1
|
Jia W, Chen S, Yang L, Liu G, Li C, Cheng Z, Wang G, Yang X. Ankylosing spondylitis prediction using fuzzy K-nearest neighbor classifier assisted by modified JAYA optimizer. Comput Biol Med 2024; 175:108440. [PMID: 38701589 DOI: 10.1016/j.compbiomed.2024.108440] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2023] [Revised: 03/20/2024] [Accepted: 04/07/2024] [Indexed: 05/05/2024]
Abstract
The diagnosis of ankylosing spondylitis (AS) can be complex, necessitating a comprehensive assessment of medical history, clinical symptoms, and radiological evidence. This multidimensional approach can exacerbate the clinical burden and increase the likelihood of diagnostic inaccuracies, which may result in delayed or overlooked cases. Consequently, supplementary diagnostic techniques for AS have become a focal point in clinical research. This study introduces an enhanced optimization algorithm, SCJAYA, which incorporates salp swarm foraging behavior with cooperative predation strategies into the JAYA algorithm framework, noted for its robust optimization capabilities that emulate the evolutionary dynamics of biological organisms. The integration of salp swarm behavior is aimed at accelerating the convergence speed and enhancing the quality of solutions of the classical JAYA algorithm while the cooperative predation strategy is incorporated to mitigate the risk of convergence on local optima. SCJAYA has been evaluated across 30 benchmark functions from the CEC2014 suite against 9 conventional meta-heuristic algorithms as well as 9 state-of-the-art meta-heuristic counterparts. The comparative analyses indicate that SCJAYA surpasses these algorithms in terms of convergence speed and solution precision. Furthermore, we proposed the bSCJAYA-FKNN classifier: an advanced model applying the binary version of SCJAYA for feature selection, with the aim of improving the accuracy in diagnosing and prognosticating AS. The efficacy of the bSCJAYA-FKNN model was substantiated through validation on 11 UCI public datasets in addition to an AS-specific dataset. The model exhibited superior performance metrics-achieving an accuracy rate, specificity, Matthews correlation coefficient (MCC), F-measure, and computational time of 99.23 %, 99.52 %, 0.9906, 99.41 %, and 7.2800 s, respectively. These results not only underscore its profound capability in classification but also its substantial promise for the efficient diagnosis and prognosis of AS.
Collapse
Affiliation(s)
- Wenyuan Jia
- Department of Orthopedics, The Second Hospital of Jilin University, Changchun, 130041, China; Scientific and Technological Innovation Center of Health Products and Medical Materials with Characteristic Resources of Jilin Province, China.
| | - Shu Chen
- Department of Thoracic Surgery, The Second Hospital of Jilin University, Changchun, 130041, China.
| | - Lili Yang
- Department of Orthopedics, The Second Hospital of Jilin University, Changchun, 130041, China.
| | - Guomin Liu
- Department of Orthopedics, The Second Hospital of Jilin University, Changchun, 130041, China; Scientific and Technological Innovation Center of Health Products and Medical Materials with Characteristic Resources of Jilin Province, China.
| | - Chiyu Li
- Department of Orthopedics, The Second Hospital of Jilin University, Changchun, 130041, China.
| | - Zhiqiang Cheng
- Scientific and Technological Innovation Center of Health Products and Medical Materials with Characteristic Resources of Jilin Province, China; College of Resources and Environment, Jilin Agriculture University, Changchun, 130118, China.
| | - Guoqing Wang
- Zhejiang Suosi Technology Co. Ltd, Wenzhou, 325000, Zhejiang, China.
| | - Xiaoyu Yang
- Department of Orthopedics, The Second Hospital of Jilin University, Changchun, 130041, China.
| |
Collapse
|
2
|
Aljohani R, Barradah N, Kashkari A. Awareness and knowledge of the common features of inflammatory back pain among primary care physicians in the western region of Saudi Arabia. Medicine (Baltimore) 2022; 101:e31626. [PMID: 36316825 PMCID: PMC9622622 DOI: 10.1097/md.0000000000031626] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/05/2022] Open
Abstract
Often, there is a delay in the diagnosis of inflammatory back pain (IBP) in the primary care setting. This may be attributed to the inability of healthcare providers to distinguish between inflammatory and mechanical back pain. This study aimed to evaluate primary care physicians' current practices for assessing patients with IBP using clinical, radiographic, and laboratory tests. A questionnaire-based survey was emailed to all primary care physicians in the western region of Saudi Arabia by the Saudi Commission of Health Specialists from February to May 2021. The questionnaire included data about axial spondyloarthropathy based on the Calin, Berlin, and European Spondyloarthropathy Study Group criteria. A total of 103 primary care physicians responded who represented around 24% of primary care physicians at primary healthcare. The most often perceived IBP symptoms include a response to NSAIDs, morning stiffness lasting >30 minutes, age of onset <45 years old, duration of back pain >3 months, and improvement with exercise. The most frequently questioned patient or family history conditions were peripheral arthritis (92.2%), family history of spondyloarthritis (83.5%), and inflammatory bowel disease (97.6%). The most-reported investigations were CRP/ESR (86.4%) and spinal radiography (66%). For treatment of IBP, NSAIDs were most prescribed (48.6%), followed by physiotherapy (45.6%) and disease-modifying anti-rheumatic drugs (41.7%). Primary care physicians were more confident in management of mechanical back pain than IBP (P < .001). Primary care physicians have good knowledge of IBP symptoms but not of disease-specific features and modest confidence in evaluating patients with IBP, indicating the need for educational programs and a more effective, feasible referral strategy.
Collapse
Affiliation(s)
- Roaa Aljohani
- Department of Medicine, College of Medicine, Taibah University, Madinah, Saudi Arabia
- *Correspondence: Roaa Aljohani, Department of Medicine, College of Medicine, Taibah University, Madinah 42312, Saudi Arabia (e-mail: )
| | - Noha Barradah
- Department of Medicine, Taibah University, Medina, Saudi Arabia
| | - Amnah Kashkari
- Department of Medicine, Taibah University, Medina, Saudi Arabia
| |
Collapse
|
3
|
Early differential diagnosis of ankylosing spondylitis among patients with low back pain in primary care. BMC FAMILY PRACTICE 2020; 21:90. [PMID: 32416713 PMCID: PMC7231415 DOI: 10.1186/s12875-020-01161-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 04/20/2020] [Accepted: 05/08/2020] [Indexed: 11/18/2022]
Abstract
Diagnosing and treating low back pain (LBP) is a worldwide major primary care challenge in which a differential diagnosis between non-specific LBP and conditions with a known pathology is essential for choosing the optimal treatment strategy. The time required for the diagnosis of a condition such as ankylosing spondylitis (AS) was previously found too long. However, a recently published paper by Bashir et al. found that distinct episodes of axial pain separated by more than 6 months seem more predictive than currently applied characteristics in reaching an early diagnosis of AS.
Collapse
|