Classifier Chains Research Articles

MAPRS: An intelligent approach for post-prescription review based on multi-label learning

Antimicrobial resistance (AMR) is a major threat to public health worldwide. It is a promising way to improve appropriate prescription by the review and stewardship of antimicrobials, and Post-Prescription Review (PPR) is currently the main tool used in hospitals. Existing methods of PPR typically focus on the dichotomy of antimicrobial prescription based on binary classification which, however, is usually a multi-label classification problem. Moreover, previous research did not explain the causes beneath the inappropriate antimicrobial used in the clinical setting, which could be practically important for problem location and decision improvement. In this paper, we collected antimicrobial prescriptions and related data from clean surgery in a hospital in northeastern China, and proposed a Multi-label Antimicrobial Post-Prescription Review System (MAPRS). MAPRS first uses NLP techniques to process unstructured data in prescriptions and explores the value of clinical record text for solving medical problems. Then, Classifier Chains are used to deal with multi-label problems and fused with machine learning algorithms to construct a classifier. At last, a SHAP explanation module is introduced to explain the inappropriate prescriptions. The experimental results show that MAPRS could achieve great performance in a challenging six-category multi-label task, with a subset accuracy of 90.7 % and an average AUROC of 94.3 %. Our results can help hospitals to perform intelligent prescription review and improve the antimicrobial stewardship.

Classifier Chains for LOINC Transcoding.

Mapping clinical observations and medical test results into the standardized vocabulary LOINC is a prerequisite for exchanging clinical data between health information systems and ensuring efficient interoperability. We present a comparison of three approaches for LOINC transcoding applied to French data collected from real-world settings. These approaches include both a state-of-the-art language model approach and a classifier chains approach. Our study demonstrates that we successfully improve the performance of the baselines using the classifier chains approach and compete effectively with state-of-the-art language models. Our approach proves to be efficient, cost-effective despite reproducibility challenges and potential for future optimizations and dataset testing.

Colorectal cancer prognosis based on dietary pattern using synthetic minority oversampling technique with K-nearest neighbors approach

Generally, a person’s life span depends on their food consumption because it may cause deadly diseases like colorectal cancer (CRC). In 2020, colorectal cancer accounted for one million fatalities globally, representing 10% of all cancer casualties. 76,679 males and 78,213 females over the age of 59 from ten states in the United States participated in this analysis. During follow-up, 1378 men and 981 women were diagnosed with colon cancer. This prospective cohort study used 231 food items and their variants as input features to identify CRC patients. Before labelling any foods as colorectal cancer-causing foods, it is ethical to analyse facts like how many grams of food should be consumed daily and how many times a week. This research examines five classification algorithms on real-time datasets: K-Nearest Neighbour (KNN), Decision Tree (DT), Random Forest (RF), Logistic Regression with Classifier Chain (LRCC), and Logistic Regression with Label Powerset (LRLC). Then, the SMOTE algorithm is applied to deal with and identify imbalances in the data. Our study shows that eating more than 10 g/d of low-fat butter in bread (RR 1.99, CI 0.91–4.39) and more than twice a week (RR 1.49, CI 0.93–2.38) increases CRC risk. Concerning beef, eating in excess of 74 g of beef steak daily (RR 0.88, CI 0.50–1.55) and having it more than once a week (RR 0.88, CI 0.62–1.23) decreases the risk of CRC, respectively. While eating beef and dairy products in a daily diet should be cautious about quantity. Consuming those items in moderation on a regular basis will protect us against CRC risk. Meanwhile, a high intake of poultry (RR 0.2, CI 0.05–0.81), fish (RR 0.82, CI 0.31–2.16), and pork (RR 0.67, CI 0.17–2.65) consumption negatively correlates to CRC hazards.

A novel bayesian network-based ensemble classifier chains for multi-label classification

In this paper, we address the challenges of random label ordering and limited interpretability associated with Ensemble Classifier Chains (ECC) by introducing a novel ECC method, ECC-MOO&BN, which integrates Bayesian Networks (BN) and Multi-Objective Optimization (MOO). This approach is designed to concurrently overcome these ECC limitations. The ECC-MOO&BN method focuses on extracting diverse and interpretable label orderings for the ECC classifier. We initiated this process by employing mutual information to investigate label relationships and establish the initial structures of the BN. Subsequently, an enhanced NSGA-II algorithm was applied to develop a series of Directed Acyclic Graphs (DAGs) that effectively balance the likelihood and complexity of the BN structure. The rationale behind using the MOO method lies in its ability to optimize both complexity and likelihood simultaneously, which not only diversifies DAG generation but also helps avoid overfitting during the production of label orderings. The DAGs, once sorted topologically, yielded a series of label orderings, which were then seamlessly integrated into the ECC framework for addressing multi-label classification (MLC) problems. Experimental results show that when benchmarked against eleven leading-edge MLC algorithms, our proposed method achieves the highest average ranking across seven evaluation criteria on nine out of thirteen MLC datasets. The results of the Friedman test and Nemenyi test also indicate that the performance of the proposed method has a significant advantage compared to other algorithms.

Classifier chain-based monitoring method for multivariate surgical outcomes

Risk-adjusted control charts were considered to be the most effective method for monitoring surgical outcomes in previous studies. However, existing methods focus only on monitoring postoperative mortality, while ignoring other important outcome indicators. In this paper, we develop a new monitoring model based on a multi-label learning framework to monitor multivariate surgical outcomes. The monitoring model is based on the Classifier Chain in multi-label learning to depict the unidirectional correlations between multiple outcome indicators. Comparing the proposed chart to existing multivariate methods, simulation results demonstrate that the proposed chart is more effective at detecting small changes in surgical risk. The proposed method is also more stable than a univariate control chart that only measures mortality risk. The utility of our chart was demonstrated by using a data set of the Surgical Outcome Monitoring and Improvement Program in Hong Kong.

A model for identifying potentially inappropriate medication used in older people with dementia: a machine learning study.

Older adults with dementia often face the risk of potentially inappropriate medication (PIM) use. The quality of PIM evaluation is hindered by researchers' unfamiliarity with evaluation criteria for inappropriate drug use. While traditional machine learning algorithms can enhance evaluation quality, they struggle with the multilabel nature of prescription data. This study aimed to combine six machine learning algorithms and three multilabel classification models to identify correlations in prescription information and develop an optimal model to identify PIMs in older adults with dementia. This study was conducted from January 1, 2020, to December 31, 2020. We used cluster sampling to obtain prescription data from patients 65 yearsand older with dementia. We assessed PIMs using the 2019 Beers criteria, the most authoritative and widely recognized standard for PIM detection. Our modeling process used three problem transformation methods (binary relevance, label powerset, and classifier chain) and six classification algorithms. We identified 18,338 older dementia patients and 36 PIMs types. The classifier chain + categorical boosting (CatBoost) model demonstrated superior performance, with the highest accuracy (97.93%), precision (95.39%), recall (94.07%), F1 score (95.69%), and subset accuracy values (97.41%), along with the lowest Hamming loss value (0.0011) and an acceptable duration of the operation (371s). This research introduces a pioneering CC + CatBoost warning model for PIMs in older dementia patients, utilizing machine-learning techniques. This model enables a quick and precise identification of PIMs, simplifying the manual evaluation process.

Business text classification with imbalanced data and moderately large label spaces for digital transformation

Digital transformation refers to an organization’s use of digital technology to improve its products, services, and operations, aligning them with evolving business requirements. To demonstrate this transformative process, we present a real-life case study where a company seeks to automate the classification of their textual data rather than relying on manual methods. Transitioning to automated classification involves deploying machine learning models, which rely on pre-labeled datasets for training and making predictions on new data. However, upon receiving the dataset from the company, we faced challenges due to the imbalanced distribution of labels and moderately large label spaces. To tackle text classification with such a business dataset, we evaluated four distinct methods for multi-label text classification: fine-tuned Bidirectional Encoder Representations from Transformers (BERT), Binary Relevance, Classifier Chains, and Label Powerset. The results revealed that fine-tuned BERT significantly outperformed the other methods across key metrics like Accuracy, F1-score, Precision, and Recall. Binary Relevance also displayed competence in handling the dataset effectively, while Classifier Chains and Label Powerset exhibited comparatively less impressive performance. These findings highlight the remarkable effectiveness of fine-tuned BERT model and the Binary Relevance classifier in multi-label text classification tasks, particularly when dealing with imbalanced training datasets and moderately large label spaces. This positions them as valuable assets for businesses aiming to automate data classification in the digital transformation era.

Multi-label classification with XGBoost for metabolic pathway prediction

BackgroundMetabolic pathway prediction is one possible approach to address the problem in system biology of reconstructing an organism’s metabolic network from its genome sequence. Recently there have been developments in machine learning-based pathway prediction methods that conclude that machine learning-based approaches are similar in performance to the most used method, PathoLogic which is a rule-based method. One issue is that previous studies evaluated PathoLogic without taxonomic pruning which decreases its performance.ResultsIn this study, we update the evaluation results from previous studies to demonstrate that PathoLogic with taxonomic pruning outperforms previous machine learning-based approaches and that further improvements in performance need to be made for them to be competitive. Furthermore, we introduce mlXGPR, a XGBoost-based metabolic pathway prediction method based on the multi-label classification pathway prediction framework introduced from mlLGPR. We also improve on this multi-label framework by utilizing correlations between labels using classifier chains. We propose a ranking method that determines the order of the chain so that lower performing classifiers are placed later in the chain to utilize the correlations between labels more. We evaluate mlXGPR with and without classifier chains on single-organism and multi-organism benchmarks. Our results indicate that mlXGPR outperform other previous pathway prediction methods including PathoLogic with taxonomic pruning in terms of hamming loss, precision and F1 score on single organism benchmarks.ConclusionsThe results from our study indicate that the performance of machine learning-based pathway prediction methods can be substantially improved and can even outperform PathoLogic with taxonomic pruning.

Data‐Driven Decision Algorithm for Open Caisson Foundation Construction

The accuracy of instructions for the extraction of large open caissons directly affects the construction quality and safety. This study is focused on developing a smart construction methodology for predicting open caisson excavation instructions. The proposed approach aims to reduce the errors in excavation instructions attributable to the subjective and varying experiences of decision‐makers. The multilabel classification task of predicting the instructions of large open caisson excavation is accomplished through the problem analysis. The study conducted a comparative analysis of a multilayer perceptron model, a classifier chain model, and a multilabel K‐nearest neighbor model (MLKNN) based on Hamming loss and accuracy. The results revealed that MLKNN exhibits significant differences from the other models and is most suitable for predicting open caisson excavation instructions. Furthermore, the traditional MLKNN model was improved by refining the normalization and distance measurement methods for the open caisson scenario. The prediction accuracy of the improved MLKNN model is 89.04% for the excavation instructions and 98.63% for the nonexcavation decisions. The successful prediction of excavation instructions for a large open caisson can compensate for the lack of data mining capability of the existing monitoring system. This can reduce construction risks. Finally, this study discussed the robustness of the improved MLKNN in a real project, highlighting the model’s high accuracy during the midstage of open caisson construction.

Enhanced approach of multilabel learning for the Arabic aspect category detection of the hotel reviews

AbstractIn many fields, like aspect category detection (ACD) in aspect‐based sentiment analysis, it is necessary to label each instance with more than one label at the same time. This study tackles the multilabel classification problem in the ACD task for the Arabic language. For this purpose, we used Arabic hotel reviews from the SemEval‐2016 dataset, comprising 13,113 annotated tuples provided for training (10,509) and testing (2,604). To extract valuable information, we first propose specific data preprocessing. Then, we suggest using the dynamic weighted loss function and a data augmentation method to fix the problem with this dataset's imbalance. Using two possible approaches, we develop new ways to find different categories of things in a review sentence. The first is based on classifier chains using machine learning models. The second is based on transfer learning using pretrained AraBERT fine‐tuning for contextual representation. Our findings show that both approaches outperformed the related works for ACD on the Arabic SemEval‐2016. Moreover, we observed that AraBERT fine‐tuning performed much better and achieved a promising ‐score of .

A filter-based feature selection approach in multilabel classification

Multi-label classification is a fast-growing field of machine learning. Recent developments have shown several applications, including social media, healthcare, bio-molecular analysis, scene, and music classification associated with the multilabel classification. In classification problems, multiple labels (multilabel or more than one class label) are assigned to an unseen record instead of a single-label class assignment. Feature selection is a preprocessing phase used to identify the most relevant features that could improve the accuracy of the multilabel classifiers. The focus of this study is the feature selection method in multilabel classification. The study used a feature selection filter method involving the Fisher score, analysis of variance test, mutual information, Chi-Square, and ensembles of these statistical methods. An extensive range of machine learning algorithms is applied in the modelling phase of a multilabel classification model that includes binary relevance, classifier chain, label powerset, binary relevance KNN, multi-label twin support vector machine, multi-label KNN. Besides, label space partitioning and majority voting of ensemble methods are used and Random Forest is the base learner. The experiments are carried out over five different multilabel benchmarking datasets. The evaluation of the classification model is measured using accuracy, precision, recall, F1 score, and hamming loss. The study demonstrated that the filter methods (i.e. mutual information) having top weighted to features provided significant outcomes.

Knowledge Graph-Based Prediction of Potentially Inappropriate Medication

To improve the accuracy of potentially inappropriate medication (PIM) prediction, a PIM prediction model that combines knowledge graph and machine learning was proposed. Firstly, based on Beers criteria 2019 and using the knowledge graph as the basic structure, a PIM knowledge representation framework with logical expression capabilities was constructed, and a PIM inference process was implemented from patient information nodes to PIM nodes. Secondly, a machine learning prediction model for each PIM label was established based on the classifier chain algorithm, to learn the potential feature associations from the data. Finally, based on a threshold of sample size, a portion of reasoning results from the knowledge graph was used as output labels on the classifier chain to enhance the reliability of the prediction results of low-frequency PIMs. 11 741 prescriptions from 9 medical institutions in Chengdu were used to evaluate the effectiveness of the model. Experimental results show that the accuracy of the model for PIM quantity prediction is 98.10%, the F1 is 93.66%, the Hamming loss for PIM multi-label prediction is 0.06%, and the macroF1 is 66.09%, which has higher prediction accuracy than the existing models. The method proposed has better prediction performance for potentially inappropriate medication and significantly improves the recognition of low-frequency PIM labels.

ECC + +: An algorithm family based on ensemble of classifier chains for classifying imbalanced multi-label data

Multi-label learning has attracted a great deal of research interests as it has a wide range of real-world applications. Although many multi-label learning methods have been proposed, very few of them have addressed the problem of class imbalance distribution in multi-label data. Moreover, most of the existing class imbalance multi-label learning algorithms only focus on solving the class imbalance problem, without taking into account the correlations among labels. To address these issues simultaneously, we propose to combine the well-known ensemble of classifier chain (ECC) algorithm with various binary-class imbalance learning techniques such as sampling, cost-sensitive learning, and threshold moving. This approach creates a new algorithm family called ECC++, designed specifically for class imbalance multi-label learning. ECC is already an excellent ensemble high-order binary relevance multi-label learning algorithm that is well-suited to exploiting correlations among labels. Combining it with binary-class imbalance learning techniques enables each link in a classifier chain (CC) to overcome the negative effect of skewed data distribution. ECC++ is a dynamic algorithm family that can be extended arbitrarily by applying any new binary-class imbalance learning techniques. To demonstrate the effectiveness and superiority of the proposed ECC++ algorithm family, we developed several ECC++ family members using some popular binary-class imbalance learning techniques. We then compared them with several state-of-the-art class imbalance multi-label learning algorithms on twelve benchmark and four real-world multi-label datasets. Our experimental results showed the effectiveness and superiority of the proposed ECC++ algorithm family over existing class imbalance multi-label learning algorithms. In conclusion, the proposed ECC++ algorithm family combines the strengths of the well-established ECC algorithm and binary-class imbalance learning techniques, resulting in a superior methodology for class imbalance multi-label learning.

Tagging Multi-Label Categories to Points of Interest From Check-In Data

Category tag of Point Of Interest (POI) serves a crucial role in numerous Location Based Services (LBS) like finding a place of interest, POI recommendation, location-based advertisement, etc. However, it has been found that many POIs (around 30%) do not have any category information. Manual tagging of these categories is a very costly affair as it requires a physical visit to each POI. Hence, an automated method for category tagging of POIs has been identified as an important research problem. The problem of category tagging of POIs is still in its primary stage, requiring further exploration. In this work, we solve the problem in three broad steps i). feature identification, ii). feature extraction, and iii). tag assignment. For the first step, we consider sequential features, temporal features, and spatial features, which can be constructed using check-in data. For the second step, we generate POI embedding representing its features, using a graph-based unsupervised approach. For the final step, the problem is considered a multi-label classification problem. For this, we have used Classifier Chain algorithms which preserves inter-tag correlation. Comparison with state-of-the-art methodologies along with multiple variants of features and classification algorithms show a significant improvement of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$5-34\%$</tex-math></inline-formula> by standard metric of average F1-score.

Multiple voice disorders in the same individual: Investigating handcrafted features, multi-label classification algorithms, and base-learners

Non-invasive acoustic analyses of voice disorders have been at the forefront of current biomedical research. Usual strategies, essentially based on machine learning (ML) algorithms, commonly classify a subject as being either healthy or pathologically-affected. Nevertheless, the latter state is not always a result of a sole laryngeal issue, i.e., multiple disorders might exist, demanding multi-label classification procedures for effective diagnoses. Consequently, the objective of this paper is to investigate the application of five multi-label classification methods based on problem transformation to play the role of base-learners, i.e., Label Powerset, Binary Relevance, Nested Stacking, Classifier Chains, and Dependent Binary Relevance with Random Forest (RF) and Support Vector Machine (SVM), in addition to a Deep Neural Network (DNN) from an algorithm adaptation method, to detect multiple voice disorders, i.e., Dysphonia, Laryngitis, Reinke’s Edema, Vox Senilis, and Central Laryngeal Motion Disorder. Receiving as input three handcrafted features, i.e., signal energy (SE), zero-crossing rates (ZCRs), and signal entropy (SH), which allow for interpretable descriptors in terms of speech analysis, production, and perception, we observed that the DNN-based approach powered with SE-based feature vectors presented the best values of F1-score among the tested methods, i.e., 0.943, as the averaged value from all the balancing scenarios, under Saarbrücken Voice Database (SVD) and considering 20% of balancing rate with Synthetic Minority Over-sampling Technique (SMOTE). Finally, our findings of most false negatives for laryngitis may explain the reason why its detection is a serious issue in speech technology. The results we report provide an original contribution, allowing for the consistent detection of multiple speech pathologies and advancing the state-of-the-art in the field of handcrafted acoustic-based non-invasive diagnosis of voice disorders.

Prediction of rhinitis based on label-links classifier chain using feature-block

Rhinitis is a common chronic inflammation of the upper respiratory tract with multiple symptoms and signs. The clinical classification of rhinitis is a multi-label classification, characterized by high dimensionality, poor correlation and class imbalance. Low recognition rate and poor generalization performance often occur for minority class instances. Therefore, this paper proposes a Feature-Block classification model, MBLCC based on Label-Links Classifier Chain. We apply kernel density estimation and Deborah Hellinger distance to partition allergic rhinitis instance with similar characteristics, calculate the correlation matrix of label characteristics, build an ordered classification chain for each block, and integrate the predictions of each block classifiers by evidence theory as the outcome. The cross-validation experiments conducted on 2231 cases of clinical rhinitis show that the evaluation indicators of MBLCC, i.e. sensitivity, specificity, accuracy, F1-score, and G-Mean, are 91.80 %, 96.8 %, 96.9 %, 0.925, and 0.941 respectively. In comparison with the other baselines, MBLCC achieves better generalization performance and is more effective and rapid in early clinical diagnosis of rhinitis. In addition, we calculate the feature importance ranking for rhinitis features via Label-Links Classifier Chain on the grounds of the purity of nodes in decision-making tree inside Random Forest and study the correlation between rhinitis features and classification that can provides the reference for the clinical rhinitis diagnosis.

Multilabel Classifier Chains Algorithm Based on Maximum Spanning Tree and Directed Acyclic Graph

The classifier chains algorithm is aimed at solving the multilabel classification problem by composing the labels into a randomized label order. The classification effect of this algorithm depends heavily on whether the label order is optimal. To obtain a better label ordering, the authors propose a multilabel classifier chains algorithm based on a maximum spanning tree and a directed acyclic graph. The algorithm first uses Pearson's correlation coefficient to calculate the correlation between labels and constructs the maximum spanning tree of labels, then calculates the mutual decision difficulty between labels to transform the maximum spanning tree into a directed acyclic graph, and it uses topological ranking to output the optimized label ordering. Finally, the authors use the classifier chains algorithm to train and predict against this label ordering. Experimental comparisons were conducted between the proposed algorithm and other related algorithms on seven datasets, and the proposed algorithm ranked first and second in six evaluation metrics, accounting for 76.2% and 16.7%, respectively. The experimental results demonstrated the effectiveness of the proposed algorithm and affirmed its contribution in exploring and utilizing label-related information.

Decision system for copper flotation backbone process

This study proposed a decision system that can output the flotation backbone flowchart using the natural properties of copper ore. The proposed decision system includes three decision tasks: product scheme, flotation scheme and grinding scheme. Each decision task is a multi-label classification problem. To improve the classification effect of each sub-label, extreme gradient boosting (XGBoost) is used as a subclassifier, because of its ability to deal with small and high-dimensional samples. To selectively utilize the relations between the sub-labels in the same task, a modified classifier chain (MCC) was proposed. To specifically use the effect of a front-end task on a back-end task, the decision system connects the MCC-XGBoost corresponding to the three tasks in series. Accordingly, the outputs of a front-end task becomes the candidate features of a back-end task. To improve the recall rates of minority classes, the classification thresholds are customized using the Yoden index. Finally, the high performance of the decision system was demonstrated by hypothesis testing.

BRMCF: Binary Relevance and MLSMOTE Based Computational Framework to Predict Drug Functions From Chemical and Biological Properties of Drugs.

In silico machine learning based prediction of drug functions considering the drug properties would substantially enhance the speed and reduce the cost of identifying promising drug leads. The drug function prediction capability of different drug properties happens to be different. So assessing these is advantageous in drug discovery. The task of drug function prediction is multi-label in nature reason being, in case of several drugs, multiple functions are associated with a drug. A number of existing works have ignored this inherent multi-label nature of the problem in context of addressing the issue of class imbalance. In the present work, a computational framework named as BRMCF has been proposed for analysing the prediction capability of chemical and biological properties of drugs toward drug functions in view of multi-label nature of problem. It employs Binary Relevance (BR) approach along with five base classifiers for handling the multi-label prediction task and MLSMOTE for addressing the issue of class imbalance. The proposed framework has been validated and compared with BR, Classifier Chains (CC) and Deep Neural Network (DNN) method on four drug properties datasets: SMILES Strings (SS) dataset, 17 Molecular Descriptors (17MD) dataset, Protein Sequences (PS) dataset and drug perturbed Gene EXpression Profiles (GEX) dataset. The analysis of results shows that the proposed framework BRMCF has outperformed BR, CC and DNN method in terms of exact match ratio, precision, recall, F1-score, ROC-AUC which signifies the effectiveness of MLSMOTE. Further, assessment of prediction capability of different drug properties is done and they are ranked as SS GEX PS 17MD. Additionally, the visualization and analysis of drug function co-occurrences signify the appropriateness of the proposed framework for drug function co-occurrence detection and in signaling the new possible drug leads where the detection rate varies from 94.34% to 99.61%.

Predicting and characterising persuasion strategies in misinformation content over social media based on the multi-label classification approach

Persuasion aims at affecting the audience’s attitude and behaviour through a series of messages containing persuasion strategies. In the context of misinformation spread, identifying the persuasion strategies is important in order to warn people to be aware of the analogous persuasion attempts in the future. In this work, we address the prediction of persuasion strategies in micro-blogging posts through a multi-label classification approach based on a variety of lexical and semantic features. We conduct our experiments using a set of well-known multi-label classification algorithms, including multi-label decision tree, multi-label k-nearest neighbours, multi-label random forest, binary relevance and classifier chains. The results show that the model incorporating classifier chains and XGBoost algorithm achieves the best subset accuracy of 0.779 and the highest macro F1-score of 0.847. In addition, we evaluated and compared the features’ importance for different persuasion strategies and analysed the major errors of miss-out prediction. The findings of this article provide a benchmark for the multi-label classification of persuasion strategies in micro-blogging posts and lead to a better understanding of different persuasion attempts contained in social media misinformation.