• International Journal of Heart Failure
• /
• v.6 no.1
• /
• pp.11-19
• /
• 2024

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.

• Investigative and Clinical Urology
• /
• v.63 no.3
• /
• pp.301-308
• /
• 2022

Purpose To diagnose lower urinary tract symptoms (LUTS) in a noninvasive manner, we created a prediction model for bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using simple uroflowmetry. In this study, we used deep learning to analyze simple uroflowmetry. Materials and Methods We performed a retrospective review of 4,835 male patients aged ≥40 years who underwent a urodynamic study at a single center. We excluded patients with a disease or a history of surgery that could affect LUTS. A total of 1,792 patients were included in the study. We extracted a simple uroflowmetry graph automatically using the ABBYY Flexicapture^® image capture program (ABBYY, Moscow, Russia). We applied a convolutional neural network (CNN), a deep learning method to predict DUA and BOO. A 5-fold cross-validation average value of the area under the receiver operating characteristic (AUROC) curve was chosen as an evaluation metric. When it comes to binary classification, this metric provides a richer measure of classification performance. Additionally, we provided the corresponding average precision-recall (PR) curves. Results Among the 1,792 patients, 482 (26.90%) had BOO, and 893 (49.83%) had DUA. The average AUROC scores of DUA and BOO, which were measured using 5-fold cross-validation, were 73.30% (mean average precision [mAP]=0.70) and 72.23% (mAP=0.45), respectively. Conclusions Our study suggests that it is possible to differentiate DUA from non-DUA and BOO from non-BOO using a simple uroflowmetry graph with a fine-tuned VGG16, which is a well-known CNN model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.25-34
• /
• 2024

This paper presents the development of a mobile application that detects and identifies canine skin diseases by training a deep learning-based U-Net model to infer the presence and location of skin lesions from images. U-Net, primarily used in medical imaging for image segmentation, is effective in distinguishing specific regions of an image in a polygonal form, making it suitable for identifying lesion areas in dogs. In this study, six major canine skin diseases were defined as classes, and the U-Net model was trained to differentiate among them. The model was then implemented in a mobile app, allowing users to perform lesion analysis and prediction through simple camera shots, with the results provided directly to the user. This enables pet owners to monitor the health of their pets and obtain information that aids in early diagnosis. By providing a quick and accurate diagnostic tool for pet health management through deep learning, this study emphasizes the significance of developing an easily accessible service for home use.

• Clinical and Experimental Pediatrics
• /
• v.45 no.6
• /
• pp.773-782
• /
• 2002

Purpose : To identify the necessity of more reasonable diagnostic criteria and the possibility of early prediction of coronary involvement in the higher risk group, we investigated and compared clinical and laboratory findings in the acute phase and coronary involvements in those younger (n=17) and older(n=53) than one year of age in Kawasaki disease(KD). Methods : Retrospective chart reviews were performed on 70 patients with KD who were admitted to the Chung-Ang University Hospital from April 1997 to May 2001. Results : Male were significantly higher in the younger age group(M : F ratio 3.3 : 1 vs. 1.0 : 1, P=0.004). Fever durations before intravenous immunoglobulin(IVIG) and echocardiography were significantly shorter in the younger group($4.6{\pm}1.3$ vs. $6.2{\pm}2.5$, P=0.004 vs. 0.01, respectively). Cases meeting typical diagnostic criteria were significantly less in the younger group(P=0.006). In the laboratory findings, serum albumin, BUN and $K^+$ levels in the acute febrile phase were significantly higher in the younger group(P=0.002, 0.006, <0.001, respectively) and incidences of coronary artery dilatation in the acute phase were significantly higher in the younger group(P=0.01). Conclusion : Although less met the typical diagnostic criteria of KD, infants younger than one year of age are more susceptible to coronary artery change in the acute febrile phase. Therefore, KD should be entertained as a diagnostic possibility in young infants with prolonged fever without distinct fever focus, and echocardiography should be considered as part of the evaluation of these patients, and then early diagnosis and prompt IVIG should be conducted.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1207-1217
• /
• 2021

Purpose To evaluate the safety and efficacy of ultrasound-guided percutaneous core needle biopsy (USPCB) of pancreatic and peripancreatic lesions adjacent to critical vessels. Materials and Methods Data were collected retrospectively from 162 patients who underwent USPCB of the pancreas (n = 98), the peripancreatic area adjacent to the portal vein, the paraaortic area adjacent to pancreatic uncinate (n = 34), and lesions on the third duodenal portion (n = 30) during a 10-year period. An automated biopsy gun with an 18-gauge needle was used for biopsies under US guidance. The USPCB results were compared with those of the final follow-up imaging performed postoperatively. The diagnostic accuracy and major complication rate of the USPCB were calculated. Multiple factors were evaluated for the prediction of successful biopsies using univariate and multivariate analyses. Results The histopathologic diagnosis from USPCB was correct in 149 (92%) patients. The major complication rate was 3%. Four cases of mesenteric hematomas and one intramural hematoma of the duodenum occurred during the study period. The following factors were significantly associated with successful biopsies: a transmesenteric biopsy route rather than a transgastric or transenteric route; good visualization of targets; and evaluation of the entire US pathway. In addition, the number of biopsies required was less when the biopsy was successful. Conclusion USPCB demonstrated high diagnostic accuracy and a low complication rate for the histopathologic diagnosis of pancreatic and peripancreatic lesions adjacent to critical vessels.

• Journal of Yeungnam Medical Science
• /
• v.33 no.1
• /
• pp.8-12
• /
• 2016

Background: The decision to administer oral anticoagulation therapy depends on accurate assessment of stroke risk in patients with atrial fibrillation (AF). Various stroke risk stratification schemes have been developed to help inform clinical decision making. The CHADS2 and CHA2DS2-VASc scores have been used in estimating the risk of stroke in patients with AF. Recently R2CHA2DS2-VASc score was developed. The objective of the current study is to validate the usefulness of the R2CHA2DS2-VASc score and to compare the accuracy of the CHADS2, CHA2DS2-VASc, and R2CHA2DS2-VASc scores in predicting a patient's risk of stroke. Methods: Based on medical records, we conducted a retrospective study of patients hospitalized with AF from March 2011 to July 2013. A total of 448 AF patients were included in this study. The receiver operating characteristic (ROC) curve analysis in MedCalc was used for comparison with respective diagnostic values. Results: The patient characteristics showed male predominance (60.9%). Among the 448 AF patients, 131 (29.2%) patients had strokes during the study. A R2CHA2DS2-VASc score of more than 5 is the optimal cut-off value for prediction of stroke. A risk score of three, the area under the ROC curve (AUC) of R2CHA2DS2-VASc score (AUC 0.631; 95% confidence interval, 0.585-0.679) was the highest. A significant difference was observed between AUC for R2CHA2DS2-VASc, CHADS2, and CHA2DS2-VASc scores, but no meaningful difference between CHADS2 and CHA2DS2-VASc scores. Conclusion: We determined the usefulness of the R2CHA2DS2-VASc score, which showed better association with stroke than the CHADS2 and CHA2DS2-VASc scores.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.846-855
• /
• 2007

Significant feature extraction in cancer cell image analysis is an important process for grading cell carcinoma. In this study, we propose a method for 3D quantitative analysis of cell nuclei based upon digital image cytometry. First, we acquired volumetric renal cell carcinoma data for each grade using confocal laser scanning microscopy and segmented cell nuclei employing color features based upon a supervised teaming scheme. For 3D visualization, we used a contour-based method for surface rendering and a 3D texture mapping method for volume rendering. We then defined and extracted the 3D morphological features of cell nuclei. To evaluate what quantitative features of 3D analysis could contribute to diagnostic information, we analyzed the statistical significance of the extracted 3D features in each grade using an analysis of variance (ANOVA). Finally, we compared the 2D with the 3D features of cell nuclei and analyzed the correlations between them. We found statistically significant correlations between nuclear grade and 3D morphological features. The proposed method has potential for use as fundamental research in developing a new nuclear grading system for accurate diagnosis and prediction of prognosis.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.9
• /
• pp.4483-4486
• /
• 2016

Background: Despite the fact that ovarian cancer is the seventh most common cancer in women worldwide and the fifth leading cause of cancer death, It is the most common cause of death due to reproductive cancers in Thailand where epithelial ovarian cancer (EOC) is commonly found. According to a Thai statistical analysis in 2010 by the Department of Medical Services, epithelial ovarian cancer was the sixth most common cancer in Thailand from 2001to 2003.The incidence of 5.1 per 100,000 women per year. Human epididymis protein 4 (HE4) is a novo diagnostic tumor marker for EOC. The combination of HE4 and carcinoma antigen 125 (CA 125) is a tool for detecting epithelial ovarian cancer (EOC) better than using CA 125 alone. Therefore, the researcher is interested in HE4 does have a role to predict recurrent epithelial ovarian cancer. Materials and Methods: The patients who had complete response after diagnosed with epithelial ovarian cancer by pathology, FIGO stage 3 or more had been treated through surgery and chemotherapy at the Sunpasitthiprasong Hospital from June 2014 until March 2016. The patients were followed up every three months, using tumor marker (CA 125, HE4,Carcinoma antigen 19-9) together with other checkup methods, such as rectovaginal examination, CXR every year and other imaging as indication. Afterwards, the data was analyzed for the ability of HE4 to detect recurrence of epithelial ovarian cancer. Results: In 47 patients in this study follow-up for 22 months after complete response treatment from surgery and chemotherapy in epithelial ovarian cancer, 23 had recurrent disease and HE4 titer rising. The patients with recurrent epithelial ovarian cancer demonstrated high levels of both HE4 and CA125 with sensitivity of 91.3% and 52.7% respectively, specificity of 87.5% and 95.6% and positive predictive values of 87.5% and 85.7%. HE4 can predict recurrent epithelial ovarian cancer (p-value=0.02242). Comparing HE4 and CA125 in predicting recurrent epithelial ovarian cancer HE4 had more potential than CA125 (p-value =0.8314). Conclusions: The present study showed HE4 to have a role in predicting recurrent epithelial ovarian cancer and HE4 is potentially better than CA125 as a marker for this purpose.

• The korean journal of orthodontics
• /
• v.26 no.5 s.58
• /
• pp.601-611
• /
• 1996

Craniofacial growth pattern is an important diagnostic data in the course of orthodontic diagnosis and treatment planning ; it also has great influence in the establishment of occlusion as well as shaping and development of face. There have been many studies to classify different craniofacial growth patterns and attempts to predict growth patterns. This study aimed to correlate craniofacial growth pattern and symphysis morphology. 120 adult patients with age from 19 to 39 (mean age : 23.1) were chosen as subjects , using lateral cephalometric films. their anterior to posterior facial height ratios were calculated. They were divided into 3 groups - clockwise growth pattern with $56\%-62\%$(36subjects), counter-clockwise growth pattern group with $65\%$-80\%$(43subjects) and normal growth pattern group with $62\%-65\%$(41subjects). Symphysis morphology and Prominence evaluation in each subject were studied and the following conclusions were drawn : 1. In comparison of symphysis morphology between the sex groups, men showed large symphysis height and prominence. 2. Concerning the symphysis morphology, the clockwise growth pattern group showed larger height, H/D ratio and actual length but smaller depth, angle, effective length and E/A ratio compared to the counter -clockwise growth pattern group. 3. Those with smaller prominance of symphysis showed clockwise growth tendency and those with larger prominance showed counter-clockwise growth tendency.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.10 no.2
• /
• pp.35-46
• /
• 2008

Soil moisture is one of the important components in hydrological processes and also controls the subsurface flow mechanism at a hillslope scale. In this study, time series of soil moisture were measured at a hillslope located in Gwangneung National Arboretum, Korea using a multiplex Time Domain Reflectometry(TDR) system measuring soil moisture with bi-hour interval. The Box-Jenkins transfer function and noise model was used to estimate spatial distributions of soil moisture histories between May and September, 2007. Rainfall was used as an input parameter and soil moisture at 10 cm depth was used as an output parameter in the model. The modeling process consisted of a series of procedures(e.g., data pretreatment, model identification, parameter estimation, and diagnostic checking of selected models), and the relationship between soil moisture and rainfall was assessed. The results indicated that the patterns of soil moisture at different locations and slopes along the hillslope were similar with those of rainfall during the measurment period. However, the spatial distribution of soil moisture was not associated with the slope of the monitored location. This implies that the variability of the soil moisture was determined more by rainfall than by the slope of the site. Due to the influence of vegetation activity on soil moisture flow in spring, the soil moisture prediction in spring showed higher variability and complexity than that in early autumn did. This indicates that vegetation activity is an important factor explaining the patterns of soil moisture for an upland forested hillslope.