Development and evaluation of a nomogram for adverse outcomes of preeclampsia in Chinese pregnant women.

OBJECTIVE: Preeclampsia, the main cause of maternal and perinatal deaths, is associated with several maternal complications and adverse perinatal outcomes. Some prediction models are uesd to evaluate adverse pregnancy outcomes. However, some of the current prediction models are mainly carried out in developed countries, and many problems are still exist. We, thus, developed and validated a nomogram to predict the risk of adverse pregnancy outcomes of preeclampsia in Chinese pregnant women. METHODS: The clinical data of 720 pregnant women with preeclampsia in seven medical institutions in Chongqing from January 1, 2010, to December 31, 2020, were analyzed retrospectively. The patients were divided into two groups: 180 cases (25%) with adverse outcomes and 540 cases (75%) without adverse outcomes. The indicators were identified via univariate analysis. Logistic regression analysis was used to establish the prediction model, which was displayed by a nomogram. The performance of the nomogram was evaluated in terms of the area under the receiver operating characteristic (ROC) curve, calibration, and clinical utility. RESULTS: Univariate analysis showed that 24 indicators were significantly different (P < 0.05). Logistic regression analysis showed that gestational age, 24 h urine protein qualitative, and TT were significantly different (P < 0.05). The area under the ROC curve was 0.781 (95% CI 0.737-0.825) in training set and 0.777 (95% CI 0.689-0.865) in test set. The calibration curve of the nomogram showed good agreement between prediction and observation. The analysis of the clinical decision curve showed that the nomogram is of practical significance. CONCLUSION: Our study identified gestational age, 24 h urine protein qualitative, and TT as risk factors for adverse outcomes of preeclampsia in pregnant women, and constructed a nomogram that can easily predict and evaluate the risk of adverse pregnancy outcomes in women with preeclampsia.

Developing a Quality Evaluation Index System for E-Consultation Doctor-Patient Communication Using the Delphi Method.

Background: E-consultation medical services have become popular globally, which offers patients more options, regardless of time or location. However, research indicates a prevalent issue with the communication quality in e-consultations, leading to sub-optimal patient experiences. Objective: This study aims to design an evaluation system for e-consultation quality. The developed scale guides operators in improving services and users in assessing their experience. It aids in selecting e-consultation services, saving costs, and assisting doctors in making informed decisions. Methods: This study combines existing scales, literature analysis, and expert consultation to form preliminary evaluation indicators. Fourteen experts were invited using stratified purposive sampling. Two rounds of Delphi method were conducted to exclude indicators that did not meet basic conditions. The final evaluation system was determined through expert discussions and revisions. The Analytic Hierarchy Process (AHP) quantified indicator weights. Results: Both rounds of the questionnaire saw compelling response rates of 100% (14 out of 14) and 92.86% (13 out of 14), respectively. Meanwhile, the Expert Authority Coefficient (Cr) was recorded at 0.89 and 0.88, respectively, while the Kendall Consistency Coefficient (Kendall W) for all level indicators fluctuated between 0.133 and 0.37 (P<0.05). The ultimate indicator system formulated includes three primary indicators, ten secondary indicators, and thirty-two tertiary indicators. The highest to lowest weighted first-level indicators were 'Joint Decision-Making between Doctors and Patients' (0.6232), 'Patient Responsiveness' (0.2395), and "Interpersonal Relationship between Doctors and Patients" (0.1373). Weights for the second-level and third-level indicators were also determined. Conclusion: A scientific scale for e-consultation quality evaluation has been created, which effectively captures the essence of online medical communication and patient experiences. It enriches the theoretical framework for evaluating e-consultation quality, broadens perspectives in Internet medicine, provides practical guidance for network medical service managers and users and the development of the "Internet + medical health" service model.

Textual Features and Risk Preference Effects on Mental Health Education Among Teenager Students in Chongqing, China.

Background: Mental health is a public health problem of great concern. Previous studies show that textual features and individual psychological characteristics can influence the effect of receiving information. Purpose: This study explores whether textual features influence the persuasiveness of teenager students' mental health education while considering the influence of risk preference. Methods: From November to December 2021, a cross-sectional study was conducted among 1,869 teenager students in grade 7-12 in Chongqing, China. Wilcoxon signed-rank test, multiple logistic regression, and subgroup analysis were used to analyze the data. Results: Among the four textual features mentioned in this study, a significant difference was reported in the persuasive effects of information with and without numerical features (p < 0.001), and such information tended to include digital features. The result for the symbolic features (p < 0.001) was consistent with the numerical features. The persuasive effects of positive and negative emotional information significantly differed (p < 0.001), with the former showing a better performance. No significant differences were observed between the persuasive effects of information with and without emotional conflicts (p > 0.05). Combined with those from the risk preference analysis, results showed that the regulatory effect of risk preference was only reflected in emotional conflicts. Students who prefer having no emotional conflict in the text showed the characteristics of risk avoidance, or lower grades, or rural or school accommodation. Most teenager students are also risk averse, especially females (or = 2.223, 95%CI:1.755-2.815) and juniors (or = 1.533, 95%CI: 1.198-1.963). Conclusion: The numbers, symbols, and positive emotions in the text generate an active effect on teenager students receiving mental health education. Students avoiding risk are inclined to read texts without emotional conflicts. The probability of male choosing texts with positive emotional polarity is 33.5% lower than that of female. Female students and those from lower grades also demonstrate a higher inclination to risk avoidance compared with their male and higher grade counterparts. Therefore, educational materials with different text characteristics should be developed for teenager students with varying characteristics.

A Machine Learning Model to Predict Intravenous Immunoglobulin-Resistant Kawasaki Disease Patients: A Retrospective Study Based on the Chongqing Population.

Objective: We explored the risk factors for intravenous immunoglobulin (IVIG) resistance in children with Kawasaki disease (KD) and constructed a prediction model based on machine learning algorithms. Methods: A retrospective study including 1,398 KD patients hospitalized in 7 affiliated hospitals of Chongqing Medical University from January 2015 to August 2020 was conducted. All patients were divided into IVIG-responsive and IVIG-resistant groups, which were randomly divided into training and validation sets. The independent risk factors were determined using logistic regression analysis. Logistic regression nomograms, support vector machine (SVM), XGBoost and LightGBM prediction models were constructed and compared with the previous models. Results: In total, 1,240 out of 1,398 patients were IVIG responders, while 158 were resistant to IVIG. According to the results of logistic regression analysis of the training set, four independent risk factors were identified, including total bilirubin (TBIL) (OR = 1.115, 95% CI 1.067-1.165), procalcitonin (PCT) (OR = 1.511, 95% CI 1.270-1.798), alanine aminotransferase (ALT) (OR = 1.013, 95% CI 1.008-1.018) and platelet count (PLT) (OR = 0.998, 95% CI 0.996-1). Logistic regression nomogram, SVM, XGBoost, and LightGBM prediction models were constructed based on the above independent risk factors. The sensitivity was 0.617, 0.681, 0.638, and 0.702, the specificity was 0.712, 0.841, 0.967, and 0.903, and the area under curve (AUC) was 0.731, 0.814, 0.804, and 0.874, respectively. Among the prediction models, the LightGBM model displayed the best ability for comprehensive prediction, with an AUC of 0.874, which surpassed the previous classic models of Egami (AUC = 0.581), Kobayashi (AUC = 0.524), Sano (AUC = 0.519), Fu (AUC = 0.578), and Formosa (AUC = 0.575). Conclusion: The machine learning LightGBM prediction model for IVIG-resistant KD patients was superior to previous models. Our findings may help to accomplish early identification of the risk of IVIG resistance and improve their outcomes.

Application of Machine Learning for the Prediction of Etiological Types of Classic Fever of Unknown Origin.

Background: The etiology of fever of unknown origin (FUO) is complex and remains a major challenge for clinicians. This study aims to investigate the distribution of the etiology of classic FUO and the differences in clinical indicators in patients with different etiologies of classic FUO and to establish a machine learning (ML) model based on clinical data. Methods: The clinical data and final diagnosis results of 527 patients with classic FUO admitted to 7 medical institutions in Chongqing from January 2012 to August 2021 and who met the classic FUO diagnostic criteria were collected. Three hundred seventy-three patients with final diagnosis were divided into 4 groups according to 4 different etiological types of classical FUO, and statistical analysis was carried out to screen out the indicators with statistical differences under different etiological types. On the basis of these indicators, five kinds of ML models, i.e., random forest (RF), support vector machine (SVM), Light Gradient Boosting Machine (LightGBM), artificial neural network (ANN), and naive Bayes (NB) models, were used to evaluate all datasets using 5-fold cross-validation, and the performance of the models were evaluated using micro-F1 scores. Results: The 373 patients were divided into the infectious disease group (n = 277), non-infectious inflammatory disease group (n = 51), neoplastic disease group (n = 31), and other diseases group (n = 14) according to 4 different etiological types. Another 154 patients were classified as undetermined group because the cause of fever was still unclear at discharge. There were significant differences in gender, age, and 18 other indicators among the four groups of patients with classic FUO with different etiological types (P < 0.05). The micro-F1 score for LightGBM was 75.8%, which was higher than that for the other four ML models, and the LightGBM prediction model had the best performance. Conclusions: Infectious diseases are still the main etiological type of classic FUO. Based on 18 statistically significant clinical indicators such as gender and age, we constructed and evaluated five ML models. LightGBM model has a good effect on predicting the etiological type of classic FUO, which will play a good auxiliary decision-making function.

Framing Effects and Evidence Type: Influence on the Persuasive Effect of Myopia Prevention Messages Among Elementary School Students in China.

Background: The myopia is a public health issue that attracts much attention. However, limited attention has been paid to the effect of primary school students' acceptance of health messages. Previous studies have found that framing effects and evidence types influence the persuasive effect of messages. Purpose: This study explored whether framing effects and evidence type influence the persuasive effect of myopia prevention messages among elementary school students and the influence of children's myopia prevention cognition was considered. Methods: A cross-sectional study was conducted among 1,493 elementary school students aged 9 to 13 in China from May to July 2020 by convenience sampling. Wilcoxon signed-rank test and multinomial logistic regression were used for data analysis. Results: Significant differences were found in the persuasive effect between statistical and non-statistical evidence messages (p < 0.001). Among non-statistical evidence messages, gain-framed messages showed a greater persuasive effect than loss-framed messages (p < 0.001). Among statistical evidence messages, loss-framed messages performed better than gain-framed messages (p < 0.001). Children's myopia prevention cognition exerted no significant effect on the persuasive effect of the messages (p > 0.05). Conclusion: This study demonstrated the influence of framing effect on the persuasive effect of myopia prevention messages among children aged 9 to 13 in China. Non-statistical evidence messages showed a better persuasive effect than statistical evidence messages. Different types of evidence influenced the persuasive effect of gain- and loss- framed messages. These findings have implications for strategies more or less likely to work in making myopia prevention messages for children.

Factors Associated With Influential Health-Promoting Messages on Social Media: Content Analysis of Sina Weibo.

BACKGROUND: Social media is a powerful tool for the dissemination of health messages. However, few studies have focused on the factors that improve the influence of health messages on social media. OBJECTIVE: To explore the influence of goal-framing effects, information organizing, and the use of pictures or videos in health-promoting messages, we conducted a case study of Sina Weibo, a popular social media platform in China. METHODS: Literature review and expert discussion were used to determine the health themes of childhood obesity, smoking, and cancer. Web crawler technology was employed to capture data on health-promoting messages. We used the number of retweets, comments, and likes to evaluate the influence of a message. Statistical analysis was then conducted after manual coding. Specifically, binary logistic regression was used for the data analyses. RESULTS: We crawled 20,799 Sina Weibo messages and selected 389 health-promoting messages for this study. Results indicated that the use of gain-framed messages could improve the influence of messages regarding childhood obesity (P<.001), smoking (P=.03), and cancer (P<.001). Statistical expressions could improve the influence of messages about childhood obesity (P=.02), smoking (P=.002), and cancer (P<.001). However, the use of videos significantly improved the influence of health-promoting messages only for the smoking-related messages (P=.009). CONCLUSIONS: The findings suggested that gain-framed messages and statistical expressions can be successful strategies to improve the influence of messages. Moreover, appropriate pictures and videos should be added as much as possible when generating health-promoting messages.