DDI-MuG: Multi-aspect graphs for drug-drug interaction extraction.

Introduction: Drug-drug interaction (DDI) may lead to adverse reactions in patients, thus it is important to extract such knowledge from biomedical texts. However, previously proposed approaches typically focus on capturing sentence-aspect information while ignoring valuable knowledge concerning the whole corpus. In this paper, we propose a Multi-aspect Graph-based DDI extraction model, named DDI-MuG. Methods: We first employ a bio-specific pre-trained language model to obtain the token contextualized representations. Then we use two graphs to get syntactic information from input instance and word co-occurrence information within the entire corpus, respectively. Finally, we combine the representations of drug entities and verb tokens for the final classification. Results: To validate the effectiveness of the proposed model, we perform extensive experiments on two widely used DDI extraction dataset, DDIExtraction-2013 and TAC 2018. It is encouraging to see that our model outperforms all twelve state-of-the-art models. Discussion: In contrast to the majority of earlier models that rely on the black-box approach, our model enables visualization of crucial words and their interrelationships by utilizing edge information from two graphs. To the best of our knowledge, this is the first model that explores multi-aspect graphs to the DDI extraction task, and we hope it can establish a foundation for more robust multi-aspect works in the future.

Phenonizer: A Fine-Grained Phenotypic Named Entity Recognizer for Chinese Clinical Texts.

Biomedical named entity recognition (BioNER) from clinical texts is a fundamental task for clinical data analysis due to the availability of large volume of electronic medical record data, which are mostly in free text format, in real-world clinical settings. Clinical text data incorporates significant phenotypic medical entities (e.g., symptoms, diseases, and laboratory indexes), which could be used for profiling the clinical characteristics of patients in specific disease conditions (e.g., Coronavirus Disease 2019 (COVID-19)). However, general BioNER approaches mostly rely on coarse-grained annotations of phenotypic entities in benchmark text dataset. Owing to the numerous negation expressions of phenotypic entities (e.g., "no fever," "no cough," and "no hypertension") in clinical texts, this could not feed the subsequent data analysis process with well-prepared structured clinical data. In this paper, we developed Human-machine Cooperative Phenotypic Spectrum Annotation System (http://www.tcmai.org/login, HCPSAS) and constructed a fine-grained Chinese clinical corpus. Thereafter, we proposed a phenotypic named entity recognizer: Phenonizer, which utilized BERT to capture character-level global contextual representation, extracted local contextual features combined with bidirectional long short-term memory, and finally obtained the optimal label sequences through conditional random field. The results on COVID-19 dataset show that Phenonizer outperforms those methods based on Word2Vec with an F1-score of 0.896. By comparing character embeddings from different data, it is found that character embeddings trained by clinical corpora can improve F-score by 0.0103. In addition, we evaluated Phenonizer on two kinds of granular datasets and proved that fine-grained dataset can boost methods' F1-score slightly by about 0.005. Furthermore, the fine-grained dataset enables methods to distinguish between negated symptoms and presented symptoms. Finally, we tested the generalization performance of Phenonizer, achieving a superior F1-score of 0.8389. In summary, together with fine-grained annotated benchmark dataset, Phenonizer proposes a feasible approach to effectively extract symptom information from Chinese clinical texts with acceptable performance.

Utilizing Text Mining, Data Linkage and Deep Learning in Police and Health Records to Predict Future Offenses in Family and Domestic Violence.

Family and Domestic violence (FDV) is a global problem with significant social, economic, and health consequences for victims including increased health care costs, mental trauma, and social stigmatization. In Australia, the estimated annual cost of FDV is $22 billion, with one woman being murdered by a current or former partner every week. Despite this, tools that can predict future FDV based on the features of the person of interest (POI) and victim are lacking. The New South Wales Police Force attends thousands of FDV events each year and records details as fixed fields (e.g., demographic information for individuals involved in the event) and as text narratives which describe abuse types, victim injuries, threats, including the mental health status for POIs and victims. This information within the narratives is mostly untapped for research and reporting purposes. After applying a text mining methodology to extract information from 492,393 FDV event narratives (abuse types, victim injuries, mental illness mentions), we linked these characteristics with the respective fixed fields and with actual mental health diagnoses obtained from the NSW Ministry of Health for the same cohort to form a comprehensive FDV dataset. These data were input into five deep learning models (MLP, LSTM, Bi-LSTM, Bi-GRU, BERT) to predict three FDV offense types ("hands-on," "hands-off," "Apprehended Domestic Violence Order (ADVO) breach"). The transformer model with BERT embeddings returned the best performance (69.00% accuracy; 66.76% ROC) for "ADVO breach" in a multilabel classification setup while the binary classification setup generated similar results. "Hands-off" offenses proved the hardest offense type to predict (60.72% accuracy; 57.86% ROC using BERT) but showed potential to improve with fine-tuning of binary classification setups. "Hands-on" offenses benefitted least from the contextual information gained through BERT embeddings in which MLP with categorical embeddings outperformed it in three out of four metrics (65.95% accuracy; 78.03% F1-score; 70.00% precision). The encouraging results indicate that future FDV offenses can be predicted using deep learning on a large corpus of police and health data. Incorporating additional data sources will likely increase the performance which can assist those working on FDV and law enforcement to improve outcomes and better manage FDV events.

CovidXrayNet: Optimizing data augmentation and CNN hyperparameters for improved COVID-19 detection from CXR.

To mitigate the spread of the current coronavirus disease 2019 (COVID-19) pandemic, it is crucial to have an effective screening of infected patients to be isolated and treated. Chest X-Ray (CXR) radiological imaging coupled with Artificial Intelligence (AI) applications, in particular Convolutional Neural Network (CNN), can speed the COVID-19 diagnostic process. In this paper, we optimize the data augmentation and the CNN hyperparameters for detecting COVID-19 from CXRs in terms of validation accuracy. This optimization increases the accuracy of the popular CNN architectures such as the Visual Geometry Group network (VGG-19) and the Residual Neural Network (ResNet-50), by 11.93% and 4.97%, respectively. We then proposed CovidXrayNet model that is based on EfficientNet-B0 and our optimization results. We evaluated CovidXrayNet on two datasets, including our generated balanced COVIDcxr dataset (960 CXRs) and the benchmark COVIDx dataset (15,496 CXRs). With only 30 epochs of training, CovidXrayNet achieves state-of-the-art accuracy of 95.82% on the COVIDx dataset in the three-class classification task (COVID-19, normal or pneumonia). The CovidXRayNet model, the COVIDcxr dataset, and several optimization experiments are publicly available at https://github.com/MaramMonshi/CovidXrayNet.

A novel method for clinical risk prediction with low-quality data.

In real-world data, predictive models for clinical risks (such as adverse drug reactions, hospital readmission, and chronic disease onset) are constantly struggling with low-quality issues, namely redundant and highly correlated features, extreme category imbalances, and most importantly, a large number of missing values. In most existing work, each patient is represented as a value vector with the fixed-length from some feature space, and missing values are forced to be imputed, which introduces much noise for prediction if the data set is highly incomplete. Besides, other challenges are either remaining unresolved or only partially solved when modeling, but without a systematic approach. In this paper, we propose a novel framework to address these low-quality problems, that we first treat patients as bags with the various number of feature-value pairs, called instances, and map them to an embedding space through our proposed feature embedding method to learn from it directly. In this way, predictive models can avoid the negative impact of missing data naturally. A novel multi-instance neural network is then connected, using two computational modules to deal with the problems of correlated and redundant features: multi-head attention and attention-based multi-instance pooling. They are capable of capturing the instance correlations and locating valuable information in each instance or bag. The feature embedding and multi-instance neural network are parameterized and optimized jointly in an end-to-end manner. Moreover, the training process is under both main and auxiliary supervision with focal loss functions to avoid the caveat of a highly imbalanced label set. This proposed framework is named AMI-Net3. We evaluate it on three suitable data sets from real-world settings with different clinical risk prediction tasks: adverse drug reaction of risperidone, schizophrenia relapse, and invasive fungi infection, respectively. The comprehensive experimental results demonstrate the effectiveness and superiority of our proposed method over competitive baselines.

Clinical features and the traditional Chinese medicine therapeutic characteristics of 293 COVID-19 inpatient cases.

Coronavirus disease 2019 (COVID-19) is now pandemic worldwide and has heavily overloaded hospitals in Wuhan City, China during the time between late January and February. We reported the clinical features and therapeutic characteristics of moderate COVID-19 cases in Wuhan that were treated via the integration of traditional Chinese medicine (TCM) and Western medicine. We collected electronic medical record (EMR) data, which included the full clinical profiles of patients, from a designated TCM hospital in Wuhan. The structured data of symptoms and drugs from admission notes were obtained through an information extraction process. Other key clinical entities were also confirmed and normalized to obtain information on the diagnosis, clinical treatments, laboratory tests, and outcomes of the patients. A total of 293 COVID-19 inpatient cases, including 207 moderate and 86 (29.3%) severe cases, were included in our research. Among these cases, 238 were discharged, 31 were transferred, and 24 (all severe cases) died in the hospital. Our COVID-19 cases involved elderly patients with advanced ages (57 years on average) and high comorbidity rates (61%). Our results reconfirmed several well-recognized risk factors, such as age, gender (male), and comorbidities, as well as provided novel laboratory indications (e.g., cholesterol) and TCM-specific phenotype markers (e.g., dull tongue) that were relevant to COVID-19 infections and prognosis. In addition to antiviral/antibiotics and standard supportive therapies, TCM herbal prescriptions incorporating 290 distinct herbs were used in 273 (93%) cases. The cases that received TCM treatment had lower death rates than those that did not receive TCM treatment (17/273 = 6.2% vs. 7/20= 35%, P = 0.0004 for all cases; 17/77= 22% vs. 7/9= 77.7%, P = 0.002 for severe cases). The TCM herbal prescriptions used for the treatment of COVID-19 infections mainly consisted of Pericarpium Citri Reticulatae, Radix Scutellariae, Rhizoma Pinellia, and their combinations, which reflected the practical TCM principles (e.g., clearing heat and dampening phlegm). Lastly, 59% of the patients received treatment, including antiviral, antibiotics, and Chinese patent medicine, before admission. This situation might have some effects on symptoms, such as fever and dry cough. By using EMR data, we described the clinical features and therapeutic characteristics of 293 COVID-19 cases treated via the integration of TCM herbal prescriptions and Western medicine. Clinical manifestations and treatments before admission and in the hospital were investigated. Our results preliminarily showed the potential effectiveness of TCM herbal prescriptions and their regularities in COVID-19 treatment.

Deep learning in generating radiology reports: A survey.

Substantial progress has been made towards implementing automated radiology reporting models based on deep learning (DL). This is due to the introduction of large medical text/image datasets. Generating radiology coherent paragraphs that do more than traditional medical image annotation, or single sentence-based description, has been the subject of recent academic attention. This presents a more practical and challenging application and moves towards bridging visual medical features and radiologist text. So far, the most common approach has been to utilize publicly available datasets and develop DL models that integrate convolutional neural networks (CNN) for image analysis alongside recurrent neural networks (RNN) for natural language processing (NLP) and natural language generation (NLG). This is an area of research that we anticipate will grow in the near future. We focus our investigation on the following critical challenges: understanding radiology text/image structures and datasets, applying DL algorithms (mainly CNN and RNN), generating radiology text, and improving existing DL based models and evaluation metrics. Lastly, we include a critical discussion and future research recommendations. This survey will be useful for researchers interested in DL, particularly those interested in applying DL to radiology reporting.

Worldwide research trends on aristolochic acids (1957-2017): Suggestions for researchers.

Aristolochic acids and their derivatives are components of many traditional medicines that have been used for thousands of years, particularly in Asian countries. To study the trends of research into aristolochic acids and provide suggestions for future study, we performed the following work. In this paper, we performed a bibliometric analysis using CiteSpace and HistCite software. We reviewed the three phases of the development of aristolochic acids by using bibliometrics. In addition, we performed a longitudinal review of published review articles over 60 years: 1,217 articles and 189 review articles on the history of aristolochic acid research published between 1957 and 2017 were analyzed. The performances of relevant countries, institutions, and authors are presented; the evolutionary trends of different categories are revealed; the history of research into aristolochic acids is divided into three phases, each of which has unique characteristics; and a roadmap of the historical overview of aristolochic acid research is finally established. Finally, five pertinent suggestions for future research into aristolochic acid are offered: (1) The study of the antitumor efficacy of aristolochic acids is of value; (2) The immune activity of aristolochic acids should be explored further; (3) Researchers should perform a thorough overview of the discovery of naturally occurring aristolochic acids; (4) More efforts should be directed toward exploring the correlation between aristolochic acid mutational signature and various cancers; (5) Further efforts should be devoted to the research and review work related to analytical chemistry. Our study is expected to benefit researchers in shaping future research directions.

Prediction of Radix Astragali Immunomodulatory Effect of CD80 Expression from Chromatograms by Quantitative Pattern-Activity Relationship.

The current use of a single chemical component as the representative quality control marker of herbal food supplement is inadequate. In this CD80-Quantitative-Pattern-Activity-Relationship (QPAR) study, we built a bioactivity predictive model that can be applicable for complex mixtures. Through integrating the chemical fingerprinting profiles of the immunomodulating herb Radix Astragali (RA) extracts, and their related biological data of immunological marker CD80 expression on dendritic cells, a chemometric model using the Elastic Net Partial Least Square (EN-PLS) algorithm was established. The EN-PLS algorithm increased the biological predictive capability with lower value of RMSEP (11.66) and higher values of Rp2 (0.55) when compared to the standard PLS model. This CD80-QPAR platform provides a useful predictive model for unknown RA extract's bioactivities using the chemical fingerprint inputs. Furthermore, this bioactivity prediction platform facilitates identification of key bioactivity-related chemical components within complex mixtures for future drug discovery and understanding of the batch-to-batch consistency for quality clinical trials.

An Ensemble Approach for Record Matching in Data Linkage.

OBJECTIVES: To develop and test an optimal ensemble configuration of two complementary probabilistic data matching techniques namely Fellegi-Sunter (FS) and Jaro-Wrinkler (JW) with the goal of improving record matching accuracy. METHODS: Experiments and comparative analyses were carried out to compare matching performance amongst the ensemble configurations combining FS and JW against the two techniques independently. RESULTS: Our results show that an improvement can be achieved when FS technique is applied to the remaining unsure and unmatched records after the JW technique has been applied. DISCUSSION: Whilst all data matching techniques rely on the quality of a diverse set of demographic data, FS technique focuses on the aggregating matching accuracy from a number of useful variables and JW looks closer into matching the data content (spelling in this case) of each field. Hence, these two techniques are shown to be complementary. In addition, the sequence of applying these two techniques is critical. CONCLUSION: We have demonstrated a useful ensemble approach that has potential to improve data matching accuracy, particularly when the number of demographic variables is limited. This ensemble technique is particularly useful when there are multiple acceptable spellings in the fields, such as names and addresses.

Ensemble learning for prediction of the bioactivity capacity of herbal medicines from chromatographic fingerprints.

BACKGROUND: Recent quality control of complex mixtures, including herbal medicines, is not limited to chemical chromatographic definition of one or two selected compounds; multivariate linear regression methods with dimension reduction or regularisation have been used to predict the bioactivity capacity from the chromatographic fingerprints of the herbal extracts. The challenge of this type of analysis requires a multi-dimensional approach at two levels: firstly each herb comprises complex mixtures of active and non-active chemical components; and secondly there are many factors relating to the growth, production, and processing of the herbal products. All these factors result in the significantly diverse concentrations of bioactive compounds in the herbal products. Therefore, it is imminent to have a predictive model with better generalisation that can accurately predict the bioactivity capacity of samples when only the chemical fingerprints data are available. RESULTS: In this study, the algorithm of Stacking Multivariate Linear Regression (SMLR) and a few other commonly used chemometric approaches were evaluated. They were to predict the Cluster of Differentiation 80 (CD80) expression bioactivity of a commonly used herb, Astragali Radix (AR), from the corresponding chemical chromatographic fingerprints. SMLR provides a superior prediction accuracy in comparison with the other multivariate linear regression methods of PCR, PLSR, OPLS and EN in terms of MSEtest and the goodness of prediction of test samples. CONCLUSIONS: SMLR is a better platform than some multivariate linear regression methods. The first advantage of SMLR is that it has better generalisation to predict the bioactivity capacity of herbal medicines from their chromatographic fingerprints. Future studies should aim to further improve the SMLR algorithm. The second advantage of SMLR is that single chemical compounds can be effectively identified as highly bioactive components which demands further CD80 bioactivity confirmation..

Mining Symptom-Herb Patterns from Patient Records Using Tripartite Graph.

Unlike the western medical approach where a drug is prescribed against specific symptoms of patients, traditional Chinese medicine (TCM) treatment has a unique step, which is called syndrome differentiation (SD). It is argued that SD is considered as patient classification because prior to the selection of the most appropriate formula from a set of relevant formulae for personalization, a practitioner has to label a patient belonging to a particular class (syndrome) first. Hence, to detect the patterns between herbs and symptoms via syndrome is a challenging problem; finding these patterns can help prepare a prescription that contributes to the efficacy of a treatment. In order to highlight this unique triangular relationship of symptom, syndrome, and herb, we propose a novel three-step mining approach. It first starts with the construction of a heterogeneous tripartite information network, which carries richer information. The second step is to systematically extract path-based topological features from this tripartite network. Finally, an unsupervised method is used to learn the best parameters associated with different features in deciding the symptom-herb relationships. Experiments have been carried out on four real-world patient records (Insomnia, Diabetes, Infertility, and Tourette syndrome) with comprehensive measurements. Interesting and insightful experimental results are noted and discussed.

An improved independent component analysis model for 3D chromatogram separation and its solution by multi-areas genetic algorithm.

BACKGROUND: The 3D chromatogram generated by High Performance Liquid Chromatography-Diode Array Detector (HPLC-DAD) has been researched widely in the field of herbal medicine, grape wine, agriculture, petroleum and so on. Currently, most of the methods used for separating a 3D chromatogram need to know the compounds' number in advance, which could be impossible especially when the compounds are complex or white noise exist. New method which extracts compounds from 3D chromatogram directly is needed. METHODS: In this paper, a new separation model named parallel Independent Component Analysis constrained by Reference Curve (pICARC) was proposed to transform the separation problem to a multi-parameter optimization issue. It was not necessary to know the number of compounds in the optimization. In order to find all the solutions, an algorithm named multi-areas Genetic Algorithm (mGA) was proposed, where multiple areas of candidate solutions were constructed according to the fitness and distances among the chromosomes. RESULTS: Simulations and experiments on a real life HPLC-DAD data set were used to demonstrate our method and its effectiveness. Through simulations, it can be seen that our method can separate 3D chromatogram to chromatogram peaks and spectra successfully even when they severely overlapped. It is also shown by the experiments that our method is effective to solve real HPLC-DAD data set. CONCLUSIONS: Our method can separate 3D chromatogram successfully without knowing the compounds' number in advance, which is fast and effective.

Increased workload for systematic review literature searches of diagnostic tests compared with treatments: challenges and opportunities.

BACKGROUND: Comprehensive literature searches are conducted over multiple medical databases in order to meet stringent quality standards for systematic reviews. These searches are often very laborious, with authors often manually screening thousands of articles. Information retrieval (IR) techniques have proven increasingly effective in improving the efficiency of this process. IR challenges for systematic reviews involve building classifiers using training data with very high class-imbalance, and meeting the requirement for near perfect recall on relevant studies. Traditionally, most systematic reviews have focused on questions relating to treatment. The last decade has seen a large increase in the number of systematic reviews of diagnostic test accuracy (DTA). OBJECTIVE: We aim to demonstrate that DTA reviews comprise an especially challenging subclass of systematic reviews with respect to the workload required for literature screening. We identify specific challenges for the application of IR to literature screening for DTA reviews, and identify potential directions for future research. METHODS: We hypothesize that IR for DTA reviews face three additional challenges, compared to systematic reviews of treatments. These include an increased class-imbalance, a broader definition of the target class, and relative inadequacy of available metadata (ie, medical subject headings (MeSH) terms for medical literature analysis and retrieval system online). Assuming these hypotheses to be true, we identify five manifestations when we compare literature searches of DTA versus treatment. These manifestations include: an increase in the average number of articles screened, and increase in the average number of full-text articles obtained, a decrease in the number of included studies as a percentage of full-text articles screened, a decrease in the number of included studies as a percentage of all articles screened, and a decrease in the number of full-text articles obtained as a percentage of all articles screened. As of July 12 2013, 13 published Cochrane DTA reviews were available and all were included. For each DTA review, we randomly selected 15 treatment reviews published by the corresponding Cochrane Review Group (N=195). We then statistically tested differences in these five hypotheses, for the DTA versus treatment reviews. RESULTS: Despite low statistical power caused by the small sample size for DTA reviews, strong (P<.01) or very strong (P<.001) evidence was obtained to support three of the five expected manifestations, with evidence for at least one manifestation of each hypothesis. The observed difference in effect sizes are substantial, demonstrating the practical difference in reviewer workload. CONCLUSIONS: Reviewer workload (volume of citations screened) when screening literature for systematic reviews of DTA is especially high. This corresponds to greater rates of class-imbalance when training classifiers for automating literature screening for DTA reviews. Addressing concerns such as lower quality metadata and effectively modelling the broader target class could help to alleviate such challenges, providing possible directions for future research.

Application of genetic algorithm for discovery of core effective formulae in TCM clinical data.

Research on core and effective formulae (CEF) does not only summarize traditional Chinese medicine (TCM) treatment experience, it also helps to reveal the underlying knowledge in the formulation of a TCM prescription. In this paper, CEF discovery from tumor clinical data is discussed. The concepts of confidence, support, and effectiveness of the CEF are defined. Genetic algorithm (GA) is applied to find the CEF from a lung cancer dataset with 595 records from 161 patients. The results had 9 CEF with positive fitness values with 15 distinct herbs. The CEF have all had relative high average confidence and support. A herb-herb network was constructed and it shows that all the herbs in CEF are core herbs. The dataset was divided into CEF group and non-CEF group. The effective proportions of former group are significantly greater than those of latter group. A Synergy index (SI) was defined to evaluate the interaction between two herbs. There were 4 pairs of herbs with high SI values to indicate the synergy between the herbs. All the results agreed with the TCM theory, which demonstrates the feasibility of our approach.

Evidence-based toxicity evaluation and scheduling of Chinese herbal medicines.

ETHNOPHARMACOLOGICAL RELEVANCE: While there is an increasing number of toxicity report cases and toxicological studies on Chinese herbal medicines, the guidelines for toxicity evaluation and scheduling of Chinese herbal medicines are lacking. AIM: The aim of this study was to review the current literature on potentially toxic Chinese herbal medicines, and to develop a scheduling platform which will inform an evidence-based regulatory framework for these medicines in the community. MATERIALS AND METHODS: The Australian and Chinese regulations were used as a starting point to compile a list of potentially toxic herbs. Systematic literature searches of botanical and pharmaceutical Latin name, English and Chinese names and suspected toxic chemicals were conducted on Medline, PubMed and Chinese CNKI databases. RESULTS: Seventy-four Chinese herbal medicines were identified and five of them were selected for detailed study. Preclinical and clinical data were summarised at six levels. Based on the evaluation criteria, which included risk-benefit analysis, severity of toxic effects and clinical and preclinical data, four regulatory classes were proposed: Prohibited for medicinal usage, which are those with high toxicity and can lead to injury or death, e.g., aristolochia; Restricted for medicinal usage, e.g., aconite, asarum, and ephedra; Required warning label, e.g., coltsfoot; and Over-the-counter herbs for those herbs with a safe toxicity profile. CONCLUSION: Chinese herbal medicines should be scheduled based on a set of evaluation criteria, to ensure their safe use and to satisfy the need for access to the herbs. The current Chinese and Australian regulation of Chinese herbal medicines should be updated to restrict the access of some potentially toxic herbs to Chinese medicine practitioners who are qualified through registration.

Feature representation in the biclustering of symptom-herb relationship in Chinese medicine.

OBJECTIVE: To find an appropriate feature representation in the biclustering of symptom-herb relationship in Chinese medicine (CM). METHODS: Four different representation schemes were tested in identifying the complex relationship between symptoms and herbs using a biclustering algorithm on an insomnia data set. These representation schemes were effective count, binary value, relative success ratio, or modified relative success ratio. The comparison of the schemes was made on the number and size of biclusters with respect to different threshold values. RESULTS AND CONCLUSIONS: The modified relative success ratio scheme was the most appropriate feature representation among the four tested. Some of the biclusters selected from this representation scheme were known to follow the therapeutic principles of CM, while others may offer clues for further clinical investigations.

A novel approach in discovering significant interactions from TCM patient prescription data.

The efficacy of a traditional Chinese medicine medication derives from the complex interactions of herbs or Chinese Materia Medica in a formula. The aim of this paper is to propose a new approach to systematically generate combinations of interacting herbs that might lead to good outcome. Our approach was tested on a data set of prescriptions for diabetic patients to verify the effectiveness of detected combinations of herbs. This approach is able to detect effective higher orders of herb-herb interactions with statistical validation. We present an exploratory analysis of clinical records using a pattern mining approach called Interaction Rules Mining.