• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.2
• /
• pp.113-118
• /
• 2023

The WiFi fingerprint method for location estimation within the home has the advantage of using the existing infrastructure and estimating absolute coordinates, so many studies are being conducted. Existing studies have mainly focused on the study of localization algorithms, but the improvement of accuracy has reached its limits. However, since a wireless LAN receiver such as a smartphone cannot measure signals smaller than the reception sensitivity of radio signals, the position estimation error varies depending on the method of processing these values. In this paper, we proposed a method to increase the location estimation accuracy by pre-processing the received signal data of the measured wireless LAN router in various ways and applying it to the existing algorithm, and greatly improved accuracy was obtained. In addition, the preprocessed data was applied to the KNN method and the CNN method and the performance was compared.

• Journal of Chest Surgery
• /
• v.56 no.3
• /
• pp.179-185
• /
• 2023

Background: Assessments of air leaks are usually performed subjectively, precluding the use of air leaks as an evaluation factor. We aimed to identify objective parameters as predictive factors for prolonged air leak (PAL) and air leak cessation (ALC) from air flow data produced by a digital drainage system. Methods: Flow data records of 352 patients who underwent lung lobectomy were reviewed, and flow data at designated intervals (1, 2, and 3 hours postoperatively [POH] and 3 times a day thereafter [06:00, 13:00, 19:00]) were extracted. ALC was defined by flow less than 20 mL/min over 12 hours, and PAL was defined as ALC after 5 days. Cumulative incidence curves were obtained using Kaplan-Meier estimates of time to ALC. Cox regression analysis was performed to determine the effects of variables on the rate of ALC. Results: The incidence of PAL was 18.2% (64/352). Receiver operating characteristic curve analysis showed cut-off values of 180 mL/min for the flow at 3 POH and 73.3 mL/min for the flow on postoperative day 1; the sensitivity and specificity of these values were 88.9% and 82.5%, respectively. The rates of ALC by Kaplan-Meier analysis were 56.8% at 48 POH and 65.6% at 72 POH. Multivariate Cox regression analysis revealed that the flow at 3 POH (≤80 mL/min), operation time (≤220 minutes), and right middle lobectomy independently predicted ALC. Conclusion: Air flow measured by a digital drainage system is a useful predictor of PAL and ALC and may help optimize the hospital course.

• Korean Journal of Radiology
• /
• v.22 no.5
• /
• pp.735-741
• /
• 2021

Objective: To evaluate circularity as a quantitative shape factor of small renal tumor on computed tomography (CT) in differentiating fat-poor angiomyolipoma (AML) from renal cell carcinoma (RCC). Materials and Methods: In 257 consecutive patients, 257 pathologically confirmed renal tumors (either AML or RCC less than 4 cm), which did not include visible fat on unenhanced CT, were retrospectively evaluated. A radiologist drew the tumor margin to measure the perimeter and area in all the contrast-enhanced axial CT images. In each image, a quantitative shape factor, circularity, was calculated using the following equation: 4 x π x (area ÷ perimeter²). The median circularity (circularity index) was adopted as a representative value in each tumor. The circularity index was compared between fat-poor AML and RCC, and the receiver operating characteristic (ROC) curve analysis was performed. Univariable and multivariable binary logistic regression analysis was performed to determine the independent predictor of fat-poor AML. Results: Of the 257 tumors, 26 were AMLs and 231 were RCCs (184 clear cell RCCs, 25 papillary RCCs, and 22 chromophobe RCCs). The mean circularity index of AML was significantly lower than that of RCC (0.86 ± 0.04 vs. 0.93 ± 0.02, p < 0.001). The mean circularity index was not different between the subtypes of RCCs (0.93 ± 0.02, 0.92 ± 0.02, and 0.92 ± 0.02 for clear cell, papillary, and chromophobe RCCs, respectively, p = 0.210). The area under the ROC curve of circularity index was 0.924 for differentiating fat-poor AML from RCC. The sensitivity and specificity were 88.5% and 90.9%, respectively (cut-off, 0.90). Lower circularity index (≤ 0.9) was an independent predictor (odds ratio, 41.0; p < 0.001) for predicting fat-poor AML on multivariable logistic regression analysis. Conclusion: Circularity is a useful quantitative shape factor of small renal tumor for differentiating fat-poor AML from RCC.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.442-453
• /
• 2021

Artificial intelligence (AI) will likely affect various fields of medicine. This article aims to explain the fundamental principles of clinical validation, device approval, and insurance coverage decisions of AI algorithms for medical diagnosis and prediction. Discrimination accuracy of AI algorithms is often evaluated with the Dice similarity coefficient, sensitivity, specificity, and traditional or free-response receiver operating characteristic curves. Calibration accuracy should also be assessed, especially for algorithms that provide probabilities to users. As current AI algorithms have limited generalizability to real-world practice, clinical validation of AI should put it to proper external testing and assisting roles. External testing could adopt diagnostic case-control or diagnostic cohort designs. A diagnostic case-control study evaluates the technical validity/accuracy of AI while the latter tests the clinical validity/accuracy of AI in samples representing target patients in real-world clinical scenarios. Ultimate clinical validation of AI requires evaluations of its impact on patient outcomes, referred to as clinical utility, and for which randomized clinical trials are ideal. Device approval of AI is typically granted with proof of technical validity/accuracy and thus does not intend to directly indicate if AI is beneficial for patient care or if it improves patient outcomes. Neither can it categorically address the issue of limited generalizability of AI. After achieving device approval, it is up to medical professionals to determine if the approved AI algorithms are beneficial for real-world patient care. Insurance coverage decisions generally require a demonstration of clinical utility that the use of AI has improved patient outcomes.

• Korean Journal of Radiology
• /
• v.23 no.8
• /
• pp.821-827
• /
• 2022

Objective: To determine the anatomical characteristics of the petrous ridge and trigeminal nerve in trigeminal neuralgia (TN) without neurovascular compression (NVC). Materials and Methods: From May 2017 to March 2021, 66 patients (49 female and 17 male; mean age ± standard deviation [SD], 56.8 ± 13.3 years) with TN without NVC and 57 controls (46 female and 11 male; 52.0 ± 15.6 years) were enrolled. The angle of the petrous ridge (APR) and angle of the trigeminal nerve (ATN) were measured using magnetic resonance imaging with a high-resolution three-dimensional T2 sequence. Data on the symptomatic side were compared with those on the asymptomatic side in patients and with the mean measurements of the bilateral sides in controls. Receiver operating characteristic (ROC) analysis was conducted to evaluate the performance of APR and ATN in distinguishing TN patients from controls. Results: In TN patients without NVC, the mean ± standard deviation (SD) of APR on the symptomatic side (98.40° ± 19.75°) was significantly smaller than that of the asymptomatic side (105.59° ± 22.45°, p = 0.019) and controls (108.44° ± 15.98°, p = 0.003). The mean ATN ± SD on the symptomatic side (144.41° ± 8.92°) was significantly smaller than that of the asymptomatic side (149.67° ± 8.09°, p = 0.003) and controls (150.45° ± 8.48°, p = 0.001). The area under the ROC curve for distinguishing TN patients from controls was 0.673 (95% confidence interval [CI]: 0.579-0.758) for APR and 0.700 (CI: 0.607-0.782) for ATN. The sensitivity and specificity using the diagnostic cutoff yielding the highest Youden index were 81.8% (54/66) and 49.1% (28/57), respectively, for APR (with a cutoff score of 94.30°) and 65.2% (43/66) and 66.7% (38/57), respectively, for ATN (cutoff score, 148.25°). Conclusion: In patients with TN without NVC, APR and ATN were smaller than those in controls, which may explain the potential cause of TN and provide additional information for diagnosis.

• Korean Journal of Radiology
• /
• v.20 no.4
• /
• pp.589-598
• /
• 2019

Objective: To evaluate whether data acquired from perfusion computed tomography (PCT) parameters can aid in the prediction of treatment outcome after palliative chemotherapy in patients with unresectable advanced gastric cancer (AGC). Materials and Methods: Twenty-one patients with unresectable AGCs, who underwent both PCT and palliative chemotherapy, were prospectively included. Treatment response was assessed according to Response Evaluation Criteria in Solid Tumors version 1.1 (i.e., patients who achieved complete or partial response were classified as responders). The relationship between tumor response and PCT parameters was evaluated using the Mann-Whitney test and receiver operating characteristic analysis. One-year survival was estimated using the Kaplan-Meier method. Results: After chemotherapy, six patients exhibited partial response and were allocated to the responder group while the remaining 15 patients were allocated to the non-responder group. Permeability surface (PS) value was shown to be significantly different between the responder and non-responder groups (51.0 mL/100 g/min vs. 23.4 mL/100 g/min, respectively; p = 0.002), whereas other PCT parameters did not demonstrate a significant difference. The area under the curve for prediction in responders was 0.911 (p = 0.004) for PS value, with a sensitivity of 100% (6/6) and specificity of 80% (12/15) at a cut-off value of 29.7 mL/100 g/min. One-year survival in nine patients with PS value > 29.7 mL/100 g/min was 66.7%, which was significantly higher than that in the 12 patients (33.3%) with PS value ≤ 29.7 mL/100 g/min (p = 0.019). Conclusion: Perfusion parameter data acquired from PCT demonstrated predictive value for treatment outcome after palliative chemotherapy, reflected by the significantly higher PS value in the responder group compared with the non-responder group.

• Journal of Cardiovascular Imaging
• /
• v.31 no.4
• /
• pp.200-206
• /
• 2023

BACKGROUND: Right ventricular (RV) dysfunction is a significant risk of major adverse cardiac events in patients with acute heart failure (AHF). In this study, we evaluated RV-pulmonary artery (PA) coupling, assessed by tricuspid annular plane systolic excursion (TAPSE)/pulmonary artery systolic pressure (PASP) and assessed its prognostic significance, in AHF patients. METHODS: We measured the TAPSE/PASP ratio and analyzed its correlations with other echocardiographic parameters. Additionally, we assessed its prognostic role in AHF patients. RESULTS: A total of 1147 patients were included in the analysis (575 men, aged 70.81 ± 13.56 years). TAPSE/PASP ratio exhibited significant correlations with left ventricular (LV) ejection fraction(r = 0.243, p < 0.001), left atrial (LA) diameter(r = -0.320, p < 0.001), left atrial global longitudinal strain (LAGLS, r = 0.496, p < 0.001), mitral E/E' ratio(r = -0.337, p < 0.001), and right ventricular fractional area change (RVFAC, r = 0.496, p < 0.001). During the median follow-up duration of 29.0 months, a total of 387 patients (33.7%) died. In the univariate analysis, PASP, TAPSE, and TAPSE/PASP ratio were significant predictors of mortality. After the multivariate analysis, TAPSE/PASP ratio remained a statistically significant parameter for all-cause mortality (hazard ratio [HR], 0.453; p = 0.037) after adjusting for other parameters. In the receiver operating curve analysis, the optimal cut-off level of TAPSE/PASP ratio for predicting mortality was 0.33 (area under the curve = 0.576, p < 0.001), with a sensitivity of 65% and a specificity of 47%. TAPSE/PASP ratio < 0.33 was associated with an increased risk of mortality after adjusting for other variables (HR, 1.306; p = 0.025). CONCLUSIONS: In AHF patients, TAPSE/PASP ratio demonstrated significant associations with RVFAC, LA diameter and LAGLS. Moreover, a decreased TAPSE/PASP ratio < 0.33 was identified as a poor prognostic factor for mortality.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.27 no.2
• /
• pp.79-87
• /
• 2024

Purpose: Recently, the prevalence of eosinophilic gastrointestinal disease (EGID) has shown an increasing trend worldwide. As the diagnosis of EGID requires invasive endoscopy with biopsy, noninvasive markers for detecting EGID in suspected patients, particularly children, are urgently needed. Therefore, this study aimed to evaluate the diagnostic accuracy of serum eosinophil cationic protein (ECP) beyond peripheral eosinophil counts in pediatric patients with EGID. Methods: Overall, 156 children diagnosed with EGID were enrolled and 150 children with functional abdominal pain disorder (FAPD) were recruited as controls. All participants underwent endoscopic biopsy in each segment of the gastrointestinal (GI) tract and serum ECP measurement, as well as peripheral eosinophil percent and absolute eosinophil count. Results: Comparing EGID (n=156) with FAPD (n=150) patients, serum ECP levels were significantly higher in pediatric patients with EGID than in those with FAPD (25.8±28.6 ㎍/L vs. 19.5±21.0 ㎍/L, p=0.007), while there was no significant difference in peripheral eosinophil percent and absolute eosinophil counts between the two groups. Serum ECP levels were correlated with peripheral eosinophil percent (r=0.593, p<0.001) and the absolute eosinophil count (r=0.660, p<0.001). The optimal cutoff value of serum ECP for pediatric EGID was 10.5 ㎍/mL, with a sensitivity of 69.9% and a specificity of 43.4% with an area under the receiver operating characteristic curve of 0.562. Conclusion: The combination of serum ECP levels and peripheral eosinophil counts, when employed with appropriated thresholds, could serve as a valuable noninvasive biomarker to distinguish between EGID and FAPD in pediatric patients manifesting GI symptoms.

• Journal of Chest Surgery
• /
• v.57 no.3
• /
• pp.302-311
• /
• 2024

Background: Unexpected conversion to thoracotomy during planned video-assisted thoracoscopic surgery (VATS) can lead to poor outcomes and comparatively high morbidity. This study was conducted to assess preoperative risk factors associated with unexpected thoracotomy conversion and to develop a risk scoring model for preoperative use, aimed at identifying patients with an elevated risk of conversion. Methods: A retrospective analysis was conducted of 1,506 patients who underwent surgical resection for non-small cell lung cancer. To evaluate the risk factors, univariate analysis and logistic regression were performed. A risk scoring model was established to predict unexpected thoracotomy conversion during VATS of the lung, based on preoperative factors. To validate the model, an additional cohort of 878 patients was analyzed. Results: Among the potentially significant clinical variables, male sex, previous ipsilateral lung surgery, preoperative detection of calcified lymph nodes, and clinical T stage were identified as independent risk factors for unplanned conversion to thoracotomy. A 6-point risk scoring model was developed to predict conversion based on the assessed risk, with patients categorized into 4 groups. The results indicated an area under the receiver operating characteristic curve of 0.747, with a sensitivity of 80.5%, specificity of 56.4%, positive predictive value of 1.8%, and negative predictive value of 91.0%. When applied to the validation cohort, the model exhibited good predictive accuracy. Conclusion: We successfully developed and validated a risk scoring model for preoperative use that can predict the likelihood of unplanned conversion to thoracotomy during VATS of the lung.

• Korean Circulation Journal
• /
• v.53 no.10
• /
• pp.677-689
• /
• 2023

Background and Objectives: There is limited evidence regarding machine-learning prediction for the recurrence of atrial fibrillation (AF) after electrical cardioversion (ECV). This study aimed to predict the recurrence of AF after ECV using machine learning of clinical features and electrocardiograms (ECGs) in persistent AF patients. Methods: We analyzed patients who underwent successful ECV for persistent AF. Machine learning was designed to predict patients with 1-month recurrence. Individual 12-lead ECGs were collected before and after ECV. Various clinical features were collected and trained the extreme gradient boost (XGBoost)-based model. Ten-fold cross-validation was used to evaluate the performance of the model. The performance was compared to the C-statistics of the selected clinical features. Results: Among 718 patients (mean age 63.5±9.3 years, men 78.8%), AF recurred in 435 (60.6%) patients after 1 month. With the XGBoost-based model, the areas under the receiver operating characteristic curves (AUROCs) were 0.57, 0.60, and 0.63 if the model was trained by clinical features, ECGs, and both (the final model), respectively. For the final model, the sensitivity, specificity, and F1-score were 84.7%, 28.2%, and 0.73, respectively. Although the AF duration showed the best predictive performance (AUROC, 0.58) among the clinical features, it was significantly lower than that of the final machine-learning model (p<0.001). Additional training of extended monitoring data of 15-minute single-lead ECG and photoplethysmography in available patients (n=261) did not significantly improve the model's performance. Conclusions: Machine learning showed modest performance in predicting AF recurrence after ECV in persistent AF patients, warranting further validation studies.