ABSTRACT
Background/Aims@#Although guidelines exist regarding the evaluation and management of patients with chronic constipation (CC), little is known about real-world clinical practice patterns. This study aimed to evaluate the various practices used to manage CC patients in various clinical settings in South Korea. @*Methods@#A nationwide web-based survey was conducted, randomly selecting gastroenterologists and non-gastroenterologists. The 25-item questionnaire included physicians’ perceptions and practices regarding the available options for diagnosing and managing CC patients in Korea. @*Results@#The study participants comprised 193 physicians (86 gastroenterologists, 44.6%) involved in the clinical management of CC patients. The mean clinical experience was 12 years. Only 21 of 193 respondents (10.9%) used the Rome criteria when diagnosing CC. The Bristol Stool Form Scale was used by 29% of the respondents (56/193), while the digital rectal examination was performed by 11.9% of the respondents (23/193). Laboratory testing and colonoscopies were performed more frequently by gastroenterologists than by non-gastroenterologists (both p=0.001). Physiologic testing was used more frequently by gastroenterologists (p=0.046), phy-sicians at teaching hospitals, and physicians with clinical experience ≤10 years (both p<0.05). There were also significant differences in the preference for laxatives depending on the type of hospital. @*Conclusions@#There were discrepancies in the diagnosis and management of CC patients depending on the clinical setting. The utilization rates of the Bristol Stool Form Scale and digital rectal examination by physicians are low in real-world clinical practice. These results imply the need for better and more practical training of physicians in the assessment and management of CC.
ABSTRACT
Objective@#Numerous studies have identified hemodynamic changes in adults with major depressive disorder (MDD) by using functional near-infrared spectroscopy (fNIRS). However, studies on adolescents with MDD are limited. As adolescence is a stage of rapid brain development, differences may occur depending on age. This study used fNIRS as an objective tool to investigate hemodynamic changes in the frontal lobe according to depression severity and age in adolescents with MDD. @*Methods@#Thirty adolescents (12 aged 12−15 years and 18 aged 16−18 years) were retrospectively investigated. The Children’s Depression Inventory was used as a psychiatric evaluation scale, fNIRS was used as an objective brain function evaluation tool, and the Verbal Fluency Test was performed. @*Results@#During the Verbal Fluency Test, in the younger MDD group, oxygenated-hemoglobin concentration increased in the right dorsolateral prefrontal cortex region as the severity of depression increased. In the older MDD group, the oxygenated-hemoglobin concentration decreased in the right dorsolateral prefrontal cortex region as the severity of depression increased. @*Conclusion@#These results suggest that fNIRS may be an objective tool for identifying age differences among adolescents with MDD. To generalize the results and verify fNIRS as a potential biomarker tool, follow-up studies with a larger sample group should be conducted.
ABSTRACT
Background: The COVID-19 outbreak caused the border closure, martial law declaration, and lockdown to prevent the spread of the disease. These policies caused reduced interaction among people,social isolation, and higher levels of anxiety and depression. Objectives: This study aimed to examine changes in depressive symptoms of residents of the Democratic Republic of Congo (DRC) that may have arisen due to the COVID-19 and lockdown measures and to identify relevant influencing factors. Methods: This cross-sectional study involved 300 residents of the DRC. An online survey tool investigated general and public health characteristics and included the Patient Health Questionnaire-9 for measuring depressive symptoms. The study was conducted from April 730, 2020. Results: The average depression score was low at 2.74±3.33. Factors influencing depression were the number of family members, probability of death due to COVID-19, knowledge of COVID-19, and time at home. The factor that most significantly influenced depression and these variables accounted for 26.9% of the influence of COVID-19 on depression (F= 9.936, p<.001). Conclusion: This study investigated the influence of COVID-19 outbreak on depression in DRC. Levels of depression increased for individuals who were living alone, had low levels of knowledge of COVID-19 and awareness of the disease severity, and spent a long time at home.
Subject(s)
Humans , Male , Female , Anxiety , Signs and Symptoms , Health Knowledge, Attitudes, Practice , Mental Health , Cross-Sectional Studies , Depression , COVID-19 , Democratic Republic of the Congo , DiagnosisABSTRACT
Breast cancer is the most common cancer and a frequent cause of cancer-related deaths among women wordlwide. As therapeutic strategies for breast cancer have limitations, novel chemotherapeutic reagents and treatment strategies are needed. In this study, we investigated the anti-cancer effect of synthetic homoisoflavane derivatives of cremastranone on breast cancer cells. Homoisoflavane derivatives, SH-17059 and SH-19021, reduced cell proliferation through G2/M cell cycle arrest and induced caspase-independent cell death. These compounds increased heme oxygenase-1 (HO-1) and 5-aminolevulinic acid synthase 1 (ALAS1), suggesting downregulation of heme. They also induced reactive oxygen species (ROS) generation and lipid peroxidation. Furthermore, they reduced expression of glutathione peroxidase 4 (GPX4). Therefore, we suggest that the SH-17059 and SH-19021 induced the caspase-independent cell death through the accumulation of iron from heme degradation, and the ferroptosis might be one of the potential candidates for caspase-independent cell death.
ABSTRACT
Background/Aims@#This study aimed to evaluate the characteristics of endoscopic retrograde cholangiopancreatography (ERCP) or endoscopic ultrasonography (EUS)-related adverse events (AEs) that eventually lead to medical disputes or claims on medical professional liability. @*Methods@#Medical disputes for ERCP/EUS-related AEs filed in the Korea Medical Dispute Mediation and Arbitration Agency between April 2012 and August 2020 were evaluated using corresponding medical records. AEs were categorized into three sections: procedure-related, sedation-related, and safety-related AEs. @*Results@#Among a total of 34 cases, procedure-related AEs were 26 (76.5%; 12 duodenal perforations, 7 post-ERCP pancreatitis, 5 bleedings, 2 perforations combined with post-ERCP pancreatitis); sedation-related AEs were 5 (14.7%; 4 cardiac arrests, 1 desaturation), and safety-related AEs were 5 (8.8%; 1 follow-up loss for stent removal, 1 asphyxia, 1 fall). Regarding clinical outcomes, 20 (58.8%) were fatal and eventually succumbed to AEs. For the types of medical institutions, 21 cases (61.8%) occurred at tertiary or academic hospitals, and 13 (38.2%) occurred at community hospitals. @*Conclusions@#The ERCP/EUS-related AEs filed in Korea Medical Dispute Mediation and Arbitration Agency showed distinct features: duodenal perforation was the most frequent AE, and clinical outcomes were fatal, resulting in at least more than permanent physical impairment.
ABSTRACT
Chronic constipation is one of the most common digestive diseases encountered in clinical practice. Constipation manifests as a variety of symptoms, such as infrequent bowel movements, hard stools, feeling of incomplete evacuation, straining at defecation, a sense of anorectal blockage during defecation, and use of digital maneuvers to assist defecation. During the diagnosis of chronic constipation, the Bristol Stool Form Scale, colonoscopy, and a digital rectal examination are useful for objective symptom evaluation and differential diagnosis of secondary constipation. Physiological tests for functional constipation have complementary roles and are recommended for patients who have failed to respond to treatment with available laxatives and those who are strongly suspected of having a defecatory disorder. As new evidence on the diagnosis and management of functional constipation emerged, the need to revise the previous guideline was suggested. Therefore, these evidence-based guidelines have proposed recommendations developed using a systematic review and meta-analysis of the treatment options available for functional constipation. The benefits and cautions of new pharmacological agents (such as lubiprostone and linaclotide) and conventional laxatives have been described through a meta-analysis. The guidelines consist of 34 recommendations, including 3 concerning the definition and epidemiology of functional constipation, 9 regarding diagnoses, and 22 regarding managements. Clinicians (including primary physicians, general health professionals, medical students, residents, and other healthcare professionals) and patients can refer to these guidelines to make informed decisions regarding the management of functional constipation.
ABSTRACT
Background/Aims@#It remains unclear which maintenance treatment modality is most appropriate for mild gastroesophageal reflux disease (GERD).We aimed to compare on-demand treatment with continuous treatment using a proton pump inhibitor (PPI) in the maintenance treatment for patients with non-erosive GERD or mild erosive esophagitis. @*Methods@#Patients whose GERD symptoms improved after 4 weeks of standard dose PPI treatment were prospectively enrolled at 25 hospitals.Subsequently, the enrolled patients were randomly assigned to either an on-demand or a continuous maintenance treatment group, and followed in an 8-week interval for up to 24 weeks. @*Results@#A total of 304 patients were randomized to maintenance treatment (continuous, n = 151 vs on-demand, n = 153). The primary outcome, the overall proportion of unwillingness to continue the assigned maintenance treatment modality, failed to confirm the noninferiority of on-demand treatment (45.9%) compared to continuous treatment (36.1%). Compared with the on-demand group, the GERD symptom and health-related quality of life scores significantly more improved and the overall satisfaction score was significantly higher in the continuous treatment group, particularly at week 8 and week 16 of maintenance treatment. Work impairment scores were not different in the 2 groups, but the prescription cost was less in the on-demand group. Serum gastrin levels significantly elevated in the continuous treatment group, but not in the on-demand group. @*Conclusions@#Continuous treatment seems to be more appropriate for the initial maintenance treatment of non-erosive GERD or mild erosive esophagitis than on-demand treatment. Stepping down to on-demand treatment needs to be considered after a sufficient period of continuous treatment.
ABSTRACT
Objective@#To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software. @*Materials and Methods@#This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1–7 according to acquisition conditions. CT images in groups 2–7 were converted into the target CT sty le (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system. @*Results@#Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2–7 improved after CT conversion (original vs. converted: 0.63vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists’ scores were significantly higher (P < 0.001) and less variable on converted CT. @*Conclusion@#CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD.
ABSTRACT
Crohn’s disease (CD) is a relapsing and progressive condition characterized by diarrhea, abdominal pain, weight loss, and hematochezia that results in serious complications such as perforations, fistulas, and abscesses. Various medications, interventions, and surgical treatments have been used to treat CD. The Korean guidelines for CD management were distributed in 2012 and revised in 2017 by the Inflammatory Bowel Disease (IBD) Research Group of the Korean Association for the Study of Intestinal Diseases. Substantial progress in mucosal immunologic research has elucidated the pathophysiology of IBD, leading to development of biological agents for treatment of CD. The first developed biologic agent, tumor necrosis factor-α agents, were shown to be efficacious in CD, heralding a new era in management of CD. Subsequently, vedolizumab, a monoclonal antibody against integrin α4β7, and ustekinumab, a human monoclonal antibody that inhibits the common p40 subunit of interleukin-12 and interleukin-23, were both approved for clinical use and are efficacious and safe for both induction and maintenance of remission in moderate-to-severe CD patients. Moreover, a recent study showed the non-inferiority of CT-P13, an infliximab biosimilar, compared with infliximab in CD patients. The third Korean guidelines for CD management provide updated information regarding treatment of moderate-to-severe CD patients with biologic agents.
ABSTRACT
Purpose@#Although the taller-than-wide (TTW) sign has been regarded as one of the most specific ultrasound (US) features of thyroid malignancy, uncertainty still exists regarding the US probe’s orientation when evaluating it. This study investigated which US plane would be optimal to identify the TTW sign based on malignancy risk stratification using a registry-based imaging dataset. @*Methods@#A previous study by 17 academic radiologists retrospectively analyzed the US images of 5,601 thyroid nodules (≥1 cm, 1,089 malignant and 4,512 benign) collected in the webbased registry of Thyroid Imaging Network of Korea through the collaboration of 26 centers. The present study assessed the diagnostic performance of the TTW sign itself and fine needle aspiration (FNA) indications via a comparison of four international guidelines, depending on the orientation of the US probe (criterion 1, transverse plane; criterion 2, either transverse or longitudinal plane). @*Results@#Overall, the TTW sign was more frequent in malignant than in benign thyroid nodules (25.3% vs. 4.6%). However, the statistical differences between criteria 1 and 2 were negligible for sensitivity, specificity, and area under the curve (AUC) based on the size effect (all P0.05, respectively). @*Conclusion@#A longitudinal US probe orientation provided little additional diagnostic value over the transverse orientation in detecting the TTW sign of thyroid nodules.
ABSTRACT
Background@#The quality-of-life of patients with irritable bowel syndrome is low; incorrect diagnosis/treatment causes economic burden and inappropriate consumption of medical resources. This survey-based study aimed to analyze the current status of irritable bowel syndrome treatment to examine differences in doctors’ perceptions of the disease, and treatment patterns. @*Methods@#From October 2019 to February 2020, the irritable bowel syndrome and Intestinal Function Research Study Group of the Korean Society of Neurogastroenterology and Motility conducted a survey on doctors working in primary, secondary, and tertiary healthcare institutions. The questionnaire included 37 items and was completed anonymously using the NAVER platform (a web-based platform), e-mails, and written forms. @*Results@#A total of 272 doctors responded; respondents reported using the Rome IV diagnostic criteria (amended in 2016) for diagnosing and treating irritable bowel syndrome.Several differences were noted between the primary, secondary, and tertiary physicians’ groups. The rate of colonoscopy was high in tertiary healthcare institutions. During a colonoscopy, the necessity of random biopsy was higher among physicians who worked at tertiary institutions. ‘The patient did not adhere to the diet’ as a reason for ineffectiveness using low-fermentable oligo-, di-, and mono-saccharides, and polyols diet treatment was higher among physicians in primary/secondary institutions, and ‘There are individual differences in terms of effectiveness’ was higher among physicians in tertiary institutions. In irritable bowel syndrome constipation predominant subtype, the use of serotonin type 3 receptor antagonist (ramosetron) and probiotics was higher in primary/secondary institutions, while serotonin type 4 receptor agonist was used more in tertiary institutions. In irritable bowel syndrome diarrhea predominant subtype, the use of antispasmodics was higher in primary/secondary institutions, while the use of serotonin type 3 receptor antagonist (ramosetron) was higher in tertiary institutions. @*Conclusion@#Notable differences were observed between physicians in primary/secondary and tertiary institiutions regarding the rate of colonoscopy, necessity of random biopsy, the reason for the ineffectiveness of low-fermentable oligo-, di-, and mono-saccharides, and polyols diet, and use of drug therapy in irritable bowel syndrome. In South Korea, irritable bowel syndrome is diagnosed and treated according to the Rome IV diagnostic criteria, revised in 2016.
ABSTRACT
Objective@#This study aimed to compare the accuracy of the visual estimation of blood loss between medical personnel (MP) and non-medical personnel (NP) and to evaluate how it varies with changes in the bleeding volume and environment. @*Methods@#A total of 78 MP and 132 NP were recruited for the study and asked to evaluate nine artificial blood stations and three different volumes of artificial blood (192 mL, 384 mL, 768 mL) in three different environments (floor, diaper, and commode). Statistical analysis and the two-way repeated measures analysis of variance test were used for data analysis. @*Results@#There were significant differences between MP and NP regardless of the actual bleeding loss in all the bleeding environments-floor (F=25.332, P<0.001), diaper (F=9.942, P=0.002), and commode (F=29.588, P<0.001). NP consistently had higher estimates of bleeding volume compared to MP. The interaction effect between group and volume was statistically significant for the floor and diaper-floor (F=9.708, P<0.001) and diaper (F=5.420, P=0.013), but there was no significant difference for the commode (P=0.087). Additionally, the standard deviation of bleeding volume estimates was higher for NP. @*Conclusion@#Visual estimation of blood loss differed significantly between MP and NP, with NP consistently overestimating and demonstrating lower accuracy and reliability compared to MP. These findings underscore the need for caution when relying on estimates by NP as a diagnostic tool for assessing blood loss.
ABSTRACT
Background@#Long-term growth data of very low birth weight (VLBW) infants are currently collected in the Korean Neonatal Network (KNN) and National Health Insurance Service (NHIS) database. However, variance in the number of infants, check-up time, and check-up parameters led to decreased credibility of cumulated data. We aimed to compare the data on serial growth outcomes by major morbidities from birth to 5 years in VLBW infants between the KNN and NHIS databases. @*Methods@#We combined the NHIS and KNN data of VLBW infants born between 2013 and 2015. The check-up times in the NHIS database were at 4–6, 9–12, 18–24, 30–36, 42–48, and 54–60 months of age, whereas in the KNN were at 18–24 months of corrected age and at 36 months of age.Result: Among 8,864 VLBW infants enrolled based on the birth certificates from the Statistics Korea, 6,086 infants (69%) were enrolled in the KNN, and 5,086 infants (57%) participated in the NHIS health check-up. Among 6,068 infants, 3,428 infants (56%) were enrolled at a corrected age of 18–24 months and 2,572 infants (42%) were enrolled at a chronological age of 33–36 months according to the KNN follow-up registry. However, based on the national birth statistics data, the overall follow-up rate of the KNN at 36 months of age was as low as 29%. The NHIS screening rate was lower at first (23%); however, it increased over time to exceed the KNN follow-up rate. Growth failure (weight under 10th percentile) at corrected ages of 18–24 months and 36 months were more common in the NHIS than KNN (42% vs. 20%, 37% vs. 34.5%). Infants with bronchopulmonary dysplasia and periventricular leukomalacia showed similar rates of growth failure at 2 years but varying rates at 3 years between the KNN and NHIS. @*Conclusion@#By integrating the KNN and NHIS data indirectly at continuous time points according to morbidities, we found that there are discontinuities and discrepancies between the two databases among VLBW infants. Establishing an integrated system by patient level linking the KNN and NHIS databases can lead to better understanding and improved neonatal outcomes in VLBW infants in Korea.
ABSTRACT
Purpose@#This descriptive study aimed to identify the incidence and related factors of reintubation after unplanned extubation in the neonatal intensive care unit. @*Methods@#A secondary data analysis was conducted using electronic medical records. All events of unplanned extubation were audited from January 2020 to August 2021. The data were analyzed by chi-square test using IBM SPSS Statistics ver. 24.0 program. @*Results@#Fifty-eight unplanned extubation events were identified for 20 months. The incidence was 2.6 per 100 ventilation days during the study period. After unplanned extubation, 35 neonates (60.3%) were immediately reintubated. There was a statistically significant difference between the gestational age (p=0.018) and postconceptional age at unplanned extubation (p=0.044) and the total intubation period (p=0.003) between the reintubation and nonreintubation groups. @*Conclusion@#These findings indicate that the incidence of unplanned extubation was significantly higher than that of an adult in South Korea. According to this study, targeting interventions are required to prevent unplanned extubation and ensure patient safety.
ABSTRACT
Purpose@#This study investigates the relationship between sleep duration, sleep quality, time use, and dietary quality of adolescents. @*Methods@#A cross-sectional study was conducted, enrolling 423 high school students (112 male and 311 female students) in Chungnam using a questionnaire comprising general characteristics, sleep status, use of time, and Nutrition Quotient for Korean Adolescents (NQ-A). @*Results@#On weekdays, male students reported getting 6.6 hours of sleep, which was significantly higher than the 5.8 hours reported by female students. The sleep quality score between male and female students was not significantly different on weekdays and weekends.Comparing the students categorized as getting 6 hours of sleep duration on weekdays and 8 hours on weekends, a significantly higher total NQ-A score was obtained for the long sleep duration group of female students on weekdays. In male students who reported increased screen time on weekdays and study time on weekends, there was a greater frequency of short sleep duration. Our data also revealed that the longer the sleep duration higher the NQ-A score. In addition, higher NQ-A scores were determined with shorter screen time and more prolonged exercise time. @*Conclusion@#Our results suggest that intense study time and excessive use of smartphones have a negative effect on sleep in high school students. In addition, poor sleep quality and lack of sleep are likely to affect eating habits and nutritional status. Therefore, there is a need to provide nutritional education to adolescents imparting knowledge that associates desirable sleep habits and the correct use of time.
ABSTRACT
A 44-year-old male with a huge left pleural mass was admitted due to chest discomfort. Chest computed tomography showed a large pleural mass with punctate calcification and serpentine-shaped enhancement in the left pleural space. Magnetic resonance imaging showed markedly high signal intensity with septa on fat-suppressed T2-weighted imaging (WI) and gradual peripheral delayed enhancement on dynamic-enhancing T1-WI. With hemangioma as the suspected diagnosis, the entire mass was surgically removed carefully and the final histopathological diagnosis was confirmed to be a cavernous hemangioma. Cavernous hemangioma of the pleural space is a rare benign vascular tumor. Precise radiologic diagnosis is important before the surgical operation of hemangiomas because of risk of massive hemorrhage requiring meticulous bleeding control.
ABSTRACT
Gastroesophageal reflux disease (GERD) is a condition in which gastric contents regurgitate into the esophagus or beyond, resulting in either troublesome symptoms or complications. GERD is heterogeneous in terms of varied manifestations, test findings, and treatment responsiveness. GERD diagnosis can be established with symptomatology, pathology, or physiology. Recently the Lyon consensus defined the “proven GERD” with concrete evidence for reflux, including advanced grade erosive esophagitis (Los Angeles classification grades C and or D esophagitis), long-segment Barrett’s mucosa or peptic strictures on endoscopy or distal esophageal acid exposure time > 6% on 24-hour ambulatory pH-impedance monitoring. However, some Asian researchers have different opinions on whether the same standards should be applied to the Asian population. The prevalence of GERD is increasing in Asia. The present evidence-based guidelines were developed using a systematic review and meta-analysis approach. In GERD with typical symptoms, a proton pump inhibitor test can be recommended as a sensitive, cost-effective, and practical test for GERD diagnosis. Based on a meta-analysis of 19 estimated acid-exposure time values in Asians, the reference range upper limit for esophageal acid exposure time was 3.2% (95% confidence interval 2.7-3.9%) in the Asian countries. Esophageal manometry and novel impedance measurements, including mucosal impedance and a post-reflux swallow-induced peristaltic wave, are promising in discrimination of GERD among different reflux phenotypes, thus increasing its diagnostic yield. We also propose a long-term strategy of evidence-based GERD treatment with proton pump inhibitors and other drugs.
ABSTRACT
The positive rate of Clonorchis sinensis is the highest among intestinal parasites in the Republic of Korea (Korea). More than 1.2 million people were at risk of C. sinensis infection in Korea in 2012. An intensive control program is being implemented for residents of the 5 major river basins to reduce helminthic infections, including C. sinensis infection. This study evaluated the continuous intensive control program for parasitic diseases including clonorchiasis in areas near the 5 major river basins in Korea over the past 10 years (2011-2020). A total of 335,020 fecal samples (one sample per resident) prepared by the modified sedimentation technic were microscopically examined. Those who expelled helminth eggs were treated with anthelmintics through local health centers and re-examined 3 months later. The overall positive rate of helminths egg was 7.1%. The annual positive rates were dramatically decreased from 14.4% (2011) to 5.9% (2020). The egg positive rate was highest in C. sinensis (5.3%), followed by heterophyid flukes (1.5%) and Trichuris trichiura (0.2%). The prevalence of C. sinensis was significantly higher in males (7.6%) than in females (3.7%), and the highest in the 50–59 years (7.0%) age group. Our results are beneficial to establish prevention and control policies against helminthiases including clonorchiasis in endemic areas in this country.
ABSTRACT
Purpose@#The aims of the study were to develop and evaluate a machine learning model with which to predict postnatal growth failure (PGF) among very low birth weight (VLBW) infants. @*Materials and Methods@#Of 10425 VLBW infants registered in the Korean Neonatal Network between 2013 and 2017, 7954 infants were included. PGF was defined as a decrease in Z score >1.28 at discharge, compared to that at birth. Six metrics [area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity, specificity, and F1 score] were obtained at five time points (at birth, 7 days, 14 days, 28 days after birth, and at discharge). Machine learning models were built using four different techniques [extreme gradient boosting (XGB), random forest, support vector machine, and convolutional neural network] to compare against the conventional multiple logistic regression (MLR) model. @*Results@#The XGB algorithm showed the best performance with all six metrics across the board. When compared with MLR, XGB showed a significantly higher AUROC (p=0.03) for Day 7, which was the primary performance metric. Using optimal cut-off points, for Day 7, XGB still showed better performances in terms of AUROC (0.74), accuracy (0.68), and F1 score (0.67). AUROC values seemed to increase slightly from birth to 7 days after birth with significance, almost reaching a plateau after 7 days after birth. @*Conclusion@#We have shown the possibility of predicting PGF through machine learning algorithms, especially XGB. Such models may help neonatologists in the early diagnosis of high-risk infants for PGF for early intervention.
ABSTRACT
Objective@#To retrospectively review the characteristics of preschool children with speech and language disorders to determine their clinical features and compares the average degrees of language delay based on hospital visit purposes, language developmental delay causes, and maternal language. @*Methods@#One thousand one hundred two children (832 males, 270 females) with the chief complaint of language or speech problems who underwent language assessment for the first time were included. Their medical records, including demographic data, language environments, and family history of language problems and other developmental problems, were collected. Furthermore, the results of language and developmental assessments and hearing tests were collected. @*Results@#Among the children enrolled in this study, 24% had parental problems and 9% were nurtured by their grandparents. The average degree of language delay did not differ regarding purposes of hospital visits. The average degree of language delay was greatest in children with autism spectrum disorders and least in children with mixed receptive–expressive language disorders. In children with mothers who do not speak Korean as their native language, social quotients in the social maturity scale were less than 70. @*Conclusion@#Language environment is an essential factor that may cause speech and language disorders. Moreover, maternal language seems to affect the social quotient of the social maturity scale.