Association rule mining and network analysis in oriental medicine

Occupational health knowledge discovery based on association rules applied to workers' body parts protection: a case study in the automotive industry

Occupational Health Protection (OHP) is mandatory by law and can be accomplished by considering the participation of others besides occupational physicians. The data shared can originate knowledge that might influence other processes related to occupational risk prevention. In this study, we used Artificial Intelligence (AI) methods to extract patterns among records shared under these circumstances over two years in the automotive industry. Records featuring OHP data against physical working conditions were selected, and a database of 383 profiles was designed. As Occupational Health Protection profiles under study are associated with work functional ability reduction, the body part(s) (n = 14) where it occurred were identified. Association Rules (ARs) coupled with Natural Language Processing techniques were applied to find meaningful hidden relationships and to identify the occurrence of protection profiles being assigned to at least two body parts simultaneously. After filtering ARs using three metrics (support, confidence, and lift), 54 ARs were found. The distribution of simultaneous body parts is presented as being higher in Special projects (n = 5). The results can use in: (i) design a multi-site body parts functional work ability (loss) model; (ii) model the capacity of organizations to retain workers in their working settings and (iii) prevent work-related musculoskeletal symptoms.

Risk Factors in Japanese Drug Overdose Patients: Identifying Their Associations With Suicide Risk

Several suicide attempts presented at the emergency department are due to drug overdose associated with psychiatric disorders. We examined and identified the major risk factors among Japanese drug overdose patients and several close associations of suicide risk. We enrolled 101 patients who attempted suicide by drug overdose between January 2015 and April 2018, assessed their background using the SAD PERSONS scale, and performed association rule analysis to characterize the major risk factors and their associations. We identified three main nodes-depressive state, social support lacking, and no spouse-as considerable risk factors. Furthermore, we identified several close associations of suicide risk and their intensity; in cases with previous suicide attempts and ethanol abuse or substance use, a simultaneous social support lacking is likely. These findings align with previous studies that used conventional statistical analysis on suicide and suicide attempt risk and highlight its importance.

Data mining analysis reveals key acupoints and meridians for the treatment of chemotherapy-induced peripheral neuropathy

OBJECTIVE

To explore effective acupoints and combinations for the treatment of chemotherapy-induced peripheral neuropathy (CIPN) METHODS: Clinical controlled trials and randomized controlled trials of acupuncture for CIPN were sourced from PubMed, Embase, Web of Science, and Chinese databases, including the Wanfang database, VIP Journals database, and China National Knowledge Infrastructure database. The quality of eligible research was evaluated based on CONSORT and STRICTA statements. The common acupoints, meridians, and acupoint combinations were determined from acupuncture prescriptions reporting positive effects and were analyzed using SPSS 23.0 and SPSS Modeler 14.1. Finally, a complex network was constructed using Cytoscape 3.8.2 to explore the core acupoints.

RESULTS

The quality of 24 clinical trials was evaluated, and 20 acupuncture prescriptions that reported positive outcomes were included in subsequent data mining analysis. The most frequently used acupoints are ST36, LI11, LI4, LR3, and SP6. Meanwhile, they are also the core acupoints in acupuncture prescriptions according to the complex network with 28 nodes and 177 edges. The most commonly used meridians were the large intestine, stomach, and spleen. Acupoint combinations of LI11 and ST36, SP6 and ST36 were frequently used.

CONCLUSION

Our study provides a reference for the selection of effective acupoints for CIPN treatment and a basis for the effective use of this form of traditional Chinese medicine. Furthermore, we found limitations in the design and implementation of the available clinical research, which should be minimized in future studies.

Effect of Chinese Herbal Medicine Therapy on Risks of Overall, Diabetes-Related, and Cardiovascular Diseases-Related Mortalities in Taiwanese Patients With Hereditary Hemolytic Anemias

Hereditary Hemolytic Anemias (HHAs) are a rare but heterogeneous group of erythrocytic diseases, characterized by intrinsic cellular defects due to inherited genetic mutations. We investigated the efficacy of Chinese herbal medicine (CHM) in reducing the overall, diabetes-related, and cardiovascular diseases (CVDs)-related mortalities among patients with HHAs using a nationwide population database. In total, we identified 33,278 patients with HHAs and included 9,222 non-CHM and 9,222 CHM matched pairs after matching. The Cox proportional hazards model was used to compare the risk of mortality between non-CHM and CHM users. The Kaplan-Meier method and log-rank test were used to compare the cumulative incidence mortality between non-CHM and CHM users. The CHM prescription patterns were presented by the association rules and network analyses, respectively. The CHM prescription patterns were presented by the association rules and network analyses, respectively. CHM users showed significant reduced risks for of overall (adjusted hazard ratio [aHR]: 0.67, 95% confidence interval [CI]: 0.61-0.73, p < 0.001), diabetes-related (aHR: 0.57, 95% CI: 0.40-0.82, p < 0.001), and CVDs-related (aHR: 0.59, 95% CI: 0.49-0.72, p < 0.001) mortalities compared with non-CHM users. Two CHM clusters are frequently used to treat Taiwanese patients with HHAs. Cluster 1 is composed of six CHMs: Bei-Mu (BM; Fritillaria cirrhosa D.Don), Gan-Cao (GC; Glycyrrhiza uralensis Fisch.), Hai-Piao-Xiao (HPX; Endoconcha Sepiae), Jie-Geng (JG; Platycodon grandiflorus (Jacq.) A.DC.), Yu-Xing-Cao (YXC; Houttuynia cordata Thunb.), and Xin-Yi-Qing-Fei-Tang (XYQFT). Cluster 2 is composed of two CHMs, Dang-Gui (DG; Angelica sinensis (Oliv.) Diels) and Huang-Qi (HQi; Astragalus membranaceus (Fisch.) Bunge). Further randomized clinical trials are essential to evaluate the safety and effectiveness of above CHM products and to eliminate potential biases in the current retrospective study.

Oral Administration of East Asian Herbal Medicine for Inflammatory Skin Lesions in Plaque Psoriasis: A Systematic Review, Meta-Analysis, and Exploration of Core Herbal Materials

Psoriasis is an inflammatory autoimmune skin disease with various clinical manifestations. The aim of this review was to systematically evaluate the efficacy and safety of oral administration of East Asian herbal medicine (EAHM) for inflammatory skin lesions in psoriasis and to explore core herbal materials for drug discovery. A comprehensive search was conducted in 10 electronic databases for randomized controlled trials from their inception until 29 July 2021. Statistical analysis was performed in R version 4.1.2 and R studio. When heterogeneity in studies was detected, the cause was identified through sensitivity analysis, meta-regression, and subgroup analysis. Methodological quality was independently assessed using the revised tool for risk of bias in randomized trials. A total of 56 trials with 4966 psoriasis patients met the selection criteria. Meta-analysis favored EAHM monotherapy on Psoriasis Area Severity Index (PASI) 70 (RR: 1.2845; 95% CI: 1.906 to 1.3858, p < 0.0001), PASI 60 (RR: 1.1923; 95% CI: 1.1134 to 1.2769, p < 0.0001), continuous PASI score (MD: −2.3386, 95% CI: −3.3068 to −1.3704, p < 0.0001), IL-17, IL-23, TNF-α, and Dermatology Life Quality Index. Patients treated with EAHM monotherapy had significantly reduced adverse events incidence rate. In addition, based on additional examination of the herb data included in this meta-analysis, 16 core materials were identified. They are utilized in close proximity to one another, and all have anti-inflammatory properties. The findings in this study support that oral EAHM monotherapy may be beneficial for inflammatory skin lesions in psoriasis. Meanwhile, the identified core materials are expected to be utilized as useful drug candidate hypotheses through follow-up studies on individual pharmacological activities and synergistic effects.

Chinese herbal medicines in the treatment of ulcerative colitis: a review

Objective

To investigate how the ulcerative colitis (UC) be treated with Chinese herbal medicines (CHM), using Chinese medicine (CM) pattern (zheng) identification, in the current clinical practice.

Methods

A total of 7 electronic databases were systematically searched for UC clinical studies with CHM interventions (including single herbs and CHM formulas) published in English and Chinese from the date of their inception to November 25, 2020. Descriptive statistics were adopted to demonstrate the characteristics of study design, and to collate the commonly CM patterns of UC and frequently used CHM herbs and formulas. Further, IBM SPSS Modeler 18.0 and Cytoscape 3.7.1 software were used to analyze and visualize the associations between different categories of CHM and their zheng indications.

Results

A total of 2311 articles were included in this study, of which most (> 90%) were RCTs with CHM formulas. The most common zheng of UC was Large intestine dampness-heat, while the basic type of CM patten was Spleen deficiency. The most frequently used classical formula was Bai-Tou-Weng-Tang, followed by Shen-Ling-Bai-Zhu-San, and the commonly used proprietary CHM was Xi-Lei-San (enema). Sulfasalazine and Mesalazine are commonly used as concomitant western medicines. The most frequently used single medicinals were Huang Lian and Bai Zhu, which also identified as the core herbs for different CM patterns.

Conclusion

This study examined the application of CHM interventions for UC and summarized their characteristics in clinical practice. These data indicated there were limited information about the safety assessment of CHM formulas and further RCTs including CM pattern(s) with strict design are necessary.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13020-022-00591-x.

Chinese Herbal Medicine Therapy Reduces the Risks of Overall and Anemia-Related Mortalities in Patients With Aplastic Anemia: A Nationwide Retrospective Study in Taiwan

Aplastic Anemia (AA) is a rare but fatal hematologic disease that may occur at any age and especially higher in Asia. We investigated whether Chinese herbal medicine (CHM) is beneficial to AA patients as a complementary therapy using a nationwide population-based database in Taiwan between 2000-2016. Patient survival was estimated by Kaplan‒Meier survival analyses and Cox proportional-hazard model. CHM-users presented lower risks of overall and anemia-related mortalities when compared to non-users. The risk of overall mortality for CHM-users in AA patients was 0.70-fold [adjusted hazard ratio (aHR): 0.70, 95% confidence interval (CI): 0.66-0.74, p < 0.001). The risk of anemia-related mortality was lower in CHM-users when compared to non-users (aHR: 0.46, 95% CI: 0.32-0.67, p < 0.001). The association rule analysis revealed that CHM pairs were Ban-Zhi-Lian (BZL; Scutellaria barbata D. Don)→Bai-Hua-She-She-Cao (BHSSC; Oldenlandia diffusa (Willd.) Roxb.), followed by Dang-Gui (DG; Angelica sinensis (Oliv.) Diels)→Huang-Qi (HQi; Astragalus membranaceus (Fisch.) Bunge), and Xian-He-Cao (XHC; Agrimonia pilosa f. borealis (Kitag.) Chu)→Gui-Pi-Tang (GPT). Network analysis showed that BZL, BHSSC, DG, HQi, XHC, GPT, and Dan-Shen (DanS; Salvia miltiorrhiza var. charbonnelii (H.Lév.) C.Y.Wu) were commonly used CHMs for AA patients. Therefore, further studies for these commonly prescribed herbs are needed in functional investigations in hematopoiesis-stimulating effect and large-scale randomized controlled trials (RCT) in bone marrow failure related diseases.

Association Rules Mining for Hospital Readmission: A Case Study

As an indicator of healthcare quality and performance, hospital readmission incurs major costs for healthcare systems worldwide. Understanding the relationships between readmission factors, such as input features and readmission length, is challenging following intricate hospital readmission procedures. This study discovered the significant correlation between potential readmission factors (threshold of various settings for readmission length) and basic demographic variables. Association rule mining (ARM), particularly the Apriori algorithm, was utilised to extract the hidden input variable patterns and relationships among admitted patients by generating supervised learning rules. The mined rules were categorised into two outcomes to comprehend readmission data; (i) the rules associated with various readmission length and (ii) several expert-validated variables related to basic demographics (gender, race, and age group). The extracted rules proved useful to facilitate decision-making and resource preparation to minimise patient readmission.

Network Analysis of Herbs Recommended for the Treatment of COVID-19

PURPOSE

In this study, we aimed to identify the pattern and combination of herbs used in the formulae recommended for treating different stages of COVID-19 using a network analysis approach.

METHODS

The herbal formulae recommended by official guidelines for the treatment of COVID-19 are included in the present analysis. To describe the tendency of herbs to form a "herb pair", we computed the mutual information (MI) value and distance-based mutual information model (DMIM) score. We also performed modularity, degree, betweenness, and closeness centrality analysis. Network analyses were performed and visualized for each disease stage.

RESULTS

A total of 142 herbal formulae comprising 416 herbs were analyzed. All possible herbal pairs were examined, and the top frequently used herbal pairs were identified for each disease stage. The herb Glycyrrhizae radix et rhizoma is only identified in one herb pair, even though this herb is identified as one of the herbs with high frequency of use for every disease stage. This suggests that the DMIM score could be used to identify the optimal combination rule of herbal formulae by achieving a balance among the herbs' frequency and relative distance in herbal formulae.

CONCLUSION

Our results presented the prescription patterns and herbal combinations of the herbal formulae recommended for the treatment of COVID-19. This study may provide new insights and ideas for clinical research in the future.

Effect of Chinese Herbal Medicine Therapy on Overall and Cancer Related Mortality in Patients With Advanced Nasopharyngeal Carcinoma in Taiwan

Nasopharyngeal carcinoma (NPC) is a head and neck cancer involving epithelial squamous-cell carcinoma of the nasopharynx that mainly occurs in individuals from East and Southeast Asia. We investigated whether Chinese herbal medicine (CHM) as a complementary therapy offers benefits to these patients. We retrospectively evaluated the Taiwan Cancer Registry (Long Form) database for patients with advanced NPC, using or not using CHM, between 2007–2013. Cox proportional-hazard model and Kaplan‒Meier survival analyses were applied for patient survival. CHM-users showed a lower overall and cancer-related mortality risk than non-users. For advanced NPC patients, the overall mortality risk was 0.799-fold for CHM-users, after controlling for age, gender, and Charlson comorbidity index (CCI) score (Cancer stages 3 + 4: adjusted hazard ratio [aHR]: 0.799, 95% confidence interval [CI]: 0.676–0.943, p = 0.008). CHM-users also showed a lower cancer-related mortality risk than non-users (aHR: 0.71, 95% CI: 0.53–0.96, p = 0.0273). Association rule analysis showed that CHM pairs were Ban-Zhi-Lian (BZL; Scutellaria barbata D.Don) and For single herbs, Bai-Hua-She-She-Cao (Herba Hedyotis Diffusae; Scleromitrion diffusum (Willd.) R.J.Wang (syn. Hedyotis diffusa Willd.) and Mai-Men-Dong (MMD; Ophiopogon japonicus (Thunb.) Ker Gawl.), and Gan-Lu-Yin (GLY) and BHSSC. Network analysis revealed that BHSSC was the core CHM, and BZL, GLY, and Xin-Yi-Qing-Fei-Tang (XYQFT) were important CHMs in cluster 1. In cluster 2, ShengDH, MMD, Xuan-Shen (XS; Scrophularia ningpoensis Hensl.), and Gua-Lou-Gen (GLG; Trichosanthes kirilowii Maxim.) were important CHMs. Thus, as a complementary therapy, CHM, and particularly the 8 CHMs identified, are important for the treatment of advanced NPC patients.

Administration of a herbal formulation enhanced blastocyst implantation via IκB activation in mouse endometrium

Background

BaelanChagsangBang (BCB), a herbal formulation consisting of eleven herbs, may be prescribed as a reproductive functional supplement to improve ovulation and implantation during the treatment of infertility and recurrent abortion in Korean Medicine. This study aimed to investigate the effects and action mechanisms of water-extracted BCB on endometrial receptivity and blastocyst implantation under normal conditions and in a mifepristone (RU486)-induced implantation failure murine model.

Methods

In vitro, the antioxidant potentials of BCB were evaluated using DPPH and superoxide anion radical scavenging assays and a DCFH-DA assay, and the cytotoxic and cytoprotective effects of BCB were confirmed using an MTT assay. In vivo, C57BL/6 female mice (n = 6 per group) orally received BCB (300 mg/kg/day), a dose similar to that used clinically, from 7 days before pregnancy until the end of the experiment. On day 4 of pregnancy, RU486 (4 mg/kg) was injected subcutaneously to induce implantation failure. The effect of BCB on embryo implantation was evaluated by implantation rate analysis, histological examination, and western blotting of uterus tissues.

Results

BCB water extract showed strong anti-oxidative and cytoprotective effects in vitro. In vivo administration of BCB water extract increased the number of newborn pups in BCB-treated mice versus sham-treated mice under normal conditions and improved the number of implantation sites in pregnant mice despite RU486 injection. BCB increased the protein levels of cyclooxygenase-2 and inducible nitric oxide synthase through IκB activation. Moreover, the expression levels of matrix metalloproteinases at uterus implantation sites were up-regulated in the BCB-treated group as compared with those in the RU486-treated group.

Conclusion

These results show BCB improved embryo implantation through IκB activation in our mouse model and suggest that BCB has therapeutic potential in the context of poor endometrial receptivity.

Decreased overall mortality rate with Chinese herbal medicine usage in patients with decompensated liver cirrhosis in Taiwan

Background

Liver cirrhosis is one of the main causes of the morbidity and mortality in liver diseases. Chinese herbal medicine (CHM) has long been used for the clinical treatment of liver diseases. This study was designed to explore the usage frequency and prescription patterns of CHM for patients with decompensated liver cirrhosis and to evaluate the long-term effects of CHM on overall mortality.

Methods

Two thousand four hundred sixty-seven patients with decompensated liver cirrhosis (ICD-9-CM code: 571.2, 571.5, and 571.6) diagnosed between 2000 and 2009 in Taiwan were identified from the registry for catastrophic illness patients. Of these, 149 CHM users and 298 CHM non-users were matched for age, gender, and Charlson comorbidity index score. The chi-squared test, paired Student’s t-test, Cox proportional hazard model, and Kaplan–Meier method were applied for various comparisons between these groups of patients.

Results

CHM-treated patients showed a lower overall mortality risk compared with non-treated patients (Multivariable: p < 0.0001; HR: 0.54, 95% CI: 0.42–0.69). The cumulative incidence of overall mortality was lower in the CHM-treated group (stratified log-rank test, p = 0.0002). The strongest CHM co-prescription pattern- Yin-Chen-Hao-Tang (YCHT) → Long-Dan-Xie-Gan-Tang (LDXGT) had the highest support, followed by Zhi-Zi (ZZ) → Yin-Chen-Wu-Ling-San (YCWLS) and Bai-Hua-She-She-Cao (BHSSC) → Da-Huang (DaH).

Conclusion

CHM, as adjunct therapy, might decrease the risk of overall mortality in patients with decompensated liver cirrhosis. CHM co-prescription patterns and network analysis showed that comprehensive herbal medicines have a protective role against liver fibrosis. Further studies are required to enhance the knowledge of safety and efficacy of CHM in patients with decompensated liver cirrhosis.

Exploring Technology Influencers from Patent Data Using Association Rule Mining and Social Network Analysis

A patent is an important document issued by the government to protect inventions or product design. Inventions consist of mechanical structures, production processes, quality improvements of products, and so on. Generally, goods or appliances in everyday life are a result of an invention or product design that has been published in patent documents. A new invention contributes to the standard of living, improves productivity and quality, reduces production costs for industry, or delivers products with higher added value. Patent documents are considered to be excellent sources of knowledge in a particular field of technology, leading to inventions. Technology trend forecasting from patent documents depends on the subjective experience of experts. However, accumulated patent documents consist of a huge amount of text data, making it more difficult for those experts to gain knowledge precisely and promptly. Therefore, technology trend forecasting using objective methods is more feasible. There are many statistical methods applied to patent analysis, for example, technology overview, investment volume, and the technology life cycle. There are also data mining methods by which patent documents can be classified, such as by technical characteristics, to support business decision-making. The main contribution of this study is to apply data mining methods and social network analysis to gain knowledge in emerging technologies and find informative technology trends from patent data. We experimented with our techniques on data retrieved from the European Patent Office (EPO) website. The technique includes K-means clustering, text mining, and association rule mining methods. The patent data analyzed include the International Patent Classification (IPC) code and patent titles. Association rule mining was applied to find associative relationships among patent data, then combined with social network analysis (SNA) to further analyze technology trends. SNA provided metric measurements to explore the most influential technology as well as visualize data in various network layouts. The results showed emerging technology clusters, their meaningful patterns, and a network structure, and suggested information for the development of technologies and inventions.

Effects of Chinese herbal medicine therapy on survival and hepatic outcomes in patients with hepatitis C virus infection in Taiwan

BACKGROUND

Chinese herbal medicine (CHM) is a complementary natural medicine that is used widely for the treatment of hepatic diseases. The aim of this study was to investigate the effects of the long-term use of CHM for the treatment of liver diseases, as prescribed by TCM doctors, on overall mortality and hepatic outcomes in patients with HCV.

PATIENTS AND METHODS

We identified 98788 patients with HCV. Of these, 829 and 829 patients who were users and non-users of CHM, respectively, were matched for age, gender, CCI, and comorbidities prior to CHM treatment. The chi-squared test, Cox proportional hazard model, Kaplan--Meier method, and log-rank test were used for comparisons.

RESULTS

CHM users had a lower risk of overall mortality than non-users after adjustment for comorbidities by using a multivariate Cox proportional hazard model (p-value < 0.001; HR: 0.12, 95% CI: 0.06-0.26). In addition,the CHM users had a lower risk of liver cirrhosis than non-users after adjustment for comorbidities (p-value = 0.028; HR: 0.29, 95% CI: 0.09-0.88). The 12-year cumulative incidences of overall mortality and liver cirrhosis were lower in the CHM group (p-value < 0.05 for both, log rank test). The CHM co-prescription for Dan-Shen, Bie-Jia, Jia-Wei-Xiao-Yao-San => E-Shu was found to occur most often associated for the specific treatment of HCV infection.

CONCLUSION

CHM as adjunctive therapy may reduce the overall mortality and the risk of liver cirrhosis in patients with HCV. The comprehensive list of the herbal medicines that may be used for the treatment of patients with HCV may be useful in future scientific investigations or for future therapeutic interventions to prevent negative hepatic outcomes in patients with HCV.

Effects of Chinese Herbal Medicines on the Risk of Overall Mortality, Readmission, and Reoperation in Hip Fracture Patients

Hip fracture is a major public health concern, with high incidence rates in the elderly worldwide. Hip fractures are associated with increased medical costs, patient dependency on families, and higher rates of morbidity and mortality. Chinese herbal medicine (CHM) is typically characterized as cost-effective and suitable for long-term use with few side effects. To better understand the effects of CHM on hip fracture patients, we utilized a population-based database to investigate the demographic characteristics, cumulative incidence of overall mortality, readmission, reoperation, and patterns of CHM prescription. We found that CHM usage was associated with a lower risk of overall mortality [P = 0.0009; adjusted hazard ratio (HR): 0.47, 95% confidence interval (CI): 0.30-0.73], readmission (P = 0.0345; adjusted HR: 0.67, 95% CI: 0.46-0.97), and reoperation (P = 0.0009; adjusted HR: 0.57, 95% CI: 0.40-0.79) after adjustment for age, type of hip fracture, surgical treatment type, and comorbidities. We also identified the herbal formulas, single herbs, and prescription patterns for the treatment of hip fracture by using association rule mining and network analysis. For hip fracture patients, the most common CHM coprescription pattern was Du-Zhong (DZ) → Xu-Duan (XD), followed by Du-Huo-Ji-Sheng-Tang (DHJST) → Shu-Jing-Huo-Xue-Tang (SJHXT), and Gu-Sui-Bu (GSB) → Xu-Duan (XD). Furthermore, XD was the core prescription, and DZ, GSB, SJHXT, and DHJST were important prescriptions located in cluster 1 of the prescription patterns. This study provides evidence for clinical CHM use as an adjunctive therapy that offers benefits to hip fracture patients.

Survey of disease awareness, treatment behavior and treatment satisfaction in patients with atopic dermatitis in Korea: A multicenter study

In Korea, there is a high dependency on oriental medicine and folk remedies (Korean J Asthma Allergy Clin Immunol, 25, 2005, 110). In addition, inaccurate information available through the Internet is increasing (Korean J Dermatol, 44, 2006, 137). So, there is always a possibility that patients may have difficulty obtaining accurate information about atopic dermatitis (AD). The aim was to determine the awareness, treatment behavior and treatment satisfaction of patients with AD and their caregivers. In October 2017, patients diagnosed with AD at nine hospitals were enrolled in this study. A questionnaire was completed by each patient. A total of 371 subjects were surveyed. In response to the question asking about knowledge of AD, the correct answer rate was 55.4%. Bathing using soap, body scrub and moisturizer showed favorable outcomes. A total of 54.9% patients responded that they were reluctant to use steroid ointment. When asked about their previous treatment, 39.6% reported using oriental medicine and 26.5% had tried folk remedies. The hospital treatment satisfaction score was 6.6. Patients usually applied their knowledge in their daily lives. However, there was a lot of inaccurate knowledge. Therefore, it is important for patients to understand the characteristics of this disease and obtain correct information.

Medication regularity of pulmonary fibrosis treatment by contemporary traditional Chinese medicine experts based on data mining

Background

Treatment of pulmonary fibrosis by traditional Chinese medicine (TCM) has accumulated important experience. Our interest is in exploring the medication regularity of contemporary Chinese medical specialists treating pulmonary fibrosis.

Methods

Through literature search, medical records from TCM experts who treat pulmonary fibrosis, which were published in Chinese and English medical journals, were selected for this study. As the object of study, a database was established after analysing the records. After data cleaning, the rules of medicine in the treatment of pulmonary fibrosis in medical records of TCM were explored by using data mining technologies such as frequency analysis, association rule analysis, and link analysis.

Results

A total of 124 medical records from 60 doctors were selected in this study; 263 types of medicinals were used a total of 5,455 times; the herbs that were used more than 30 times can be grouped into 53 species and were used a total of 3,681 times. Using main medicinals cluster analysis, medicinals were divided into qi-tonifying, yin-tonifying, blood-activating, phlegm-resolving, cough-suppressing, panting-calming, and ten other major medicinal categories. According to the set conditions, a total of 62 drug compatibility rules have been obtained, involving mainly qi-tonifying, yin-tonifying, blood-activating, phlegm-resolving, qi-descending, and panting-calming medicinals, as well as other medicinals used in combination.

Conclusions

The results of data mining are consistent with clinical practice and it is feasible to explore the medical rules applicable to the treatment of pulmonary fibrosis in medical records of TCM by data mining.

Evaluation of rational nonsteroidal anti-inflammatory drugs and gastro-protective agents use; association rule data mining using outpatient prescription patterns

Background

Nonsteroidal anti-inflammatory drugs (NSAIDs) and gastro-protective agents should be co-prescribed following a standard clinical practice guideline; however, adherence to this guideline in routine practice is unknown. This study applied an association rule model (ARM) to estimate rational NSAIDs and gastro-protective agents use in an outpatient prescriptions dataset.

Methods

A database of hospital outpatients from October 1st, 2013 to September 30th, 2015 was searched for any of following drugs: oral antacids (A02A), peptic ulcer and gastro-oesophageal reflux disease drugs (GORD, A02B), and anti-inflammatory and anti-rheumatic products, non-steroids or NSAIDs (M01A). Data including patient demographics, diagnoses, and drug utilization were also retrieved. An association rule model was used to analyze co-prescription of the same drug class (i.e., prescriptions within A02A-A02B, M01A) and between drug classes (A02A-A02B & M01A) using the Apriori algorithm in R. The lift value, was calculated by a ratio of confidence to expected confidence, which gave information about the association between drugs in the prescription.

Results

We identified a total of 404,273 patients with 2,575,331 outpatient visits in 2 fiscal years. Mean age was 48 years and 34% were male. Among A02A, A02B and M01A drug classes, 12 rules of associations were discovered with support and confidence thresholds of 1% and 50%. The highest lift was between Omeprazole and Ranitidine (340 visits); about one-third of these visits (118) were prescriptions to non-GORD patients, contrary to guidelines. Another finding was the concomitant use of COX-2 inhibitors (Etoricoxib or Celecoxib) and PPIs. 35.6% of these were for patients aged less than 60 years with no GI complication and no Aspirin, inconsistent with guidelines.

Conclusions

Around one-third of occasions where these medications were co-prescribed were inconsistent with guidelines. With the rapid growth of health datasets, data mining methods may help assess quality of care and concordance with guidelines and best evidence.

Identifying Chinese herbal medicine network for treating acne: Implications from a nationwide database

ETHNO-PHARMACOLOGICAL RELEVANCE

Acne is a highly prevalent inflammatory skin disease which causes patients great psychological stress, especially teenagers. Chinese herbal medicine (CHM) is commonly used to treat acne with personalized but complicated prescriptions. The aim of this study is to determine a CHM network and core CHM treatments for acne by analyzing a nationwide database.

MATERIALS AND METHODS

From January 1st to December 31st, 2011, all CHM prescriptions made for acne (ICD-9-CM code: 706.0 or 706.1) were included in this study. Visits with acupuncture, manual therapy or other treatment modalities were excluded, and CHM visits with other diagnoses were also excluded in final analysis. Association rule mining (ARM) and social network analysis (SNA) were used to explore and demonstrate a CHM network.

RESULTS

A total of 91,129 patients used traditional Chinese medicine, and 99% of them chose CHM for acne treatment. Most CHM users were teenagers, and there were twice as many female patients as male patients. A total of 279,823 CHM prescriptions were made for acne in 2011. Qing-Shang-Fang-Feng-Tang was the most commonly used CHM (31.2% of all prescriptions), and Zhen-Ren-Huo-Ming-Yin combined with Forsythia suspensa (Thunb.) Vahl. (Lian Qiao) was the most commonly used CHM-CHM combination. Thirty-one important CHM-CHM combinations were identified, and the CHM network could be built. Extensive coverage of the known pathogenesis of acne could be found in the CHM network when incorporating CHM pharmacological mechanisms into the network. Anti-inflammatory and anti-bacterial effects were commonly found in the CHM network, and CHMs with anti-androgen, anti-depressive and skin whitening effects were frequently used in combination.

CONCLUSIONS

The CHM combination patterns and core treatments for acne were disclosed in this study by applying network analysis to a CHM prescription database. These results may be beneficial for further bench or clinical studies when choosing target CHM.

Spatial Patterns of the Indications of Acupoints Using Data Mining in Classic Medical Text: A Possible Visualization of the Meridian System

The indications of acupoints are thought to be highly associated with the lines of the meridian systems. The present study used data mining methods to analyze the characteristics of the indications of each acupoint and to visualize the relationships between the acupoints and disease sites in the classic Korean medical text Chimgoogyeongheombang. Using a term frequency-inverse document frequency (tf-idf) scheme, the present study extracted valuable data regarding the indications of each acupoint according to the frequency of the cooccurrences of eight Source points and eighteen disease sites. Furthermore, the spatial patterns of the indications of each acupoint on a body map were visualized according to the tf-idf values. Each acupoint along the different meridians exhibited different constellation patterns at various disease sites. Additionally, the spatial patterns of the indications of each acupoint were highly associated with the route of the corresponding meridian. The present findings demonstrate that the indications of each acupoint were primarily associated with the corresponding meridian system. Furthermore, these findings suggest that the routes of the meridians may have clinical implications in terms of identifying the constellations of the indications of acupoints.

Chinese herbal medicine network and core treatments for allergic skin diseases: Implications from a nationwide database

ETHNO-PHARMACOLOGICAL RELEVANCE

Chinese herbal medicine (CHM) is commonly used to treat skin diseases, but CHM prescription patterns are difficult to understand due to their complexity and inter-connections. This study aimed to demonstrate CHM core treatments and network for treatment of allergic skin diseases by analyzing a nationwide prescription database.

MATERIALS AND METHODS

All CHM prescriptions made for atopic dermatitis (with age limitation ≤ 12 years) and urticaria for the entire year of 2011 were included. Association rule mining (ARM) combined with social network analysis (SNA) were used to analyze CHM prescriptions and explore the CHM prescription pattern and network.

RESULTS

A total of 27,350 and 97,188 prescriptions for atopic dermatitis and urticaria, respectively, were analyzed. Xiao-Feng-San (XFS) was the most commonly used CHM (32% of prescriptions for atopic dermatitis and 47.4% for urticaria) and was the core treatment for both diseases. Moreover, 42 and 82 important CHM-CHM combinations were identified to establish the CHM network, and XFS with Dictamnus dasycarpus Turcz was the most prevalent (6.4% for atopic dermatitis and 9.1% for urticaria). Traditional Chinese Medicine heat syndrome was most prevalent cause. Extensive anti-inflammation, anti-allergy, anti-oxidation, and anti-bacterial effects were also found among the CHMs.

CONCLUSIONS

Network analysis on CHM prescriptions provides graphic and comprehensive illustrations regarding CHM treatment for atopic dermatitis and urticaria. The CHM network analysis of prescriptions is essential to realize the CHM treatments and to select suitable candidates for clinical use or further studies.

Identifying chinese herbal medicine network for eczema: implications from a nationwide prescription database

Eczema is a highly prevalent dermatological disease that can severely affect the patient's quality of life. Chinese herbal medicine (CHM) is commonly used in combination for eczema due to the complicated pathogenesis. This study aimed to identify a CHM network for the treatment of eczema by using a nationwide database. During 2011, 381,282 CHM prescriptions made for eczema (ICD-9-CM 692.x) were obtained from the National Health Insurance Research Database (NHIRD) in Taiwan and analyzed by using association rule mining and social network analysis. Among 661 available CHMs, 44 important combinations were identified. Among the CHM networks, seven clusters with the predominant traditional Chinese medicine (TCM) pattern were recognized. The largest CHM cluster was used to treat the wind-dampness-heat pattern, and Xiao-Feng-San (24.1% of all prescriptions) was the core of this cluster with anti-inflammation, antioxidation, and antiallergic effects. Lonicera japonica (11.0% of all prescriptions) with Forsythia suspense (17.0% of all prescriptions) was the most commonly used CHM combination and was also the core treatment for treating the heat pattern, in which an antimicrobial effect is found. CHM network analysis is helpful for TCM doctors or researchers to choose candidates for clinical practice or further studies.

Use of traditional Chinese medicine reduces exposure to corticosteroid among atopic dermatitis children: a 1-year follow-up cohort study

ETHNOPHARMACOLOGICAL RELEVANCE

Atopic dermatitis is a prevalent dermatologic disease in children. Corticosteroid is an important treatment but side effects caused by long-term and excessive use heavily concern patients. Traditional Chinese medicine (TCM) is potentially an alternative treatment and might cause less adverse effects. This nationwide retrospective cohort study aimed to examine the hypothesis that TCM use is associated with lower exposure to corticosteroid.

MATERIALS AND METHODS

Children under 12 years of age with ICD-9 codes 691.8 and 692.x were identified as atopic dermatitis patients from 2007/1/1 to 2007/12/31. Corticosteroid use was compared between TCM users and non-users for one-year follow-up by using a general estimation equation model with propensity-score matching.

RESULTS

A total of 9012 TCM users were identified and the use of corticosteroid after treatment was compared with matched TCM non-users. Use of TCM significantly reduced exposure to corticosteroids after 1-year follow-up. Among TCM users, the exposure to any corticosteroids was lower (42.1% reduction in TCM users versus 34.5% increase in TCM non-users, relative risk: 0.36; p-Value<0.001), the duration was shorter (relative risk for using corticosteroid more than 14 days: 0.37; p-Value<0.001), and the rate of frequent visits with steroid prescription was also lower. CHM was the most commonly used TCM modality (98.5% of all visits) and Xiao-Feng-San was the most commonly used CHM (33% of all prescriptions) with extensive coverage for pathogenesis of atopic dermatitis.

CONCLUSIONS

Lower use rate of corticosteroid can be found after TCM treatment, which can be considered as an integrative therapy for atopic dermatitis. Further studies are warranted on the basis of this study.

Data Mining of Acupoint Characteristics from the Classical Medical Text: DongUiBoGam of Korean Medicine

Throughout the history of East Asian medicine, different kinds of acupuncture treatment experiences have been accumulated in classical medical texts. Reexamining knowledge from classical medical texts is expected to provide meaningful information that could be utilized in current medical practices. In this study, we used data mining methods to analyze the association between acupoints and patterns of disorder with the classical medical book DongUiBoGam of Korean medicine. Using the term frequency-inverse document frequency (tf-idf) method, we quantified the significance of acupoints to its targeting patterns and, conversely, the significance of patterns to acupoints. Through these processes, we extracted characteristics of each acupoint based on its treating patterns. We also drew practical information for selecting acupoints on certain patterns according to their association. Data analysis on DongUiBoGam's acupuncture treatment gave us an insight into the main idea of DongUiBoGam. We strongly believe that our approach can provide a novel understanding of unknown characteristics of acupoint and pattern identification from the classical medical text using data mining methods.

Hedyotis diffusa Combined with Scutellaria barbata Are the Core Treatment of Chinese Herbal Medicine Used for Breast Cancer Patients: A Population-Based Study

Traditional Chinese medicine (TCM), which is the most common type of complementary and alternative medicine (CAM) used in Taiwan, is increasingly used to treat patients with breast cancer. However, large-scale studies on the patterns of TCM prescriptions for breast cancer are still lacking. The aim of this study was to determine the core treatment of TCM prescriptions used for breast cancer recorded in the Taiwan National Health Insurance Research Database. TCM visits made for breast cancer in 2008 were identified using ICD-9 codes. The prescriptions obtained at these TCM visits were evaluated using association rule mining to evaluate the combinations of Chinese herbal medicine (CHM) used to treat breast cancer patients. A total of 37,176 prescriptions were made for 4,436 outpatients with breast cancer. Association rule mining and network analysis identified Hedyotis diffusa plus Scutellaria barbata as the most common duplex medicinal (10.9%) used for the core treatment of breast cancer. Jia-Wei-Xiao-Yao-San (19.6%) and Hedyotis diffusa (41.9%) were the most commonly prescribed herbal formula (HF) and single herb (SH), respectively. Only 35% of the commonly used CHM had been studied for efficacy. More clinical trials are needed to evaluate the efficacy and safety of these CHM used to treat breast cancer.

Inferring characteristic phenotypes via class association rule mining in the bone dysplasia domain

Finding, capturing and describing characteristic features represents a key aspect in disorder definition, diagnosis and management. This process is particularly challenging in the case of rare disorders, due to the sparse nature of data and expertise. From a computational perspective, finding characteristic features is associated with some additional major challenges, such as formulating a computationally tractable definition, devising appropriate inference algorithms or defining sound validation mechanisms. In this paper we aim to deal with each of these problems in the context provided by the skeletal dysplasia domain. We propose a clear definition for characteristic phenotypes, we experiment with a novel, class association rule mining algorithm and we discuss our lessons learned from both an automatic and human-based validation of our approach.

A probabilistic model for reducing medication errors

Background

Medication errors are common, life threatening, costly but preventable. Information technology and automated systems are highly efficient for preventing medication errors and therefore widely employed in hospital settings. The aim of this study was to construct a probabilistic model that can reduce medication errors by identifying uncommon or rare associations between medications and diseases.

Methods and Finding(s)

Association rules of mining techniques are utilized for 103.5 million prescriptions from Taiwan’s National Health Insurance database. The dataset included 204.5 million diagnoses with ICD9-CM codes and 347.7 million medications by using ATC codes. Disease-Medication (DM) and Medication-Medication (MM) associations were computed by their co-occurrence and associations’ strength were measured by the interestingness or lift values which were being referred as Q values. The DMQs and MMQs were used to develop the AOP model to predict the appropriateness of a given prescription. Validation of this model was done by comparing the results of evaluation performed by the AOP model and verified by human experts. The results showed 96% accuracy for appropriate and 45% accuracy for inappropriate prescriptions, with a sensitivity and specificity of 75.9% and 89.5%, respectively.

Conclusions

We successfully developed the AOP model as an efficient tool for automatic identification of uncommon or rare associations between disease-medication and medication-medication in prescriptions. The AOP model helps to reduce medication errors by alerting physicians, improving the patients’ safety and the overall quality of care.