Machine Learning-Based Prediction of Abdominal Subcutaneous Fat Thickness During Pregnancy.

Objective: Current evidence regarding the safety of abdominal subcutaneous injections in pregnant women is limited. In this study, we developed a predictive model for abdominal skin-subcutaneous fat thickness (S-ScFT) by gestational periods (GP) in pregnant women. Methods: A total of 354 cases were measured for S-ScFT. Three machine learning algorithms, namely deep learning, random forest, and support vector machine, were used for S-ScFT predictive modeling and factor analysis for each abdominal site. Data analysis was performed using SPSS and RapidMiner softwares. Results: The deep learning algorithm best predicted the abdominal S-ScFT. The common important variables in all three algorithms for the prediction of abdominal S-ScFT were menarcheal age, prepregnancy weight, prepregnancy body mass index (categorized), large fetus for gestational age, and alcohol consumption. Conclusion: Predicting the safety of subcutaneous injections during pregnancy could be beneficial for managing gestational diabetes mellitus in pregnant women.

Abdominal skin subcutaneous fat thickness over the gestational period in Korean pregnant women: a descriptive observational study.

Purpose: Although insulin is usually injected into the abdominal subcutaneous fat, in pregnancy women tend to avoid abdominal injections due to concern about fetal damage. Prior studies have been limited to only measuring skin-subcutaneous fat thickness (S-ScFT) at one site at specific pregnancy points. This study aimed to measure S-ScFT across several abdominal sites and over the gestational period in Korean pregnant women. This can identify which site would be relatively safe for subcutaneous injection during pregnancy. Methods: Healthy women over 24 weeks of pregnancy in Korea were invited to voluntarily participate in this descriptive study. For the 142 women, S-ScFT of 12 sites in the abdomen were measured by ultrasound, several times over the pregnancy. Each incidence was treated as a case and a total of 262 cases were analyzed. Results: The mean S-ScFT during pregnancy was 1.14±0.47 cm (1.25±0.54 cm at 24+0-27+6 weeks; 1.17±0.48 cm at 28+0-31+6 weeks; 1.09+0.40 cm at 32+0-35+6 weeks; and 1.06±0.47 cm at 36+0-40 weeks of pregnancy). Most S-ScFT were thicker than 10 mm. But S-ScFTs in the lateral abdomen and some sites were suboptimal (<6 mm), especially in the pre-pregnancy underweight body mass index group, who had a high rate of suboptimal thickness (27.1% overall and 33.9% in the lateral side). Conclusion: The whole abdomen seems to be appropriate for subcutaneous injection in most Korean women during pregnancy, with a 4 to 5-mm short needle. However, for the lateral abdomen, making the skin fold might be needed for fetal safety.

The appropriateness of the length of insulin needles based on determination of skin and subcutaneous fat thickness in the abdomen and upper arm in patients with type 2 diabetes.

BACKGROUND: Longer needle and complicated insulin injection technique such as injecting at a 45-degree angle and making skinfolds may decrease patient compliance to insulin injection therapy. In this light, shorter insulin needles have been recently developed. However, it is necessary to ascertain that such shorter needles are appropriate for Korean patients with diabetes as well. METHODS: First, the diverse demographic and diabetic features of 156 Korean adults with diabetes were collected by a questionnaire and a device unit of body fat measurement. The skin and subcutaneous fat thicknesses of each subject were measured by Ultrasound device with a 7- to 12-MHz probe. Data were analyzed using analysis of variance and multiple linear regression. RESULTS: The mean skin thickness was 2.29±0.37 mm in the abdomen and 2.00±0.34 mm in the upper arms, and the mean subcutaneous fat thickness was to 10.15±6.54 mm in the abdomen and 5.50±2.68 mm in the upper arms. Our analysis showed that the factors affecting the skin thickness of the abdomen and upper arms were gender and body mass index (BMI), whereas the factors influencing the subcutaneous fat thickness in the abdomen were gender and BMI, and the factors influencing the subcutaneous fat thickness in the upper arms were gender, BMI, and age. Insulin fluids may not appear to be intradermally injected into the abdomen and upper arms at any needle lengths. The risk of intramuscular injection is likely to increase with longer insulin needles and lower BMI. CONCLUSION: It is recommended to fully inform the patients about the lengths of needles for insulin injections. As for the recommended needle length, the findings of this study indicate that needles as short as 4 mm are sufficient to deliver insulin for Korean patients with diabetes.

[A comparison of the rates of hemolysis and repeated blood sampling using syringe needles versus vacuum tube needles in the emergency department].

PURPOSE: This study was done to compare the rates of hemolysis and repeated sampling in blood samples obtained by a syringe needle versus a vacuum tube needle. METHODS: A randomized, prospective study was used to evaluate the differences between the two blood sampling methods. The study group consisted of patients seen in the emergency department (ED) for blood sampling to determine electrolyte level. ED patients were randomly assigned to either the syringe group or the vacuum tube group. All blood samples were collected by experienced ED nurses and hemolysis was determined by experienced laboratory technologists. Data were analyzed using Fisher's exact test and binary logistic regression. RESULTS: One hundred forty-five valid samples were collected (74 in the syringe group versus 71 in the vacuum tube group). 5 of 74 (6.8%) blood samples in the syringe group and 8 of 71 (11.3%) in the vacuum tube group hemolyzed. Repeated blood sampling occurred for 2 of 74 (2.7%) and 3 of 71 (4.2%) in each group respectively. There were no significant differences in rates of hemolysis and repeated sampling between two groups (B=1.97, p=.204; B=2.36, p=.345). CONCLUSION: Venipuncture with syringe needles can be recommended for ED nurses to obtain blood samples.

Effect of Music Therapy as Intervention on Peripheral Neuropathic Pain and Anxiety of Gynecologic Cancer Patients Undergoing Paclitaxel Chemotherapy.

PURPOSE: This study was to investigate the effect of music therapy as intervention on peripheral neuropathic pain and anxiety of gynecologic cancer patients who were undergoing paclitaxel chemotherapy. METHODS: Hospitalized 62 patients were assigned to an experimental group (n=30) and a control group (n=33) in this quasi-experimental study. The experimental group participated in music therapy that includes listening, singing and song writing during 1 hour. The peripheral neuropathic pain, anxiety and depression were examined as pre-intervention evaluation by using pain scale, anxiety scale (20 questions) and depression scale (20 questions) in both groups. There were no further treatments for the control group while the experimental group involved in music therapy. The peripheral neuropathic pain and anxiety were evaluated in both groups as post-intervention evaluation. RESULTS: Outcomes were verified through hypothesis testing. The level of peripheral neuropathic pain and anxiety in the experimental group was decreased, compared to the control group. CONCLUSION: According to the study, music therapy is a beneficial intervention that reduces peripheral neuropathic pain and anxiety in gynecologic cancer patients. These findings are encouraging and suggest that music therapy can be applied as an effective intervention for minimizing chemotherapy related symptoms.

[Effects of a palliative care program based on home care nursing].

PURPOSE: This study was done to develop and test a palliative care program based on home care nursing. METHODS: A quasi-experimental design was employed. Changes in the variables were evaluated to test effects of the developed program. Participants were patients with terminal cancer and their families receiving home care nursing from six hospitals (experimental group: 24 and control group: 22). Data collection was conducted from February to October, 2006. chi-square test, Fisher's exact test, t-test, Mann-Whitney U test and repeated measures ANOVA were used to analyse the data. RESULTS: Hypothesis 1, the experimental group receiving this program will experience less pain (severe, average, weak pain) than the control group, was supported. Hypothesis 2, the experimental group will have less symptom experience than the control group, was supported. Hypothesis 3, the experimental group will have higher QOL than the control group, was supported and the last hypothesis 4, family burden in the experimental group will be less than the control group, was supported. CONCLUSION: The home care nursing based palliative program developed in this study was found to be an effective program to reduce patient pain and symptom experience, to improve patient QOL and to decrease family burden.