Haomin Li

Identification of Gene Expression Pattern Related to Breast Cancer Survival Using Integrated TCGA Datasets and Genomic Tools

Several large-scale human cancer genomics projects such as TCGA offered huge genomic and clinical data for researchers to obtain meaningful genomics alterations which intervene in the development and metastasis of the tumor. A web-based TCGA data analysis platform called TCGA4U was developed in this study. TCGA4U provides a visualization solution for this study to illustrate the relationship of these genomics alternations with clinical data. A whole genome screening of the survival related gene expression patterns in breast cancer was studied. The gene list that impacts the breast cancer patient survival was divided into two patterns. Gene list of each of these patterns was separately analyzed on DAVID. The result showed that mitochondrial ribosomes play a more crucial role in the cancer development. We also reported that breast cancer patients with low HSPA2 expression level had shorter overall survival time. This is widely different to findings of HSPA2 expression pattern in other cancer types. TCGA4U provided a new perspective for the TCGA datasets. We believe it can inspire more biomedical researchers to study and explain the genomic alterations in cancer development and discover more targeted therapies to help more cancer patients.

A finite-state automata based negation detection algorithm for Chinese clinical documents

In this paper we described an algorithm called NegDetector for locating concerned clinical terms mentioned in electronic narrative text clinical documents and detecting whether the particular terms appeared in different positions are negated or affirmed. The algorithm infers the status of a condition with regard to the property from simple lexical clues occurring in the context of condition, maybe more than a few words away from the term. Considering the diverse types of negative structures, this paper selects typical, common and recognizable usage patterns of negatives as criteria of judgment. The judging results during one complete process are driven by many different types of symbols, and the response to a particular symbol depends on the sequence of previous judging results. In this situation, the finite-state automata is useful to address lots of symbols that trigger one another. When evaluating NegDetector with testing case history, we measured a recall of 0.9985, a precision of 0.9498 and a fallout of 0.5147.

A concise drug alerting rule set for Chinese hospitals and its application in computerized physician order entry (CPOE)

BackgroundA minimized and concise drug alerting rule set can be effective in reducing alert fatigue.ObjectivesThis study aims to develop and evaluate a concise drug alerting rule set for Chinese hospitals. The rule set covers not only western medicine, but also Chinese patent medicine that is widely used in Chinese hospitals.SettingA 2600-bed general hospital in China.MethodsIn order to implement the drug rule set in clinical information settings, an information model for drug rules was designed and a rule authoring tool was developed accordingly. With this authoring tool, clinical pharmacists built a computerized rule set that contains 150 most widely used and error-prone drugs. Based on this rule set, a medication-related clinical decision support application was built in CPOE. Drug alert data between 2013/12/25 and 2015/07/01 were used to evaluate the effect of the rule set.Main outcome measureNumber of alerts, number of corrected/overridden alerts, accept/override rate.ResultsTotally 18,666 alerts were fired and 2803 alerts were overridden. Overall override rate is 15.0% (2803/18666) and accept rate is 85.0%.ConclusionsThe rule set has been well received by physicians and can be used as a preliminary medical order screening tool to reduce pharmacists’ workload. For Chinese hospitals, this rule set can serve as a starter kit for building their own pharmaceutical systems or as a reference to tier commercial rule set.

Lexical Characteristics Analysis of Chinese Clinical Documents

Understanding lexical characteristics of clinical documents is the foundation of sublanguage based Medical Language Processing (MLP) approach. However, there are limited studies focused on the lexical characters of Chinese clinical documents. In this study, a lexical characteristics analysis on both syntactic and semantic levels was conducted in a clinical corpus which contains 3,500 clinical documents generated during daily practices. The analysis was based on the automatic tagging results of a lexicon-based part-of-speech (POS) and semantic tagging method. The medical lexicon contains 237,291 entries annotated with both semantic and syntactic classes. The normalized frequency of different terms, syntactic and semantic classes was calculated and visualized. Major contribution of this paper is providing a wide-coverage Chinese medical semantic lexicon and presenting the lexical characteristics of Chinese clinical documents. Both of these will lay a good foundation for sublanguage based MLP studies in China.

A CRF-based Method for Automatic Construction of Chinese Symptom Lexicon

Lexicon plays a key role in Medical Language Processing (MLP) technology. Construction of semantic lexicon has become the prerequisite of MLP study in China where there are limited clinical terminology resources available. In this study, an iterative machine learning algorithm based on Conditional Random Field (CRF) was proposed aiming to automatically build a symptom lexicon from clinical corpus. Comprehensive evaluation was conducted in terms of exact and inexact for the algorithm. The algorithm achieved the performance, with F-measure of 87.23%, precision and recall were 99.95% and 72.23%, respectively. Furthermore, a lexicon which contained 22,501 symptoms was constructed based on this approach.

Identification of Adverse Drug Events in Chinese Clinical Narrative Text

Drug is an effective measure of alleviating pain and treating diseases. Whereas medication-related harms due to both adverse drug effects and drug errors have become the leading iatrogenic injury. However, such medication-related harms often remain unrecognized and unreported. The purpose of this study is to automatically identify adverse drug events (ADEs) in routine clinical documents. Firstly, ADE related Chinese lexical resource was collected and maintained. Then, a natural language processing (NLP) application which could automatically extract ADE symptom from drug manuals was developed and applied for building an ADE knowledge base for 3,733 drugs. Finally, based on these resources, an ADE detection algorithm was proposed to identify ADEs in the clinical free-text. Results revealed that the precision of the ADE detection algorithm was 80.8 %.

An integration profile of rule engines for clinical decision support systems

Rule engine has become an indispensable component for many clinical decision support systems. Due to the complexity and heterogeneity of clinical data, one big challenge for rule-based clinical applications is mapping the data from various data sources to rule variables. This paper proposed a rule engine integration profile that uses a shared ontology between the rule engine and external systems to facilitate data acquisition. Based on the integration profile, a diagnostic clinical decision support application was successfully deployed in a Chinese hospital.

A Knowledge Base Driven Clinical Pharmacist Information System

Recent years, clinical pharmacists have been introduced into many Chinese hospitals to promote rational drug use. However, there lacks of an information system to facilitate such a novel clinical pharmacy workflow and monitor the whole hospital with limited pharmacy experts. In this paper, a knowledge base driven clinical pharmacist information system was proposed and developed. A clinical decision support service based on a customizable knowledge base can monitor every medication order placed at real time and notify both the clinician and clinical pharmacist. A collaboration information system between clinicians and pharmacists was developed to facilitate communication between them and manage the quality of clinical pharmacy. Through evaluating the system in a 2000-beded hospital, it can significantly reduce medication related error. It also showed a very good acceptance from both clinical pharmacists and clinicians.

An Integration Framework for Clinical Decision Support Applications

Clinical Decision Support (CDS) applications have been widely recognized for improving health care quality and medical knowledge translation. However, its adoption and utilization in a real clinical environment is still subject to many factors, an important one of which is the lack of mechanism to easily integrate these applications to clinical workflow. This paper designs and develops an extensible CDS application integration and management system framework. This framework achieves interoperability between Clinical Information System (CIS) and CDS applications at two levels under predefined integration protocols; and through a mechanism of registration, management and delivery, various CDS applications can be delivered to targeted scenarios and executed in a context-aware way. This framework was validated in real clinical environment, and proved to be effective in both integration and interoperability. Meanwhile, targeted CDS application delivery further facilitates CDS in clinical promotion.

A Surveillance Platform of Antimicrobial Use in Hospital Based on Defined Daily Dose

Antimicrobial abuse is very serious and is increasing threat China. It is important to make antimicrobials’ better service for patients through the information technology. The surveillance platform which provides the public health authorities the patterns of consumption of antimicrobial drugs is necessary for a constructive approach to many problems that arise from the multiplicity of antibiotics now available, their high cost and the ecological sequelae of their use. In this study, DDD (Defined Daily Dose) which is an international general concept to investigate the drug consumption is used to build such a surveillance platform in a Chinese 3A hospital. First, we will explain how to classify and grade each antimicrobial drug and obtain their corresponding DDD. Then the surveillance platform was described. In the end, this paper shows how we analyzed the consumption pattern of antimicrobial drugs through this platform.