Methods: Adolescent idiopathic scoliosis (AIS) patients ages 10 to 19 years completed the Korean version of the Quality of Life Profile for Spinal Deformities (K-QLPSD), the Scoliosis Research Society-22 self-image subscale (K-SRS-22-si), Korean version of the Spinal Appearance Questionnaire (K-SAQ), Korean version of the Body Image Disturbance Questionnaire-Scoliosis (K-BIDQ-S), and Korean version of the Italian Spine Youth Quality of Life (K-ISYQOL). Four body image questionnaires were compared with K-ISYQOL and radiographic major curve magnitude, coronal balance, and sagittal balance. Spearman’s correlation was performed to compare the four body image questionnaires. Results: The study included 84 AIS patients, with a mean age of 12.6 years and a major Cobb angle of 29.4°. The four surveys were correlated with major curve magnitude and K-ISYQOL. K-SAQ and K-BIDQ-S were correlated better than K-QLPSD, and K-SRS-22-si was correlated with K-ISYQOL. The four surveys were moderately correlated with major curve magnitude, but there was no correlation with age, coronal balance, and sagittal balance. Conclusions K-SAQ and K-BIDQ-S correlate better with K-ISYQOL than K-QLPSD and K-SRS-22-si.

Background: Measuring accurate and reliable scores of quality of life in patients with ankylosing spondylitis (AS) is important in both decision-making and treatment planning for the disease. Questionnaire, The ankylosing spondylitis quality of life (ASQoL), is one of the representative tools for assessing how seriously AS patients view their disease severity, activity, as well as their overall health. To make these types of questionnaires readable and understandable, local language translation of surveys should be required. A Korean version of the ASQoL questionnaire has accordingly been developed. This study assessed the Korean version of the ASQoL survey to evaluate the reliability and validity of it. Methods: Translation and reverse translation of the English ASQoL survey were conducted. A total of 120 consecutive AS patients received a mail including the Korean-translated 36-Item Short Form Survey (SF-36), the ASQoL survey, and the visual analog scale (pain). The coefficient of intraclass correlation and Cronbach’s alpha were computed, and factor analysis, as well as reliability assessments utilizing the kappa agreement statistics for each item, was undertaken. By analyzing the responses to SF-36 and ASQoL questionnaire utilizing Pearson’s correlation coefficient, construct validity was calculated. Results: Factor analysis was performed regarding pain, physical function, and mental function. The kappa statistic of agreement was larger than 0.6 for all items. The ASQoL questionnaire had adequate test and re-test reliability (0.814). Furthermore, Cronbach’s α, the internal consistency, was very good (0.877). The Korean-translated ASQoL questionnaire demonstrated a significantly strong correlation between the single domain and total SF-36 scores. Conclusions The Korean version of the ASQoL questionnaire showed acceptable properties of measurement and successful translation. Thus, it can be said that the questionnaire is appropriate for evaluating the outcomes of Korean patients with AS.

Background: Tuberculous meningitis (TBM) is the most severe form of tuberculosis, but differentiating between the diagnosis of TBM and viral meningitis (VM) is difficult. Thus, we have developed machine-learning modules for differentiating TBM from VM.Material and Methods: For the training data, confirmed or probable TBM and confirmed VM cases were retrospectively collected from five teaching hospitals in Korea between January 2000 - July 2018. Various machine-learning algorithms were used for training. The machinelearning algorithms were tested by the leave-one-out cross-validation. Four residents and two infectious disease specialists were tested using the summarized medical information. Results: The training study comprised data from 60 patients with confirmed or probable TBM and 143 patients with confirmed VM. Older age, longer symptom duration before the visit, lower serum sodium, lower cerebrospinal fluid (CSF) glucose, higher CSF protein, and CSF adenosine deaminase were found in the TBM patients. Among the various machinelearning algorithms, the area under the curve (AUC) of the receiver operating characteristics of artificial neural network (ANN) with ImperativeImputer for matrix completion (0.85; 95% confidence interval 0.79 - 0.89) was found to be the highest. The AUC of the ANN model was statistically higher than those of all the residents (range 0.67 - 0.72, P <0.001) and an infectious disease specialist (AUC 0.76; P = 0.03). Conclusion The machine-learning techniques may play a role in differentiating between TBM and VM. Specifically, the ANN model seems to have better diagnostic performance than the non-expert clinician.

Background: Tuberculous meningitis (TBM) is the most severe form of tuberculosis, but differentiating between the diagnosis of TBM and viral meningitis (VM) is difficult. Thus, we have developed machine-learning modules for differentiating TBM from VM.Material and Methods: For the training data, confirmed or probable TBM and confirmed VM cases were retrospectively collected from five teaching hospitals in Korea between January 2000 - July 2018. Various machine-learning algorithms were used for training. The machinelearning algorithms were tested by the leave-one-out cross-validation. Four residents and two infectious disease specialists were tested using the summarized medical information. Results: The training study comprised data from 60 patients with confirmed or probable TBM and 143 patients with confirmed VM. Older age, longer symptom duration before the visit, lower serum sodium, lower cerebrospinal fluid (CSF) glucose, higher CSF protein, and CSF adenosine deaminase were found in the TBM patients. Among the various machinelearning algorithms, the area under the curve (AUC) of the receiver operating characteristics of artificial neural network (ANN) with ImperativeImputer for matrix completion (0.85; 95% confidence interval 0.79 - 0.89) was found to be the highest. The AUC of the ANN model was statistically higher than those of all the residents (range 0.67 - 0.72, P <0.001) and an infectious disease specialist (AUC 0.76; P = 0.03). Conclusion The machine-learning techniques may play a role in differentiating between TBM and VM. Specifically, the ANN model seems to have better diagnostic performance than the non-expert clinician.