Nearest Neighbor Classifiers Versus Random Forests and Support Vector Machines

BackgroundLumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.MethodsWe utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.ResultsIn the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.ConclusionsThe RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China

In todays’ era, the health sector has become a rich source of information due to the existence of many data analysis tools with the huge availability of any patients’ disease datasets. Since, Coronary Heart Disease (CHD) is one of the world’s leading causes of death, detecting it can help reduce mortality rates. When making predictions using conventional methods, the complexity of the data and correlations is a problem. The purpose of this research is to leverage historical medical data to predict CHD using machine learning technologies. Random forest (RF), Support vector machine (SVM), and k–Nearest neighbour classification (k–NN) are three supervised learning approaches used in this paper to detect whether a patient is suffering from CHD or not with a higher prediction rate. The authors also validate the associativity of Heart disease and family history(famhist). South African (SA) heart disease dataset of 462 instances with 10–fold cross-validation method is used here for experimental results. RF model is found promising in detecting CHD with 95% accuracy. Moreover, famhist and CHD are found statistically significant associated (p <0.05) with χ²(1)=34.27.

Background and aimsThe birth weight of a newborn is a crucial factor that affects their overall health and future well-being. Low birth weight (LBW) is a widespread global issue, which the World Health Organization defines as weighing less than 2,500 g. LBW can have severe negative consequences on an individual’s health, including neonatal mortality and various health concerns throughout their life. To address this problem, this study has been conducted using BDHS 2017–2018 data to uncover important aspects of LBW using a variety of machine learning (ML) approaches and to determine the best feature selection technique and best predictive ML model.MethodsTo pick out the key features, the Boruta algorithm and wrapper method were used. Logistic Regression (LR) used as traditional method and several machine learning classifiers were then used, including, DT (Decision Tree), SVM (Support Vector Machine), NB (Naïve Bayes), RF (Random Forest), XGBoost (eXtreme Gradient Boosting), and AdaBoost (Adaptive Boosting), to determine the best model for predicting LBW. The model’s performance was evaluated based on the specificity, sensitivity, accuracy, F1 score and AUC value.ResultsResult shows, Boruta algorithm identifies eleven significant features including respondent’s age, highest education level, educational attainment, wealth index, age at first birth, weight, height, BMI, age at first sexual intercourse, birth order number, and whether the child is a twin. Incorporating Boruta algorithm’s significant features, the performance of traditional LR and ML methods including DT, SVM, NB, RF, XGBoost, and AB were evaluated where LR, had a specificity, sensitivity, accuracy and F1 score of 0.85, 0.5, 85.15% and 0.915. While the ML methods DT, SVM, NB, RF, XGBoost, and AB model’s respective accuracy values were 85.35%, 85.15%, 84.54%, 81.18%, and 84.41%. Based on the specificity, sensitivity, accuracy, F1 score and AUC, RF (specificity = 0.99, sensitivity = 0.58, accuracy = 85.86%, F1 score = 0.9243, AUC = 0.549) outperformed the other methods. Both the classical (LR) and machine learning (ML) models’ performance has improved dramatically when important characteristics are extracted using the wrapper method. The LR method identified five significant features with a specificity, sensitivity, accuracy and F1 score of 0.87, 0.33, 87.12% and 0.9309. The region, whether the infant is a twin, and cesarean delivery were the three key features discovered by the DT and RF models, which were implemented using the wrapper technique. All three models had the identical F1 score of 0.9318. However, “child is twin” was recognized as a significant feature by the SVM, NB, and AB models, with an F1 score of 0.9315. Ultimately, with an F1 score of 0.9315, the XGBoost model recognized “child is twin” and “age at first sex” as relevant features. Random Forest again beat the other approaches in this instance.ConclusionsThe study reveals Wrapper method as the optimal feature selection technique. The ML method outperforms traditional methods, with Random Forest (RF) being the most effective predictive model for Low-Birth-Weight prediction. The study suggests that policymakers in Bangladesh can mitigate low birth weight newborns by considering identified risk factors.

Developing machine learning models with multi-source environmental data to predict wheat yield in China

Cancer survival classification using integrated data sets and intermediate information.

PurposeTo determine predictors of self-efficacy in breast cancer survivors and identify vulnerable groups.MethodsThis descriptive study was conducted between November 2023 and April 2024 at three hospitals in Türkiye and involved 430 breast cancer survivors. Data were collected through face-to-face surveys using a patient identification form and the Breast Cancer Survivor Self-Efficacy Scale. This study identified patient characteristics that indicate a tendency towards higher self-efficacy using four machine learning models; Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), XGBoost (XGB).ResultsThe mean age of participants was 50.7 ± 11.5 years. Majority of the participants (n = 425) were female. AUC values were used as ranker for the machine learning models. The ranks of the models were as follows; logistic regression model (0.715), RF (0.710), SVM (0.704), and XGBoost (0.694). Education level ranked first in the LR (0.3874), RF (0.3290), and SVM (0.1250) models, and was the second most important variable in the XGB (0.2327) model. Conversely, the cancer stage stood out in the LR (0.2466) and RF (0.1935) models, ranking third and fourth, respectively, while it ranked third in SVM (0.0683) and fourth in XGB (0.1872). Additionally, comorbidity ranked third in importance in the LR (0.2213) and RF (0.1681) models, but second in SVM (0.0705) and seventh in XGB (0.1393).ConclusionThe study demonstrated that the self-efficacy of breast cancer survivors was associated with their sociodemographic and medical characteristics. These characteristics may assist healthcare professionals in enhancing the care provided to breast cancer survivors. It is of the utmost importance to consider the aforementioned patient group as being vulnerable with regard to breast cancer survivor self-efficacy. There is a clear need for a focus on this vulnerable cohort.

BackgroundA considerable portion of patients with fever of unknown origin (FUO) present concomitant lymphadenopathy. Diseases within the spectrum of FUO accompanied by lymphadenopathy include lymphoma, infections, and rheumatic diseases. Particularly, lymphoma has emerged as the most prevalent etiology of FUO with associated lymphadenopathy. Distinguishing between benign and malignant lymph node lesions is a major challenge for physicians and an urgent clinical concern for patients. However, conventional imaging techniques, including PET/CT, often have difficulty accurately distinguishing between malignant and benign lymph node lesions. This study utilizes PET/CT radiomics to differentiate between lymphoma and benign lymph node lesions in patients with FUO, aiming to improve diagnostic accuracy.ResultsData were collected from 204 patients who underwent 18F-FDG PET/CT examinations for FUO, including 114 lymphoma patients and 90 patients with benign lymph node lesions. Patients were randomly divided into training and testing groups at a ratio of 7:3. A total of 15 effective features were obtained by the least absolute shrinkage and selection operator (LASSO) algorithm. Machine learning models were constructed using logistic regression (LR), support vector machine (SVM), random forest (RF), and k-nearest neighbors (KNN) algorithms. In the training group, the area under the curve (AUC) values for predicting lymphoma and benign cases by LR, SVM, RF, and KNN models were 0.936, 0.930, 0.998, and 0.938, respectively. There were statistically significant differences in AUC between the RF and other models (all P < 0.001). In the testing group, the AUC values for the four models were 0.860, 0.866, 0.915, and 0.891, respectively, with no statistically significant differences observed among them (all P > 0.05). The decision curve analysis (DCA) curves of the RF model outperformed those of the other three models in both the training and testing groups.ConclusionsPET/CT radiomics demonstrated promising performance in discriminating lymphoma from benign lymph node lesions in patients with FUO, with the RF model showing the best performance.

The effects of the spatial resolution of remote sensing (RS) data on wildfire susceptibility prediction are not fully understood. In this study, we evaluate the effects of coarse (Landsat 8 and SRTM) and medium (Sentinel-2 and ALOS) spatial resolution data on wildfire susceptibility prediction using random forest (RF) and support vector machine (SVM) models. In addition, we investigate the fusion of the predictions from the different spatial resolutions using the Dempster–Shafer theory (DST) and 14 wildfire conditioning factors. Seven factors are derived separately from the coarse and medium spatial resolution datasets for the whole forest area of the Guilan Province, Iran. All conditional factors are used to train and test the SVM and RF models in the Google Earth Engine (GEE) software environment, along with an inventory dataset from comprehensive global positioning system (GPS)-based field survey points of wildfire locations. These locations are evaluated and combined with coarse resolution satellite data, namely the thermal anomalies product of the moderate resolution imaging spectroradiometer (MODIS) for the period 2009 to 2019. We assess the performance of the models using four-fold cross-validation by the receiver operating characteristic (ROC) curve method. The area under the curve (AUC) achieved from the ROC curve yields 92.15% and 91.98% accuracy for the respective SVM and RF models for the coarse RS data. In comparison, the AUC for the medium RS data is 92.5% and 93.37%, respectively. Remarkably, the highest AUC value of 94.71% is achieved for the RF model where coarse and medium resolution datasets are combined through DST.

Objective: Using methylation characteristics of human genes to construct machine learning predictive models for screening cervical cancer and precancerous lesions. Methods: Human DNA methylation detection was performed on 224 cervical exfoliated cell specimens from the Cancer Hospital of the Chinese Academy of Medical Sciences, Tianjin Central Hospital of Gynecology Obstetrics, Xinmi Maternal and Child Health Hospital of Henan Province, West China Second Affiliated Hospital of Sichuan University, and Heping Hospital Affiliated to Changzhi Medical College collected during April 2014 and March 2015. The hypermethylated gene fragments related to cervical cancer were selected by high-density, high-association, and hypermethylated gene fragment screening and the LASSO regression algorithm. Taking cervical intraepithelial neoplasia grade 2 (CIN2) or more severe lesions as the research outcome, machine learning predictive models based on the random forest (RF), naive Bayes (NB), and support vector machine (SVM) algorithm, respectively, were constructed. A total of 144 outpatient specimens were used as the training set and 80 cervical exfoliated cell specimens from women participating in the cervical cancer screening program were used as the test set to verify the predictive models. Using histological diagnosis results as the gold standard, the detection efficacy for CIN2 or more severe lesions of the three machine learning predictive models were compared with that of the human papilloma virus (HPV) detection and cytological diagnosis. Results: In the training set of 144 cases, there were 34 cases of HPV positivity, with a positive rate of 23.61%. Cytologically, there were 37 cases diagnosed as no intraepithelial lesion or malignancy (NILM), and 107 cases diagnosed as atypical squamous cells of undetermined significance (ASC-US) or above. Histologically, there were 28 cases without cervical intraepithelial neoplasia or benign cervical lesions, 31 cases of CIN1, 18 cases of CIN2, 31 cases of CIN3, and 36 cases of squamous cell carcinoma. Seven hypermethylated gene fragments were selected from 45 genes, and three machine learning prediction models based on the RF, NB, and SVM algorithm, respectively, were constructed. In the validation set of 80 cases, there were 28 cases of HPV positivity, with a positive rate of 35.00%. Cytologically, there were 65 cases diagnosed as NILM and 15 cases as ASC-US or above. Histologically, there were 39 cases without cervical intraepithelial neoplasia or benign cervical lesions, 10 cases of CIN1, 10 cases of CIN2, 11 cases of CIN3, and 10 cases of squamous cell carcinoma. In the validation set, the area under the curve (AUC) values of the RF model, NB model, SVM model, HPV detection, and cytological diagnosis of CIN2 or above were 0.90, 0.88, 0.82, 0.68, and 0.45, respectively. The DeLong test showed that there was no statistically significant difference in the AUC values between the RF, NB, and SVM models (all P＞0.05), and the AUC values of the RF and NB models were higher than that of HPV detection (both P＜0.01), and the AUC values of the RF, NB, and SVM models were higher than that of cytological diagnosis (all P＜0.01). Compared with the NB model, the sensitivity of the RF model was similar (80.65% vs. 77.42%), but the specificity of the NB model was much higher than that of the RF model (93.88% vs. 73.47%). Conclusion: Among the machine learning prediction models for cervical cancer and precancerous lesions constructed based on human DNA methylation, the NB model has good predictive performance for CIN2 and above lesions, and may be used for screening of cervical cancer and precancerous lesions.

Soil total nitrogen (STN) is an important indicator of soil quality and plays a key role in global nitrogen cycling. Accurate prediction of STN content is essential for the sustainable use of soil resources. Synthetic aperture radar (SAR) provides a promising source of data for soil monitoring because of its all-weather, all-day monitoring, but it has rarely been used for STN mapping. In this study, we explored the potential of multi-temporal Sentinel-1 data to predict STN by evaluating and comparing the performance of boosted regression trees (BRTs), random forest (RF), and support vector machine (SVM) models in STN mapping in the middle reaches of the Heihe River Basin in northwestern China. Fifteen predictor variables were used to construct models, including land use/land cover, multi-source remote sensing-derived variables, and topographic and climatic variables. We evaluated the prediction accuracy of the models based on a cross-validation procedure. Results showed that tree-based models (RF and BRT) outperformed SVM. Compared to the model that only used optical data, the addition of multi-temporal Sentinel-1A data using the BRT method improved the root mean square error (RMSE) and the mean absolute error (MAE) by 17.2% and 17.4%, respectively. Furthermore, the combination of all predictor variables using the BRT model had the best predictive performance, explaining 57% of the variation in STN, with the highest R2 (0.57) value and the lowest RMSE (0.24) and MAE (0.18) values. Remote sensing variables were the most important environmental variables for STN mapping, with 59% and 50% relative importance in the RF and BRT models, respectively. Our results show the potential of using multi-temporal Sentinel-1 data to predict STN, broadening the data source for future digital soil mapping. In addition, we propose that the SVM, RF, and BRT models should be calibrated and evaluated to obtain the best results for STN content mapping in similar landscapes.

ObjectiveTo develop and validate a generalized prediction model that can classify epidermal growth factor receptor (EGFR) mutation status in non–small cell lung cancer patients.MethodsA total of 346 patients (296 in the training cohort and 50 in the validation cohort) from four centers were included in this retrospective study. First, 1085 features were extracted using IBEX from the computed tomography images. The features were screened using the intraclass correlation coefficient, hypothesis tests and least absolute shrinkage and selection operator. Logistic regression (LR), decision tree (DT), random forest (RF), and support vector machine (SVM) were used to build a radiomics model for classification. The models were evaluated using the following metrics: area under the curve (AUC), calibration curve (CAL), decision curve analysis (DCA), concordance index (C-index), and Brier score.ResultsSixteen features were selected, and models were built using LR, DT, RF, and SVM. In the training cohort, the AUCs was .723, .842, .995, and .883; In the validation cohort, the AUCs were .658, 0567, .88, and .765. RF model with the best AUC, its CAL, C-index (training cohort=.998; validation cohort=.883), and Brier score (training cohort=.007; validation cohort=0.137) showed a satisfactory predictive accuracy; DCA indicated that the RF model has better clinical application value.ConclusionMachine learning models based on computed tomography images can be used to evaluate EGFR status in patients with non–small cell lung cancer, and the RF model outperformed LR, DT, and SVM.

BackgroundPredicting hypoglycemia while maintaining a low false alarm rate is a challenge for the wide adoption of continuous glucose monitoring (CGM) devices in diabetes management. One small study suggested that a deep learning model based on the long short-term memory (LSTM) network had better performance in hypoglycemia prediction than traditional machine learning algorithms in European patients with type 1 diabetes. However, given that many well-recognized deep learning models perform poorly outside the training setting, it remains unclear whether the LSTM model could be generalized to different populations or patients with other diabetes subtypes.ObjectiveThe aim of this study was to validate LSTM hypoglycemia prediction models in more diverse populations and across a wide spectrum of patients with different subtypes of diabetes.MethodsWe assembled two large data sets of patients with type 1 and type 2 diabetes. The primary data set including CGM data from 192 Chinese patients with diabetes was used to develop the LSTM, support vector machine (SVM), and random forest (RF) models for hypoglycemia prediction with a prediction horizon of 30 minutes. Hypoglycemia was categorized into mild (glucose=54-70 mg/dL) and severe (glucose<54 mg/dL) levels. The validation data set of 427 patients of European-American ancestry in the United States was used to validate the models and examine their generalizations. The predictive performance of the models was evaluated according to the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).ResultsFor the difficult-to-predict mild hypoglycemia events, the LSTM model consistently achieved AUC values greater than 97% in the primary data set, with a less than 3% AUC reduction in the validation data set, indicating that the model was robust and generalizable across populations. AUC values above 93% were also achieved when the LSTM model was applied to both type 1 and type 2 diabetes in the validation data set, further strengthening the generalizability of the model. Under different satisfactory levels of sensitivity for mild and severe hypoglycemia prediction, the LSTM model achieved higher specificity than the SVM and RF models, thereby reducing false alarms.ConclusionsOur results demonstrate that the LSTM model is robust for hypoglycemia prediction and is generalizable across populations or diabetes subtypes. Given its additional advantage of false-alarm reduction, the LSTM model is a strong candidate to be widely implemented in future CGM devices for hypoglycemia prediction.

Sepsis is a leading cause of mortality in the intensive care unit. Early prediction of sepsis can reduce the overall mortality rate and cost of sepsis treatment. Some studies have predicted mortality and development of sepsis using machine learning models. However, there is a gap between the creation of different machine learning algorithms and their implementation in clinical practice.This study utilized data from the Medical Information Mart for Intensive Care III. We established and compared the gradient boosting decision tree (GBDT), logistic regression (LR), k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM).A total of 3937 sepsis patients were included, with 34.3% mortality in the Medical Information Mart for Intensive Care III group. In our comparison of 5 machine learning models (GBDT, LR, KNN, RF, and SVM), the GBDT model showed the best performance with the highest area under the receiver operating characteristic curve (0.992), recall (94.8%), accuracy (95.4%), and F1 score (0.933). The RF, SVM, and KNN models showed better performance (area under the receiver operating characteristic curve: 0.980, 0.898, and 0.877, respectively) than the LR (0.876).The GBDT model showed better performance than other machine learning models (LR, KNN, RF, and SVM) in predicting the mortality of patients with sepsis in the intensive care unit. This could be used to develop a clinical decision support system in the future.

Introducing two Random Forest based methods for cloud detection in remote sensing images