OBJECTIVE: To explore the influencing factors on the prognosis of patients with multiple myeloma (MM) after bortezomib treatment, and construct a decision tree risk prediction model based on the influencing factors. METHODS: One hundred and seventy MM patients admitted to the People's Hospital of Jianyang City from January 2019 to June 2022 were selected as research subjects, and divided into poor prognosis group and good prognosis group according to the prognosis after bortezomib treatment. The clinical data of the patients were analyzed, univariate and logistic regression analysis were used to screen influencing factors, SPSS Modeler software was used to construct a decision tree prediction model, and the diagnostic performance of the decision tree risk prediction model was analyzed. RESULTS: The incidence of poor prognosis in 170 MM patients after bortezomib-based chemotherapy was 21.18%. Kappa light chain level≥19.4 mg/L, platelet count (PLT) ≤100×10⁹/L, homocysteine (Hcy) >22 μmol/L, serum creatinine (Scr) ≥176 μmol/L, lactate dehydrogenase (LDH) ≥300 U/L, serum ferritin (SF) >500 mg/L, and β₂-microglobulin (MG) >6 μg/L were independent risk factors for poor prognosis in MM patients after bortezomib treatment (all P < 0.05). The decision tree model selected 7 explanatory variables (Kappa light chain level, LDH, PLT, SF, β₂-MG, Scr, and Hcy) as nodes of the model, among which Kappa light chain level was the most important predictor. In addition, the area under the ROC curve (AUC) values of the decision tree model and logistic regression model were 0.895 and 0.881, respectively. The prediction performance of the decision tree model was better than that of the logistic regression model ( Z=3.325, P =0.005). CONCLUSION The decision tree model has high value in predicting the prognosis after bortezomib treatment in MM patients, which can screen high-risk factors that affect poor prognosis, providing practical references for clinical healthcare professionals to take preventive treatment for high-risk MM patients.
Humans ; Bortezomib/therapeutic use* ; Multiple Myeloma/diagnosis* ; Decision Trees ; Prognosis ; Algorithms ; Risk Factors ; Male ; Female ; Middle Aged

OBJECTIVES: To develop risk prediction models for postoperative hypothermia after transurethral holmium laser enucleation of the prostate (HoLEP) using machine learning algorithms. METHODS: We retrospectively analyzed the clinical data of 403 patients from our center (283 patients in the training set and 120in the internal validation set) and 120 patients from Weifang People's Hospital (as the external validation set). The risk prediction models were built using logistic regression, decision tree and support vector machine (SVM), and model performance was evaluated in terms of accuracy, recall, precision, F1 score and AUC. RESULTS: Operation duration, prostate weight, intraoperative irrigation volume, and being underweight were identified as the predictors of postoperative hypothermia following HoLEP. Among the 3 algorithms, SVM showed the best precision rate and accuracy in all the 3 data sets and the best area under the ROC (AUC) in the training set and validation set, followed by logistic regression, which had a similar AUC in the two data sets. SVM outperformed logistic regression and decision tree models in the validation set in precision, accuracy, recall, F1 score, and AUC, and performed well in the external validation set with better precision rate and accuracy than logistic regression and decision tree models but slightly lower recall rate, F1 index, and AUC value than the decision tree model. SVM outperformed logistic regression and decision tree models in precision, accuracy, F1 score, and AUC in the training set, but had slightly lower recall rate than the decision tree. CONCLUSIONS Among the 3 models, SVM has the best performance and generalizability for predicting post-HoLEP hypothermia risk to provide support for clinical decisions.
Humans ; Male ; Retrospective Studies ; Machine Learning ; Transurethral Resection of Prostate/adverse effects* ; Hypothermia/etiology* ; Prostatic Hyperplasia/surgery* ; Algorithms ; Lasers, Solid-State ; Risk Assessment ; Postoperative Complications ; Decision Trees ; Logistic Models ; Aged ; Middle Aged ; Support Vector Machine

OBJECTIVES: This study aimed to use machine learning algorithms to build a prediction model of the first permanent molar caries of 9-year-old children in Suzhou and screen out risk factors. METHODS: Random stratified whole group sampling was applied to randomly select 9-year-old students from 38 primary schools in 14 townships and streets in Wuzhong District for oral examination and questionnaire survey. Multifactor Logistics regression was used to analyze the risk factors of tooth decay. The data set was randomly divided into training sets and verification sets according to 8∶2, and R 4.3.1 was used to build five machine learning algorithms: random forest, decision tree, extreme gradient boosting (XGBoost), Logistics regression, and lightweight gradient enhancement (LightGBM). The predictive effect of these five models was evaluated using the area under the characteristic curve (AUC). The marginal contribution of quantitative characteristics to the caries prediction model was determined through Shapley additive explanations (SHAP). RESULTS: This study included 7 225 samples that met the standard. The caries rate of the first permanent molar was 54.96%. Multifactor Logistic regression analysis showed that sweet drinks, dessert and candy, snack frequency, and snacks before going to bed after brushing teeth were correlated with the occurrence of first permanent molar caries (P<0.05). The AUC values of decision tree, Logistic regression, LightGBM, random forest, and XGBoost were 75.5%, 83.9%, 88.6%, 88.9%, and 90.1%, respectively. Compared with the variables after single heat coding, the SHAP value of high-frequency sweets (such as dessert candy ≥2 times a day, mother's sugary diet ≥2 times a day) and bad oral hygiene habits (such as frequent snacks before going to bed after brushing teeth and irregular brushing teeth) exhibited the highest positive. CONCLUSIONS XGBoost algorithm has a good prediction effect for first permanent molar caries in 9-year-old children. High-frequency sweet factors and bad oral hygiene habits have a strong positive impact on the risk of first permanent molar caries and are key drivers that can be used in the formulation of targeted interventions.
Humans ; Dental Caries/epidemiology* ; Child ; Machine Learning ; China/epidemiology* ; Molar ; Risk Factors ; Female ; Logistic Models ; Male ; Decision Trees ; Algorithms

Maxillary sinus floor augmentation using lateral window and crestal technique is considered as predictable methods to increase the residual bone height; however, this surgery is commonly complicated by Schneiderian membrane perforation, which is closely related to anatomical factors. This article aimed to assess anatomical factors on successful augmentation procedures. After review of the current evidence on sinus augmentation techniques, anatomical factors related to the stretching potential of Schneiderian membrane were assessed and a decision tree for the rational choice of surgical approaches was proposed. Schneiderian membrane perforation might occur when local tension exceeds its stretching potential, which is closely related to anatomical variations of the maxillary sinus. Choice of a surgical approach and clinical outcomes are influenced by the stretching potential of Schneiderian membrane. In addition to the residual bone height, clinicians should also consider the stretching potential affected by the membrane health condition, the contours of the maxillary sinus, and the presence of antral septa when evaluating the choice of surgical approaches and clinical outcomes.
Sinus Floor Augmentation ; Decision Trees

Humans ; Cost-Benefit Analysis ; HIV Infections/drug therapy* ; Cost-Effectiveness Analysis ; Decision Trees

Objective: To investigate the influencing factors of HBV intrauterine transmission and their interaction effects by integrating logistic regression model and Chi-squared automatic interaction detector (CHAID) decision tree model. Methods: A total of 689 pairs of HBsAg-positive mothers and their neonates in the obstetrics department of the Third People's Hospital of Taiyuan from 2007 to 2013 were enrolled, and the basic information of mothers and their neonates were obtained by questionnaire survey and medical record review, such as the general demographic characteristics, gestational week and delivery mode. HBV DNA and HBV serological markers of the mothers and newborns were detected by fluorescence quantitative PCR and electrochemiluminescence immunoassay respectively. The CHAID decision tree model and unconditional logistic regression analysis were used to explore the factors influencing HBV intrauterine transmission in neonates of HBsAg-positive mothers. Results: Among the 689 neonates, the incidence of HBV intrauterine transmission was 11.47% (79/689). After adjusted for confounding factors, the first and second logistic multivariate analysis showed that cesarean delivery was a protective factor for HBV intrauterine transmission (OR=0.25, 95%CI: 0.14-0.43; OR=0.27, 95%CI: 0.15-0.46); both models indicated that maternal HBeAg positivity and HBV DNA load ≥2×10⁵ IU/ml before delivery were risk factors of HBV intrauterine transmission (OR=3.89, 95%CI: 2.32-6.51; OR=3.48, 95%CI: 2.12-5.71), respectively. The CHAID decision tree model screened three significant factors influencing HBV intrauterine transmission, the most significant one was maternal HBeAg status, followed by delivery mode and maternal HBV DNA load. There were interactions between maternal HBeAg status and delivery modes, as well as delivery mode and maternal HBV DNA load before delivery. The rate of HBV intrauterine transmission in newborns of HBeAg-positive mothers by vaginal delivery increased from 19.08% to 29.37%; among HBeAg-positive mothers with HBV DNA ≥2×10⁵ IU/ml, the rate of HBV intrauterine transmission increased to 33.33% in the newborns by vaginal delivery. Conclusions: Maternal HBeAg positivity,maternal HBV DNA ≥2×10⁵ IU/ml and vaginal delivery could be risk factors for HBV intrauterine transmission in newborns. Interaction effects were found between maternal HBeAg positivity and vaginal delivery, as well as vaginal delivery and high maternal HBV DNA load. Logistic regression model and the CHAID decision tree model can be used in conjunction to identify the high-risk populations and develop preventive strategies accurately.
DNA, Viral/genetics* ; Decision Trees ; Female ; Hepatitis B Surface Antigens ; Hepatitis B e Antigens ; Hepatitis B virus/genetics* ; Humans ; Infant, Newborn ; Infectious Disease Transmission, Vertical ; Logistic Models ; Mothers ; Pregnancy ; Pregnancy Complications, Infectious/epidemiology*

OBJECTIVES: To study the clinical value of attention time combined with behavior scale in the screening of attention deficit hyperactivity disorder (ADHD) in preschool children. METHODS: A total of 200 preschool children with ADHD diagnosed in Fujian Maternal and Child Health Hospital from February 2019 to March 2020 were enrolled as the ADHD group. A total of 200 children who underwent physical examination in the hospital or kindergartens during the same period were enrolled as the control group. Attention time was recorded. Chinese Version of Swanson Nolan and Pelham, Version IV Scale-Parent Form (SNAP-IV) scale was used to evaluate symptoms. With clinical diagnosis as the gold standard, the decision tree analysis was used to evaluate the clinical value of attention time combined with behavior scale in the screening of ADHD. RESULTS: Compared with the control group, the ADHD group had significantly higher scores of SNAP-IV items 1, 4, 7, 8, 10, 11, 14, 15, 16, 18, 20, 21, and 22 (P<0.05) and a significantly shorter attention time (P<0.05). The variables with statistically significant differences between the two groups in univariate analysis were used as independent variables to establish a decision tree model. The accuracy of the model in predicting ADHD was 81%, that in predicting non-ADHD was 69%, and the overall accuracy was 75%, with an area under the ROC curve of 0.816 (95% CI: 0.774-0.857, P<0.001). CONCLUSIONS The decision tree model for screening ADHD in preschool children based on attention time and assessment results of behavior scale has a high accuracy and can be used for rapid screening of ADHD among children in clinical practice.
Asians ; Attention Deficit Disorder with Hyperactivity/diagnosis* ; Child, Preschool ; Decision Trees ; Humans ; Mass Screening ; Prospective Studies

Adolescent ; Adult ; Child ; Decision Trees ; Female ; HIV Infections ; economics ; transmission ; Humans ; Infectious Disease Transmission, Vertical ; economics ; prevention & control ; Kenya ; Middle Aged ; Mothers ; South Africa ; Vietnam ; Young Adult

BACKGROUND: This study evaluated the cost-effectiveness of 21 different national dyslipidemia screening strategies according to total cholesterol (TC) cutoff and screening interval among 40 years or more for the primary prevention of coronary heart disease over a lifetime in Korea, from a societal perspective. METHODS: A decision tree was used to estimate disease detection with the 21 different screening strategies, while a Markov model was used to model disease progression until death, quality-adjusted life years (QALYs) and costs from a Korea societal perspective. RESULTS: The results showed that the strategy with TC 200 mg/dL and 4-year interval cost ￦4,625,446 for 16.65105 QALYs per person and strategy with TC 200 mg/dL and 3-year interval cost ￦4,691,771 for 16.65164 QALYs compared with ￦3,061,371 for 16.59877 QALYs for strategy with no screening. The incremental cost-effectiveness ratio of strategy with TC 200 mg/dL and 4-year interval versus strategy with no screening was ￦29,916,271/QALY. At a Korea willingness-to-pay threshold of ￦30,500,000/QALY, strategy with TC 200 mg/dL and 4-year interval is cost-effective compared with strategy with no screening. Sensitivity analyses showed that results were robust to reasonable variations in model parameters. CONCLUSION: In this study, revised national dyslipidemia screening strategy with TC 200 mg/dL and 4-year interval could be a cost-effective option. A better understanding of the Korean dyslipidemia population may be necessary to aid in future efforts to improve dyslipidemia diagnosis and management.
Cholesterol ; Coronary Disease ; Cost-Benefit Analysis ; Decision Trees ; Diagnosis ; Disease Progression ; Dyslipidemias ; Humans ; Korea ; Mass Screening ; Primary Prevention ; Quality-Adjusted Life Years

Scratching is a main behavioral response accompanied by acute and chronic itch conditions, and has been quantified as an objective correlate to assess itch in studies using laboratory animals. Scratching has been counted mostly by human annotators, which is a time-consuming and laborious process. It has been attempted to develop automated scoring methods using various strategies, but they often require specialized equipment, costly software, or implantation of device which may disturb animal behaviors. To complement limitations of those methods, we have adapted machine learning-based strategy to develop a novel automated and real-time method detecting mouse scratching from experimental movies captured using monochrome cameras such as a webcam. Scratching is identified by characteristic changes in pixels, body position, and body size by frame as well as the size of body. To build a training model, a novel two-step J48 decision tree-inducing algorithm along with a C4.5 post-pruning algorithm was applied to three 30-min video recordings in which a mouse exhibits scratching following an intradermal injection of a pruritogen, and the resultant frames were then used for the next round of training. The trained method exhibited, on average, a sensitivity and specificity of 95.19% and 92.96%, respectively, in a performance test with five new recordings. This result suggests that it can be used as a non-invasive, automated and objective tool to measure mouse scratching from video recordings captured in general experimental settings, permitting rapid and accurate analysis of scratching for preclinical studies and high throughput drug screening.
Animals ; Animals, Laboratory ; Behavior, Animal ; Body Size ; Complement System Proteins ; Decision Trees ; Drug Evaluation, Preclinical ; Humans ; Injections, Intradermal ; Machine Learning ; Methods ; Mice ; Motion Pictures as Topic ; Pruritus ; Research Design ; Sensitivity and Specificity ; Video Recording