| Jae Hyeon Park | 6 Articles |
Objective
To present new classification methods of knee osteoarthritis (KOA) using machine learning and compare its performance with conventional statistical methods as classification techniques using machine learning have recently been developed. Methods A total of 84 KOA patients and 97 normal participants were recruited. KOA patients were clustered into three groups according to the Kellgren-Lawrence (K-L) grading system. All subjects completed gait trials under the same experimental conditions. Machine learning-based classification using the support vector machine (SVM) classifier was performed to classify KOA patients and the severity of KOA. Logistic regression analysis was also performed to compare the results in classifying KOA patients with machine learning method. Results In the classification between KOA patients and normal subjects, the accuracy of classification was higher in machine learning method than in logistic regression analysis. In the classification of KOA severity, accuracy was enhanced through the feature selection process in the machine learning method. The most significant gait feature for classification was flexion and extension of the knee in the swing phase in the machine learning method. Conclusion The machine learning method is thought to be a new approach to complement conventional logistic regression analysis in the classification of KOA patients. It can be clinically used for diagnosis and gait correction of KOA patients. Citations Citations to this article as recorded by
It can be difficult for clinicians to distinguish a paradoxical response to antituberculous therapy, worsening of an existing lesion despite adequate treatment, treatment failure, and drug resistance. We report a case of a 69-year-old woman who experienced bilateral lower extremity paralysis secondary to a paradoxical response. She had been suffering for 1 month from low back pain, due to tuberculous spondylitis. Her low back pain improved after antituberculous therapy. The low back pain, however, reappeared 2 months after treatment, accompanied by newly developed lower extremity weakness. Imaging studies showed an increased extent of her previous lesions. Consequently, the patient underwent a vertebral corpectomy with interbody fusion of the thoracolumbar spine. Histopathological examination showed chronic inflamed granulation tissue with no microorganisms. Although the antituberculous medication was not changed, the patient's symptoms and signs, including the paralysis, resolved after surgery. Citations Citations to this article as recorded by
To compare fluid thickeners composed of starch polysaccharide (STA), guar gum-based polysaccharide (GUA), and xanthan gum-based polysaccharide (XAN) with the use of a viscometer and a line spread test (LST) under various measurement conditions. The viscosity of thickened fluid with various concentrations (range, GUA 1%-4%, XAN 1%-6%, STA 1%-7%, at intervals of 1%) was measured with a rotational viscometer with various shear rates (1.29 s-1, 5.16 s-1, 51.6 s-1, and 103 s-1) at a temperature of 35℃, representing body temperature. The viscosity of STA showed time dependent alteration. So STA was excluded. Viscosities of GUA and XAN (range of concentration, GUA 1%-3%, XAN 1%-6%, at intervals of 1%) were measured at a room temperature of 20℃. LST was conducted to compare GUA and XAN (concentration, 1.5%, 2.0%, and 3.0%) at temperatures of 20℃ and 35℃. The viscosities of 1% GUA and XAN were similar. However, viscosity differences between GUA and XAN were gradually larger as concentration increased. The shear thinning effect, the inverse relationship between the viscosity and the shear rate, was more predominant in XAN than in GUA. The results of LST were not substantially different from GUA and XAN, in spite of the difference in viscosity. However manufacturers' instructions do not demonstrate the rheological properties of thickeners. The viscosities of thickened fluid were different when the measurement conditions changed. Any single measurement might not be sufficient to determine comparable viscosity with different thickeners. Clinical decision for the use of a specific thickener seems to necessitate cautious consideration of results from a viscometer, LST, and an expert's opinion. Citations Citations to this article as recorded by
To translate the MD Anderson Dysphagia Inventory (MDADI) which is a self-administered questionnaire that assesses effect of dysphagia on the quality of life for patients with head and neck cancer, into Korean and to verify the validity and reliability of the Korean version of MDADI. We performed 6 steps for the cross-cultural adaptation which consisted of translation, synthesis, back translation, review by an expert committee, cognitive debriefing, and final proof reading. A total of 34 dysphagia patients with head and neck cancers from Seoul National University Hospital answered the translated version of the questionnaire for the pre-testing. The patients answered the same questionnaire 2 weeks later to verify the test-retest reliability. One patient was excluded at second survey because he changed his feeding strategy. Overall, 33 patients completed the study. Linguistic validations were achieved by each step of cross-cultural adaptation. We gathered statistically strong construct validity (Spearman rho for subdomain scores to total score correlation range from 0.852 to 0.927), internal consistency for subdomains (Cronbach's alpha coefficients range from 0.785 to 0.889) and test-retest reliability (intra-class correlation coefficient range from 0.820 to 0.955) The Korean version of the MDADI achieved linguistic validations and demonstrated good construct validity and reliability. It can be a useful tool for screening and treatment planning for the dysphagia of patients with head and neck cancers. Citations Citations to this article as recorded by
Objective
Primary frozen shoulder causes significant pain and progressively restricts shoulder movements. Diagnosis is primarily clinically based on patient history and physical examination. Management is mainly non-invasive owing to its self-limiting clinical course. However, clinical practice guidelines for frozen shoulder have not yet been developed in Korea. The developed guidelines aim to provide evidence-based recommendations for the diagnosis and treatment of frozen shoulder. Methods A guideline development committee reviewed the literature from four databases (PubMed, Embase, Cochrane Library, and KMbase). Using the PICO (Population, Intervention, Comparator, and Outcome) framework, the committee formulated two backgrounds and 16 key questions to address common clinical concerns. Recommendations were made using the Grading of Recommendations, Assessment, Development, and Evaluation framework. Results Diabetes, thyroid disease, and dyslipidemia significantly increase the risk of developing a frozen shoulder. Although frozen shoulder is often self-limiting, some patients may experience long-term disabilities. Ultrasound and magnetic resonance imaging should be used as adjunctive tools alongside clinical diagnosis, and not as independent diagnostic methods. Noninvasive approaches, such as medications, physical modalities, exercises, electrical stimulation, and manual therapy, may reduce pain and improve shoulder function. Other noninvasive interventions have limited evidence, and their application should be based on clinical judgment. Intra-articular steroid injections are recommended for treatment, and physiotherapy or hydrodilation with steroid injections can also be beneficial. Conclusion These guidelines provide evidence-based recommendations for diagnosing and treating primary frozen shoulder.
|
|
