OBJECTIVES: Breast cancer is the second most common cancer among Korean women. Because breast cancer is strongly associated with negative emotional and physical changes, early detection and treatment of breast cancer are very important. As a supporting tool for classifying breast cancer, we tried to identify the best meta-learner model in a stacking ensemble when the same machine learning models for the base learner and meta-learner are used. METHODS: We used machine learning models, such as the gradient boosted model, distributed random forest, generalized linear model, and deep neural network in a stacking ensemble. These models were used to construct a base learner, and each of them was used as a meta-learner again. Then, we compared the performance of machine learning models in the meta-learner to determine the best meta-learner model in the stacking ensemble. RESULTS: Experimental results showed that using the GBM as a meta-learner led to higher accuracy than that achieved with any other model for breast cancer data and using the GLM as a meta learner led to low root-mean-squared error for both sets of breast cancer data. CONCLUSIONS: We compared the performance of every meta-learner model in a stacking ensemble as a supporting tool for classifying breast cancer. The study showed that using specific models as a metalearner resulted in better performance than single classifiers, and using GBM and GLM as a meta-learner is appropriate as a supporting tool for classifying breast cancer data.
Breast Neoplasms ; Breast ; Classification ; Female ; Forests ; Humans ; Linear Models ; Machine Learning ; Medical Informatics ; Statistics as Topic

Recently, interest in machine learning (ML) has increased as the application fields have expanded significantly. Although ML methods excel in many fields, establishing an ML pipeline requires considerable time and human resources. Automated ML (AutoML) tools offer a solution by automating repetitive tasks, such as data preprocessing, model selection, hyperparameter optimization, and prediction analysis. This review introduces the use of AutoML tools for general research, including clinical studies. In particular, it outlines a simple approach that is accessible to beginners using the R programming language (R Foundation for Statistical Computing). In addition, the practical code and output results for binary classification are provided to facilitate direct application by clinical researchers in future studies.

Since the era of evidence-based medicine, it has become a matter of course to use statistics to create objective evidence in clinical research. As an extension of this, it has become essential in clinical research to calculate the correct sample size to demonstrate a clinically significant difference before starting the study.Also, because sample size calculation methods vary from study design to study design, there is no formula for sample size calculation that applies to all designs. It is very important for us to understand this. In this review, each sample size calculation method suitable for various study designs was introduced using the R program (R Foundation for Statistical Computing). In order for clinical researchers to directly utilize it according to future research, we presented practice codes, output results, and interpretation of results for each situation.

Nonsyndromic cleft lip with or without cleft palate (CL/P) is a common craniofacial birth defect that is the result of a mixture of genetic and environmental factors. While studies have identified a number of different candidate genes and loci for the etiology of CL/P, the results have not been consistent among different ethnic groups. To study the genetic association of the candidate genes in Korean patients affected by CL/P, we genotyped 97 nonsyndromic CL/P patients and 100 control individuals using single nucleotide polymorphic markers at the MTHFR, TGFA, and IRF6 genes. We report that the T3827C marker at TGFA showed significant association with nonsyndromic CL/P, but all the other markers tested were not significantly associated with nonsyndromic CL/P in Korean patients.
Cleft Lip* ; Cleft Palate* ; Congenital Abnormalities ; Ethnic Groups ; Humans

PURPOSE: Atypical femoral fractures (AFFs) occur in two distinct part, subtrochanter and diaphysis. The aim of this study was to investigate the relationship between the lateral femoral bowing angle and the location of AFF. MATERIALS AND METHODS: This study included a total of 56 cases in 45 patients who underwent surgical treatment between January 2010 and December 2015. For the diaphyseal and subtrochanteric AFFs, we evaluated the relationship between the anatomic location and lateral femoral bowing angle. Lateral femoral bowing angle was measured by two orthopaedic surgeons and average value of two calibrators was used in statistic analysis. Other variables like age, height, weight, body mass index and bone mineral density were also evaluated. We also calculated the cutoff value for the location of the fractures from the raw data. RESULTS: The average lateral femoral bowing angle was 10.10°±3.79° (3°-19°) in diaphyseal group and 3.33°±2.45° (1.5°-11°) in subtrochanter group. Lateral femoral bowing angle was statistically significant in logistic regression analysis. According to the receiver operating characteristic curve, cutoff value for the location of the fracture was 5.25°. In other words, the femoral diaphyseal fractures are more frequent if the lateral femoral bowing angle is greater than 5.25°. CONCLUSION: The lateral femoral bowing angle is associated with the location of the AFFs and the cutoff value of lateral femoral bowing angle was 5.25°.
Body Weight ; Bone Density ; Diaphyses ; Femoral Fractures* ; Femur ; Humans ; Logistic Models ; ROC Curve ; Surgeons

Purpose: This study evaluated aggressive hyperbaric oxygen therapy (HBOT) by understanding various exposure routes of acute carbon monoxide (CO) poisoning, the risk factors causing acute cardiovascular, and neurological toxicity caused by poisoning. Methods: A retrospective study was conducted based on the medical records of 417 acute CO poisoning patients who visited the emergency care unit from March 2017 to August 2019. The exposure routes, HBOT performance, age, sex, medical history (hypertension, diabetes mellitus, ischemic heart disease, heart failure), intentionality, loss of consciousness (LOC), intake with alcohol or sedatives, and initial test results (carboxyhemoglobin (COHb), troponin- I, electrocardiography, echocardiography, brain MRI) were examined. Comparative analysis of the clinical information was conducted between the groups that showed acute cardiovascular toxicity and neurological toxicity, and groups that did not. Results: Among 417 patients diagnosed with acute CO poisoning, 201 cases (48.2%) were intentional, and charcoal briquette was the most common route (169 patients (40.5%)). Two hundred sixteen cases (51.8%) were accidental, and fire was the most common route (135 patients (32.4%)). The exposure route was more diverse with accidental poisoning. Three hundred ninety-nine patients were studied for acute cardiovascular toxicity, and 62 patients (15.5%) were confirmed to be positive. The result was statistically significant in intentionality, LOC, combined sedatives, initial COHb, HTN, and IHD. One hundred two patients were studied for acute neurological toxicity, which was observed in 26 patients (25.5%). The result was statistically significant in age and LOC. Conclusion Active HBOT should be performed to minimize damage to the major organs by identifying the various exposure routes of CO poisoning, risk factors for acute cardiovascular toxicity (intentionality, LOC, combined sedatives, initial COHb, HTN, IHD), and the risk factors for acute neurological toxicity (age, LOC).

BACKGROUND: Caudal block is a popular regional anesthesia in children undergoing infraumbilical surgeries including inguinal hernia repair and orchiopexy. We evaluated the efficacy of eutectic mixture of local anesthetic (EMLA) cream for reducing needle insertion pain during caudal block in pediatric patients. METHODS: Forty-one children between the ages of 13 months and 5 years undergoing infraumbilical surgery were randomized to receive either topical EMLA or placebo cream over the sacral hiatus one hour before caudal block. All children were assessed with the Multidimensional Assessment Pain Scale (MAPS) at the following time points. T0: arrival at the operation room; T1: just before needle insertion; T2: immediately after needle insertion into the sacral hiatus. The need for sevoflurane inhalation due to procedural pain response was also assessed at the same time as MAPS assessment. RESULTS: MAPS scores were significantly lower in the EMLA group compared with the placebo group at T2 (P = 0.001). Moreover, need for sevoflurane inhalation due to procedural pain response was significantly lower in the EMLA group compared with the control group at T2 (P < 0.001). CONCLUSIONS: We suggest that pretreatment with EMLA cream over the sacral hiatus before caudal block has significant advantages in alleviating procedure pain during caudal block in children.
Anesthesia, Caudal ; Anesthesia, Conduction ; Child* ; Hernia, Inguinal ; Humans ; Inhalation ; Needles ; Orchiopexy ; Pediatrics ; Punctures* ; Skin*

PURPOSE: The aim of this study was to investigate the clinical characteristics and causative organisms of meningitis in the Daegu region and seek a useful tool for the early prediction of bacterial meningitis in children. METHODS: We retrospectively reviewed the medical records of 115 pediatric patients diagnosed with bacterial or aseptic meningitis at Yeungnam university hospital in Daegu from March 2012 to July 2013. We evaluated their clinical symptoms, laboratory findings, clinical courses, bacterial meningitis scores and complications. RESULTS: The subjects included 106 with aseptic meningitis and 9 with bacterial meningitis. At the time of visit, fever was the most frequent symptom, followed by headache, vomiting and neck stiffness. In cerebrospinal fluid (CSF) analysis, white blood cell (WBC) count were higher in the bacterial meningitis group (1423.8+/-1980.4 vs. 120.0+/-161.6 mg/dL). Mean CSF protein was 219.4+/-183.6 mg/dL in bacterial meningitis and 42.4+/-27.0 mg/dL in aseptic meningitis (P <0.001). Bacterial meningitis score (BMS) were higher in the group with bacterial meningitis. Abnormal radiological findings were found in 44% of the group with bacterial meningitis. CONCLUSION: Although the clinical features between the groups were similar, the CSF analysis revealed significant differences statistically. Furthermore, BMS could be helpful to predict bacterial meningitis in children. During the outbreak of aseptic meningitis, it might reduce unnecessary hospital admissions and antibiotic treatments.
Cerebrospinal Fluid ; Child ; Daegu ; Fever ; Headache ; Humans ; Leukocytes ; Medical Records ; Meningitis ; Meningitis, Aseptic* ; Meningitis, Bacterial ; Neck ; Retrospective Studies ; Vomiting

No abstract available.

Objectives: This study was conducted to develop a generalizable annotation tool for bilingual complex clinical text annotation, which led to the design and development of a clinical text annotation tool, ANNO. Methods: We designed ANNO to enable human annotators to support the annotation of information in clinical documents efficiently and accurately. First, annotations for different classes (word or phrase types) can be tagged according to the type of word using the dictionary function. In addition, it is possible to evaluate and reconcile differences by comparing annotation results between human annotators. Moreover, if the regular expression set for each class is updated during annotation, it is automatically reflected in the new document. The regular expression set created by human annotators is designed such that a word tagged once is automatically labeled in new documents. Results: Because ANNO is a Docker-based web application, users can use it freely without being subjected to dependency issues. Human annotators can share their annotation markups as regular expression sets with a dictionary structure, and they can cross-check their annotated corpora with each other. The dictionary-based regular expression sharing function, cross-check function for each annotator, and standardized input (Microsoft Excel) and output (extensible markup language [XML]) formats are the main features of ANNO. Conclusions With the growing need for massively annotated clinical data to support the development of machine learning models, we expect ANNO to be helpful to many researchers.