finger-specific information between hands. Compared to conventional machine learning models, the FANN model demonstrated superior performance, achieving an area under the receiver operating characteristic curve of 0.85, accuracy of 0.79, precision of 0.87, recall of 0.79, and F1-score of 0.83. Furthermore, analysis using the SHapley Additive exPlanations (SHAP) algorithm revealed that the FANN predictions were most significantly influenced by the proximal interphalangeal joints of the right hand, in which arthritis is the most clinically prevalent. These findings indicate that the FANN significantly enhances arthritis prediction, representing a promising tool for clinical decision-making in arthritis diagnosis.

Authors

  • Hwa-Ah-Ni Lee
    the Medical Artificial Intelligence Center, Chungbuk National University Hospital, Cheongju-si, Chungcheongbuk-do, 28644, Republic of Korea. Electronic address: toy0276@korea.ac.kr.
  • Geun-Hyeong Kim
    Medical AI Research Team, Chungbuk National University Hospital, Cheongju-si, Chungcheongbuk-do, 28644, Rep. of Korea.
  • Seung Park
    Biomedical Engineering, Chungbuk National University Hospital, Cheongju-si, Chungcheongbuk-do 28644, Republic of Korea.
  • In Ah Choi
    Division of Rheumatology, Department of Internal Medicine, Chungbuk National University Hospital, 776, 1sunhwan-ro, Seowon-gu, Cheongju, 28644, Republic of Korea. iachoi@chungbuk.ac.kr.
  • Hyun Woo Kwon
    the Department of Nuclear Medicine, Korea University Ansan Hospital, Ansan-si, Gyeonggi-do, 15355, Republic of Korea; Korea University College of Medicine, Seoul, 02841, Republic of Korea. Electronic address: hnwoo@korea.ac.kr.
  • Hansol Moon
    the Department of Nuclear Medicine, Chungbuk National University Hospital, Cheongju-si, Chungcheongbuk-do, 28644, Republic of Korea. Electronic address: sprtual@cbnuh.or.kr.
  • Jae Hyun Jung
    Korea University College of Medicine, Seoul, 02841, Republic of Korea; the Department of Internal Medicine, Korea University Ansan Hospital, Ansan-si, Gyeonggi-do, 15355, Republic of Korea. Electronic address: cjhtmod@korea.ac.kr.
  • Chulhan Kim
    the Department of Nuclear Medicine, Chungbuk National University Hospital and Chungbuk National University College of Medicine, Cheongju-si, Chungcheongbuk-do, 28644, Republic of Korea. Electronic address: chulhankim@chungbuk.ac.kr.