Exploring the use of association rules in random forest for predicting heart disease

Heart disease is one of the most dangerous diseases in the world. People with these diseases, most of them end up losing their lives. Therefore, machine learning algorithms have proven to be useful in this sense to help decision-making and prediction from the large amount of data generated by the healthcare sector. In this work, we have proposed a novel method that allows increasing the performance of the classical random forest technique so that this technique can be used for the prediction of heart disease with its better performance. We used in this study other classifiers such as classical random forest, support vector machine, decision tree, Naïve Bayes, and XGBoost. This work was done in the heart dataset Cleveland. According to the experimental results, the accuracy of the proposed model is better than that of other classifiers with 83.5%.This study contributed to the optimization of the random forest technique as well as gave solid knowledge of the formation of this technique.

The lower He-sea points playing a significant role in postoperative ileus in colorectal cancer treated with acupuncture: based on machine-learning

Background

Postoperative ileus (POI) is a common complication following abdominal surgery, which can lead to significant negative impacts on patients' well-being and healthcare costs. However, the efficacy of current treatments is not satisfactory. The purpose of this study was to evaluate the therapeutic effects of acupuncture intervention and explore the regulation of acupoint selection for treating POI in colorectal cancer (CRC) patients.

Methods

We searched eight electronic databases to identify randomized controlled trials (RCTs) on acupuncture for POI in CRC and conducted a meta-analysis. Subsequently, we utilized the Apriori algorithm and the Frequent pattern growth algorithm, in conjunction with complex network and cluster analysis, to identify association rules of acupoints.

Results

The meta-analysis showed that acupuncture led to significant reductions in time to first defecation (MD=-20.93, 95%CI: -25.35, -16.51; I2 = 93.0%; p < 0.01; n=2805), first flatus (MD=-15.08, 95%CI: -18.39, -11.76; I2 = 96%; p < 0.01; n=3284), and bowel sounds recovery (MD=-10.96, 95%CI: -14.20, -7.72; I2 = 94%; p < 0.01; n=2043). A subgroup analysis revealed that acupuncture not only reduced the duration of POI when administered alongside conventional care but also further expedited the recovery of gut function after colorectal surgery when integrated into the enhanced recovery after surgery (ERAS) pathway. The studies included in the analysis reported no instances of serious adverse events associated with acupuncture. We identified Zusanli (ST36), Shangjuxu (ST37), Neiguan (PC6), Sanyinjiao (SP6), Xiajuxu (ST39), Hegu (LI4), Tianshu (ST25), and Zhongwan (RN12) as primary acupoints for treating POI. Association rule mining suggested potential acupoint combinations including {ST37, ST39}≥{ST36}, {PC6, ST37}≥{ST36}, {SP6, ST37}≥{ST36}, and {ST25, ST37}≥{ST36}.

Conclusion

Meta-analysis indicates acupuncture's safety and superior effectiveness over postoperative care alone in facilitating gastrointestinal recovery. Machine-learning approaches highlight the importance of the lower He-sea points, including Zusanli (ST36) and Shangjuxu (ST37), in treating POI in CRC patients. Incorporating additional acupoints such as Neiguan (PC6) (for pain and vomiting) and Sanyinjiao (SP6) (for abdominal distension and poor appetite) can optimize treatment outcomes. These findings offer valuable insights for refining treatment protocols in both clinical and experimental settings, ultimately enhancing patient care.

Semantic Retrieval of Remote Sensing Images Based on the Bag-of-Words Association Mapping Method

With the increasing demand for remote sensing image applications, extracting the required images from a huge set of remote sensing images has become a hot topic. The previous retrieval methods cannot guarantee the efficiency, accuracy, and interpretability in the retrieval process. Therefore, we propose a bag-of-words association mapping method that can explain the semantic derivation process of remote sensing images. The method constructs associations between low-level features and high-level semantics through visual feature word packets. An improved FP-Growth method is proposed to achieve the construction of strong association rules to semantics. A feedback mechanism is established to improve the accuracy of subsequent retrievals by reducing the semantic probability of incorrect retrieval results. The public datasets AID and NWPU-RESISC45 were used to validate these experiments. The experimental results show that the average accuracies of the two datasets reach 87.5% and 90.8%, which are 22.5% and 20.3% higher than VGG16, and 17.6% and 15.6% higher than ResNet18, respectively. The experimental results were able to validate the effectiveness of our proposed method.

Identification of status quo and association rules for chronic comorbidity among Chinese middle-aged and older adults rural residents

Background

Chronic comorbidity has become a major challenge in chronic disease prevention and control. This issue is particularly pronounced in rural areas of developing countries, where the prevalence of chronic disease comorbidity is high, especially among middle-aged and older adults populations. However, the health status of middle-aged and older adults individuals in rural areas of China has received inadequate attention. Therefore, it is crucial to investigate the correlation among chronic diseases to establish a reference basis for adjusting health policies aimed at promoting the prevention and management of chronic diseases among middle-aged and older adults individuals.

Methods

This study selected 2,262 middle-aged and older adults residents aged 50 years or older in Shangang Village, Jiangsu Province, China, as the study population. To analyze the chronic comorbidity of middle-aged and older adults residents with different characteristics, we used the χ² test with SPSS statistical software. Data analysis was conducted using the Apriori algorithm of Python software, set to mine the strong association rules of positive correlation between chronic disease comorbidities of middle-aged and older adults residents.

Results

The prevalence of chronic comorbidity was 56.6%. The chronic disease comorbidity group with the highest prevalence rate was the lumbar osteopenia + hypertension group. There were significant differences in the prevalence of chronic disease comorbidity among middle-aged and older adults residents in terms of gender, BMI, and chronic disease management. The Apriori algorithm was used to screen 15 association rules for the whole population, 11 for genders, and 15 for age groups. According to the order of support, the most common association rules of comorbidity of three chronic diseases were: {lumbar osteopenia} → {hypertension} (support: 29.22%, confidence: 58.44%), {dyslipidemia} → {hypertension} (support: 19.14%, confidence: 65.91%) and {fatty liver} → {hypertension} (support: 17.82%, confidence: 64.17%).

Conclusion

The prevalence of chronic comorbidity among middle-aged and older adults rural residents in China is relatively high. We identified many association rules among chronic diseases, dyslipidemia is mostly the antecedent, and hypertension is primarily the result. In particular, the majority of comorbidity aggregation patterns consisted of hypertension and dyslipidemia. By implementing scientifically-proven prevention and control strategies, the development of healthy aging can be promoted.

Predicting new mineral occurrences and planetary analog environments via mineral association analysis

The locations of minerals and mineral-forming environments, despite being of great scientific importance and economic interest, are often difficult to predict due to the complex nature of natural systems. In this work, we embrace the complexity and inherent "messiness" of our planet's intertwined geological, chemical, and biological systems by employing machine learning to characterize patterns embedded in the multidimensionality of mineral occurrence and associations. These patterns are a product of, and therefore offer insight into, the Earth's dynamic evolutionary history. Mineral association analysis quantifies high-dimensional multicorrelations in mineral localities across the globe, enabling the identification of previously unknown mineral occurrences, as well as mineral assemblages and their associated paragenetic modes. In this study, we have predicted (i) the previously unknown mineral inventory of the Mars analogue site, Tecopa Basin, (ii) new locations of uranium minerals, particularly those important to understanding the oxidation-hydration history of uraninite, (iii) new deposits of critical minerals, specifically rare earth element (REE)- and Li-bearing phases, and (iv) changes in mineralization and mineral associations through deep time, including a discussion of possible biases in mineralogical data and sampling; furthermore, we have (v) tested and confirmed several of these mineral occurrence predictions in nature, thereby providing ground truth of the predictive method. Mineral association analysis is a predictive method that will enhance our understanding of mineralization and mineralizing environments on Earth, across our solar system, and through deep time.

Selected Data Mining Tools for Data Analysis in Distributed Environment

In this paper, we deal with distributed data represented either as a finite set T of decision tables with equal sets of attributes or a finite set I of information systems with equal sets of attributes. In the former case, we discuss a way to the study decision trees common to all tables from the set T: building a decision table in which the set of decision trees coincides with the set of decision trees common to all tables from T. We show when we can build such a decision table and how to build it in a polynomial time. If we have such a table, we can apply various decision tree learning algorithms to it. We extend the considered approach to the study of test (reducts) and decision rules common to all tables from T. In the latter case, we discuss a way to study the association rules common to all information systems from the set I: building a joint information system for which the set of true association rules that are realizable for a given row ρ and have a given attribute a on the right-hand side coincides with the set of association rules that are true for all information systems from I, have the attribute a on the right-hand side, and are realizable for the row ρ. We then show how to build a joint information system in a polynomial time. When we build such an information system, we can apply various association rule learning algorithms to it.

A Data Mining-Based Study on Medication Rules of Chinese Herbs to Treat Heart Failure with Preserved Ejection Fraction

OBJECTIVE

To summarize the medication rules of Chinese herbs to treat heart failure with preserved ejection fraction (HFPEF) based on data mining and to provide references for clinical utilization.

METHODS

The China National Knowledge Infrastructure (CNKI), Wanfang database (Wanfang), VIP database (VIP), Chinese Biomedical Literature (CBM), PubMed, Embase, and Cochrane Library databases were searched from inception to October 2021 to identify relevant literature on treating HFPEF with Chinese herbs. Microsoft Excel 2019 was used to set up a database, and then, association rule analysis and hierarchical cluster analysis were performed by using apriori algorithm and hclust function respectively in R-Studio (Version 4.0.3).

RESULTS

A total of 182 qualified papers were included, involving a total of 92 prescriptions, 130 Chinese herbs, and 872 individual herbs prescribed, with an average of 9.5 herbs per prescription. The six most frequently prescribed herbs were Astragali Radix (Huangqi), Salviae Miltiorrhizae Radix Et Rhizoma (Danshen), Poria (Fuling), Glycyrrhizae Radix Et Rhizoma (Gancao), Cinnamomi Ramulus (Guizhi), and Ginseng Radix Et Rhizoma (Renshen). There were 35 herbs used more than 5 times, involving 11 efficacy categories. The top three categories were deficiency-tonifying herbs, blood-activating and stasis-removing herbs, and dampness-draining diuretic herbs. The most commonly used herbs were mainly warm and sweet. The primary meridian tropisms were Lung Meridian, Heart Meridian and Spleen Meridian. Association rule analysis yielded 26 association rules, such as Astragali Radix (Huangqi) & Salviae Miltiorrhizae Radix Et Rhizoma (Danshen), Poria (Fuling), Cinnamomi Ramulus (Guizhi) & Atractylodis Macrocephalae Rhizoma (Baizhu). Hierarchical cluster analysis yielded four herb classes, and their functions were mainly qi-replenishing and yang-warming, blood-activating and diuresis-inducing.

CONCLUSIONS

HFPEF is the syndrome of root vacuity and tip repletion, and its core pathogenesis is "deficiency", "stasis", and "water", with "deficiency" being the most principal, which is closely related to Xin (heart), Fei (Lung), and Pi (Spleen). The treatment of this disease occurs by improving qi, warming yang, activating blood and inducing diuresis. Astragali Radix (Huangqi) with Salviae Miltiorrhizae Radix Et Rhizoma (Danshen) is the basic combination of herbs applied.

Dependence Graphs Based on Association Rules to Explore Delusional Experiences

Methods to estimate dependence graphs among variables, have quickly gained popularity in psychopathology research. To date, multiple methods have been proposed but recent studies report several drawbacks impacting on the validity of the conclusions as it is argued that assumptions and conditions underlying the methods commonly used and the nature of the data is lacking alignment. A particularly important issue is that underlying dynamics potentially present in heterogeneous datasets are disregarded, as the methods focus on the variables but not on individuals. This work also argues that the networks may lack relevant components as current methods ignore connections beyond pairwise interactions between individual symptoms. This study addresses these issues with a novel method for constructing dependence graphs based on applying Association Rules to binary records, which is often the type of records in the psychopathology domain. To demonstrate the benefits, we examine 12 delusional experiences in a sample of 1423 subjects with psychotic disorders. We show that by extracting Association Rules using an algorithm called apriori, in addition to facilitating an intuitive interpretation, previously unseen relevant dependencies are revealed from higher order interactions among psychotic experiences in subgroups of patients.

SCARF: a biomedical association rule finding webserver

The analysis of enormous datasets with missing data entries is a standard task in biological and medical data processing. Large-scale, multi-institution clinical studies are the typical examples of such datasets. These sets make possible the search for multi-parametric relations since from the plenty of the data one is likely to find a satisfying number of subjects with the required parameter ensembles. Specifically, finding combinatorial biomarkers for some given condition also needs a very large dataset to analyze. For fast and automatic multi-parametric relation discovery association-rule finding tools are used for more than two decades in the data-mining community. Here we present the SCARF webserver for generalized association rule mining. Association rules are of the form: a AND b AND … AND x → y, meaning that the presence of properties a AND b AND … AND x implies property y; our algorithm finds generalized association rules, since it also finds logical disjunctions (i.e., ORs) at the left-hand side, allowing the discovery of more complex rules in a more compressed form in the database. This feature also helps reducing the typically very large result-tables of such studies, since allowing ORs in the left-hand side of a single rule could include dozens of classical rules. The capabilities of the SCARF algorithm were demonstrated in mining the Alzheimer’s database of the Coalition Against Major Diseases (CAMD) in our recent publication (Archives of Gerontology and Geriatrics Vol. 73, pp. 300–307, 2017). Here we describe the webserver implementation of the algorithm.

[Analysis of acupoint-symptom relationship in CHENG Dan-an's Note About Treatise on Cold-Attack based on complex network]

Acupoint-symptom relationship in CHENG Dan-an's Note About Treatise on Cold-Attack was analyzed based on complex network, acupoint names and indications were extracted from the book, which provided ideas and methods for promoting the modernization of acupuncture and moxibustion by using complex network technology. A total of 112 acupoints in 201 acupuncture prescriptions were included, and the total frequency of acupoints was 880 times, forming 42 034 acupoint pairs. In terms of network indexes, compared with the complex network of comprehensive acupuncture books, such as Meridian and Acupoint Science, Zhenjiu Dacheng, Acupuncture A and B Meridians formed based on the same mathematical method, the complex network model for CHENG Dan-an's Note About Treatise on Cold-Attack shows more typical small world effect, which is characterized by higher network density (6.762) and shorter average path length (1.064). This phenomenon may be related to the tongue and pulse which added the link between acupoints. For the node indexes, the analysis of topological indexes such as Page Rank shows that acupoints represented by Dazhui (GV 14) has higher compatibility value in the treatment of exogenous diseases, which further demonstrates the clinical value of eigenvector centrality in guiding intelligent compatibility of points.

COVID-19 patient diagnosis and treatment data mining algorithm based on association rules

Association rules are used in different data mining applications, including Web mining, intrusion detection, and bioinformatics. This study mainly discusses the COVID-19 patient diagnosis and treatment data mining algorithm based on association rules. General data The key time interval during the main diagnosis and treatment process (including onset to dyspnea, first diagnosis, admission, mechanical ventilation, death, and the time from first diagnosis to admission, etc.), the cause of death by laboratory examination, and so forth. The frequency of drug use was counted and association rule algorithm was used to analyse and study the effect of drug treatment. The results could provide reference for rational drug use in COVID-19 patients. In this study, in order to improve the efficiency of data mining in data processing, it is necessary to pre-process these data. Secondly, in the application of this data mining, the main objective is to extract association rules of COVID-19 complications. So its properties for mining should be various diseases. Therefore, it is necessary to classify individual disease types. During the construction of association rules database, the data in the data warehouse is analysed online and the association rules data mining is analysed. The results are stored in the knowledge base for decision support. For example, the prediction results of the decision tree can be displayed at this level. After the construction of the mining model, the display interface can be mined, and the decision-maker can input the corresponding attribute value and then predict it. 0.76% of people had both COVID-19, CHD and hypertension, while 46.5% of people with COVID-19 and CHD were likely to have hypertension. This study is helpful to analyse the imaging factors of COVID-19 disease.

An analysis of occupational accidents involving national and international construction workers in Spain using the association rule technique

Worker safety awareness on construction sites is a major concern due to the hazardous work conditions. Additionally, globalization is increasing the cultural diversity of the workforce and this influences workers' attitudes, beliefs and behaviour. The growing number of migrant workers in this sector has become a distinctive feature of the industry's labour market. The objective of this article is to analyse occupational accidents that occurred on Spanish construction sites while taking into consideration the nationality of the workers. Due to the large number of accidents and attributes associated with them, the use of association rules is proposed. Overall, results evince similar behaviour, although interesting differences can be observed regarding the occupation of workers. In addition, the results are in accordance with previous studies carried out in other countries. The analysis of these accidents will serve to establish initiatives that provide safer work environments.

ASSOCIATION RULES IN HEART FAILURE READMISSION RATES AND PATIENT EXPERIENCE SCORES

OBJECTIVE

Thirty-day readmission rates are closely monitored in today's healthcare ecosystem to prevent higher-than-average rates in inpatient settings. Excess readmission rates result in decreased reimbursement for healthcare facilities. Additionally, feedback from patients about their hospital experience may indicate areas of improvement for healthcare facilities. This feedback is a national survey that collects data on patient experience through a standardized survey called Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS). The objective of this study is to identify significant patterns between readmission rates and HCAHPS survey data through the application of association rules.

MATERIALS AND METHODS

Publically accessible HCAHPS survey data and 30-day readmission rates provided by the Centers for Medicare and Medicaid Services (CMS) were utilized for this study. Through the implementation of association rules using SAS Enterprise Miner, significant rules were identified in the data.

RESULTS

Association rules were developed in SAS Enterprise Miner and produced three significant rules associated with high heart failure (HF) readmission as the right-hand rule. The rules indicated that a high pneumonia readmission, a low cleanliness star rating, and a low medication communication star rating were associated with a high readmission rate for heart failure.

CONCLUSIONS

The rules provided strong associations between HCAHPS star ratings and determining a high readmission rate for HF. It was interesting to find that pneumonia readmissions exist as well with a high HF readmission. Hospitals should work on improving their star ratings for the HCAHPS domains identified and work on lowering pneumonia readmissions to lower their HF readmissions.

[Characteristics analysis for Chinese patent medicine containing Jujubea Fructus based on data mining]

Chinese patent medicine prescriptions containing Jujubea Fructus in 2015 edition of Chinese Pharmacopoeia and the Composition Principles of Chinese Patent Drug were collected, and the characteristics of Chinese patent medicine containing Jujubea Fructus were analyzed by using data mining technology. Statistical software Excel 2019, Clementine 12.0 and SPSS 21.0 were used to conduct statistical analysis of conforming Chinese patent medicine prescriptions by means of frequency statistics, association rule analysis and cluster analysis. Finally, a total of 185 Chinese patent medicine prescriptions containing Jujubea Fructus were included in this study, involving 402 Chinese medicines and 28 kinds of high frequency Chinese medicines, with Jujubea Fructus, Poria, Zingiberis Rhizoma Recens, Glycyrrhizae Radix et Rhizoma, and Codonopsis Radix as the top five. The deficiency-nourishing drugs were in the most common efficacy classification, mainly sweet, bitter and pungent, with most medicine properties of warm and gentle, main meridians of spleen lung and stomach, dosage forms of pills, granules and tablets, and main indications of splenic diseases. Fifteen drug combinations were obtained in association rule analysis. Eleven drug combinations were obtained by association rule analysis of Chinese patent medicine containing Jujubea Fructus in the treatment of splenic diseases, and the drugs were divided into two categories by cluster analysis. According to the above analysis, it is found that the Chinese patent medicine prescriptions containing Jujubea Fructus are mainly composed of deficiency-nourishing drugs, mostly compatible with drugs of sweet, bitter and pungent flavors, warm and gentle properties, and spleen, lung, and stomach meridians in the treatment of splenic diseases, with Sijunzi Decoction as the main drug. This study provides guidance for modern clinical application and development of Jujubea Fructus.

Identifying frequent drug combinations associated with delirium in older adults: Application of association rules method to a case-time-control design

BACKGROUND

Older adults are at an increased risk of delirium because of age, polypharmacy, multiple comorbidities, frailty, and acute illness. Although medication-induced delirium in older adults is well understood, limited population-level evidence is available, particularly on combinations of medications associated with delirium in older adults.

OBJECTIVES

We aimed to apply association rule analysis to identify drug combinations contributing to delirium risk in adults aged 65 and older using a case-time-control design.

METHOD

We sourced a nationwide representative sample of New Zealander's aged ≥65 years from the pharmaceutical collections and hospital discharge information. Prescription records (2005-2015) were obtained from New Zealand pharmaceutical collections (Pharms). Medication exposures were coded as binary variables (exposed vs. not exposed) at the individual drug level. All medications, including antimicrobials, antihistamines, diuretics, opioids, and nonsteroidal anti-inflammatory medications, were considered drugs of interest. The first-time coded diagnosis of delirium was extracted from the National Minimal Dataset (NMDS). A unique patient identifier linked the prescription dataset to the event dataset to set up a case-time-control cohort, indexed at the first delirium event. Association rules were then applied to identify frequent drug combinations in the case and the control periods (l-day with a 35-day washout period) that are statistically associated with delirium, and the association was tested by computing a time-trend adjusted matched odds-ratio (MOR) and its 95% confidence interval (CI).

RESULTS

We identified 28 503 individuals (mean age 84.1 years) from 2005 to 2015 with delirium. Our combined association rule and case-time-control analysis identified several drug classes, including antipsychotics, benzodiazepines, opioids, and diuretics associated with delirium. Our analysis also identified frequently used drug combinations that are associated with delirium. Examples include combined exposures to quetiapine and furosemide (MOR = 6.17; 95%CI = [2.05-18.54]), haloperidol (MOR = 4.81; 95%CI = [3.16-6.69]), combined exposures to furosemide, omeprazole, and lorazepam (MOR = 3.94; 95%CI = [3.03-5.10]), and fentanyl exposure (MOR = 3.46; 95%CI [2.05-9.21]).

CONCLUSION

The association rule method applied to a case-time-control design is a novel approach to identifying drug combinations contributing to delirium with adjustment for any temporal trends in exposures. The study provides new insight into the combination of medicines linked to delirium.

Correlation in Causality: A Progressive Study of Hierarchical Relations within Human and Organizational Factors in Coal Mine Accidents

It has been revealed in numerous investigation reports that human and organizational factors (HOFs) are the fundamental causes of coal mine accidents. However, with various kinds of accident-causing factors in coal mines, the lack of systematic analysis of causality within specific HOFs could lead to defective accident precautions. Therefore, this study centered on the data-driven concept and selected 883 coal mine accident reports from 2011 to 2020 as the original data to discover the influencing paths of specific HOFs. First, 55 manifestations with the characteristics of the coal mine accidents were extracted by text segmentation. Second, according to their own attributes, all manifestations were mapped into the Human Factors Analysis and Classification System (HFACS), forming a modified HFACS-CM framework in China's coal-mining industry with 5 categories, 19 subcategories and 42 unsafe factors. Finally, the Apriori association algorithm was applied to discover the causal association rules among external influences, organizational influences, unsafe supervision, preconditions for unsafe acts and direct unsafe acts layer by layer, exposing four clear accident-causing "trajectories" in HAFCS-CM. This study contributes to the establishment of a systematic causation model for analyzing the causes of coal mine accidents and helps form corresponding risk prevention measures directly and objectively.

[Research on regularity of traditional Chinese medicine in treatment of Alzheimer's disease based on data mining]

To explore prescription medication regularity in the treatment of Alzheimer's disease with traditional Chinese medicine(TCM). With Alzheimer's disease or senile dementia as the subject, collecting and sorting out the journal papers in CNKI were collected as the data source to establish the literature research database of Alzheimer's disease prescriptions, and then the association rule analysis, factor analysis and systematic cluster analysis on the included TCM were conducted. Among the 113 prescriptions included in the standard, the single herb Acori Tatarinowii Rhizoma was the most common. The herbs were mainly warm and flat among four pro-perties, mainly sweet, bitter and spicy among five flavors. The drugs were mainly distributed in five internal organs, and the most commonly used drugs were deficiency tonifying drugs as well as blood activating and stasis removing drugs. In the association rule analysis, it was found that there were 6 drug pairs with the highest association strength. Eight common factors were extracted from the factor analysis, and they were classified into 6 categories in the systematic cluster analysis. The results have shown that the overall principles in treating Alzheimer's disease with modern Chinese medicine are tonifying deficiency, invigorating circulation, activating blood and dispelling phlegm.

Apriori Algorithm for the Data Mining of Global Cyberspace Security Issues for Human Participatory Based on Association Rules

This study explored the global cyberspace security issues, with the purpose of breaking the stereotype of people’s cognition of cyberspace problems, which reflects the relationship between interdependence and association. Based on the Apriori algorithm in association rules, a total of 181 strong rules were mined from 40 target websites and 56,096 web pages were associated with global cyberspace security. Moreover, this study analyzed support, confidence, promotion, leverage, and reliability to achieve comprehensive coverage of data. A total of 15,661 sites mentioned cyberspace security-related words from the total sample of 22,493 professional websites, accounting for 69.6%, while only 735 sites mentioned cyberspace security-related words from the total sample of 33,603 non-professional sites, accounting for 2%. Due to restrictions of language, the number of samples of target professional websites and non-target websites is limited. Meanwhile, the number of selections of strong rules is not satisfactory. Nowadays, the cores of global cyberspace security issues include internet sovereignty, cyberspace security, cyber attack, cyber crime, data leakage, and data protection.

Comorbidity Patterns of Older Lung Cancer Patients in Northeast China: An Association Rules Analysis Based on Electronic Medical Records

Purposes: This study aims to identify the comorbidity patterns of older men with lung cancer in China. Methods: We analyzed the electronic medical records (EMRs) of lung cancer patients over age 65 in the Jilin Province of China. The data studied were obtained from 20 hospitals of Jilin Province in 2018. In total, 1510 patients were identified. We conducted a rank–frequency analysis and social network analysis to identify the predominant comorbidities and comorbidity networks. We applied the association rules to mine the comorbidity combination with the values of confidence and lift. A heatmap was utilized to visualize the rules. Results: Our analyses discovered that (1) there were 31 additional medical conditions in older patients with lung cancer. The most frequent comorbidities were pneumonia, cerebral infarction, and hypertension. (2) The network-based analysis revealed seven subnetworks. (3) The association rules analysis provided 41 interesting rules. The results revealed that hypertension, ischemic cardiomyopathy, and pneumonia are the most frequent comorbid combinations. Heart failure may not have a strong implicating role in these comorbidity patterns. Cerebral infarction was rarely combined with other diseases. In addition, glycoprotein metabolism disorder comorbid with hyponatremia or hypokalemia increased the risk of anemia by more than eight times in older lung cancer patients. Conclusions: This study provides evidence on the comorbidity patterns of older men with lung cancer in China. Understanding the comorbidity patterns of older patients with lung cancer can assist clinicians in their diagnoses and contribute to developing healthcare policies, as well as allocating resources.

Association Rule Mining and Prognostic Stratification of 2-Year Longevity in Octogenarians Undergoing Endovascular Therapy for Lower Extremity Arterial Disease: Observational Cohort Study

Background

Two-year longevity is a crucial consideration in revascularization strategies for patients with symptomatic lower extremity arterial disease (LEAD). However, factors associated with 2-year longevity and risk stratification in octogenarians or nonagenarians have been underreported.

Objective

This paper aims to investigate the associated variables and stratify the 2-year prognosis in older patients with LEAD.

Methods

We performed logistic regression and association rule mining based on the Apriori algorithm to discover independent variables and validate their associations with 2-year longevity. Malnutrition, inflammation, and stroke factors were identified. C statistics and Kaplan-Meier analysis were used to assess the impact of different numbers of malnutrition, inflammation, and stroke factors on 2-year longevity.

Results

We recruited a total of 232 octogenarians or nonagenarians (mean age 85 years, SD 4.2 years) treated with endovascular therapy. During the study period, 81 patients died, and 27 of those (33%) died from a cardiac origin within 2 years. Association rules analysis showed the interrelationships between 2-year longevity and the neutrophil-lymphocyte ratio (NLR) and nutritional status as determined by the Controlling Nutritional Status (CONUT) score or Geriatric Nutritional Risk Index (GNRI). The cut-off values of NLR, GNRI, and CONUT were ≥3.89, ≤90.3, and >3, respectively. The C statistics for the predictive power for 2-year longevity were similar between the CONUT score and the GNRI-based models (0.773 vs 0.760; P=.57). The Kaplan-Meier analysis showed that 2-year longevity was worse as the number of malnutrition, inflammation, and stroke factors increased from 0 to 3 in both the GNRI-based model (92% vs 68% vs 46% vs 12%, respectively; P<.001) and the CONUT score model (87% vs 75% vs 49% vs 10%, respectively; P<.001). The hazard ratio between those with 3 factors and those without was 18.2 (95% CI 7.0-47.2; P<.001) in the GNRI and 13.6 (95% CI 5.9-31.5; P<.001) in the CONUT score model.

Conclusions

This study demonstrated the association and crucial role of malnutrition, inflammation, and stroke factors in assessing 2-year longevity in older patients with LEAD. Using this simple risk score might assist clinicians in selecting the appropriate treatment.

[Application of special acupoints for chronic gastritis in ancient literature of acupuncture and moxibustion]

The application of special acupoints for different primary symptoms of chronic gastritis in ancient literature of acupuncture and moxibustion was analyzed and summarized. With keywords, electronic and manual retrieval of ancient literature being performed to establish a database, the association rules were performed with SPSS Modeler 18. As a result, ① among all the 2243 items included, 109 items mentioned special acupoints (excluding those only mentioned crossing acupoint). The frequency of special acupoints was 2554 (71.7%), and the special acupoints on the spleen meridian, the stomach meridian, the conception vessel were frequently used. The frequency of five-shu point was highest, followed by front-mu points. ② The special acupoints for four main primary symptoms of chronic gastritis, "stomachache" "vomiting and regurgitation" "belching and acid regurgitation" and "epigastric fullness", included Zusanli (ST 36), Neiguan (PC 6), Zhongwan (CV 12), Gongsun (SP 4), Taibai (SP 3). In addition, the back-shu points were also selected to treat the primary symptoms other than "epigastric fullness". Zhangmen (LR 13) was added to treat "belching and acid regurgitation". The combination of Neiguan (PC 6) and Gongsun (SP 4) showed the strongest correlation; due to different primary symptoms, the combination had different emphasis.

[Study on clinical characteristics of Danshen Chuanxiongqin Injection in treatment of cerebral infarction in real world]

In this study, the clinical characteristics and drug combination rules of Danshen Chuanxiongqin Injection in the treatment of patients with cerebral infarction were analyzed. The inpatient information of 2 857 patients of cerebral infarction treated with Danshen Chuanxiongqin Injection in HIS database of 20 grade Ⅲ class A hospitals in China was collected, and a model was established by description analysis and Apriori algorithm, in order to explore the clinical characteristics and drug combination rules of Danshen Chuan-xiongqin Injection in the treatment of cerebral infarction. The results showed that among patients of cerebral infarction treated with Danshen Chuanxiongqin Injection, 1 727 patients were older than 65 years old, accounting for 69.61%, and 1 610 were males, accounting for 63.59%. Commonly used drugs included lipid-lowering agents, anticoagulant thrombolytic agents, antiplatelet agents, stimulants of brain metabolism, vasodilators and other Western drugs, as well as traditional Chinese medicines, such as blood-activating agents, heat-clearing agents and expectorant agents. The Western medicine with the highest use frequency in combination with Danshen Chuan-xiongqin Injection was aspirin enteric-coated tablets(1 528 cases, 53.48%). The traditional Chinese medicine with the highest use frequency in combination with Danshen Chuanxiongqin Injection was Xingnaojing Injection, with a total of 378 cases, accounting for 13.23%. Among them, the most commonly used Western drugs combined with Danshen Chuanxiongqin Injection were anticoagulant thrombolytic and antiplatelet drugs, with a usage rate as high as 83.48%. In order to further explore the drug combination rules of Danshen Chuanxiongqin Injection, the association analysis of drug combination in patients of cerebral infarction treated with Danshen Chuanxiongqin Injection was carried out. In clinical combination of two Western drugs, Atorvastatin Calcium Capsules+Cerebral Proteolytic Injection were the most common combination, with a support of 27.10%. In clinical combination with 3 Western drugs, Clopidogrel Bisulfate Tablets+Atorvastatin Calcium Capsules+Cerebral Proteolytic Injection were most commonly used, with a support of 15.90%. The results showed that the patients of cerebral infarction treated with Danshen Chuanxiongqin Injection were mainly elderly males, and often complicated with hypertension, coronary heart disease, diabetes and other basic diseases. The clinical application of Danshen Chuanxiongqin Injection was principally in line with the guidelines. In the treatment of cerebral infarction, it was often combined with Western medicine anticoagulant thrombolysis, antiplatelet drugs, traditional Chinese medicine blood-activating and stasis-dissolving prescription and other drugs with similar pharmacological effects, with an auxiliary therapeutic effect on patients of cerebral infarction complicated with other diseases, and can provide guidance for clinical medication.

[Analysis on formula of Mongolian medicine for prevention of COVID-19]

The epidemic situation of coronavirus disease 2019(COVID-19) is developing rapidly in the world, and the influence is serious. In this study, the prescription of Mongolian medicine to prevent new type of COVID-19 was investigated. Based on the second edition and the third edition of COVID-19 Mongolian Medicine Prevention and Treatment Guidance Program issued by the Inner Mongolia Autonomous Region Health Commission, using Excel 2007, SPSS Modeler 18, SPSS Statistics 25, Cytoscape 3.7.1 statistical software as a tool, the association rules analysis and cluster analysis of Mongolian medicine included in the standard were carried out. Among the 45 prophylactic prescriptions included in the standard, a total of 34 high-frequency drugs using frequency ≥5 were used, of which Carthami Flos(21 times, 4.46%), Chebulae Fructus(20 times, 4.26%), Moschus(13 times, 2.77%), Myristicae Semen(12 times, 2.55%), Santali Albi Lignum(12 times, 2.55%), and Bovis Calculus(12 times, 2.55%) were the most common. The main drugs for the prevention of COVID-19 were Liang(13 times, 38.23%), Wen(9 times, 26.47%), the flavor was Ku(20 times, 34.48%), Xin(13 times, 22.41%), Gan(11 times, 18.97%), the most used drugs treating hot evil(99 times, 32.46%), treatment of &quot;Heyi&quot; drugs(51 times, 16.72%), treatment of &quot;Badagan&quot; drugs(40 times, 13.11%), treatment of &quot;sticky&quot; drugs(37 times, 12.13%), and a cough, eliminating phlegm and antiasthmatic(31 times, 10.16%), the association rule analysis found that the highest association intensity of the drug pair combination of 11. Clustering analysis using the cluster analysis of inter-group join method found a total of 8 categories. In this study, 45 prescriptions of Mongolian medicine for the prevention of COVID-19 were collec-ted and further analyzed, hoping to provide new ideas for clinical diagnosis and treatment.

Organization and recall of visual information after traumatic brain injury

BACKGROUND

Subjective organization (SO) is the ability to structure information to help facilitate storage and retrieval. There is a paucity of research concerning how a person subjectively organizes visual information.

OBJECTIVES

This study investigates whether traumatic brain injury (TBI) hinders the ability to subjectively organize and recall visual symbols. The authors use an Association Rule Modeling (ARM) procedure to measure SO and explore whether the complexity of the rules generated from the ARM predicted recall of symbols.

METHOD

Twenty-two collegiate athletes with self-reported, repetitive, mild TBI and 22 college students without TBI participated. All participants completed a list learning task that assessed their free recall of unfamiliar symbols. ARM revealed the associative structure among the symbols in the list for each participant.

RESULTS

Results showed that collegiate athletes with repetitive, mild TBI develop significantly fewer association rules for visual stimuli compared to college students without TBI. Furthermore, collegiate athletes with TBI produce fewer complex SO rules for the visual stimuli relative to college students without TBI.

CONCLUSION

Brain injury diminishes a person's ability to subjectively organize novel visual information. ARM is a sensitive clinical measure of SO for patients with TBI.

A precision medicine framework using artificial intelligence for the identification and confirmation of genomic biomarkers of response to an Alzheimer's disease therapy: Analysis of the blarcamesine (ANAVEX2-73) Phase 2a clinical study

INTRODUCTION

The search for drugs to treat Alzheimer's disease (AD) has failed to yield effective therapies. Here we report the first genome-wide search for biomarkers associated with therapeutic response in AD. Blarcamesine (ANAVEX2-73), a selective sigma-1 receptor (SIGMAR1) agonist, was studied in a 57-week Phase 2a trial (NCT02244541). The study was extended for a further 208 weeks (NCT02756858) after meeting its primary safety endpoint.

METHODS

Safety, clinical features, pharmacokinetic, and efficacy, measured by changes in the Mini-Mental State Examination (MMSE) and the Alzheimer's Disease Cooperative Study-Activities of Daily Living scale (ADCS-ADL), were recorded. Whole exome and transcriptome sequences were obtained for 21 patients. The relationship between all available patient data and efficacy outcome measures was analyzed with unsupervised formal concept analysis (FCA), integrated in the Knowledge Extraction and Management (KEM) environment.

RESULTS

Biomarkers with a significant impact on clinical outcomes were identified at week 57: mean plasma concentration of blarcamesine (slope MMSE:P < .041), genomic variants SIGMAR1 p.Gln2Pro (ΔMMSE:P < .039; ΔADCS-ADL:P < .063) and COMT p.Leu146fs (ΔMMSE:P < .039; ΔADCS-ADL:P < .063), and baseline MMSE score (slope MMSE:P < .015). Their combined impact on drug response was confirmed at week 148 with linear mixed effect models.

DISCUSSION

Confirmatory Phase 2b/3 clinical studies of these patient selection markers are ongoing. This FCA/KEM analysis is a template for the identification of patient selection markers in early therapeutic development for neurologic disorders.

[Study on medication regularity of traditional Chinese medicine in treatment of COVID-19 based on data mining]

The coronavirus disease 2019(COVID-19) is developing rapidly and posing great threat to public health. There is no specific medicine available for treating the disease. Luckily, traditional Chinese medicine has played a positive role in the fighting against COVID-19. In this paper, We collected and sorted the prescriptions of modern Chinese medicine for COVID-19 released by national government, different provinces, autonomous regions and municipalities, as well as online databases, such as CNKI, WanFang medical network, and VIP database. These prescriptions were combined with the inheritance of traditional Chinese medicine auxiliary V2.5, and the complex system entropy clustering method was used to determine the association rules and frequency of single drug and drug combination in the prescription. In the end, 96 effective prescriptions were included. Among them, the four properties were mainly concentrated in temperature, cold and level, the five tastes were mainly concentrated in bitter, hot and sweet, and the meridians were mainly concentrated in lung, stomach and spleen. The high-frequency drugs were Glycyrrhizae Radix et Rhizoma, Armeniacae Semen Amarum, Gypsum Fibrosum, etc., and the high-frequency combinations are Gypsum Fibrosum-Armeniacae Semen Amarum, Gypsum Fibrosum-Glycyrrhizae Radix et Rhizoma, Armeniacae Semen Amarum-Glycyrrhizae Radix et Rhizoma, the core combinations are Lepidii Semen-Armeniacae Semen Amarum-Gypsum Fibrosum, Pogostemonis Herba-Zingiberis Rhizoma Recens-Magnoliae Officinalis Cortex, Ophiopogonis Radix-Armeniacae Semen Amarum-Scutellariae Radix and so on. Form new prescriptions Lepidii Semen, Armeniacae Semen Amarum, Gypsum Fibrosum, Pogostemonis Herba, Zingiberis Rhizoma Recens, Magnoliae Officinalis Cortex. Ophiopogonis Radix, Armeniacae Semen Amarum, Scutellariae Radix, Schisandrae Sphenantherae Fructus, Panacis Quinquefolii Radix. From the medicinal properties to high-frequency drugs and new prescriptions, it could be seen that the overall treatment of COVID-19 by traditional Chinese medicine was to strengthen body resistance, eliminate pathogenic factors, and give attention to Qi and Yin.

[Rule of acupoint selection for cancer pain based on association rule and entropy clustering]

OBJECTIVE

To analyze the rule of acupoint selection for cancer pain based on data mining.

METHODS

The published literature regarding acupuncture for cancer pain in the recent 10 years was searched in PubMed, CNKI, VIP and Wanfang database. The acupoint selection was summarized and analyzed by TCMISS V2.5.

RESULTS

Totally 68 literature was collected and 73 acupoint prescriptions were included, involving 117 acupoints. These acupoints were mainly in bladder meridian, stomach meridian, liver meridian and spleen meridian. Among them, 40 acupoints used more than 4 times were identified, and the top three acupoints were Zusanli (ST 36, 65 times), Neiguan (PC 6, 55 times) and Taichong (LR 3, 50 times). A total of 68 acupoint combinations used more than 19 times were identified, and the top three acupoint combinations were Zusanli (ST 36)-Neiguan (PC 6), Taichong (LR 3)-Zusanli (ST 36) and Zusanli (ST 36)-Sanyinjiao (SP 6). There were 103 acupoint combinations with strong association; based on the entropy clustering algorithm, 20 new acupoint combinations and 10 new acupoint prescriptions were obtained.

CONCLUSION

The main meridians for cancer pain are bladder meridian, stomach meridian, liver meridian and spleen meridian, with Zusanli (ST 36), Neiguan (PC 6), Taichong (LR 3), Hegu (LI 4), Sanyinjiao (SP 6) and ashi points as core acupoints, and regulating spleen-stomach and treating qi-blood are the main principles.

[Regularity of prescription medication of Xin'an Wang's internal medicine in treating stomach cramps based on data mining]

The study analyzes the medication rules of Xin&apos;an Wang&apos;s internal medicine for treating stomach cramps by data mining technology,in order to provide reference for clinical medication. Through the summarization of the medical cases of stomach cramps treated by Xin&apos;an Wang&apos;s doctors( Wang Ren-zhi,Wang Zhong-qi,Wang Le-tao),statistics was made for the frequency of symptoms,signs,syndromes and drugs in Office 2010. Apriori algorithm in IBM SPSS Modeler 14. 1,and SPSS Statistics 22. 0 were used for association rule analysis and cluster analysis. The results showed that the 310 prescriptions collected involved totally 322 syndromes( including symptoms and signs) and 336 drugs,with the cumulative dose of 4 072 times; the symptoms were correlated to the spleen and stomach,liver and gallbladder,and the heart system; syndrome differentiation was mainly based on liver-Qi invasion of the stomach,diet impairment to the stomach,deficiency of spleen and stomach and cold syndrome; commonly used drugs were Qi regulating drugs,phlegm eliminating drugs and blood circulation promoting and stasis removing drugs; high-frequency drug complex network diagram showed that Pinelliae Rhizoma,Aurantii Fructus,Trichosanthis Fructus,Allii Macrostemonis Bulbus were closely related; the analysis showed 12,20,and 17 two,three,and four association rules; cluster analysis showed 10 pairs of Trichosanthis Fructus-Allii Macrostemonis Bulbus,Pinelliae Rhizoma-Aurantii Fructus,and Aspongopus-Toosendan Fructus drug combinations. According to Xin&apos; an Wang&apos;s doctors,stomach cramps are closely related to liver and spleen,Qi stagnation,phlegm and blood stasis are the standard.Xin&apos;an Wang&apos;s doctors give the first priority on &quot; deoppilation&quot;,focus on soothing the liver and spleen,activating Qi and eliminating phlegm,and promoting blood circulation,and refer to use modified Xiaoxianxiong Decoction and modified Gualou Xiebai Banxia Decoction based on symptoms.

[Study on characteristics and data mining of 464 cases of lung diseases in Xin'an Wang's medicine]

The purpose of this paper is to study the use rules of drugs for lung diseases in internal medicine department of Xin'an Wang's family, discuss the compatibility of common drugs for lung diseases, guide clinical application, and inherit Xin'an medicine. By retrospective study on lung diseases cases in Wang's internal medicine works, the lung diseases and use frequency of common drugs treated by Wang's medicine were counted, and the systematic clustering and association rule analysis of common drugs were conducted by using SPSS Statistic 20 and SPSS Modeler 18.0, respectively. The results showed that asthma, cold and cough were the main lung diseases treated by Wang's medicine, and the commonly used medicines included antitussive and antiasthmatic drugs, spleen-invigorating and dampness-removing drugs, and expectorants. The medicine taste was mainly bitter, pungent and sweet, with cold and warm properties in a balanced way, without severely cold or hot herbs, mainly attributing to the lung and stomach meridians. In clustering analysis, 10 drug combinations were obtained; association analysis showed that two, three, four association rules respectively had 11, 21, and 10 groups, and each drug group had 11, 16, and 5 items. Core combinations: Poria, Armeniacae Semen Amarum, Asteris Radix et Rhizome, Coicis Semen, Farfarae Flos, Dendrobii Caulis, Perilla Frutescens, Stemonae Radix, Citri Reticulatae Pericarpium, Cynanchi Stauntonii Rhizome et Radix, Meretricis Concha Cyclinae Concha, Belamcandae Rhizoma, and Pinelliae Rhizome. Xin'an Wang's medicine paid attention to the lung nature when treating lung diseases. Lung is a delicate organ, not resistant to coldness or heat, so severely cold or hot herbs shall not be used, and the clear and light drugs with functions of dispersing lung Qi, clearing phlegm evil, strengthening spleen, eliminating phlegm, and relieving cough and asthma are often used. Lung deficiency is a kind of deficiency of Qi and Yin, so both Qi and Yin shall be regulated. Deficiency of Yin would burn the lung and make the lung collaterals blocked. In this case, the lung collaterals shall be dredged for hemostasis. Long time of lung deficiency would hinder the distribution of body fluid, and lung shall be regulated to dissipate phlegm.

[Real world study on characteristics of Maixuekang Capsules combined with traditional Chinese medicines in treating nephrotic syndrome]

To analyze the clinical characteristics of Maixuekang Capsules combined with traditional Chinese medicines in the treatment of patients with nephrotic syndrome,and provide references for improving rationality of clinical drug use. Based on the database of hospital information system(HIS) in 15 hospitals in China,the electrical medical records of the patients diagnosed as nephrotic syndrome and treated with Maixuekang Capsules were collected. Their diagnostic information and characteristics of combined traditional Chinese medicines were analyzed by using association rules. The results showed that 1 588 patients of nephrotic syndrome who used Maixuekang Capsules were often complicated with hypertension(863 cases,accounting for 7. 54%),anemia(551 cases,accounting for 4. 81%),and coronary heart disease(349 cases,accounting for 3. 05%). Maixuekang Capsules were mainly combined with Tabellae Rhei et Natrii Bicarbonatis,Baining Capsules,tanshinone,Ganmao Qingre Granule,Shuxuening Injection in treating nephrotic syndrome. The results indicated that in the real world,Maixuekang Capsules was mainly used in combination with traditional Chinese medicines such as blood-activating and stasis-removing agents,pathogens eliminating and supporting healthy Qi agents,digestants,anti-bacterial and anti-inflammatory agents,wind-dispersing and antipyretic agents for patients with nephropathy. By the pharmacological effect,it was suitable for nephropathy patients based on combined diagnosis. The association rules of combination were specific,and can provide reference for subsequent studies and rational clinical medication of traditional Chinese medicines.

[Medication rules of Professor Zhang Bing in treatment of skin itching based on data mining]

Skin itching is a subjective sensation that causes the desire to scratch. It is one of the most common clinical symptoms at department of dermatology, even the only complaint of dermatological patients, which seriously affects the quality life of patients. Therefore, based on the software of traditional Chinese medicine inheritance auxiliary platform, association rules and complex system entropy clustering were adopted to collect and analyze Zhang Bing's prescriptions for skin itching, and get the drug use frequency and the relationship between drugs. Based on that, we could conclude the experience for skin itching. A total of 147 prescriptions were collected, 20 drugs with a frequency of 34 or more and 20 high-frequency drug combinations were analyzed, and 14 core combinations and 7 new prescriptions were excavated. The high-frequency drugs included Kochiae Fructus, Dictamni Cortex, Mori Cortex. The high-frequency drug combinations included "Kochiae Fructus-Dictamni Cortex" "Angelicae Dahuricae Radix-Chuanxiong Rhizoma" "Paeoniae Radix Rubra-Paeoniae Radix Alba", and the core combinations included "Schizonepetae Herba-Saposhnikoviae Radix-Cinnamomi Ramulus" "Arctii Fructus-Cicadae Periostracum-Houttuyniae Herba" "Ghrysanthemi Indici Flos-Kochiae Fructus-Dictamni Cortex", and new formulations include "Schizonepetae Herba, Saposhnikoviae Radix, Cinnamomi Ramulus, Clematidis Radix et Rhizoma, Tribuli Fructus, Dictamni Cortex", "Phellodendri Chinensis Coritex, Lonicerae Japonicae Flos, Atractylodis Rhizoma, Ghrysanthemi Indici Flos, Kochiae Fructus, Dictamni Cortex" "Arctii Fructus, Cicadae Periostracum, Houttuyniae Herba, Trichosanthis Fructus". The result of this research shows that Professor Zhang Bing's experience in the treatment of skin itching is mainly to dispelling wind and arresting itching, clearing heat and drying dampness.

[Association rules analysis for exploring combined medication characteristics of Fufang Kushen injection: real-world study based on 49 597 cases]

The present study aimed to analyze the association rules of Fufang Kushen injection in combined medications in the real world based on electrical medical records in hospital information system, and provide reference for its reasonable clinical application. The electrical medical records of the hospitalized patients using Fufang Kushen injection were extracted to analyze the frequency distribution characteristics in combined application with Western medicine, and analyze the specific association rules between these combinations by using Apriori algorithm. A total of 49 597 patients were included in the study, and its common combined medications included 5-HT receptor blockers, hepatic protector, antibiotics, chemotherapeutic drugs, immunomodulatory drugs, glucocorticoids, analgetics and proton pump inhibitors. The results revealed that the distribution characteristics in combined application and association combinations of Fufang Kushen injection had specific rules, consistent with the clinical orientation of this drug in treatment of malignant tumor. Such results may provide reference for reasonable application of Fufang Kushen injection in clinical treatment.

Knowledge Extraction and Improved Data Fusion for Sales Prediction in Local Agricultural Markets

In this paper, a monitoring system of agricultural production is modeled as a Data Fusion System (data from local fairs and meteorological data). The proposal considers the particular information of sales in agricultural markets for knowledge extraction about the associations among them. This association knowledge is employed to improve predictions of sales using a spatial prediction technique, as shown with data collected from local markets of the Andean region of Ecuador. The commercial activity in these markets uses Alternative Marketing Circuits (CIALCO). This market platform establishes a direct relationship between producer and consumer prices and promotes direct commercial interaction among family groups. The problem is presented first as a general fusion problem with a network of spatially distributed heterogeneous data sources, and is then applied to the prediction of products sales based on association rules mined in available sales data. First, transactional data is used as the base to extract the best association rules between products sold in different local markets, knowledge that allows the system to gain a significant improvement in prediction accuracy in the spatial region considered.

Computational identification of physicochemical signatures for host tropism of influenza A virus

Avian influenza viruses from migratory birds have managed to cross host species barriers and infected various hosts like human and swine. Epidemics and pandemics might occur when influenza viruses are adapted to humans, causing deaths and enormous economic loss. Receptor-binding specificity of the virus is one of the key factors for the transmission of influenza viruses across species. The determination of host tropism and understanding of molecular properties would help identify the mechanism why zoonotic influenza viruses can cross species barrier and infect humans. In this study, we have constructed computational models for host tropism prediction on human-adapted subtypes of influenza HA proteins using random forest. The feature vectors of the prediction models were generated based on seven physicochemical properties of amino acids from influenza sequences of three major hosts. Feature aggregation and associative rules were further applied to select top 20 features and extract host-associated physicochemical signatures on the combined model of nonspecific subtypes. The prediction model achieved high performance ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mtext>Accuracy</mml:mtext><mml:mo>=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>9</mml:mn><mml:mn>4</mml:mn><mml:mn>8</mml:mn></mml:math> , <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mtext>Precision</mml:mtext><mml:mo>=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>9</mml:mn><mml:mn>5</mml:mn><mml:mn>4</mml:mn></mml:math> , <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mtext>MCC</mml:mtext><mml:mo>=</mml:mo><mml:mn>0</mml:mn><mml:mo>.</mml:mo><mml:mn>9</mml:mn><mml:mn>2</mml:mn><mml:mn>2</mml:mn></mml:math> ). Support and confidence rates were calculated for the host class-association rules. The results indicated that secondary structure and normalized Van der Waals volume were identified as more important physicochemical signatures in determining the host tropism.

[Compatible principles of Xiebai decoction family based on complex network analysis]

In order to explore the compatible principles of Xiebai decoction family, formulae from ancient and modern Xiebai decoction family were collected and sorted in this study. The compatible characteristics, core herbs, as well as the relativity of herbs nature in Xiebai decoction family were analyzed based on scale free network and other data-mining methods such as association rules, clustering analysis and correspondence analysis. The scale free network results showed that in Xiebai decoction family, Mori Cortex-Lycii Cortex-Glycyrrhizae Radix et Rhizoma was used as the core compatible group and formed the complicated compatible network with other additional herbs; association rules results showed that the core herbs in such formulae included Mori Cortex, Lycii Cortex, Glycyrrhizae Radix et Rhizoma, scutellaria root, Platycodon root, Anemarrhena, and almond, which formed corresponding herbal pairs and compatibility; clustering analysis showed that Mori Cortex was the core herb in Xiebai decoction family, and Mori Cortex-Lycii Cortex-Glycyrrhizae Radix et Rhizoma was its main combination unit, which was always compatible with herbs of clearing heat, reducing phlegm, supplementing Qi and nourishing Yin to form the series prescriptions. The results indicated that the core compatibility features of Xiebai decoction family were clearing heat in lung and relieving cough and asthma, providing a basis for the clinical application of Xiebai decoction family.

Mining association rules between stroke risk factors based on the Apriori algorithm

BACKGROUND

Stroke is a frequently-occurring disease and is a severe threat to human health.

OBJECTIVE

We aimed to explore the associations between stroke risk factors.

METHODS

Subjects who were aged 40 or above were requested to do surveys with a unified questionnaire as well as laboratory examinations. The Apriori algorithm was applied to find out the meaningful association rules. Selected association rules were divided into 8 groups by the number of former items. The rules with higher confidence degree in every group were viewed as the meaningful rules.

RESULTS

The training set used in association analysis consists of a total of 985,325 samples, with 15,835 stroke patients (1.65%) and 941,490 without stroke (98.35%). Based on the threshold we set for the Apriori algorithm, eight meaningful association rules were obtained between stroke and its high risk factors. While between high risk factors, there are 25 meaningful association rules.

CONCLUSIONS

Based on the Apriori algorithm, meaningful association rules between the high risk factors of stroke were found, proving a feasible way to reduce the risk of stroke with early intervention.

Analysis of Occupational Accidents in Underground and Surface Mining in Spain Using Data-Mining Techniques

An analysis of occupational accidents in the mining sector was conducted using the data from the Spanish Ministry of Employment and Social Safety between 2005 and 2015, and data-mining techniques were applied. Data was processed with the software Weka. Two scenarios were chosen from the accidents database: surface and underground mining. The most important variables involved in occupational accidents and their association rules were determined. These rules are composed of several predictor variables that cause accidents, defining its characteristics and context. This study exposes the 20 most important association rules in the sector—either surface or underground mining—based on the statistical confidence levels of each rule as obtained by Weka. The outcomes display the most typical immediate causes, along with the percentage of accidents with a basis in each association rule. The most important immediate cause is body movement with physical effort or overexertion, and the type of accident is physical effort or overexertion. On the other hand, the second most important immediate cause and type of accident are different between the two scenarios. Data-mining techniques were chosen as a useful tool to find out the root cause of the accidents.

Rules of Meridians and Acupoints Selection in Treatment of Parkinson's Disease Based on Data Mining Techniques

OBJECTIVE

To help selecting appropriate meridians and acupoints in clinical practice and experimental study for Parkinson's disease (PD), the rules of meridians and acupoints selection of acupuncture and moxibustion were analyzed in domestic and foreign clinical treatment for PD based on data mining techniques.

METHODS

Literature about PD treated by acupuncture and moxibustion in China and abroad was searched and selected from China National Knowledge Infrastructure and MEDLINE. Then the data from all eligible articles were extracted to establish the database of acupuncture-moxibustion for PD. The association rules of data mining techniques were used to analyze the rules of meridians and acupoints selection.

RESULTS

Totally, 168 eligible articles were included and 184 acupoints were applied. The total frequency of acupoints application was 1,090 times. Those acupoints were mainly distributed in head and neck and extremities. Among all, Taichong (LR 3), Baihui (DU 20), Fengchi (GB 20), Hegu (LI 4) and Chorea-tremor Controlled Zone were the top five acupoints that had been used. Superior-inferior acupoints matching was utilized the most. As to involved meridians, Du Meridian, Dan (Gallbladder) Meridian, Dachang (Large Intestine) Meridian, and Gan (Liver) Meridian were the most popular meridians.

CONCLUSIONS

The application of meridians and acupoints for PD treatment lay emphasis on the acupoints on the head, attach importance to extinguishing Gan wind, tonifying qi and blood, and nourishing sinews, and make good use of superior-inferior acupoints matching.

[Medication rules for prescriptions containing Pterocephali Herba based on data mining]

This study was aimed to discuss and analyze the medication rules for prescriptions containing Pterocephali Herba in Chinese Medical Encyclopedia - Tibetan Medicine, Tibetan Medicine Prescription Modern Research and Clinical Application, and Interpretation of Common Tibetan Medicines based on the collection of Pterocephali Herba and by using the "Traditional Chinese Medicine Inheritance Support system(V2.0.1)",with the use of association rules, apriori algorithm and other data mining methods. The frequency of single drug, the frequency of drug combination, the association rule and the combination of core drugs were analyzed. Through collection of the prescriptions, a total of 215 prescriptions were included, involving a total of 376 herbs. Through the "frequency statistics", the prescriptions containing Pterocephali Herba were commonly used to treat cold fever, distemper virus and arthritis. The highest frequently (frequency≥15) used drugs were Corydalis Herba, Lagotidis Herba, and Gentianae Macrophyllae Radix, et al. The most frequently used drug combinations were "Pterocephali Herba, Corydalis Herba","Pterocephali Herba, Lagotidis Herba", and "Pterocephali Herba, Gentianae Macrophyllae Radix" et al. The prescriptions containing Pterocephali Herba were used to primarily treat disease for Tourette syndrome caused by the dampness heat toxin, fever, arthritis etc, such as pestilent toxicity, pneumonia and influenza, rheumatoid arthritis etc. The drugs in the prescriptions mostly had the effects of heat-clearing and detoxifying, anti-inflammatory, dispelling wind and dampness, often in compatible use with heat-clearing drugs. The drug use was concentrated and reflected the clear thought of prescription statutes.

[Distribution of traditional Chinese medicine syndromes of diabetic retinopathy and correlation between symptoms]

To investigate the distribution of traditional Chinese medicine (TCM) Syndromes of diabetic retinopathy and explore the correlation between various symptoms. Based on the literature in databases of China Journal Full-text Database (CNKI), Wanfang database, VIP network, China biomedical literature database (CBM) and PubMed, SPSS 20.0 and IBM SPSS Modeler 14.1 software were used to analyze the location of disease, symptoms, tongue and pulse, and syndrome type distribution through frequency statistics. In addition, association rule algorithm was used to explore the basic rules for underlying symptoms combinations of diabetic retinopathy. A total of 560 articles were retrieved, and a total of 240 articles met the inclusion and exclusion criteria. In these documents, 62 types of TCM syndromes were found, involving 9 820 cases, 201 symptoms, 29 tongue conditions, and 36 pulses conditions; the first two locations for the disease were liver and kidney. Then the association rule analysis of high frequency symptoms was used to dig out 15 groups of latent syndrome, and 3 underlying symptom combinations among high frequency symptoms, tongue conditions and pulse conditions. The results of the study showed that Qi and yin deficiency was most common for the diabetic retinopathy, and the location of the disease was closely related to liver and kidney. In addition, these high-frequency symptoms and tongue conditions, pulse conditions, and underlying symptom combinations can occur as main symptoms at diagnosis, providing reference for us to study the epidemiology of PRO scale of the disease. They can also increase the weight of these symptoms directly as the main symptoms, which can be also used as an alternative entry pool for TCM syndrome diagnostic scale, laying foundation for the construction and optimization of TCM symptom database of diabetic retinopathy.

[Association rules analysis of Fufang Kushen injection in combination with traditional Chinese medicine or modern medications in treating malignant tumor: real-world retrospective study]

Fufang Kushen injection is used in real world clinical situations to treat different types of malignant tumors. The present study aimed to analyze the association rules of Fufang Kushen injection in combination with other traditional Chinese medicine(TCM) or modern medications in treating malignant tumors based on the electrical medical records extracted from real-world hospital information system. This real world retrospective analysis was based on the clinicians' prescriptions regarding to such treatment by combined TCM and modern medications. Hospital information system data from 22 hospitals, including electrical medical records of 44 588 patients with malignant tumors and Fufang Kushen injection were included in this study, providing useful reference for the development of clinical treatment ideas, and providing reference for clinical rational use of Fufang Kushen injection. High correlation and causal relations were not present in this study, so further exploration and analysis were still needed for the conclusion.

[Registration of 30 026 cases of Shenqi Fuzheng injection combined with other drugs in real world]

Prospective, multi-center, large-sample and registered design was used to analyze the drug combination features of Shenqi Fuzheng injection in the real world clinical application, and comprehend the drug combination in the real world. A total of 30 026 patients with the use of Shenqi Fuzheng injection were registered, where the chemical drugs were used for 57 436 times (accounting for 82.76%), and the Chinese patent medicines were used for 11 962 times (accounting for 17.24%), mainly including anti-acid drugs and anti-ulcer drugs, nutritional agent, immune enhancement agent, etc. According to the association rules, drug combinations of 2 drugs were closely related to inhibiting gastric acid secretion and anti-tumor; drug combinations of 3 drugs were closely related to inhibiting gastric acid secretion, antiemetic and anti tumor; drug combinations of 4 drugs were closely related to inhibiting gastric acid secretion, antiemetic, anti-tumor, and immune enhancement. The above results were consistent with the Instruction, providing clues for accurate treatment, and laying the foundation for clinical rational drug use.

[Detecting shared pathways linked to rheumatoid arthritis with other autoimmune diseases in a in silico analysis]

Pathway-based analysis approach has exploded in use during the last several years. It is successful in recognizing additional biological insight of disease and finding groupings of risk genes that represent disease developing processes. Therefore, shared pathways, with pleiotropic effects, are important for understanding similar pathogenesis and indicating the common genetic origin of certain diseases. Here, we present a pathway analysis to reveal the potential disease associations between RA and three potential RA-related autoimmune diseases: psoriasis, diabetes mellitus, type 1 (T1D) and systemic lupus erythematosus (SLE). First, a comprehensive knowledge mining of public databases is performed to discover risk genes associated with RA, T1D, SLE and psoriasis; then by enrichment test of these genes, disease-related risk pathways are detected to recognize the pathways common for RA and three other diseases. Finally, the underlying disease associations are evaluated with the association rules mining method. In total, we identify multiple RA risk pathways with significant pleiotropic effects, the most unsurprising of which are the immunology related pathways. Meanwhile for the first time we highlight the involvement of the viral myocarditis pathway related to cardiovascular disease (CVD) in autoimmune diseases such as RA, psoriasis, T1D and SLE. Further Association rule mining results validate the strong association between RA and T1D and RA and SLE. It is clear that pleiotropy is a common property of pathways associated with disease traits. We provide novel pathway associations among RA and three autoimmune diseases. These results ascertain that there are shared genetic risk profiles that predispose individuals to autoimmune diseases.

Classification of Journal Articles in a Search for New Experimental Thermophysical Property Data: A Case Study

We present a case study in which we use natural language processing and machine learning techniques to automatically select candidate scientific articles that may contain new experimental thermophysical property data from thousands of articles available in five different relevant journals. The National Institute of Standards and Technology (NIST) Thermodynamic Research Center (TRC) maintains a large database of available thermophysical property data extracted from articles that are manually selected for content. Over time the number of articles requiring manual inspection has grown and assistance from machine-based methods is needed. Previous work used topic modeling along with classification techniques to classify these journal articles into those with data for the TRC database and those without. These techniques have produced classifications with accuracy between 85 % and 90 %. However, the TRC does not want to lose data from the misclassified articles that contain relevant information. In this study, we start with these topic modeling and classification techniques, and then enhance the model using information relevant to the TRC's selection process. Our goal is to minimize the number of articles that require manual selection without missing articles of importance. Through a series of selection methods, we eliminate those articles for which we can determine a rejection criterion. We can reduce the number of articles that are not of interest by 70.8 % while retaining 98.7 % of the articles of interest. We have also found that topic model classification improves when the corpus of words is derived from specific sections of the articles rather than the entire articles, and we improve on our classification by using a combination of topic models from different sections of the article. Our best classification used only the Experimental and Literature Cited sections.

Analyzing injury severity factors at highway railway grade crossing accidents involving vulnerable road users: A comparative study

OBJECTIVE

The main objective of this study is to identify the main factors associated with injury severity of vulnerable road users (VRUs) involved in accidents at highway railroad grade crossings (HRGCs) using data mining techniques.

METHODS

This article applies an ordered probit model, association rules, and classification and regression tree (CART) algorithms to the U.S. Federal Railroad Administration's (FRA) HRGC accident database for the period 2007-2013 to identify VRU injury severity factors at HRGCs.

RESULTS

The results show that train speed is a key factor influencing injury severity. Further analysis illustrated that the presence of illumination does not reduce the severity of accidents for high-speed trains. In addition, there is a greater propensity toward fatal accidents for elderly road users compared to younger individuals. Interestingly, at night, injury accidents involving female road users are more severe compared to those involving males.

CONCLUSIONS

The ordered probit model was the primary technique, and CART and association rules act as the supporter and identifier of interactions between variables. All 3 algorithms' results consistently show that the most influential accident factors are train speed, VRU age, and gender. The findings of this research could be applied for identifying high-risk hotspots and developing cost-effective countermeasures targeting VRUs at HRGCs.

CIMIDx: Prototype for a Cloud-Based System to Support Intelligent Medical Image Diagnosis With Efficiency

Background

The Internet has greatly enhanced health care, helping patients stay up-to-date on medical issues and general knowledge. Many cancer patients use the Internet for cancer diagnosis and related information. Recently, cloud computing has emerged as a new way of delivering health services but currently, there is no generic and fully automated cloud-based self-management intervention for breast cancer patients, as practical guidelines are lacking.

Objective

We investigated the prevalence and predictors of cloud use for medical diagnosis among women with breast cancer to gain insight into meaningful usage parameters to evaluate the use of generic, fully automated cloud-based self-intervention, by assessing how breast cancer survivors use a generic self-management model. The goal of this study was implemented and evaluated with a new prototype called “CIMIDx”, based on representative association rules that support the diagnosis of medical images (mammograms).

Methods

The proposed Cloud-Based System Support Intelligent Medical Image Diagnosis (CIMIDx) prototype includes two modules. The first is the design and development of the CIMIDx training and test cloud services. Deployed in the cloud, the prototype can be used for diagnosis and screening mammography by assessing the cancers detected, tumor sizes, histology, and stage of classification accuracy. To analyze the prototype’s classification accuracy, we conducted an experiment with data provided by clients. Second, by monitoring cloud server requests, the CIMIDx usage statistics were recorded for the cloud-based self-intervention groups. We conducted an evaluation of the CIMIDx cloud service usage, in which browsing functionalities were evaluated from the end-user’s perspective.

Results

We performed several experiments to validate the CIMIDx prototype for breast health issues. The first set of experiments evaluated the diagnostic performance of the CIMIDx framework. We collected medical information from 150 breast cancer survivors from hospitals and health centers. The CIMIDx prototype achieved high sensitivity of up to 99.29%, and accuracy of up to 98%. The second set of experiments evaluated CIMIDx use for breast health issues, using t tests and Pearson chi-square tests to assess differences, and binary logistic regression to estimate the odds ratio (OR) for the predictors’ use of CIMIDx. For the prototype usage statistics for the same 150 breast cancer survivors, we interviewed 114 (76.0%), through self-report questionnaires from CIMIDx blogs. The frequency of log-ins/person ranged from 0 to 30, total duration/person from 0 to 1500 minutes (25 hours). The 114 participants continued logging in to all phases, resulting in an intervention adherence rate of 44.3% (95% CI 33.2-55.9). The overall performance of the prototype for the good category, reported usefulness of the prototype (P=.77), overall satisfaction of the prototype (P=.31), ease of navigation (P=.89), user friendliness evaluation (P=.31), and overall satisfaction (P=.31). Positive evaluations given by 100 participants via a Web-based questionnaire supported our hypothesis.

Conclusions

The present study shows that women felt favorably about the use of a generic fully automated cloud-based self- management prototype. The study also demonstrated that the CIMIDx prototype resulted in the detection of more cancers in screening and diagnosing patients, with an increased accuracy rate.

Meeting people's needs in a fully interoperable domotic environment

The key idea underlying many Ambient Intelligence (AmI) projects and applications is context awareness, which is based mainly on their capacity to identify users and their locations. The actual computing capacity should remain in the background, in the periphery of our awareness, and should only move to the center if and when necessary. Computing thus becomes 'invisible', as it is embedded in the environment and everyday objects. The research project described herein aims to realize an Ambient Intelligence-based environment able to improve users' quality of life by learning their habits and anticipating their needs. This environment is part of an adaptive, context-aware framework designed to make today's incompatible heterogeneous domotic systems fully interoperable, not only for connecting sensors and actuators, but for providing comprehensive connections of devices to users. The solution is a middleware architecture based on open and widely recognized standards capable of abstracting the peculiarities of underlying heterogeneous technologies and enabling them to co-exist and interwork, without however eliminating their differences. At the highest level of this infrastructure, the Ambient Intelligence framework, integrated with the domotic sensors, can enable the system to recognize any unusual or dangerous situations and anticipate health problems or special user needs in a technological living environment, such as a house or a public space.

Association rule based similarity measures for the clustering of gene expression data

In life threatening diseases, such as cancer, where the effective diagnosis includes annotation, early detection, distinction, and prediction, data mining and statistical approaches offer the promise for precise, accurate, and functionally robust analysis of gene expression data. The computational extraction of derived patterns from microarray gene expression is a non-trivial task that involves sophisticated algorithm design and analysis for specific domain discovery. In this paper, we have proposed a formal approach for feature extraction by first applying feature selection heuristics based on the statistical impurity measures, the Gini Index, Max Minority, and the Twoing Rule and obtaining the top 100-400 genes. We then analyze the associative dependencies between the genes and assign weights to the genes based on their degree of participation in the rules. Consequently, we present a weighted Jaccard and vector cosine similarity measure to compute the similarity between the discovered rules. Finally, we group the rules by applying hierarchical clustering. To demonstrate the usability and efficiency of the concept of our technique, we applied it to three publicly available, multiclass cancer gene expression datasets and performed a biomedical literature search to support the effectiveness of our results.

Being a binding site: characterizing residue composition of binding sites on proteins

The Protein Data Bank contains the description of more than 45,000 three-dimensional protein and nucleic-acid structures today. Started to exist as the computer-readable depository of crystallographic data complementing printed articles, the proper interpretation of the content of the individual files in the PDB still frequently needs the detailed information found in the citing publication. This fact implies that the fully automatic processing of the whole PDB is a very hard task. We first cleaned and re-structured the PDB data, then analyzed the residue composition of the binding sites in the whole PDB for frequency and for hidden association rules. Main results of the paper: (i) the cleaning and repairing algorithm (ii) redundancy elimination from the data (iii) application of association rule mining to the cleaned non-redundant data set. We have found numerous significant relations of the residue-composition of the ligand binding sites on protein surfaces, summarized in two figures. One of the classical data-mining methods for exploring implication-rules, the association-rule mining, is capable to find previously unknown residue-set preferences of bind ligands on protein surfaces. Since protein-ligand binding is a key step in enzymatic mechanisms and in drug discovery, these uncovered preferences in the study of more than 19,500 binding sites may help in identifying new binding protein-ligand pairs.