Decision Tree Logic Research Articles

Clinical Implementation of DIGEST as an Evidence-Based Practice Tool for Videofluoroscopy in Oncology: A Six-Year Single Institution Implementation Evaluation.

Clinical implementation of evidence-based practice (EBP) tools is a healthcare priority. The Dynamic Grade of Swallowing Toxicity (DIGEST) is an EBP tool developed in 2016 for videofluoroscopy in head and neck (H&N) oncology with clinical implementation as a goal. We sought to examine: (1) feasibility of clinical implementation of DIGEST in a national comprehensive cancer center, and (2) fidelity of DIGEST adoption in real-world practice. A retrospective implementation evaluation was conducted in accordance with the STARI framework. Electronic health record (EHR) databases were queried for all consecutive modified barium swallow (MBS) studies conducted at MD Anderson Cancer Center from 2016 to 2021. Implementation outcomes included: feasibility as measured by DIGEST reporting in EHR (as a marker of clinical use) and fidelity as measured by accuracy of DIGEST reporting relative to the decision-tree logic (penetration-aspiration scale [PAS], residue, and Safety [S] and Efficiency [E] grades). Contextual factors examined included year, setting, cancer type, MBS indication, and provider. 13,055 MBS were conducted by 29 providers in 7,842 unique patients across the lifespan in diverse oncology populations (69% M; age 1-96 years; 58% H&N cancer; 10% inpatient, 90% outpatient). DIGEST was reported in 12,137/13,088 exams over the 6-year implementation period representing 93% (95% CI: 93-94%) adoption in all exams and 99% (95% CI: 98-99%) of exams excluding the total laryngectomy population (n = 730). DIGEST reporting varied modestly by year, cancer type, and setting/provider (> 91% in all subgroups, p < 0.001). Accuracy of DIGEST reporting was high for overall DIGEST (incorrect SE profile 1.6%, 200/12,137), DIGEST-safety (incorrect PAS 0.4% 51/12,137) and DIGEST-efficiency (incorrect residue 1.2%, 148/12,137). Clinical implementation of DIGEST was feasible with high fidelity in a busy oncology practice across a large number of providers. Adoption of the tool across the lifespan in diverse cancer diagnoses may motivate validation beyond H&N oncology.

Computational modeling of aging-related gene networks: a review

The aging process is a complex and multifaceted phenomenon affecting all living organisms. It involves a gradual deterioration of tissue and cellular function, leading to a higher risk of developing various age-related diseases (ARDs), including cancer, neurodegenerative, and cardiovascular diseases. The gene regulatory networks (GRNs) and their respective niches are crucial in determining the aging rate. Unveiling these GRNs holds promise for developing novel therapies and diagnostic tools to enhance healthspan and longevity. This review examines GRN modeling approaches in aging, encompassing differential equations, Boolean/fuzzy logic decision trees, Bayesian networks, mutual information, and regression clustering. These approaches provide nuanced insights into the intricate gene-protein interactions in aging, unveiling potential therapeutic targets and ARD biomarkers. Nevertheless, outstanding challenges persist, demanding more comprehensive datasets and advanced algorithms to comprehend and predict GRN behavior accurately. Despite these hurdles, identifying GRNs associated with aging bears immense potential and is poised to transform our comprehension of human health and aging. This review aspires to stimulate further research in aging, fostering the innovation of computational approaches for promoting healthspan and longevity.

Establishment and validation of multiclassification prediction models for pulmonary nodules based on machine learning.

Lung cancer is the leading cause of cancer-related death worldwide. This study aimed to establish novel multiclassification prediction models based on machine learning (ML) to predict the probability of malignancy in pulmonary nodules (PNs) and to compare with three published models. Nine hundred fourteen patients with PNs were collected from four medical institutions (A, B, C and D), which were organized into tables containing clinical features, radiologic features and laboratory test features. Patients were divided into benign lesion (BL), precursor lesion (PL) and malignant lesion (ML) groups according to pathological diagnosis. Approximately 80% of patients in A (total/male: 632/269, age: 57.73 ± 11.06) were randomly selected as a training set; the remaining 20% were used as an internal test set; and the patients in B (total/male: 94/53, age: 60.04 ± 11.22), C (total/male: 94/47, age: 59.30 ±9.86) and D (total/male: 94/61, age: 62.0± 11.09) were used as an external validation set. Logical regression (LR), decision tree (DT), random forest (RF) and support vector machine (SVM) were used to establish prediction models. Finally, the Mayo model, Peking University People's Hospital (PKUPH) model and Brock model were externally validated in our patients. The AUC values of RF model for MLs, PLs and BLs were 0.80 (95% CI: 0.73-0.88), 0.90 (95% CI: 0.82-0.99) and 0.75 (95% CI: 0.67-0.88), respectively. The weighted average AUC value of the RF model for the external validation set was 0.71 (95% CI: 0.67-0.73), and its AUC values for MLs, PLs and BLs were 0.71 (95% CI: 0.68-0.79), 0.98 (95% CI: 0.88-1.07) and 0.68 (95% CI: 0.61-0.74), respectively. The AUC values of the Mayo model, PKUPH model and Brock model were 0.68 (95% CI: 0.62-0.74), 0.64 (95% CI: 0.58-0.70) and 0.57 (95% CI: 0.49-0.65), respectively. The RF model performed best, and its predictive performance was better than that of the three published models, which may provide a new noninvasive method for the risk assessment of PNs.

KASP-IEva: an intelligent typing evaluation model for KASP primers.

KASP marker technology has been used in molecular marker-assisted breeding because of its high efficiency and flexibility, and an intelligent evaluation model of KASP marker primer typing results is essential to improve the efficiency of marker development on a large scale. To this end, this paper proposes a gene population delineation method based on NTC identification module and data distribution judgment module to improve the accuracy of K-Means clustering, and introduces a decision tree to construct the KASP-IEva primer typing evaluation model. The model firstly designs the NTC identification module and data distribution judgment module to extract four types of data, grouping and categorizing to achieve the improvement of the distinguishability of amplification product signals; secondly, the K-Means algorithm is used to aggregate and classify the data, to visualize the five aggregated clusters and to obtain the morphology location eigenvalues; lastly, the evaluation criteria for the typing effect level are constructed, and the logical decision tree is used to make conditional discrimination on the eigenvalues in order to realize the score prediction. The performance of the model was tested by the KASP marker typing test results of 2519 groups of cotton varieties, and the following conclusions were obtained: the model is able to visualize the aggregation and classification effects of the amplification products of NTC, pure genotypes, heterozygous genotypes, and untyped genotypes, enabling rapid and accurate KASP marker typing evaluation. Comparing and analyzing the model evaluation results with the expert evaluation results, the average accuracy rate of the four grades evaluated by the model was 87%, and the overall evaluation results showed an uneven distribution of the grades with significant differential characteristics. When evaluating 2519 KASP fractal maps, the expert evaluation consumes 15 hours, and the model evaluation only uses 8min27.45s, which makes the model intelligent evaluation significantly better than the expert evaluation from the perspective of time. The establishment of the model will further enhance the application of KASP markers in molecular marker-assisted breeding and provide technical support for the large-scale screening and identification of excellent genotypes.

Prediction of Health Insurance Cross-Selling Through Binary Logical Regression and Decision Tree Model

Cross-selling is typically a marketing strategy used to identify a customer's various wants and then sell a range of related services or products by attending to those demands. Cross-marketing refers to a variety of tactics and procedures used to encourage cross-selling. The most crucial role in conventional banking and insurance is played by cross-selling. In most nations, auto insurance has traditionally played a significant role in the insurance market. This paper is based on information from all of a medical insurance company's clients and their automobiles throughout the course of a certain year. The binary logistic regression model and decision tree model are used to examine the customer's interest in purchasing auto insurance in the dichotomy, and the two techniques are compared to identify the most accurate prediction method. Through reasonable analysis of independent variables and dependent variables, the prediction accuracy of the binary logical regression model is 87.7% and that of the decision tree model is 87.6%. The accuracy of the two is similar.

LogicDT: a procedure for identifying response-associated interactions between binary predictors

Interactions between predictors play an important role in many applications. Popular and successful tree-based supervised learning methods such as random forests or logic regression can incorporate interactions associated with the considered outcome without specifying which variables might interact. Nonetheless, these algorithms suffer from certain drawbacks such as limited interpretability of model predictions and difficulties with negligible marginal effects in the case of random forests or not being able to incorporate interactions with continuous variables, being restricted to additive structures between Boolean terms, and not directly considering conjunctions that reveal the interactions in the case of logic regression. We, therefore, propose a novel method called logic decision trees (logicDT) that is specifically tailored to binary input data and helps to overcome the drawbacks of existing methods. The main idea consists of considering sets of Boolean conjunctions, using these terms as input variables for decision trees, and searching for the best performing model. logicDT is also accompanied by a framework for estimating the importance of identified terms, i.e., input variables and interactions between input variables. This new method is compared to other popular statistical learning algorithms in simulations and real data applications. As these evaluations show, logicDT is able to yield high prediction performances while maintaining interpretability.

The application of logical decision trees to the decision-making process in ill-structured problems

Decision-making is a process which has accompanied the human being since time immemorial and in various areas of their activity. It should result in making a choice that meets the expectations (conditions) of the decision maker to the greatest extent. Decisions can be made on the basis of information which is not always complete and reliable. Sometimes it may happen that it is incomplete and reliable or complete but unreliable. Then, it concerns ill-structured problems. The purpose of this article is to verify whether ill-structured problems can be solved/supported in a way based on an operating algorithm. In the article, a case study with complete but unreliable information as well as with complete and reliable information was used. Logical decision trees were employed in the study. The result of the study allowed for, among others, establishing that the analysis of an ill-structured problem using logical decision trees consists in performing steps which follow one another in a logical sequence creating thus a sequence of operations, and therefore an operating algorithm, which confirms that solving ill-structured problems can be supported/implemented using an algorithm.

Developing a natural language-based AI-chatbot for social work training: an illustrative case study

ABSTRACT A chatbot is a computer program designed to simulate conversation with human users. In social services, many chatbots are retrieval based: they analyse users’ intents and retrieve preset answers based on decision tree logic. A major limitation of these earlier chatbots was that their conversations were rigid, unnatural, and sounded like a multiple-choice questionnaire. Recent achievements in large-scale generative pretrained transformers (LGPTs) (e.g. GPT-3, Yuan 1.0) have offered new possibilities for chatbot development. Such technology provides a high-quality natural language experience, requires much less resource input than earlier chatbot technologies, and is much more accessible to the public. However, the use of LGPT-based cfhatbots in social work, particularly in a Chinese context, is uncommon or even absent. Using an illustrative case study, this article illustrates the initial development of an LGPT-based chatbot to support social work training in a Chinese context and discusses the possibilities for further development.

The voice of COVID-19: Breath and cough recording classification with temporal decision trees and random forests

Symbolic learning is the logic-based approach to machine learning, and its mission is to provide algorithms and methodologies to extract logical information from data and express it in an interpretable way. Interval temporal logic has been recently proposed as a suitable tool for symbolic learning, specifically via the design of an interval temporal logic decision tree extraction algorithm. In order to improve their performances, interval temporal decision trees can be embedded into interval temporal random forests, mimicking the corresponding schema at the propositional level. In this article we consider a dataset of cough and breath sample recordings of volunteer subjects, labeled with their COVID-19 status, originally collected by the University of Cambridge. By interpreting such recordings as multivariate time series, we study the problem of their automated classification using interval temporal decision trees and forests. While this problem has been approached with the same dataset as well as with other datasets, in all cases, non-symbolic learning methods (usually, deep learning-based) have been applied to solve it; in this article we apply a symbolic approach, and show that it does not only outperform the state-of-the-art obtained with the same dataset, but its results are also superior to those of most non-symbolic techniques applied on other datasets. As an added bonus, thanks to the symbolic nature of our approach, we are also able to extract explicit knowledge to help physicians characterize typical COVID-positive cough and breath.

Effect of Refined Perioperative Nursing on the Efficacy of Noninvasive Ventilation in Elderly Patients with Lung Cancer and Respiratory Failure.

NIV (noninvasive ventilation) is becoming more popular as a first-line treatment for older patients with lung cancer who are experiencing acute respiratory failure. In the ICU, older age is linked to worse results with mechanical breathing. When dealing with severely sick patients, noninvasive ventilation is beneficial. Due to the risk of NIV failure and the higher mortality induced by delayed intubation, it is difficult to apply to older patients, especially those with lung cancer and respiratory insufficiency. As a result, for a successful outcome, nurse interventions should be provided to patients during noninvasive ventilation. This paper proposes the application of integrated perioperative nursing models on the elderly patients with lung cancer and respiratory failure. We have applied three nursing models: peer support nursing model, multidisciplinary cooperative nursing model, and transcultural nursing theory. The effect of the proposed nursing model on the efficacy of NIV is evaluated using the Logical Decision Tree Regression (LDTR) model. It is optimized using Iterative Fruit Fly Optimization Algorithm (IFOA). The performance of the suggested system is analysed, and it is observed that the patients showed better surgical outcomes when provided with the integrated nursing models.

Marginal Attacks of Generating Adversarial Examples for Spam Filtering

Digit information has been used in many areas and has been widely spread in the Internet era because of its convenience. However, many ill-disposed attackers, such as spammers take advantage of such convenience to send unsolicited information, such as advertisements, frauds, and pornographic messages to mislead users and this might cause severe consequences. Although many spam filters have been proposed in detecting spams, they are vulnerable and could be misled by some carefully crafted adversarial examples. In this paper, we propose the marginal attack methods of generating such adversarial examples to fool a naive Bayesian spam filter. Specifically, we propose three methods to select sensitive words from a sentence and add them at the end of the sentence. Through extensive experiments, we show that the generated adversarial examples could largely reduce the filter’s detecting accuracy, e.g. by adding only one word, the accuracy could be reduced from 93.6% to 55.8%. Furthermore, we evaluate the transferability of the generated adversarial examples against other traditional filters such as logic regression, decision tree and linear support vector machine based filters. The evaluation results show that these filters’ accuracy is also reduced dramatically; especially, the decision tree based filter’s accuracy drops from 100% to 1.51% by inserting only one word.

Hybrid AI-assistive diagnostic model permits rapid TBS classification of cervical liquid-based thin-layer cell smears

Technical advancements significantly improve earlier diagnosis of cervical cancer, but accurate diagnosis is still difficult due to various factors. We develop an artificial intelligence assistive diagnostic solution, AIATBS, to improve cervical liquid-based thin-layer cell smear diagnosis according to clinical TBS criteria. We train AIATBS with >81,000 retrospective samples. It integrates YOLOv3 for target detection, Xception and Patch-based models to boost target classification, and U-net for nucleus segmentation. We integrate XGBoost and a logical decision tree with these models to optimize the parameters given by the learning process, and we develop a complete cervical liquid-based cytology smear TBS diagnostic system which also includes a quality control solution. We validate the optimized system with >34,000 multicenter prospective samples and achieve better sensitivity compared to senior cytologists, yet retain high specificity while achieving a speed of <180s/slide. Our system is adaptive to sample preparation using different standards, staining protocols and scanners.

Prediction of Students Performance using Machine learning

An enormous measure of computerized information is being produced over a wide assortment in the field of data mining strategies. The creation of student achievement prediction models to predict student performance in academic institutions is a key area of the development of Education Data Mining. A prediction system has been proposed by using their 10th, 12th and previous semester marks. The study is evaluated using Binomial logical regression, Decision tree, and Entropy and KNN classifier. In order to attain their higher score, this framework would assist the student to recognize their final grade and improve their academic conduct.

Monitoring of Gas Emissions in Light of an OEF Application

This study analyzes the possibility to use geophysical and geochemical parameters in an OEF (Operational Earthquake Forecasting) application correlated with short-term changes in seismicity rates using a magnitude–frequency relationship. Tectonic stress over the limits of rock elasticity generates earthquakes, but it is possible that the emission of gases increases as a result of the breaking process. The question is how reliable is the emission of radon-222 and Carbon Dioxide (CO2), with effects on air ionization and aerosol concentration, in an OEF application? The first step is to select the seismic area (in our study this is the Vrancea area characterized by deep earthquakes at the bend of the Carpathian Mountains), then determine the daily and seasonal evolution of the forecast parameters, their deviations from the normal level, the short-term changes in seismicity rates using a magnitude–frequency relationship and finally to correlate the data with recorded seismic events. The results of anomaly detection, effect evaluation and data analysis alert the beneficiaries specialized in emergency situations (Inspectorate for Emergency Situations, organizations involved in managing special events). Standard methods such as the standard deviation from the mean value, time gradient, cross correlation, and linear regression are customized for the geological specificity of the area under investigation. For detection we use the short-time-average through long-time-average trigger (STA/LTA) method on time-integral data and the daily–seasonal variation of parameters is correlated with atmospheric conditions to avoid false decisions. The probability and epistemic uncertainty of the gas emissions resulting from this study, in addition to other precursor factors such as air ionization, time between earthquakes, temperature in the borehole, telluric currents, and Gutenberg Richter “a-b” parameters, act as inputs into a logical decision tree, indicating the possibility of implementing an OEF application for the Vrancea area. This study is novel in its analysis of the Vrancea area and performs a seismic forecasting procedure in a new form compared to the known ones.

Detection of breast cancer tumours based on feature reduction and classification of thermograms

ABSTRACT The patients having malignant breast tumours if detected in early stage have a better chance of survival. It is observed that the analysis of the texture features of the breast thermograms helps in providing the right information for diagnosis to a greater extent. In this study, the breast thermograms of 56 subjects having temperature recordings available at Database Mastology Research (DMR), visual labs are considered. Further, the texture features in the Gray level Run Length Matrix (GLRLM) and Gray level Co-occurrence Matrix (GLCM) are extracted from these images. The correlation of features gives a linear relationship between the variables that help to analyse the quantitative relationship between the variables. The features are selected by using unsupervised feature reduction techniques, i.e. Principal Component Analysis (PCA) and Autoencoder (AE). The features selected are observed to be relevant in detecting the abnormality between healthy and unhealthy breast. Different classifiers viz. support vector machine, decision tree, random forest, K-NN, linear Regression, and fuzzy logic are then applied to the selected features for detecting the presence of malignancy in breast. Among all the classifiers, Random Forest (RF) with PCA has been observed to yield an accuracy of 95.45% in classifying the benign and malignant tumours.

Primitives as building blocks for constructing land cover maps

Land cover maps play an integral role in environmental management. However, countries and institutes encounter many challenges with producing timely, efficient, and temporally harmonized updates to their land cover maps. To address these issues we present a modular Regional Land Cover Monitoring System (RLCMS) architecture that is easily customized to create land cover products using primitive map layers. Primitive map layers are a suite of biophysical and end member maps, with land cover primitives representing the raw information needed to make decisions in a dichotomous key for land cover classification. We present best practices to create and assemble primitives from optical satellite using computing technologies, decision tree logic and Monte Carlo simulations to integrate their uncertainties. The concept is presented in the context of a regional land cover map based on a shared regional typology with 18 land cover classes agreed on by stakeholders from Cambodia, Laos PDR, Myanmar, Thailand, and Vietnam. We created annual map and uncertainty layers for the period 2000–2017. We found an overall accuracy of 94% when taking uncertainties into account. RLCMS produces consistent time series products using free long term historical Landsat and MODIS data. The customizable architecture can include a variety of sensors and machine learning algorithms to create primitives and the best suited smoothing can be applied on a primitive level. The system is transferable to all regions around the globe because of its use of publicly available global data (Landsat and MODIS) and easily adaptable architecture that allows for the incorporation of a customizable assembly logic to map different land cover typologies based on the user's landscape monitoring objectives

An evolutionary‐based approach for dealing with numerical and categorical attributes in ILP

AbstractInductive logic programming (ILP) induces concepts from a set of positive examples, a set of negative examples, and background knowledge. ILP has been applied on tasks such as natural language processing, finite element mesh design, network mining, robotics, and drug discovery. These data sets usually contain numerical and multivalued categorical attributes; however, only a few relational learning systems are capable of handling them in an efficient way. In this paper, we present an evolutionary approach, called Grouping and Discretization for Enriching the Background Knowledge (GDEBaK), to deal with numerical and multivalued categorical attributes in ILP. This method uses evolutionary operators to create and test numerical splits and subsets of categorical values in accordance with a fitness function. The best subintervals and subsets are added to the background knowledge before constructing candidate hypotheses. We implemented GDEBaK embedded in Aleph and compared it to lazy discretization in Aleph and discretization in Top‐down Induction of Logical Decision Trees (TILDE) systems. The results obtained showed that our method improves accuracy and reduces the number of rules in most cases. Finally, we discuss these results and possible lines for future work.

Decision Making using Logical Decision Tree and Binary Decision Diagrams: A Real Case Study of Wind Turbine Manufacturing

The wind energy industry is expanding in order to be able to meet the current and future energy demand, and is supported by governments in that renewable energy investment has been made. Optimal decision making (DM) in wind turbine manufacturing is required to guarantee the competitiveness of the business. This paper considers decision making for wind turbine manufacturing using a logical decision tree (LDT) and binary decision diagrams (BDD). A qualitative analysis of wind turbine manufacturing is carried out using logical decision trees. They are used for a qualitative study of the case study. Binary decision diagrams are used to obtain the Boolean function and, therefore, to carry out a quantitative analysis. Finally, an optimization of budgets is employed based on importance measures. There is no optimal method that can establish the importance measures. The following heuristic methods have been used to find a solution close to the optimal: Fussell-Vesely, Birnbaum and Criticality. The computational cost is reduced by ranking the events. The heuristic methods to establish the best rankings are: Top-Down-Left-Right, Level based method, AND based method, Breadth-First Search (BFS) and Depth First Search (DFS). A real case study is considered, in which a static and dynamic analysis is carried out.

Mapping Plantations in Myanmar by Fusing Landsat-8, Sentinel-2 and Sentinel-1 Data along with Systematic Error Quantification

Forests in Southeast Asia are experiencing some of the highest rates of deforestation and degradation in the world, with natural forest species being replaced by cropland and plantation monoculture. In this work, we have developed an innovative method to accurately map rubber and palm oil plantations using fusion of Landsat-8, Sentinel 1 and 2. We applied cloud and shadow masking, bidirectional reflectance distribution function (BRDF), atmospheric and topographic corrections to the optical imagery and a speckle filter and harmonics for Synthetic Aperture Radar (SAR) data. In this workflow, we created yearly composites for all sensors and combined the data into a single composite. A series of covariates were calculated from optical bands and sampled using reference data of the land cover classes including surface water, forest, urban and built-up, cropland, rubber, palm oil and mangrove. This training dataset was used to create biophysical probability layers (primitives) for each class. These primitives were then used to create land cover and probability maps in a decision tree logic and Monte-Carlo simulations. Validation showed good overall accuracy (84%) for the years 2017 and 2018. Filtering for validation points with high error estimates improved the accuracy up to 91%. We demonstrated and concluded that error quantification is an essential step in land cover classification and land cover change detection. Our overall analysis supports and presents a path for improving present assessments for sustainable supply chain analyses and associated recommendations.

Classification of rubberized coir fibres using deep learning-based neural fuzzy decision tree approach

Indian coir industry is one among the small-scale cottage industries which contributes a great amount to the economy of India. India and Sri Lanka are the top two international producers, and they account for 90% of world coir manufacturing. The modern digital technologies can monitor the physical, chemical and microbiological properties in agriculture sector and can analyse the data in a faster manner. This paper highlights the large opportunities of deep learning in agriculture as an intelligent method for classifying and predicting the quality of the raw materials and thereby correlating into suitable products in the agricultural sector. Here we gathered the dataset from Central Coir Research Institute, Alappuzha, tested the chemical properties and applied several decision tree algorithms on the dataset and compared for analysis. This paper focuses specifically on a hybrid method with the usage of the back-propagation in deep learning and fuzzy logic decision tree. Experimental results reveal that the proposed method shows an accuracy of 98.75%. The comparison results with various decision tree-based classification algorithms, such as C4.5, ID3, CART, Naive Bayes, fuzzy, MLP, verify the effectiveness of the proposed method.