Objective:To explore risk factors for delayed onset of lactogenesis in prenatally overweight women and construct risk prediction models based on machine learning for early identification of high-risk individuals.Methods:Convenience sampling was adopted to select 338 prenatally overweight women who delivered in the Obstetrics Departments of four ClassⅢ Grade A hospitals in Hengyang City from October 2023 to June 2024 for the study. Delivery women were randomly divided into training set and test set in the ratio of 7∶3. The survey was conducted with the General Information Questionnaire, Breastfeeding Self-efficacy Scale Short Form, Edinburgh Postnatal Depression Scale, LATCH Scale and Pittsburgh Sleep Quality Index. One-way analysis and LASSO regression were used to screen predictors using delayed onset of lactogenesis as the outcome variable. Risk prediction models were constructed based on three machine learning algorithms of Logistic regression, support vector, and random forest, respectively. The models were tuned by ten-fold cross-validation to filter out the best models.Results:Delayed onset of lactogenesis occurred in 140 of 338 prenatally overweight women, an incidence of 41.4%. Among the three predictive model performances, the random forest model had the highest area under the receiver operating characteristic curve, accuracy, precision, recall, and F1 value. The importance of each predictor was ranked according to the fandom forest algorithm, and in descending order of importance, they were breastfeeding 1 h after the birth of the newborn, number of previous deliveries, age, feeding mode 3 d postpartum, pregnancy complications, mode of delivery, number of breastfeeding 24 h postpartum, and monthly household income.Conclusions:Risk prediction models for delayed onset of lactogenesis in prenatally overweight women are constructed based on three machine learning algorithms, aiming to help provide a scientific basis for clinical healthcare professionals to take relevant decisions.

Objective:To explore risk factors for delayed onset of lactogenesis in prenatally overweight women and construct risk prediction models based on machine learning for early identification of high-risk individuals.Methods:Convenience sampling was adopted to select 338 prenatally overweight women who delivered in the Obstetrics Departments of four ClassⅢ Grade A hospitals in Hengyang City from October 2023 to June 2024 for the study. Delivery women were randomly divided into training set and test set in the ratio of 7∶3. The survey was conducted with the General Information Questionnaire, Breastfeeding Self-efficacy Scale Short Form, Edinburgh Postnatal Depression Scale, LATCH Scale and Pittsburgh Sleep Quality Index. One-way analysis and LASSO regression were used to screen predictors using delayed onset of lactogenesis as the outcome variable. Risk prediction models were constructed based on three machine learning algorithms of Logistic regression, support vector, and random forest, respectively. The models were tuned by ten-fold cross-validation to filter out the best models.Results:Delayed onset of lactogenesis occurred in 140 of 338 prenatally overweight women, an incidence of 41.4%. Among the three predictive model performances, the random forest model had the highest area under the receiver operating characteristic curve, accuracy, precision, recall, and F1 value. The importance of each predictor was ranked according to the fandom forest algorithm, and in descending order of importance, they were breastfeeding 1 h after the birth of the newborn, number of previous deliveries, age, feeding mode 3 d postpartum, pregnancy complications, mode of delivery, number of breastfeeding 24 h postpartum, and monthly household income.Conclusions:Risk prediction models for delayed onset of lactogenesis in prenatally overweight women are constructed based on three machine learning algorithms, aiming to help provide a scientific basis for clinical healthcare professionals to take relevant decisions.

Objective To study the diagnostic value of serum long chain non coding RNA(lncRNA)CB-SLR,α trypsin H4 heavy chain(ITIH4)in early gastric cancer in the elderly.Methods From 2020 to 2022,a total of 90 elderly patients with early gastric cancer diagnosed and treated in the hospital were selected as the early gastric cancer group,while 45 patients with chronic atrophic gastritis diagnosed and treated in the same period were selected as atrophic gastritis group and 45 healthy people undergoing physical examination in the same period were selected as the healthy control group.The serum levels of lncRNA CBSLR and ITIH4 in each group were detected by fluorescence quantitative PCR and enzyme linked immunosorbent assay.Pearson correlation analysis was performed to determine the correlation between serum lncRNA CBSLR and ITIH4 levels with tumor markers carcinoembryonic antigen(CEA)and carbohydrate antigen(CA)19-9.The levels of serum lncRNA CBSLR and ITIH4 among patients with different clinicopathological characteristics were com-pared.The diagnostic value of serum lncRNA CBSLR and ITIH4 in elderly patients with early gastric cancer was analyzed by receiver operating characteristic curve.Results The serum levels of lncRNA CBSLR,ITIH4,CEA and CA19-9 in the early gastric cancer group were significantly higher than those in the atrophic gastritis group and health control group(all P＜0.05).There was significant positive correlation between serum ln-cRNA CBSLR,ITIH4 and CEA,CA19-9 levels in patients with early gastric cancer(r=0.601-0.751,all P＜0.05).In patients with early gastric cancer,serum IncRNA CBSLR and ITIH4 were related to tumor diame-ter,depth of invasion,differentiation type,and lymph node metastasis(all P＜0.05),but not related to age,gender,tumor location,and gross type(all P＞0.05).The area under the curve of combined detection of ser-um lncRNA CBSLR,ITIH4,CEA and CA19-9(0.912,95％CI:0.858-0.949)for the diagnosis of early gas-tric cancer was higher than that of serum lncRNA CBSLR(0.833,95％CI:0.784-0.879),ITIH4(0.806,95％CI:0.760-0.847),CEA(0.791,95％CI:0.742-0.830),and CA19-9(0.766,95％CI:0.710-0.815)alone(Z=4.482,5.130,5.231,6.117,all P＜0.05).Conclusion The elevated levels of serum lncRNA CB-SLR and ITIH4 in elderly patients with early gastric cancer are associated with adverse clinicopathological characteristics of gastric cancer.The combination of serum lncRNA CBSLR,ITIH4,CEA and CA19-9 has high diagnostic value for elderly patients with early gastric cancer.

Objective:To explore the demand and mode of palliative care for emergency dying patients by analyzing the case data of emergency death and cardiopulmonary resuscitation.Methods:The data of 776 cases of emergency clinical death and cardiopulmonary resuscitation in the Second Affiliated Hospital of Soochow University from 2017 to 2020 were retrospectively analyzed.Results:A total of 687 patients were included with (70.38 ± 16.57) years old, and 49.8% (342/687) of them were 75 years old and above; among them, 36.0% (247/687) patients or their families chose not to give cardiopulmonary resuscitation (DNR) in the last stage of their lives,and 63.2%(156/247) of DNR patients were 75 years old and above. The top four etiology of DNR were cerebral hemorrhage, respiratory failure, multiple organ dysfunction syndrome and out of hospital cardiac and respiratory arrest.After successful cardiopulmonary resuscitation, 37.5% (45/120) of the patients' family members chose to give up treatment again. The median stay time of DNR patients in the emergency room was 738.7 minutes.Conclusions:The patients who choosed DNR were mainly 75 years old and above, with cerebral hemorrhage, respiratory failure, multiple organ failure and cardiac and respiratory arrest. The detention of these patients in the emergency room increases the congestion of the emergency room, and at the same time, they can not get a peaceful palliative care environment. It is suggested that emergency medical staff should strengthen the awareness and improve the ability of palliative care. A relative independent area and corresponding soothing palliative treatment and nursing should be given to the DNR patients.