the aim of this study is to explore the feasibility of using machine learning (ML) technology to predict postoperative recurrence risk among stage iV colorectal cancer patients. four basic ML algorithms were used for prediction-logistic regression, decision tree, GradientBoosting and lightGBM. the research samples were randomly divided into a training group and a testing group at a ratio of 8:2. 999 patients with stage 4 colorectal cancer were included in this study. In the training group, the GradientBoosting model's AUC value was the highest, at 0.881. The Logistic model's AUC value was the lowest, at 0.734. The GradientBoosting model had the highest F1_score (0.912). In the test group, the AUC Logistic model had the lowest AUC value (0.692). The GradientBoosting model's AUC value was 0.734, which can still predict cancer progress. However, the gbm model had the highest AUC value (0.761), and the gbm model had the highest F1_score (0.974). The GradientBoosting model and the gbm model performed better than the other two algorithms. the weight matrix diagram of the GradientBoosting algorithm shows that chemotherapy, age, LogCEA, CEA and anesthesia time were the five most influential risk factors for tumor recurrence. the four machine learning algorithms can each predict the risk of tumor recurrence in patients with stage iV colorectal cancer after surgery. Among them, GradientBoosting and gbm performed best. Moreover, the GradientBoosting weight matrix shows that the five most influential variables accounting for postoperative tumor recurrence are chemotherapy, age, LogCEA, ceA and anesthesia time. Colorectal cancer is a common malignant tumor with high morbidity and mortality in clinical practice. It ranks third in mortality among all tumors 1. Approximately 1.4 million new cases are diagnosed every year, and about half of the new cases are in the progressive stage. The 5-year survival rate is 30% ~ 40%, due primarily to postoperative recurrence and metastasis, of which 10% ~ 30% have abdominal cavity metastasis, with a median survival of 7 months. In China, the incidence and mortality of colorectal cancer rank third and fifth, respectively, among systemic tumors. Currently, the main clinical approach is surgical treatment assisted with multidisciplinary methods such as radiotherapy, chemotherapy and targeted therapy. However, a meta-analysis of 18 clinical trials shows that patients have a recurrence rate of 80.00% within 3 years after surgery 2. With early diagnosis and treatment, the prognosis of early stage colorectal cancer patients is optimistic, and the middle and long-term survival rate is usually high. However, as early symptoms are not typical, they are easily ignored by patients, leading to progression to the middle and late stages when they are finally admitted to hospitals. This inhibits treatment and reduces long-term survival rates. Recent machine learning (ML) methods have shown accurate predictive ability, and have been increasingly used in the diagnosis and prognosis of various diseases and hea...
ObjectiveTo use machine learning algorithms to predict the death outcomes of patients with triple-negative breast cancer, 5 years after discharge.Methods1570 stage I-III breast cancer patients receiving treatment from Sun Yat-sen Memorial Hospital were analyzed. Machine learning was used to predict the death outcomes of patients with triple-negative breast cancer, 5 years after discharge.ResultsThe results showed that platelets, LMR (lymphocyte-to-monocyte ratio), age, PLR (the platelet-to-lymphocyte ratio) and white blood cell counts accounted for a significant weight in the 5-year prognosis of triple-negative breast cancer patients. The results of model prediction indicated that rankings for accuracy among the training group (from high to low) were forest, gbm, and DecisionTree (0.770335, 0.760766, 0.751994, 0.737640 and 0.734450, respectively). For AUC value (high to low), they were forest, Logistic and DecisionTree (0.896673, 0.895408, 0.776836, 0.722799 and 0.702804, respectively). The highest MSE value for DecisionTree was 0.2656, and the lowest MSE value for forest was 0.2297. In the test group, accuracy rankings (from high to low) were DecisionTree, and GradientBoosting (0.748408, 0.738854, 0.738854, 0.732484 and gbm, respectively). For AUC value (high to low), the rankings were GradientBoosting, gbm, and DecisionTree (0.731595, 0.715438, 0.712767, 0.708348 and 0.691960, respectively). The maximum MSE value for gbm was 0.2707, and the minimum MSE value for DecisionTree was 0.2516.ConclusionThe machine learning algorithm can predict the death outcomes of patients with triple-negative breast cancer 5 years after discharge. This can be used to estimate individual outcomes for patients with triple-negative breast cancer.
The aim of this study was to evaluate the safety and efficacy of ultrasound-guided ilioinguinal/iliohypogastric nerve block (IINB) in pediatric patients undergoing sameday inguinal region surgery. Ninety patients aged 4-6 years, ASA levels I-II, were randomly divided into three groups: U, T, or C (n=30 each). After basic anesthesia, patients in group U underwent ultrasound-guided IINB, those in group T underwent traditional Schulte-Steinberg IINB, and those in group C (controls) received intravenous anesthesia (ketamine-propofol) only. Patients who remained sensitive to intraoperative stimuli received additional intravenous doses of 1 mg/kg ketamine. Heart rate (HR), mean arterial pressure (MAP), and oxygen saturation (SPO 2 ) were recorded upon entering the operating room (T0), at skin incision (T1), while pulling the hernia sac (T2), during skin closing (T3), and upon awakening (T4) at recovery. HR and MAP at T1, T2, and T4 were higher in group C than those in the other two groups, and recovery time in group C was significantly prolonged (P<0.05). Group U required significantly lower quantities and frequency of ketamine injection, and pain scores in group U during awakening were lower than those in the other two groups (P<0.05). Ultrasound-guided IINB provided an improved nerve block effect and postoperative analgesia, reduced the amount of local anesthetic required, facilitated more rapid postoperative recovery, and was a safe and effective method of anesthesia.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.