Machine Learning Model for Classifying the Results of Fetal Cardiotocography Conducted in High-Risk Pregnancies

Purpose@#Fetal well-being is usually assessed via fetal heart rate (FHR) monitoring during the antepartum period. However, the interpretation of FHR is a complex and subjective process with low reliability. This study developed a machine learning model that can classify fetal cardiotocography results as normal or abnormal. @*Materials and Methods@#In total, 17492 fetal cardiotocography results were obtained from Ajou University Hospital and 100 fetal cardiotocography results from Czech Technical University and University Hospital in Brno. Board-certified physicians then reviewed the fetal cardiotocography results and labeled 1456 of them as gold-standard; these results were used to train and validate the model. The remaining results were used to validate the clinical effectiveness of the model with the actual outcome. @*Results@#In a test dataset, our model achieved an area under the receiver operating characteristic curve (AUROC) of 0.89 and area under the precision-recall curve (AUPRC) of 0.73 in an internal validation dataset. An average AUROC of 0.73 and average AUPRC of 0.40 were achieved in the external validation dataset. Fetus abnormality score, as calculated from the continuous fetal cardiotocography results, was significantly associated with actual clinical outcomes [intrauterine growth restriction: odds ratio, 3.626 (p=0.031); Apgar score 1 min: odds ratio, 9.523 (p<0.001), Apgar score 5 min: odds ratio, 11.49 (p=0.001), and fetal distress: odds ratio, 23.09 (p<0.001)]. @*Conclusion@#The machine learning model developed in this study showed precision in classifying FHR signals. This suggests that the model can be applied to medical devices as a screening tool for monitoring fetal status.

Development of a Risk Score for QT Prolongation in the Intensive Care Unit Using Time-Series Electrocardiogram Data and Electronic Medical Records / 대한의료정보학회지

Objectives@#Drug-induced QT prolongation can lead to life-threatening arrhythmia. In the intensive care unit (ICU), various drugs are administered concurrently, which can increase the risk of QT prolongation. However, no well-validated method to evaluate the risk of QT prolongation in real-world clinical practice has been established. We developed a risk scoring model to continuously evaluate the quantitative risk of QT prolongation in real-world clinical practice in the ICU. @*Methods@#Continuous electrocardiogram (ECG) signals measured by patient monitoring devices and Electronic Medical Records data were collected for ICU patients. QT and RR intervals were measured from raw ECG data, and a corrected QT interval (QTc) was calculated by Bazett’s formula. A case-crossover study design was adopted. A case was defined as an occurrence of QT prolongation ≥12 hours after any previous QT prolongation. The patients served as their own controls. Conditional logistic regression was conducted to analyze prescription, surgical history, and laboratory test data. Based on the regression analysis, a QTc prolongation risk scoring model was established. @*Results@#In total, 811 ICU patients who experienced QT prolongation were included in this study. Prescription information for 13 drugs was included in the risk scoring model. In the validation dataset, the high-risk group showed a higher rate of QT prolongation than the low-and low moderate-risk groups. @*Conclusions@#Our proposed model may facilitate risk stratification for QT prolongation during ICU care as well as the selection of appropriate drugs to prevent QT prolongation.

Development of a Risk Score for QT Prolongation in the Intensive Care Unit Using Time-Series Electrocardiogram Data and Electronic Medical Records / 대한의료정보학회지

Objectives@#Drug-induced QT prolongation can lead to life-threatening arrhythmia. In the intensive care unit (ICU), various drugs are administered concurrently, which can increase the risk of QT prolongation. However, no well-validated method to evaluate the risk of QT prolongation in real-world clinical practice has been established. We developed a risk scoring model to continuously evaluate the quantitative risk of QT prolongation in real-world clinical practice in the ICU. @*Methods@#Continuous electrocardiogram (ECG) signals measured by patient monitoring devices and Electronic Medical Records data were collected for ICU patients. QT and RR intervals were measured from raw ECG data, and a corrected QT interval (QTc) was calculated by Bazett’s formula. A case-crossover study design was adopted. A case was defined as an occurrence of QT prolongation ≥12 hours after any previous QT prolongation. The patients served as their own controls. Conditional logistic regression was conducted to analyze prescription, surgical history, and laboratory test data. Based on the regression analysis, a QTc prolongation risk scoring model was established. @*Results@#In total, 811 ICU patients who experienced QT prolongation were included in this study. Prescription information for 13 drugs was included in the risk scoring model. In the validation dataset, the high-risk group showed a higher rate of QT prolongation than the low-and low moderate-risk groups. @*Conclusions@#Our proposed model may facilitate risk stratification for QT prolongation during ICU care as well as the selection of appropriate drugs to prevent QT prolongation.

Discovering hidden information in biosignals from patients using artificial intelligence / 대한마취과학회지

Biosignals such as electrocardiogram or photoplethysmogram are widely used for determining and monitoring the medical condition of patients. It was recently discovered that more information could be gathered from biosignals by applying artificial intelligence (AI). At present, one of the most impactful advancements in AI is deep learning. Deep learning-based models can extract important features from raw data without feature engineering by humans, provided the amount of data is sufficient. This AI-enabled feature presents opportunities to obtain latent information that may be used as a digital biomarker for detecting or predicting a clinical outcome or event without further invasive evaluation. However, the black box model of deep learning is difficult to understand for clinicians familiar with a conventional method of analysis of biosignals. A basic knowledge of AI and machine learning is required for the clinicians to properly interpret the extracted information and to adopt it in clinical practice. This review covers the basics of AI and machine learning, and the feasibility of their application to real-life situations by clinicians in the near future.

A study on the characteristics of Maslach Burnout Inventory-General Survey (MBI-GS) of workers in one electronics company

BACKGROUND: This study investigated characteristics according to demographic, occupational factors of Maslach Burnout Inventory-General Survey (MBI-GS) and related scales to MBI-GS. METHODS: The subjects of the study were 3,331 workers in 3 different workplaces of one electronics company. They filled in demographic factors surveys, occupational factors surveys, MBI-GS, Korean Occupational Stress Scale-Short Form (KOSS-SF), Patient Health Questionnaire-9 (PHQ-9), and World Health Organization Quality Of Life-Abbreviated version (WHOQOL-BREF). The correlations between sub-scales of MBI-GS and KOSS-SF, PHQ-9, WHOQOL-BREF were analyzed respectively. And KOSS-SF, PHQ-9, and WHOQOL-BREF were categorized; mean scores of sub-scales of MBI-GS were compared; and the quartiles of sub-scales of MBI-GS were presented. RESULTS: A comparison of mean scores of MBI-GS according to demographic and occupational factors showed a significant difference according to age, problem drinking behavior, working time, and working duration in exhaustion regardless of sex. In professional efficacy, a significant difference was observed in age, marital status, working type, and working duration. And as a result of correlation analysis, the correlation coefficient between exhaustion and PHQ-9 was the highest regardless of sex. In addition, regardless of sex, exhaustion and cynicism scores tended to increase and professional efficacy score tended to decrease as the work stress level rose. Same tendency is shown in case of the more severe the symptom of depression and the lower quality of life. When the quartile for sub-scales' score of MBI-GS were investigated, the burnout was more pronounced in female than in male. CONCLUSIONS: Many demographic and occupational factors affect burnout were identified in one electronics company, and we investigated which sub-scales of MBI-GS were affected. Through this study, burnout characteristics were identified in a few population group of Korea, and the results are expected to be useful for burnout risk group identification, counseling, etc.

A Case of Growing Endobronchial Glandular Papilloma / 결핵및호흡기질환

Pulmonary papillomas are rare benign epithelial neoplasms arising in bronchial surface epithelium. They are categorized by a variety of cell types including squamous, glandular, and mixed squamous and glandular type. Among them, glandular papilloma is extremely rare and has not been reported in Korea. The patient was a 52 year-old man presenting with a 4-months' history of recurrent hemoptysis. Bronchofiberoscopy revealed a whitish, glistening, and polypoid mass lesion at the proximal bronchus in the basal segment of the left lower lung. Bronchoscopic biopsy was performed; papillary fronds lined by ciliated or nonciliated pseudostratified columnar epithelium were noted on histologic findings. We present the first case of glandular papilloma in Korea. Two years later, the patient visited our hospital again due to hemoptysis. On follow-up bronchoscopy, a mass that had been found previously showed an increase in size.

The Evaluation of Gallbladder Function by Tc-99m-DISIDA Scintigraphy in Diabetic Patients / 대한내과학회지

OBJECTIVES: Diabetic autonomic neuropathy is a common complication of long standing diabetes mellitus and is well known to induce the motor dysfunction of cardiovascular system, genitourinary system and diges tive system. Although many studies have done to eval uate the diabetic autonomic neuropathy, gallbladder motor function and biliary dynamic study to evaluate the change of gallbladder function in diabetic patients is relatively rare. This study was performed to measure the gall bladder ejection fraction using Tc- 99m-DISIDA with fatty meal in order to evaluate the gallbladder motor func tion in diabetic patients and to examine the usefulness of it in analyzing diabetic autonomic neuropathy. METHODS: 51 diabetic patients(males 31, females 18, mean age 57yr(39-77yr)) and 18 control subjects(males 14, females 4, mean aged 47yr(31-70yr)) without gall stone and impaired liver function were enrolled in our study. Also the diabetic patients were categorized by age, disease duration, body weight and diabetic complications such as retinopathy, peripheral neuropathy and cardiovas cular autonomic neuropathy accompanying with or not. RESULTS: 1) Median value and interquartile range of gallbladder ejection fraction(%) were 66%(48-79%) in diabetic pa tients group and 75%(64-80%) in control subjects. There was no statistically significant difference between the two groups, but the mean value of diabetic patients was slightly lower than that of control subjects. 2) There was no significant difference between the two groups in mean value of gallbladder ejection fraction in every age group(P>0.05). 3) Median value of gallbladder ejection fraction in diabetic groups with less than 10 years of duration (both under 5 years and 5 to 10 years groups) was similar to that of control subjects. However in patients whose diabetic conditions last more than 10 years, the median range of gallbladder ejection fraction was significantly lower than that of control subjects(p0.05). Also seven diabetic patients whose gallbladder ejection fraction was reduced under 35% have had at least two diabetic complications. CONCLUSION: We observed that gallbladder ejection fraction of diabetic patients was reduced compared with that of control subjects. This is due to the reduced gallbladder muscle contractility resulting from diabetic autonomic dysfunction. These results suggest that the assessment of gallbladder ejection fraction using 99m- Tc-DISIDA would be useful to diagnose diabetic auto nomic neropathy.