Privacy-preserving multi-party logistic regression in cloud computing

Machine learning (ML) is combined with noninvasive parameters from coronary computed tomography angiography (CTA) to construct predictive models to identify culprit lesions that may lead to acute coronary syndrome (ACS). We retrospectively analyzed 132 patients with ACS at the Fourth Affiliated Hospital of Harbin Medical University who had coronary CTA between 3 months and 3 years before the ACS event, with a total of 240 lesions. Lesions from 2020 (n=154) were included in the training set, and lesions from 2021 (n=86) were included in the test set for internal validation. We evaluated the role of plaque characteristics, hemodynamic parameters and pericoronary adipose tissue (PCAT) attenuation from CTA in identifying culprit ACS lesions. In the training set, logistic regression was used to screen CTA-derived parameters with P values <0.05 for the model construction. Logistic regression, random forest, Bayesian and K-nearest neighbor algorithms were used to build classification models, and their performance was assessed using the test set. The following models were established to evaluate the effectiveness of different combinations of models to identify culprit lesions: Model 1 was established for plaque characteristics; Model 2 was established for hemodynamic parameters; Model 3 was established for PCAT attenuation; Model 4 was established for plaque characteristics and hemodynamic parameters; and Model 5 was established for plaque characteristics, hemodynamic parameters and PCAT attenuation. A total of ten high-risk factors were screened for the ML model construction, and the ML model based on the logistic regression algorithm had the best performance among the four algorithms (accuracy =0.721; sensitivity =0.892; specificity =0.592; positive prediction =0.623; and negative prediction =0.879). In this model, the minimum lumen area, positive remodeling and lesion-specific fat attenuation index (FAI) were the risk factors significantly associated with the culprit lesion. Analysis of the effect of different combinations of models to identify culprit lesions showed that Model 5 had the best predictive effect (AUC =0.819 and 95% CI: 0.722-0.916). ACS can be predicted using ML based on CTA parameters. Compared to other models, the model combining plaque characteristics, hemodynamic parameters and PCAT attenuation performed best in predicting the culprit lesion.

Background A correct and prompt diagnosis of coronary artery disease (CAD) is a crucial component of disease management to reduce the risk of death and improve the quality of life in patients with CAD. Currently, the American College of Cardiology (ACC)/American Heart Association (AHA) and the European Society of Cardiology (ESC) guidelines recommend selecting an appropriate pre-diagnosis test for an individual patient according to the CAD probability. The purpose of this study was to develop a practical pre-test probability (PTP) for obstructive CAD in patients with chest pain using machine learning (ML); also, the performance of ML-PTP for CAD is compared to the final result of coronary angiography (CAG). Methods We used a database from a single-center, prospective, all-comer registry designed to reflect real-world practice since 2004. All subjects underwent invasive CAG at our hospital in South Korea. We used logistic regression algorithms, random forest (RF), supporting vector machine, and K-nearest neighbor classification for the ML models. The dataset was divided into two consecutive sets according to the registration period to validate the ML models. ML training for PTP and internal validation used the first dataset registered between 2004 and 2012 (8,631 patients). The second dataset registered between 2013 and 2014 (1,546 patients) was used for external validation. The primary endpoint was obstructive CAD. Obstructive CAD was defined as having a stenosis diameter of greater than 70% on the quantitative CAG of the main epicardial coronary artery. Results We derived an ML-based model consisting of three different models according to the subject used to obtain the information, such as the patient himself (dataset 1), the community's first medical center (dataset 2), and doctors (dataset 3). The performance range of the ML-PTP models as the non-invasive test had C-statistics of 0.795 to 0.984 compared to the result of invasive testing via CAG in patients with chest pain. The training ML-PTP models were adjusted to have 99% sensitivity for CAD so as not to miss actual CAD patients. In the testing dataset, the best accuracy of the ML-PTP model was 45.7% using dataset 1, 47.2% using dataset 2, and 92.8% using dataset 3 and the RF algorithm. The CAD prediction sensitivity was 99.0%, 99.0%, and 98.0%, respectively. Conclusion We successfully developed a high-performance model of ML-PTP for CAD which is expected to reduce the need for non-invasive tests in chest pain. However, since this PTP model is derived from data of a single medical center, multicenter verification is required to use it as a PTP recommended by the major American societies and the ESC.

The Adoption of Artificial Intelligence (AI), Machine Learning (ML), Internet of Things (IoT), cloud services, web-based software systems, and other wireless sensor devices in the healthcare infrastructure have led to phenomenal improvements and benefits in the healthcare sector. Digital healthcare has ensured early diagnosis of the diseases, greater accessibility, and mass outreach in terms of treatment. Despite this unprecedented success, the privacy and confidentiality of the healthcare data have become a major concern for all the stakeholders. Data breach reports reveal that the healthcare data industry is one of the key targets of cyber invaders. In fact the last few years have registered an unprecedented rise in healthcare data breaches. Hacking incidents and privilege abuse are the most common threats and have exposed sensitive and protected health data. Experts and researchers are working on various techniques, tools, and methods to address the security issues related to healthcare data. In this article, the main focus is on evaluating the impact of research studies done in the context of healthcare data breach reports to identify the contemporary privacy and confidentiality issues of sensitive healthcare data. Analysis of the research studies depicts that there is a need for proactive security mechanisms that will help the healthcare organizations to identify abnormal user behavior while accessing healthcare data. Moreover, studies also suggest that ML techniques would be highly effective in securing the privacy and confidentiality of the healthcare data. Working further on this premise, the present study also proposes a conceptual framework that will secure the privacy and confidentiality of healthcare data proactively. The proposed framework is based on ML techniques to detect deviated user access against Electronic Health Records. Further, fuzzy-based Analytical Network Process (ANP), a multi-criteria decision-making approach, is used to assess the accuracy of the supervised and unsupervised ML approaches for achieving a dynamic digital healthcare data security environment.

The government has launched the latest innovation in data collection in the realm of population data which relies on digital technology through mobile applications using photos or QR codes which aims to reduce the use of physical prints of identity cards and the availability of blank KTPs with the aim of simplifying the administrative process and no longer requiring population documents. printing or saving in physical format such as an KTP file. In implementing the population identity application, some people feel anxious due to limited internet access, lack of knowledge about the application, as well as concerns about the security and privacy of identity data in digital format. This research aims to conduct sentiment analysis on reviews of digital population identity applications by comparing logistic regression and k-nearest neighbor algorithms. The dataset was taken using the Google Play Scraper library in Python which got 1700 raw data taken from 12-February to 26 March 2024 and then pre-processed and got 1108 clean data. The results of this research show that the comparison between the logistic regression algorithm and k-nearest neighbor algorithm shows that the k-nearest neighbor algorithm is better than the logistic regression algorithm with an accuracy result of 80.43%, a difference of 3.60% compared to k-nearest neighbor. So it can be concluded that the digital population identity application is still considered poor in its use because it has a negative sentiment of 73.9% and it can be seen in this research that the comparison results of the k-nearest neighbor algorithm prove that its performance is better than logistic regression

e17570 Background: Ovarian cancer(OC) is the leading cause of death from gynecologic malignancy. Current challenges include lack of diagnostic tools, predictive biomarkers, and identifying appropriate surgical candidates. Machine learning(ML) is an emerging field that can make accurate projections by making inferences on data and may play a crucial role in OC.The objective of the current study was to review the literature on application of ML in OC and report the most commonly used algorithms and their performance in comparison to existing prediction tools and traditional regression models. Methods: This is a systematic review of published literature from January 1985 to March 2021 on the use of ML in OC. An extensive search of electronic library databases was conducted. Four independent reviewers screened the articles initially by title then full text. Quality was assessed using the MINORS criteria. P-values were generated using the Pearson’s Chi-squared(x2) test to compare performance of ML models with traditional statistics. No p-values were reported if only one study was available. Results: Among 4,295 articles screened, 88 studies on ML in OC were included. The mean age of OC patients was 54.7 years(11-90) and the most common stages at diagnosis were:Stage III (39.9%) and IV (34%). Applications of ML were in clinical datasets(33%, n = 29), preoperative diagnostics(30.7%, n = 27), serum biomarkers (21.6%, n = 19), genomics (12.5%, n = 11), and prediction of cytoreductive outcomes (2.3%, n = 2). The most commonly applied algorithms were Support Vector Machine [SVM](28%, n = 33)and Neural Networks[NN] (25.28%). Over the past decades, the number of publications on ML in OC increased three-fold from 20(1994-2010) to 67 (2011–2021). Only 9 (10%) studies compared ML techniques with existing prediction tools, or traditional regression models. Among 29 clinical dataset studies, 4 compared ML with traditional logistic regression(LR). Two studies reported better performance with ML compared to LR but not significant(accuracy: 0.88 vs 0.84, p = 0.15), one study performed comparably(accuracy: 0.1 vs 0.1) while one study performed worse(accuracy: 0.1 vs 0.97). Only one preoperative diagnostic study compared ML techniques with LR. SVM classifiers outperformed LR in classifying ovarian masses as benign or malignant(sensitivity: 0.88 vs. 0.70). One serum biomarker study compared LR with ML algorithms; LR performed better using two biomarkers for predicting OC(accuracy: 0.97 vs. 0.94). Among five studies reporting overall survival outcomes, only one study compared survival ML techniques using NN with LR and showed that NN classifiers outperformed LR in predicting overall survival(AUC: 0.72 vs. 0.62). Conclusions: This is the first systematic review exploring the literature on ML algorithms in OC. Most ML models outperformed traditional models. However, larger datasets would be required to validate findings.

This paper addresses the problem of cyberbullying on various online discussion forums in the form of social commentary. Here, supervised machine learning algorithms are employed to detect whether a particular comment is an insult, threat or a hate message. First of all, a machine learning model is developed with Logistic Regression, Random forest and naive bayes algorithms for classification and then, both Voting and AdaBoost classifiers are applied on the developed model to observe which works best in this case. In Japan, the members of PTA (Parent Teacher Association) perform net-petrol with a manual website monitoring in order to catch and stop cyberbullying activities; however, doing all this manually is very time consuming and hectic process. The main contribution of this paper includes a mechanism to detect cyberbullying and by using supervised machine learning with logistic regression algorithm, model has achieved an accuracy of 82.7%. With voting classifier, an accuracy of 84.4% was observed. The evaluation results show that voting classifier outperforms all other algorithms in detecting cyberbullying.

Introduction: Breast cancer is one of the most common cancers among women compared to all other ones. Machine learning techniques can bring a large contribute on the process of prediction and early diagnosis of breast cancer, became a research hotspot and has been proved as a strong technique. Using machine learning models performed on multidimensional dataset, this article aims to find the most efficient and accurate machine learning models for tumor classification prediction.Materials &amp; Methods: Several supervised machine learning algorithms were utilized to diagnosis and prediction of cancer tumor such as Logistic Regression Decision Tree, Random Forest and KNN. The algorithms are applied to a dataset taken from the UCI repository including 699 samples. The dataset includes Breast cancer features. To enhance the algorithms’ performance, these features are analyzed, the feature importance score and cross validation are considered. In this paper ML algorithms improved coupled by limited and selective features to produce high classification accuracy in tumor classification.Results: As a result of evaluation, Logistic Regression algorithm with accuracy value equal to 99.14%, AUC ROC equal to 99.6%, Extra Tree algorithm with accuracy value equal to 99.14% and AUC ROC equal to 99.1% have better performance than other algorithms. therefore, these techniques can be useful for diagnosis and prediction of cancer tumor and prescribe it correctly.Conclusions: The technique of machine learning can be used in medicine for analyzing the related data collections to a disease and its prediction. The area under the ROC curve and evaluating criteria related to a number of classifying algorithms of machine learning to evaluate breast cancer and indeed, the diagnosis and prediction of breast cancer is compared to determine the most appropriate classifier.

The future 6G network will be able to connect massive and various unmanned vehicles (UxVs) into the network, bringing novel requirements toward UxV network security and data privacy. Deploying machine learning (ML)-based intrusion detection on UxVs can be one promising approach. The conventional approach cannot fulfill security and privacy requirements, as the structure can be more flexible, and there may be a lack of a central node in the 6G-based UxV network. Moreover, UxV clients can exhibit high heterogeneity with extremely class-imbalanced training samples. With the presence of federated learning (FL), UxVs can collaborate to train and update ML models while preserving data privacy in the UxV security critical scenario. However, most past works focused on centralized approaches, using cloud servers to assist intrusion detection and service deployments. This article introduces an FL framework with a decentralized design for training ML models on UxVs using intrusion detection as a study case. This scheme can be more flexible, as UxV clients can collaborate to train and synchronize models without the central server. Simulation experiments were conducted to evaluate the efficiency of the proposed approach. Experimental results and theoretical analysis confirm that the proposed method outperforms baseline models with FedAvg and local-trained client models.

In recent years, the pace of innovations in the fields of machine learning (ML) has accelerated, researchers in SysML have created algorithms and systems that parallelizeML training over multiple devices or computational nodes. As ML models become more structurally complex, many systems have struggled to provide allround performance on a variety of models. Particularly, ML scale-up is usually underestimated in terms of the amount of knowledge and time required to map from an appropriate distribution strategy to the model. Applying parallel training systems tocomplex models adds nontrivial development overheads in addition to model prototyping, and often results in lower-than-expected performance. This thesis identifies and addresses research challenges in both usability and performance in parallel ML techniques and system implementations. The first part of this thesis presents a simple design principle, adaptive parallelism, that applies suitable parallelization techniques to model building blocks (e.g. layers) according to their specific ML properties. Following it, we derive a series of optimizations and implementations optimizing different aspects of ML parallelization. We examine them and show that they significantly boost the efficiency or scalability of ML training on clusters 2-10x in their applicable scenarios. Generalizing this methodology, this second part of this thesis formulates the ML parallelization as an end-to-end optimization problem, and seeks to solve it automatically, for two broad paradigms of ML parallelization tasks: single-node dynamicbatching and distributed ML parallelisms. We present principled representations to express the two classes of ML parallelisms, along with composable system architectures,Cavs and AutoDist, respectively. They enable rapid compositions of parallelization strategies for unseen models, improve parallelization performance, and simplify parallel ML programming. On top of them, the third part of this thesis presents an automatic parallelization framework, AutoSync, to automatically optimize synchronization strategies indata-parallel distributed training. AutoSync achieves high performance “out-of-thebox” – it navigates the space spanned by the proposed representation, and automaticallyidentifies synchronization strategies that report 1.2 - 1.6x speedups over existing hand-optimized systems, lowering the technical barrier of distributed ML and helping make it accessible to a larger community of users. Collectively, the set of techniques and systems developed in this thesis lead to the proof of the concept and the prototype implementation of an end-to-end compiler system for large-scale ML training on distributed environments.

Untargeted plasma metabolomic profiling combined with machine learning (ML) may lead to discovery of metabolic profiles that inform our understanding of pediatric CKD causes. We sought to identify metabolomic signatures in pediatric CKD based on diagnosis: FSGS, obstructive uropathy (OU), aplasia/dysplasia/hypoplasia (A/D/H), and reflux nephropathy (RN). Untargeted metabolomic quantification (GC-MS/LC-MS, Metabolon) was performed on plasma from 702 Chronic Kidney Disease in Children study participants (n: FSGS=63, OU=122, A/D/H=109, and RN=86). Lasso regression was used for feature selection, adjusting for clinical covariates. Four methods were then applied to stratify significance: logistic regression, support vector machine, random forest, and extreme gradient boosting. ML training was performed on 80% total cohort subsets and validated on 20% holdout subsets. Important features were selected based on being significant in at least two of the four modeling approaches. We additionally performed pathway enrichment analysis to identify metabolic subpathways associated with CKD cause. ML models were evaluated on holdout subsets with receiver-operator and precision-recall area-under-the-curve, F1 score, and Matthews correlation coefficient. ML models outperformed no-skill prediction. Metabolomic profiles were identified based on cause. FSGS was associated with the sphingomyelin-ceramide axis. FSGS was also associated with individual plasmalogen metabolites and the subpathway. OU was associated with gut microbiome-derived histidine metabolites. ML models identified metabolomic signatures based on CKD cause. Using ML techniques in conjunction with traditional biostatistics, we demonstrated that sphingomyelin-ceramide and plasmalogen dysmetabolism are associated with FSGS and that gut microbiome-derived histidine metabolites are associated with OU.

To understand students’ learning behaviors, this study uses machine learning technologies to analyze the data of interactive learning environments, and then predicts students’ learning outcomes. This study adopted a variety of machine learning classification methods, quizzes, and programming system logs, found that students’ learning characteristics were correlated with their learning performance when they encountered similar programming practice. In this study, we used random forest (RF), support vector machine (SVM), logistic regression (LR), and neural network (NN) algorithms to predict whether students would submit on time for the course. Among them, the NN algorithm showed the best prediction results. Education-related data can be predicted by machine learning techniques, and different machine learning models with different hyperparameters can be used to obtain better results.

Betel nut addiction has become a psychoactive addiction to hundreds and millions of people around the world. Among the four common hallucinatory addictions in the world, betel nut addiction is one of them after tobacco, alcohol, and caffeine. It is more acute in the countries like Bangladesh, India, Pakistan and Taiwan. This ancient habit is much harmful to the human body as it contains substances like arecoline, which is more similar to nicotine. Consuming it on a repetitive basis causes the deformation of dental structure and change in the oral mucosa. Also, people have a risk of facing several diseases such as oral cancer, neck, and head cancer, submucous fibrosis, etc. by consuming it. Unfortunately, in Bangladesh, rural women are more addicted to this harmful practice. The purpose of this research is to detect betel nut addiction so that its disadvantages can be spread among the people. In this paper, the machine learning algorithms detect whether a person is addicted or not addicted to betel nut. Nowadays, machine learning is the most popular tool for using algorithms that compute data and learn from it for decision making or prediction about something. Thus, machine learning approach was chosen. The methodology has required data, which was collected manually by analyzing some factors from previous research papers on betel nut addiction. The k-nearest neighbor (kNN), Support Vector Machine (SVM), decision tree, logistic regression, random forest and Naive Bayes algorithm was used for classification and machine learning technique have been performed and evaluated them regarding performance matrices with a featured dataset. Among all the algorithms, random forest performs the best with the highest accuracy of about 99.0% with less training time.

Text categorization is an effective activity that can be accomplished using a variety of classification algorithms. In machine learning, the classifier is built by learning the features of categories from a set of preset training data. Similarly, deep learning offers enormous benefits for text classification since they execute highly accurately with lower-level engineering and processing. This paper employs machine and deep learning techniques to classify textual data. Textual data contains much useless information that must be pre-processed. We clean the data, impute missing values, and eliminate the repeated columns. Next, we employ machine learning algorithms: logistic regression, random forest, K-nearest neighbors (KNN), and deep learning algorithms: long short-term memory (LSTM), artificial neural network (ANN), and gated recurrent unit (GRU) for classification. Results reveal that LSTM achieves 92% accuracy outperforming all other model and baseline studies.

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.

Machine Learning (ML) is an Artificial Intelligence (AI) approach that allows systems to adapt to their environment based on past experiences. Machine Learning (ML) and Natural Language Processing (NLP) techniques are commonly used in sentiment analysis and Information Retrieval Techniques (IRT). This study supports the use of ML approaches, such as K-Means, to produce accurate outcomes in clustering and classification approaches. The main objective of this research is to explore the methods for sentiment classification and Information Retrieval Techniques (IRT). So, a combination of different machine learning algorithms is used with a dataset from amazon unlocked mobile reviews and telecom tweets to achieve better accuracy as it is crucial to consider the previous predictions related to sentiment classification and IRT. The datasets consist of user reviews ratings and algorithms utilized consist of K-Means Clustering algorithm, Logistic Regression (LR), Random Forest (RF), and Decision Tree (DT) algorithms. The amalgamation of each algorithm with the K-Means resulted in high levels of accuracy. Specifically, the K-Means combined with Logistic Regression (LR) yielded an accuracy rate of 99.98%. Similarly, the K-Means integrated with Random Forest (RF) resulted in an accuracy of 99.906%. Lastly, when the K-Means was merged with the Decision Tree (DT) Algorithm, the accuracy obtained was 99.83%.We exhibited that we could foresee efficient, effective, and accurate outcomes.