Machine learning analysis of lab tests to predict bariatric readmissions.

The purpose of this study was to develop a machine learning model for predicting 30-day readmission after bariatric surgery based on laboratory tests. Data were collected from patients who underwent bariatric surgery between 2018 and 2023. Laboratory test indicators from the preoperative stage, one day postoperatively, and three days postoperatively were analyzed. Least absolute shrinkage and selection operator regression was used to select the most relevant features. Models constructed included support vector machine (SVM), generalized linear model, multi-layer perceptron, random forest, and extreme gradient boosting. Model performance was evaluated and compared using the area under the receiver operating characteristic curve (AUROC). A total of 1262 patients were included, of which 7.69% of cases were readmitted. The SVM model achieved the highest AUROC (0.784; 95% CI 0.696-0.872), outperforming other models. This suggests that machine learning models based on laboratory test data can effectively identify patients at high risk of readmission after bariatric surgery.

Assessing the impact of isolation policies on epidemic dynamics through swarm entropy.

Isolation policies are an effective measure in epidemiological models for the prediction and prevention of infectious diseases. In this paper, we use a multi-agent modeling approach to construct an infectious disease model that considers the influence of isolation policies. The model analyzes the impact of isolation policies on various stages of epidemic from two perspectives: the external environment and agents behavior. It utilizes multiple variables to simulate the extent to which isolation policies influence the spread of the pandemic. Empirical evidence indicates that the progression of the epidemic is primarily driven by factors such as public willingness and regulatory intensity. The improved model, in comparison to traditional infectious disease models, offers greater flexibility and accuracy, addressing the need for frequent modifications in fundamental models within complex environments. Meanwhile, we introduce "swarm entropy" to evaluate infection intensity under various policies. By linking isolation policies with swarm entropy, considering population structure, we quantify the effectiveness of these isolation measures. It provides a novel approach for complex population simulations. These findings have facilitated the enhancement of control strategies and provided decision-makers with guidance in combating the transmission of infectious diseases.

[Ki-67 expression in stage III cervical squamous cell carcinoma and its correlation with sensitivity to chemoradiotherapy].

OBJECTIVE: To investigate the expression of proliferating cell nuclear antigen (Ki-67) in stage III cervical squamous cell carcinoma (SCC) and its correlation with the effect of chemotherapy on sensitivity to radiotherapy. METHODS: In 50 patients with stage III cervical squamous cell carcinoma (SCC), 25 patients were treated with radiotherapy and 25 patients were treated with chemoradiotherapy. The expression of Ki-67 in the biopsy specimens of cervical SCC was detected by immunohistochemistry at diagnosis and after 10 Gy radiotherapy. The correlation of Ki-67 positive cells percentage and chemotherapy with sensitivity to radiotherapy was analyzed. RESULTS: In 25 patients with more than 48% Ki-67 positive cells at diagnosis, the rate of complete response (CR) was 72.0% (18/25). In 25 patients with less than 48% Ki-67 positive cells at diagnosis, the CR rate was 40.0% (10/25), with a significant difference between them (P = 0.023). In 26 patients with more than 31% decrease of Ki-67 positive cells after 10 Gy radiotherapy, the CR rate was 84.6% (22/26). In 24 patients with less than 31% decrease of Ki-67 positive cells after 10 Gy radiotherapy, the CR rate was 25.0% (6/24), showing a significant difference between the two groups (P < 0.001). In the cases of Ki-67<48%, decrease of Ki-67 positive cells of chemoradiotherapy group after 10 Gy radiotherapy was significantly higher than that of the radiotherapy group (P = 0.023). In the cases of Ki-67 ≥ 48%, no difference in the decease of Ki-67 positive cells between the chemoradiotherapy and radiotherapy groups was found (P = 0.173). For the radiotherapy-sensitive patients with CR recently, the 2-year progression free survival (PFS) rate and overall survival (OS) rate were 85.7% and 92.9%, respectively, both were significantly higher than those of radiotherapy-insensitive patients (18.2% and 40.9%, P < 0.05 for both). CONCLUSIONS: In stage III cervical SCC, the expression of Ki-67 before and after treatment with 10 Gy radiotherapy may be used as a biomarker to predict tumor response to radiation, and guide the choice of therapeutic strategies. Yet, the effect of chemotherapy as a radiosensitizer is unconspicuous.