Performance Comparison of Machine Learning Algorithms Using Oversampling Methods to Predict Childhood Anemia

Universities annually accept new students at the beginning of the new school year. In the acceptance of prospective students on the Seleksi Prestasi Akademik Nasional Perguruan Tinggi Keagamaan Islam Negeri (SPAN PTKIN) di State Islamic University Of Sunan Ampel Surabaya, many prospective students who do not register will have an impact on income of the State Islamic University Of Sunan Ampel Surabaya institution. If the institution can find out early on the probability of a prospective student who will resign, then the management can take action to retain the prospective student. To overcome this, data mining classification can be carried out. The methods used in this classification are decision trees and naïve bayes. The number of students who did not re register compared to reregister resulted in the data being imbalanced. Data imbalances can affect the accuracy of the classification results. The imbalance of the data used can result in an unsuitable model. The solution to handle the data imbalance is to use the SMOTE and ADASYN oversampling methods. The purpose of this study was to compare performance of the SMOTE and ADASYN methods. The results show that the SMOTE method can balance the data in a balanced way compared to ADASYN. From the test results, the SMOTE method is more suitable to use than the ADASYN method because the ROCAUC SMOTE value is higher than ADASYN.

Background: The air quality of any area depends upon the various PMs (particulate matter) and hazardous gases present in the air. Low-cost PM sensors and gas sensors are present in different target places to monitor the air quality, read the environmental data, and transmit it to local servers through the IoT device. The low-cost sensor is not reliable due to its low sensing capacity; therefore, the read data is calibrated with the meteorological data presented by the nearby meteorological Centre of that particular area. The calibrated reading data sent to the server could be analyzed through some Machine Learning [ML] models. The ML models help to predict the risk of asthma in a particular area. The risk of asthma is directly related to the air quality of the surroundings. It is observed that the air quality of the industrial area is much worse than the non-industrial belt. Air quality monitoring of industrial areas is always a challenging task due to the ununiformed pollution in some segregated places around the industry, emitting pollutants mostly from chimneys. The air quality of any area depends upon the PM (PM), i.e., PM2.5 and PM10.0, as well as the gasses like NO2(Nitrogen Dioxide), NH3 (Ammonia), SO2(Sulfur dioxide), CO(Carbon monoxide), O3(Ozone) and Benzene. These are the most hazardous gases generally emitted by common heavy industries like iron and steel. In this article, the researchers considered the industrial belt of the Asansol- Durgapur region of West Bengal, India, and predicted the risk of asthma attacks for the test dataset. The experiment was carried out on 10 different supervised machine learning [SML] models as well as semi-supervised machine learning (SSML) models. The SML models have been further refined through hyper-parameter tuning, and better results have been obtained in the case of some ML models. The result has been compared with the existing literature considering the same external environment from where the meteorological data was collected, and similar ML models have been used. The research outperformed the existing literature, which is depicted in the result and analysis section of the article. Methods: The study evaluated ML models, both supervised and semi-supervised, to assess pollution levels. Relevant features were selected while less relevant ones were discarded. Accuracy levels of different ML algorithms werecompared in the results. The most effective model for an IoT system was chosen to maximize accuracy. In semi-supervised learning, feature selection followed supervised learning, but testing was akin to unsupervised learning. Results were compared with supervised learning data, enhancing reliability. Results: The result employing various classifiers werepresented across tables after the independent parameter Ozone was removed. Following the output of several classifiers, the results were verified using the k-fold validation method, with k being set to 5 or 10, accordingly. Tables display the best outcome, which is indicated in bold characters. method: In this research work the researcher considered 9 different ML models and used them as supervised as well as semi supervised model to determine the pollution level of the certain area. In this research work the researcher also selected the most relevant features and discarded the less relevant features. In case of SML algorithm, the accuracy level of the different ML algorithm has been determined and depicted in the result analysis section. The most effective ML model has been chosen for the proposed embedded system so that accuracy could be achieved at most. In case of semi supervised algorithm the feature selection is done as per the supervised algorithm. In this case the training is done same as the SML algorithm, but the testing phase is done like unsupervised machine learning algorithm where the decision parameter is predicted and ultimately matched with the previously achieved data of SML algorithm. The reliability of this approach is much more effective than simple SML algorithm. Conclusion: This study focused on predicting asthma risk in the Asansol-Durgapur industrial belt, India, using low-cost PM and gas sensors. Data calibration with meteorological inputs enhanced accuracy. ML models predicted risk and were refined through hyper-parameter tuning. Comparative analysis showed superior performance, emphasizing the importance of precise air quality monitoring. While offering a robust framework for future research, the study’s limitation lies in its area-specific dataset.

Critical infrastructure protection and national security are enhanced by the security and reliability of networks. Various types of information circulate on these networks, ranging in classification from open to closed. The consequences of cyberattacks on these networks can be severe, including reputational damage, financial loss, operational disruption and data leakage. Traditional security methods, such as firewalls and anti-virus software, are becoming less effective against modern and ever-changing cyber threats. As a result, powerful network intrusion detection systems (IDS) have become indispensable for proactive detection and mitigation of cyber attacks. Machine learning has become a viable method for creating adaptive intrusion detection tools that can detect new and complex attack patterns. By learning from huge labelled network traffic datasets, ML models can understand the subtle patterns and differentiating features of normal and abnormal or malicious traffic flows. This allows them to detect possible cyber threats and intrusions that traditional signature-based IDSs cannot detect. Extracting discriminative features and training appropriate classification models from such data is a challenging task. In the presented study, we analyse the effectiveness of ML algorithms for detecting cyberattacks, in particular distributed denial of service (DDoS) attacks, in network traffic data. In the presented study, a network attack detection system is developed using ML and deep learning (DL) models and experimented on the CICIDS2017 dataset. The main objectives of the study are to develop a strategy for extracting valuable information from raw network streams; to study the impact of data preparation on the false positive rate; and to conduct a comparative analysis of ML models for cyberattack detection. The main goal of the study is to provide an understanding of the development of a reliable adaptive network intrusion detection system using ML approaches that increase cybersecurity capabilities and protect against future cyberattacks.

Introduction: Anemia affects more than one billion people worldwide, with pregnant women and children under five years of age comprising the vast majority of those afflicted. The development of anemia is multifactorial and could stem from a variety of factors. Nutritional deficiencies especially iron, but also folate, vitamin B12, vitamin A, and protein appear to be the biggest factor. Diagnosing anemia in children under five years of age is of utmost importance because these nutrients are essential for their rapid phase of growth and development. Objective: The purpose of this study was to determine the prevalence of anemia in children under six years of age living in Dominica. Methods: This was a retrospective, descriptive study, examining the prevalence of anemia in preschool children, aged two to six years, living in Dominica from January 1, 2012 to December 31, 2015. All available medical records of the children were collected and analyzed using Stata version 14. There were no exclusion criteria. Results and discussion: A sample population of 635 children was included in our study. The majority of children was females (54.7%), at least 3.5 years old (60.6%), and attended preschool in the parish of Saint George (58.7%). Our study determined that the prevalence of anemia was 19.3%. Additionally, we found that 22% of anemic children had a mean corpuscular volume below 75 fL, and 78% of anemic children had a mean corpuscular volume between 76 fL and 99 fL. Conclusion: The data in this study demonstrated that childhood anemia in Dominica is widely prevalent, and represents a public health issue that needs to be addressed. According to our data, 22% of anemic children had a mean corpuscular volume below 75 fL indicating a microcytic anemia. Microcytic anemia could suggest diseases such as iron deficiency and thalassemia among many other causes. Additionally, 78% of anemic children had a mean corpuscular volume between 76 fL and 99 fL indicating a normocytic anemia. Normocytic anemia could suggest chronic disease and sickle cell anemia among many others. Due to limited resources, we were unable to determine the specific cause of anemia; however, future studies should be conducted so that strategies could be developed, on a national level, to resolve this childhood burden.

<p>Groundwater use for irrigation, stock and domestic purposes from shallow unconfined aquifers is rarely metered in most parts of the world despite significant increase in the rate of use in the recent decades. Most aquifers systems are poorly characterized and monitored rendering assessment of groundwater balance and informed management decision making difficult.</p><p>Advances in automated data collection through remote sensing and other technologies in the recent years, makes available pertinent data sets that can indirectly inform groundwater balance from which groundwater recharge and discharge can be estimated. Assimilating such data sets using traditional means would require simulating the physics across multiple domains including climate, surface water, unsaturated and saturated zones and may be untenable in most decision-making contexts.</p><p>Recent advances in Artificial Intelligence and Machine Learning techniques (AI/ML) have created the opportunity to estimate groundwater balance components probabilistically by considering the correlation and causal relationships with other climatic, hydrological and geospatial variables for which data sets are readily available, for example estimates of actual evapotranspiration from remote sensing data. Such machine learning-based models need not necessarily be underpinned by the explicit solutions of governing equations pertaining to the physical processes involved across multiple domains. These ML-based models can be used either independently or in combination with physically based models for retrospective or predictive assessments of groundwater balance components and quantification of recharge and discharge components including historical pumping rates from an aquifer.</p><p>This study develops ML-based groundwater balance estimators using machine learning based on suitable supervised learning algorithm for a selected unconfined aquifer system that spans across 16 districts in northwest Bangladesh region. The study uses daily precipitation data, evapotranspiration estimates using Moderate Resolution Imaging Spectroradiometer (MODIS) data, interpolated river stages, and weekly observed water levels from monitoring bores to train, test and validate a Deep Neural Network model implemented using PYTORCH.</p><p>Simulated groundwater levels obtained using the trained and tested ML models are used to estimate long-term groundwater storage changes in region and are compared to estimates from a numerical groundwater MODFLOW model developed and history-matched using Flopy and PEST++ frameworks. Both the ML and MODFLOW models are implemented for a rectangular grid with 1500 m × 1500 m cells.  The workflow scripted using PYTORCH and Flopy libraries enabled the ready comparison of ML and numerical models’ outputs and evaluate the applicability of ML models for groundwater balance simulation.</p><p> </p>

Machine learning (ML) has recently been used as an efficient surrogate to estimate different steps of performance‐based earthquake engineering (PBEE), from dynamic structural analysis to fragility and loss assessments. However, due to the varied data, models, and features in existing literature, the relative efficiency of ML models across different PBEE steps remains unclear. Additionally, the black‐box nature of advanced ML algorithms limits their ability to provide design‐oriented insights, hindering the broader application of ML in PBEE‐based design. This study provides a comprehensive comparison of the accuracy and explainability of design‐oriented ML models across different steps of PBEE using a consistent database of 621 steel moment frames with varying designs and geometry. Eight ML algorithms were used in a careful training workflow comprising feature selection, hyperparameter tuning, cross‐validation, and model inference. The sensitivity of model accuracy to representative PBEE outputs—maximum responses, median fragility, and expected annual loss—was assessed using statistical measures. In addition, the explainability of the best models for each step was examined to explore the relationship between design parameters and the corresponding PBEE output. The results show that while ML models can reasonably map design parameters to all different PBEE outputs, models accuracy was higher for drift responses, median fragilities, and component‐based loss metrics. In addition, the optimal algorithm remained the same across different PBEE steps, where support vector machines and random forests provided the highest accuracy with an average R2 of 0.93 and 0.91 over different outputs on the test set. Although the selected feature sets varied across outputs and algorithms, height, number of stories, fundamental period, and the minimum of the beams’ moment of inertia were influential for both models and notably affected different PBEE outputs.

This study aimed to apply four machine learning algorithms to develop the optimal model to predict decline in platelet count (DPC) after interventional closure in children with patent ductus arteriosus (PDA). Data from children with PDA who underwent successful transcatheter closure at the Second Affiliated Hospital of Wenzhou Medical University and Yuying Children's Hospital from January 2016, to December 2022, were collected. The cohort data were split into training and testing sets. DPC following the intervention is defined as a percentage DPC ≥25% [(baseline platelet count-nadir platelet count)/baseline platelet count]. The extra tree algorithm was used for feature selection and four ML algorithms [random forest (RF), adaptive boosting, extreme gradient boosting, and logistic regression] were established. Moreover, SHapley Additive exPlanation (SHAP) to explain the importance of features and the ML models. This study included 330 children who underwent successful transcatheter closure of PDA, of which 113 (34.2%) experienced DPC. After 62 clinical features were considered, the extra tree algorithm selected six clinical features to build the ML models. Amongst the four ML algorithms, the RF model achieved the greatest AUC. SHAP analysis revealed that pulmonary artery systolic pressure, size of defect and weight were the top three most important clinical features in the RF model. Furthermore, clinical descriptions of two children with PDA, with accurate predictions, and explanations of the prediction results were provided. In this study, an ML model (RF) capable of predicting post-intervention DPC in children with PDA undergoing transcatheter closure was established.

ObjectiveTo investigate a panel of variables using four machine learning based classifiers, i.e., support vector machine (SVM), random forest (RF), artificial neural network (ANN) and logistic regression (LR) to make a diagnosis of ovarian cancer, differentiating it from benign ovarian masses.Materials and methodsA prospective observational pilot study was done between November 2021 and June 2023. Following data pre-processing to ensure compatibility with ML models, four ML algorithms, i.e., support vector machine (SVM), logistic regression (LR), random forest (RF) and artificial neural network (ANN) were tested by multimodal parameters from the datasets of 50 patients presenting with suspected epithelial ovarian cancer (Group A) or benign ovarian tumour (Group B). Statistical analysis was done using STATA version 14.0.ResultsWe found that the machine learning approach could predict malignant tumours with appreciably high accuracy similar to a few studies done so far in this field. All four ML algorithms showed high level of accuracy with a maximum AUROC of 0.92 in the RF model. Both RF and SVM had an accuracy of 85.87 and 83.05%.ConclusionThe ML algorithms can detect ovarian cancers with a high level of accuracy. Further, a large-volume prospective study on large volume data sets is required before inclusion of ML algorithms in clinical practice.

Developing predictive models for surgical outcomes in patients with degenerative cervical myelopathy: a comparison of statistical and machine learning approaches

Two hundred eighty-five primary schoolgirls from the urban area of Thugba, Al-Khobar, in the Eastern Province of Saudi Arabia were examined anthropometrically. Hemoglobin estimations and laboratory...

Customer churn is a serious problem in the telecommunications industry and occurs more often. The cost of maintaining existing customers is much lower than attracting new customers, and the literature stated that five times the cost of maintaining existing customers have to be spent on attracting new customers. In this article, we have identified customers who intend to stop using the organization's services. One of the most important problems in predicting customer churn is the imbalanced data, which has been tried to be solved and compared with different methods. The machine learning algorithms used in this paper are Decision Tree, Support Vector Machine, Multi-Layer Perceptron, Random Forest, and Gradient Boosting. Data was balanced by random over-sampling, random under-sampling and SMOTE methods. The methods of over-sampling and under-sampling had appropriate and almost similar results in terms of the area under the receiver character curve (AUC) index, the method of under-sampling has shown the better specificity, and the method over-sampling has shown the better sensitivity. Also, the performance of random forest and gradient boosting algorithms were better than other algorithms.

Insurance fraud is one of the most practiced frauds in the sectors of the economy. Faced with increasingly imaginative underwriters to create fraud scenarios and the emergence of organized crime groups, the fraud detection process based on artificial intelligence remains one of the most effective approaches. Real world datasets are usually unbalanced and are mainly composed of "no-fraudulent" class with a very small percentage of "fraudulent" examples to train our model, thus prediction models see their performance severely degraded when the target class appears so poorly represented. Therefore, the present work aims to propose an approach that improves the relevance of the results of the best-known machine learning algorithms and deals with imbalanced classes in classification problems for prediction against insurance fraud. We use one of the most efficient approaches to re-balance training data: SMOTE. We adopted the supervised method applied to automobile claims dataset "carclaims.txt". We compare the results of the different measurements and question the results and relevance of the measurements in the field of study of unbalanced and labeled datasets. This work shows that the SMOTE Method with the KNN Algorithm can achieve better classifier performance in a True Positive Rate than the previous research. The goal of this work is to lead a study of algorithm selections and performance evaluation among different ML classification algorithms, as well as to propose a new approach TH-SMOTE for performance improvement using the SMOTE method by defining the optimum oversampling threshold according to the G-mean measure.

We found no published data in Angola regarding the effect of combining nutrition-specific and nutrition-sensitive approaches in the reduction of anemia in preschool children. Thus, we implemented a cluster-randomized controlled trial to determine the effectiveness of two educational-plus-therapeutic interventions, in Nutrition and WASH/Malaria, in reducing anemia. We compared them to (1) a test-and-treat intervention and (2) with each other. A block randomization was performed to allocate 6 isolated hamlets to 3 study arms. A difference-in-difference technique, using Fit Generalized estimating models, was used to determine differences between the children successfully followed in all groups, between 2015 and 2016. We found no significant differences in anemia´s and hemoglobin variability between educational and the control group. However, the WASH/Malaria group had 22.8% higher prevalence of anemia when compared with the Nutrition group, having also higher prevalence of P. falciparum. Thus, our results suggest that adding a 12-month educational Nutrition or a WASH/Malaria component to a test-and-treat approach may have a limited effect in controlling anemia. Possibly, the intensity and duration of the educational interventions were not sufficient to observe the amount of behavior change needed to stop transmission and improve the general child feeding practices.

Background/Aim: The aim of this study is to evaluate the function of diagnostic computer software designed for the detection of periapical lesions on panoramic images with deep learning methods. Material and Methods: In our study, more than 500 adult retrospective panoramic radiography images obtained randomly were evaluated, and periapical lesions were labeled on the radiographs with the ResultLab.Ai labeling program (ResultLab.AI, Istanbul, Turkey). All images have been rechecked and verified by Oral, Dental and Maxillofacial Radiology experts. The model used is a U-Net based architecture customized for dental radiographs and optimized for fast operation. What is meant by customization is the structures called "Attention Gate" added to the architecture to draw the model's attention to the lesions. Results: Mask estimation was made separately for each image and F1 and IoU scores were calculated by comparing them with the marked masks. A list was created from the calculated F1 and IoU scores. The F1 and IoU score of the entire data set was calculated by taking the average of the values in this list. In IoU score calculation, Keras library's Mean IoU metric was used to calculate for 2 classes. In the F1 score calculation, the F1 score metric of the SKLearn library was used to calculate the unweighted average for 2 classes. As a result, the IoU-Score was obtained as 0.8578 and the F1-Score as 0.8587. Conclusions: Detection of periapical lesions on panoramic radiographs with an artificial intelligence approach will help practitioners reach definitive conclusions even in lesions that are likely to be overlooked. In addition, success rates for deep learning methods improve as data set size grows. As the number of images rises, the training models' success rates will follow.

Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NWO Rubicon (452019308) Amsterdam Cardiovascular Sciences Background Left Ventricular Ejection Fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD) or benefit from an ICD. Machine (ML) and deep (DL) learning provide new opportunities for personalised predictions using complex, multi-modal physiological data. Objective We hypothesise that risk stratification for ICD implantation can be improved by ML and DL models that combine clinical variables with time series features from 12-lead electrocardiograms (ECG). Methods We present a multicentre study of 1010 patients with an ischaemic, dilated or non-ischaemic cardiomyopathy and LVEF≤35% implanted with an ICD between 2007 and 2021 for primary prevention of SCD (64.9 ±10.8 years, 73.2% male) in two academic hospitals. For each patient, raw 12-lead, 10-second ECG-recordings obtained <90 days before ICD implantation and clinical details were collected. Supervised ML and DL models were trained and validated using stratified k-fold cross-validation (5 repeats, k=10) on a development cohort (n=550) from Hospital A. We used this model to predict ICD non-benefit defined as mortality without prior appropriate ICD-therapy on an external dataset from Hospital B (n=460). Kaplan-Meier survival analysis stratified by high vs. low predicted probability using Youden's J statistic as cut-off was performed. Results At 3-year follow-up, 16.0% of patients had died of whom 72.8% met the criteria for ICD non-benefit. Extreme gradient boosting models identified subjects with ICD non-benefit with an area under the receiver operator curve (AUROC) of 0.897 ±0.05 during internal validation (Figure 1, solid line). In the external cohort, the AUROC was 0.793 (95% CI 0.75-0.84) (Figure 1, dashed line). Survival analysis for low vs. high predicted risk indicated ICD non-benefit rates of 6.0% versus 30.3% at 3-year follow-up, respectively (Figure 2). Conclusion A ML model that combined clinical with ECG features better predicted ICD non-benefit at 3-years in a primary prevention population than currently available risk scores such as the MADIT-ICD score. This approach may provide new tools to support personalized decision making for ICD therapy. Prospective validation is needed to assess the real-world clinical performance of the model.