Clinical Terminology Research Articles

Conventional medical attitudes to using a traditional medicine vodou-based model of pain management: survey of French dentists and the proposal of a pain model to facilitate integration

ObjectivesThe purposes of this study were to develop a pain management model using traditional medicine (TM) vodou healing methods; to survey a sample of French dentists to rate components of conventional and proposed TM vodou-based pain management model; and to assess the possibility of conventional, allopathic providers to integrate TM or complementary and alternative medicine concepts. MethodsFrom a set of 30 fact sheets collected from TM African healers (vodou healers), main clinical concepts and terminology were extracted. Twenty vodou-based pain management concepts were collected from an interview with a TM vodou practitioner. From this information, a 7-step vodou-based pain management model was created. A sample of 40 French dentists from Nantes, France, whose practices focused on the clinical treatment of dental pain, was surveyed to assess the importance of both TM (vodou) and conventional biomedical components. ResultsSeventy percent of the dentists sampled rated the rational components of the TM model as “very important” or “important” for pain treatment, whereas 2 other traditional concepts were considered to be “supernatural” or beyond understanding. ConclusionThis study showed that traditional healers used conventional concepts and conventional practitioners could use traditional concepts. This suggests that conventional allopathic medical providers have the capacity to integrate biomedical concepts and other therapeutic and explanatory models. This information may be helpful to understand and improve risk management by anticipating and preventing potential reasons for failure in TM integration strategies and to enhance communication between patients, healers, and physicians to optimize TM or complementary and alternative medicine integration.

ABC3 Part I: a review of the guidelines for terminology, classification and management of cervical cytology in England

The provision of guidance on cytology reporting and evaluation, first outlined in 1995 with the publication of Achievable Standards, Benchmarks for Reporting, and Criteria for Evaluating Cervical Cytopathology (ABC), and subsequently revised and expanded in a second edition in 2000, has been pivotal to the success of the National Health Service Cervical Screening Programme (NHSCSP), ensuring that standards are upheld, and that rigorous evaluation and quality assurance take place. In the last decade, major changes to the NHSCSP, notably the adoption of revised age ranges and screening intervals for all women in England, implementation of liquid-based cytology and, most recently, the decision to introduce high-risk human papillomavirus (HR-HPV) testing for triage of low-grade and borderline (equivalent to 'atypical') cytological abnormalities and test of cure after treatment of cervical intraepithelial neoplasia (CIN) determined that an updated version of ABC was required. The third edition of ABC recommends adoption, with minor modification, of the revised British Society for Clinical Cytology terminology and provides guidance on the management of abnormal cytology results linked to this terminology taking account of HR-HPV testing. To accommodate these changes, expanded result codes, which are electronic codes used to transfer management information to central computers for follow-up, call and recall of individual women, have been developed. Further guidance on specimen adequacy is also provided. Revised performance indicators are described and explained in a separate article by R. Blanks in this issue of Cytopathology. All the changes in ABC3 are designed to support the mission statement of the NHSCSP that 'the objective of cervical screening is to reduce cervical cancer incidence and mortality by screening with a high sensitivity for the detection of CIN2 or worse, whilst maintaining a high specificity'.

Predefined headings in a multiprofessional electronic health record system

Applying multiprofessional electronic health records (EHRs) is expected to improve the quality of patient care and patient safety. Both EHR systems and system users depend on semantic interoperability to function efficiently. A shared clinical terminology comprising unambiguous terms is required for semantic interoperability. Empirical studies of clinical terminology, such as predefined headings, in EHR systems are scarce and limited to one profession or one clinical specialty. To study predefined headings applied by users in a Swedish multiprofessional EHR system. This was a descriptive study of predefined headings (n=3596) applied by 5509 users in a Swedish multiprofessional EHR system. The predefined headings were classified into four term and word categories. Less than half of the predefined headings were shared by two or more professional groups. All eight professionals groups shared 1.7% of the predefined headings. The distribution of predefined headings across categories yielded two-thirds "terms for special purposes" and "specialist terms" and one-third "common words" and "unclassified headings". The indicated presence of profession-specific predefined headings and the conflict between ambiguity and comprehension of terms and words used as headings are discussed. The predefined headings in the multiprofessional EHR system studied did not constitute a joint language for specific purposes. The improvement of the quality and usability of multiprofessional EHR systems requires attention.

A survey of SNOMED CT implementations

The Systematised Nomenclature of Medicine Clinical Terms (SNOMED CT) has been designated as the recommended clinical reference terminology for use in clinical information systems around the world and is reported to be used in over 50 countries. However, there are still few implementation details. This study examined the implementation of SNOMED CT in terms of design, use and maintenance issues involved in 13 healthcare organisations across eight countries through a series of interviews with 14 individuals. While a great deal of effort has been spent on developing and refining SNOMED CT, there is still much work ahead to bring SNOMED CT into routine clinical use.

Ontology Matching: An Ultimate Solution for Semantic Interoperability in Healthcare

healthcare domain is a complex domain which lacks a unified terminological set, most especially in clinical cases. As a result of this, the messaging standards employed in the healthcare domain use different terms for the same concept which often results in clinical misinterpretation, knowledge mismanagement, misdiagnosis of the patient's illness or even death. Consequently, the healthcare system is characterized by high error rate and semantic heterogeneity. A lot of efforts have been made to resolve this problem through the use of standards, clinical terminologies, web services as well as the use of achetype. However, these solutions have proved unsuccessful in resolving semantic heterogeneity in healthcare. Ontologies have also been developed to resolve this problem by making explicit the meaning of terms used in healthcare. Ontologies provide a source of shared and precisely defined terms, resulting in interoperability by knowledge sharing and reuse. Unfortunately, the variety of ways that the healthcare domain is conceptualized results in the creation of different ontologies with contradicting or overlapping parts. Thus, the available ontologies also introduce semantic heterogeneity to this domain. An effective solution to this problem is the introduction of methods for finding matches among the various components of ontologies in healthcare in order to facilitate semantic interoperability. Therefore, this paper aims at examining the various attempts for achieving semantic interoperability in healthcare and also motivates the critical needs for ontology matching in healthcare systems. General Terms Ontology, Interoperability, Semantic. Keywordsntology, ontology matching, semantic heterogeneity, interoperability, semantic interoperability.

The freetext matching algorithm: a computer program to extract diagnoses and causes of death from unstructured text in electronic health records

BackgroundElectronic health records are invaluable for medical research, but much information is stored as free text rather than in a coded form. For example, in the UK General Practice Research Database (GPRD), causes of death and test results are sometimes recorded only in free text. Free text can be difficult to use for research if it requires time-consuming manual review. Our aim was to develop an automated method for extracting coded information from free text in electronic patient records.MethodsWe reviewed the electronic patient records in GPRD of a random sample of 3310 patients who died in 2001, to identify the cause of death. We developed a computer program called the Freetext Matching Algorithm (FMA) to map diagnoses in text to the Read Clinical Terminology. The program uses lookup tables of synonyms and phrase patterns to identify diagnoses, dates and selected test results. We tested it on two random samples of free text from GPRD (1000 texts associated with death in 2001, and 1000 general texts from cases and controls in a coronary artery disease study), comparing the output to the U.S. National Library of Medicine’s MetaMap program and the gold standard of manual review.ResultsAmong 3310 patients registered in the GPRD who died in 2001, the cause of death was recorded in coded form in 38.1% of patients, and in the free text alone in 19.4%. On the 1000 texts associated with death, FMA coded 683 of the 735 positive diagnoses, with precision (positive predictive value) 98.4% (95% confidence interval (CI) 97.2, 99.2) and recall (sensitivity) 92.9% (95% CI 90.8, 94.7). On the general sample, FMA detected 346 of the 447 positive diagnoses, with precision 91.5% (95% CI 88.3, 94.1) and recall 77.4% (95% CI 73.2, 81.2), which was similar to MetaMap.ConclusionsWe have developed an algorithm to extract coded information from free text in GP records with good precision. It may facilitate research using free text in electronic patient records, particularly for extracting the cause of death.

2011 Terminology of the Vulva of the International Federation for Cervical Pathology and Colposcopy

This study aimed to present the clinical and colposcopic terminology of the vulva (including the anus) of the International Federation of Cervical Pathology and Colposcopy. The terminology has been developed by the International Federation of Cervical Pathology and Colposcopy Nomenclature Committee during 2009-2011. The terminology is part of a comprehensive terminology of the lower genital tract, allowing for standardization of nomenclature by colposcopists, clinicians, and researchers taking care of women with lesions in these areas. The terminology includes basic definitions and normal findings that are important for the clinician lacking experience with management of vulvar disease. This terminology introduces definitions for abnormal findings recently accepted by the International Society for the Study of Vulvovaginal Disease and includes patterns to identify malignancy. The terminology differs from past terminologies in that it includes colposcopic patterns and anal colposcopy. Nevertheless, the role of the colposcope in the management of vulvar disease is limited.

Evaluation of alternative standardized terminologies for medical conditions within a network of observational healthcare databases

Large electronic databases of health care information, such as administrative claims and electronic health records, are available and are being used in a number of public health settings, including drug safety surveillance. However, because of a lack of standardization, clinical terminologies may differ across databases. With the aid of existing resources and expert coders, we have developed mapping tables to convert ICD-9-CM diagnosis codes used in some existing databases to SNOMED-CT and MedDRA. In addition, previously developed definitions for specific health outcomes of interest were mapped to the same standardized vocabularies. We evaluated how vocabulary mapping affected (1) the retention of clinical data from two test databases, (2) the semantic space of outcome definitions, (3) the prevalence of each outcome in the test databases, and (4) the reliability of analytic methods designed to detect drug-outcome associations in the test databases. Although vocabulary mapping affected the semantic space of some outcome definitions, as well as the prevalence of some outcomes in the test databases, it had only minor effects on the analysis of drug-outcome associations. Furthermore, both SNOMED-CT and MedDRA were viable for use as standardized vocabularies in systems designed to perform active medical product surveillance using disparate sources of observational data.

Representation of rare diseases in health information systems: The orphanet approach to serve a wide range of end users

Rare disorders are scarcely represented in international classifications and therefore invisible in information systems. One of the major needs in health information systems and for research is to share and/or to integrate data coming from heterogeneous sources with diverse reference terminologies. ORPHANET (www.orpha.net) is a multilingual information portal on rare diseases and orphan drugs. Orphanet information system is supported by a relational database built around the concept of rare disorders. Representation of rare diseases in Orphanet encompasses levels of increasing complexity: lexical (multilingual terminology), nosological (multihierarchical classifications), relational (annotations-epidemiological data-and classes of objects-genes, manifestations, and orphan drugs-integrated in a relational database), and interoperational (semantic interoperability). Rare disorders are mapped to International Classification of Diseases (10th version), SNOMED CT, MeSH, MedDRA, and UMLS. Genes are cross-referenced with HGNC, UniProt, OMIM, and Genatlas. A suite of tools allow for extraction of massive datasets giving different views that can be used in bioinformatics to answer complex questions, intended to serve the needs of researchers and the pharmaceutical industry in developing medicinal products for rare diseases. An ontology is under development. The Orphanet nomenclature is at the crossroads of scientific data repositories and of clinical terminology standards, and is suitable to be used as a standard terminology.

Using Clinically Relevant Approaches in Teaching of Anatomical Science Courses to Medical Students

In recent years, medical schools have recognized the importance of integrating clinical information into the teaching of basic sciences. Many efforts have been made by educators to engage clinical relevance in basic science courses to bridge the gap between the basic science and clinical education. At the University of Mississippi Medical Center, we have integrated clinical information into our anatomical science courses using various approaches that have directly or indirectly transformed the courses and have provided a clinical context. These methods include (1) using clinical terminology during lectures and laboratory exercises; (2) using clinical cases and examples to make anatomic points; (3) using clinical vignettes in discussion sessions and in examinations; (4) inviting clinicians to participate in teaching our basic courses; (5) using textbooks that balance basic science and clinical knowledge; (6) using MRI, CT in teaching anatomy, preparing M1 students for future clinical years. In summary, These approaches pave the road for medical students to develop critical thinking skills and better prepare them to transfer the basic anatomic knowledge in their clinical practice.

Evaluation of Coverage of Allergy Concepts in Electronic Health Records

Increasing numbers of physicians are using electronic health records, as they are thought to have applications in facilitating communication, compliance with legal and financial requirements, evaluating provider performance, decision support, and data-mining in translational and clinical studies. Formal and computable representation of data and knowledge is fundamental in establishing a common vocabulary and semantics. In this study, we evaluated the coverage of the largest clinical terminology (SNOMED-CT).

Establishing semantic interoperability in the course of clinical document exchange using international standard for metadata registry

Around the world electronic health records data are being shared and exchanged between two different systems for direct patient care, as well as for research, reimbursement, quality assurance, epidemiology, public health, and policy development. It is important to communicate the semantic meaning of the clinical data when exchanging electronic health records data. In order to achieve semantic interoperability of clinical data, it is important not only to specify clinical entries and documents and the structure of data in electronic health records, but also to use clinical terminology to describe clinical data. There are three types of clinical terminology: interface terminology to support a user-friendly structured data entry; reference terminology to store, retrieve, and analyze clinical data; and classification to aggregate clinical data for secondary use. In order to use electronic health records data in an efficient way, healthcare providers first need to record clinical content using a systematic and controlled interface terminology, then clinical content needs to be stored with reference terminology in a clinical data repository or data warehouse, and finally, the clinical content can be converted into a classification for reimbursement and statistical reporting. For electronic health records data collected at the point of care to be used for secondary purposes, it is necessary to map reference terminology with interface terminology and classification. It is necessary to adopt clinical terminology in electronic health records systems to ensure a high level of semantic interoperability.

Semantic Interoperability in Medicine and Healthcare III

The special issue of the European Journal for Biomedical Informatics publishes selected peer-reviewed papers of students of the doctoral study at the 1st Faculty of Medicine of Charles University in Prague. These papers were also presented as lectures given by Ph.D. students during the third workshop on the topic Semantic interoperability in biomedicine and healthcare held on November 22nd, 2012 in Prague. The first workshop on the same topic was held on November 18th, 2010 in Prague, the second on November 24th, 2011 in Prague. Semantic interoperability addresses issues of how to best facilitate the coding, transmission and use of meaning across seamless health services, between providers, patients, citizens and authorities, research and training. In essence the semantic interoperability goal is to work towards and support collaboration among human actors and stakeholders, rather than only interoperability among computers. The ability of systems to understand exchanged data (semantic interoperability) requires using the same terminology (i.e. classification systems and nomenclatures) and using the same language for communication and its recording (data standards). If information in biomedicine and health care is shared using a free text, a prerequisite for semantic interoperability is the access to its meaning. Existing standards (e.g. EN 13606) suppose the use of globally unique and uniquely defined terms that can be without much difficulty transferred to other classifications (e.g. by means of the Unified Medical Language System). Probably the best applicable general classification system for healthcare is SNOMED CT. It has arisen by a combination of American SNOMED (created by the Association of American Pathologists) and British Clinical Terms (Read Codes). In connection with this merger the International Health Terminology Standards Development Organization (IHTSDO), with the residence in Denmark, was founded in 2007. IHTSDO is a not-for-profit association that develops and promotes use of SNOMED CT to support safe and effective health information exchange. SNOMED CT is a clinical terminology and is considered to be the most comprehensive, multilingual healthcare terminology in the world. SNOMED CT is now being used in a number of information systems for recording of clinical information within patient records. It is expected from modern information systems to work effectively with information and to exchange it mutually. The task of the workshop, supported by the project of the specific research at the 1st Faculty of Medicine of Charles University, is to present selected terms from papers of students and to make their description in English and classification by SNOMED CT and ICD10. Then the translations of these findings to the Czech language are also presented at the workshop. Partial semantic interoperability is supported by creation of semantically sound and focused subsets of terms coded in SNOMED CT and ICD 10 that have immediate relevance to Ph.D. theses.

Towards the harmonization of Clinical Information and Terminologies by Formal Representation

Background: Semantic interoperability of clinical information is the capability to recognize and process semantically equivalent information in a homogeneous way, even if data instances are heterogeneously represented, i.e. differently structured and/or using different terminology systems. Ontologies and terminologies are recognized as playing an important role for achieving this task. Objectives: The aim of this paper is to present an approach for enhancing clinical information by semantic annotations that makes it semantically interoperable. Methods: We propose an ontological framework rooted in an expressive upper level ontology. It is used to add standardized semantics to clinical information by combining EHR information entities with SNOMED CT. BioTop, the upper level ontology used will help to constrain the ways in which information and clinical entities can be combined. Results: We exemplify how the same clinical statement is heterogeneously represented depending on the EHR standard or terminology used. The same statement is represented according to the ontological framework proposed. Strengths and limitations of the approach are discussed. Conclusions: Our approach constitutes a irst step towards interoperable representations of patient data in health records by using a shared framework using formal ontologies based on description logics. Such framework is required for the correct exchange of clinical information from heterogeneous sources, providing clear and unambiguous meaning of medical terms and the context in which they are used.

A 2012 Workshop: Vaccine and Drug Ontology in the Study of Mechanism and Effect (VDOSME 2012)

Vaccines and drugs have contributed to dramatic improvements in public health worldwide. Over the last decade, there have been efforts in developing biomedical ontologies that represent various areas associated with vaccines and drugs. These ontologies combined with existing health and clinical terminology systems (e.g., SNOMED, RxNorm, NDF-RT, MedDRA, VO, OAE, and AERO) could play significant roles on clinical and translational research. The first “Vaccine and Drug Ontology in the Study of Mechanism and Effect” workshop (VDOSME 2012) provided a platform for discussing problems and solutions in the development and application of biomedical ontologies in representing and analyzing vaccines/drugs, vaccine/drug administrations, vaccine/drug-induced immune responses (including positive host responses and adverse events), and similar topics. The workshop covered two main areas: (i) ontologies of vaccines, of drugs, and of studies thereof; and (ii) analysis of administration, mechanism and effect in terms of representations based on such ontologies. Six full-length papers included in this thematic issue focus on ontology representation and time analysis of vaccine/drug administration and host responses (including positive immune responses and adverse events), vaccine and drug adverse event text mining, and ontology-based Semantic Web applications. The workshop, together with the follow-up activities and personal meetings, provided a wonderful platform for the researchers and scientists in the vaccine and drug communities to demonstrate research progresses, share ideas, address questions, and promote collaborations for better representation and analysis of vaccine and drug-related terminologies and clinical and research data.

Use of clinical terminology for semantic interoperability of electronic health records

Use of clinical terminology for semantic interoperability of electronic health records

Creation of an Interface Terminology of Abdominal Ultrasonography Pathologies Using a SNOMED CT to Automate the Process of Ultrasound Note Creation

Background: Ultrasound - one of the most common tests in diagnostic medicine and studies of abdominal organs are more than two thirds of all the ultrasound studies. Ultrasound findings include a description of pathologies found. Various information systems provide the ability to document the pathology found in the form of coded values. But due to the lack of uniform terminology different concepts are used to describe the same pathology. A lack of common principles of coding of health information leads to difficulties of interpretation and automatic processing of ultrasound findings, as well as the inability to ensure interoperability. Objectives: Creation of interface terminology of the pathologies found during abdominal ultrasonography using a SNOMED CT, followed by automation of the process of the creation of ultrasound note. Methods: Approach has been developed to design the interface terminology on the basis of international experience of SNOMED CT using. Approach includes five phases: domain analysis, determining level of detail for the concepts, determining selection criteria for concepts in given domain, creating subset of concepts, mapping from the subset to the set of terms already in use. Designed interface terminology of the pathologies was introduced in the hospital information system. On the basis of coded values, an automated process of forming the ultrasound note was built. Results: Interface terminology of the pathologies of the abdominal cavity have been created as the result, which included 93 pathologies, 80 of which were unambiguously mapped with SNOMED CT concepts. For the remaining 13 pathologies, post coordinated concepts were designed. The final interface terminology contains 82% more terms (from 51 to 93 terms) in comparison with the original. Conclusions: SNOMED CT has shown high efficiency in the encoding of specialized clinical terminology. The methodology used allowed us to extract the necessary terms for a given domain. W e plan to continue our work to create various interface terminologies of pathologies based on SNOMED CT for other study methods.

Pathophysiology of manganese-associated neurotoxicity

Manganese (Mn) is a well established neurotoxin associated with specific damage to the basal ganglia in humans. The phenotype associated with Mn neurotoxicity was first described in two workers with occupational exposure to Mn oxide (Couper, 1837). Although the description did not use modern clinical terminology, a parkinsonian illness characterized by slowness of movement (bradykinesia), masked facies, and gait impairment (postural instability) appears to have predominated. Nearly 100 years later an outbreak of an atypical parkinsonian illness in a Chilean Mn mine provided a phenotypic description of a fulminant neurologic disorder with parkinsonism, dystonia, and neuropsychiatric symptoms (Rodier, 1955). Exposures associated with this syndrome were massive and an order of magnitude greater than modern exposures (Rodier, 1955; Hobson et al., 2011). The clinical syndrome associated with Mn neurotoxicity has been called manganism. Modern exposures to Mn occur primarily through occupations in the steel industry and welding. These exposures are often chronic and varied, occurring over decades in the healthy workforce. Although the severe neurologic disorder described by Rodier and Couper are no longer seen, several reports have suggested a possible increased risk of neurotoxicity in these workers (Racette et al., 2005b; Bowler et al., 2007; Harris et al., 2011). Based upon limited prior imaging and pathologic investigations into the pathophysiology of neurotoxicity in Mn exposed workers (Huang et al., 2003), many investigators have concluded that the syndrome spares the dopamine system distinguishing manganism from Parkinson disease (PD), the most common cause of parkinsonism in the general population, and a disease with characteristic degenerative changes in the dopaminergic system (Jankovic, 2005). The purpose of this symposium was to highlight recent advances in the understanding of the pathophysiology of Mn associated neurotoxicity from Caenorhabditis elegans to humans. Dr. Aschner's presentation discussed mechanisms of dopaminergic neuronal toxicity in C. elegans and demonstrates a compelling potential role of Mn in dopaminergic degeneration. Dr. Guilarte's experimental, non-human primate model of Mn neurotoxicity suggests that Mn decreases dopamine release in the brain without loss of neuronal integrity markers, including dopamine. Dr. Racette's presentation demonstrates a unique pattern of dopaminergic dysfunction in active welders with chronic exposure to Mn containing welding fumes. Finally, Dr. Dydak presented novel magnetic resonance (MR) spectroscopy data in Mn exposed smelter workers and demonstrated abnormalities in the thalamus and frontal cortex for those workers. This symposium provided some converging evidence of the potential neurotoxic impact of Mn on the dopaminergic system and challenged existing paradigms on the pathophysiology of Mn in the central nervous system.

Clinical coverage of an archetype repository over SNOMED-CT

Clinical archetypes provide a means for health professionals to design what should be communicated as part of an Electronic Health Record (EHR). An ever-growing number of archetype definitions follow this health information modelling approach, and this international archetype resource will eventually cover a large number of clinical concepts. On the other hand, clinical terminology systems that can be referenced by archetypes also have a wide coverage over many types of health-care information.No existing work measures the clinical content coverage of archetypes using terminology systems as a metric. Archetype authors require guidance to identify under-covered clinical areas that may need to be the focus of further modelling effort according to this paradigm.This paper develops a first map of SNOMED-CT concepts covered by archetypes in a repository by creating a so-called terminological Shadow. This is achieved by mapping appropriate SNOMED-CT concepts from all nodes that contain archetype terms, finding the top two category levels of the mapped concepts in the SNOMED-CT hierarchy, and calculating the coverage of each category. A quantitative study of the results compares the coverage of different categories to identify relatively under-covered as well as well-covered areas. The results show that the coverage of the well-known National Health Service (NHS) Connecting for Health (CfH) archetype repository on all categories of SNOMED-CT is not equally balanced. Categories worth investigating emerged at different points on the coverage spectrum, including well-covered categories such as Attributes, Qualifier value, under-covered categories such as Microorganism, Kingdom animalia, and categories that are not covered at all such as Cardiovascular drug (product).

Data processing and analysis in real‐world traditional Chinese medicine clinical data: challenges and approaches

Traditional Chinese medicine (TCM) is a clinical-based discipline in which real-world clinical practice plays a significant role for both the development of clinical therapy and theoretical research. The large-scale clinical data generated during the daily clinical operations of TCM provide a highly valuable knowledge source for clinical decision making. Secondary analysis of these data would be a vital task for TCM clinical studies before the randomised controlled trials are conducted. In this article, we discuss the challenges and issues, such as structured data curation, data preprocessing and quality, large-scale data management and complex data analysis requirements, in the data processing and analysis of real-world TCM clinical data. Furthermore, we also discuss related state-of-the-art research and solutions in China. We have shown that the clinical data warehouse based on the collection of structured electronic medical record data and clinical terminology would be a promising approach for generating clinical hypotheses and helping the discovery of clinical knowledge from large-scale real-world TCM clinical data.