Search tips
Search criteria

Results 1-25 (2069)

Clipboard (0)

Select a Filter Below

Year of Publication
1.  An Unsupervised Self-Optimizing Gene Clustering Algorithm 
We have devised a gene-clustering algorithm that is completely unsupervised in that no parameters need be set by the user, and the clustering of genes is self-optimizing to yield the set of clusters that minimizes within-cluster distance and maximizes between-cluster distance. This algorithm was implemented in Java, and tested on a randomly selected 200-gene subset of 3000 genes from cell-cycle data in S. cerevisiae. AlignACE was used to evaluate the resulting optimized cluster set for upstream cis-regulons. The optimized cluster set was found to be of comparable quality to cluster sets obtained by two established methods (complete linkage and k-means), even when provided with only a small, randomly selected subset of the data (200 vs 3000 genes), and with absolutely no supervision. MAP and specificity scores of the highest ranking motifs identified in the largest clusters were comparable.
PMCID: PMC1357234  PMID: 12463911
2.  An unsupervised self-optimizing gene clustering algorithm. 
We have devised a gene-clustering algorithm that is completely unsupervised in that no parameters need be set by the user, and the clustering of genes is self-optimizing to yield the set of clusters that minimizes within-cluster distance and maximizes between-cluster distance. This algorithm was implemented in Java, and tested on a randomly selected 200-gene subset of 3000 genes from cell-cycle data in S. cerevisiae. AlignACE was used to evaluate the resulting optimized cluster set for upstream cis-regulons. The optimized cluster set was found to be of comparable quality to cluster sets obtained by two established methods (complete linkage and k-means), even when provided with only a small, randomly selected subset of the data (200 vs 3000 genes), and with absolutely no supervision. MAP and specificity scores of the highest ranking motifs identified in the largest clusters were comparable.
PMCID: PMC1357234  PMID: 12463911
3.  Implementing outpatient order entry to support medical necessity using the patient's electronic past medical history. 
Physician order entry is difficult to implement, both in inpatient and outpatient settings. Such systems must integrate conveniently into clinical workflows, and provide sufficient benefit to offset the burden of system use. For outpatient order entry, significant advantages can accrue when systems incorporate medical necessity guidelines - improved billing and adherence to governmental policies. The authors developed and implemented an outpatient order entry system that utilizes an electronically accessible history of patient, provider, and clinic-related diagnoses in assisting providers (when possible and appropriate) to select compliant justifications for tests and procedures. The pilot implementation site, active for more than six months, has been the Vanderbilt University Page Campbell Cardiology Clinic, with 34 providers.
PMCID: PMC2244584  PMID: 12463825
4.  The Chronus II temporal database mediator. 
Clinical databases typically contain a significant amount of temporal information. This information is often crucial in medical decision-support systems. Although temporal queries are common in clinical systems, the medical informatics field has no standard means for representing or querying temporal data. Over the past decade, the temporal database community has made a significant amount of progress in temporal systems. Much of this research can be applied to clinical database systems. This paper outlines a temporal database mediator called Chronus II. Chronus II extends the standard relational model and the SQL query language to support temporal queries. It provides an expressive general-purpose temporal query language that is tuned to the querying requirements of clinical decision support systems. This paper describes how we have used Chronus II to tackle a variety of clinical problems in decision support systems developed by our group.
PMCID: PMC2244583  PMID: 12474882
5.  A Dynamic Imaging Database for 3-D Morphologic Analysis and Clinical Assessment in Diagnostic Radiology 
Modern imaging techniques such as MRI and CT have become invaluable clinical and research tools for visualizing internal organs and anatomic structures, non-invasively. We present a dynamic imaging database for performing comparative morphologic studies in diagnostic radiology to facilitate clinical assessment. The prototype system utilizes a double elliptic Fourier transform to characterize shape in three dimensions. A prototype system was used to evaluate neuroanatomy from MR brain scans of children who have been diagnosed with Bipolar Disorder or Asperger's Syndrome.
PMCID: PMC2244582
6.  St-Guide: A State/Transition Representation Model for Clinical Guidelines 
This paper presents St-Guide, a state/transition approach to the representation and computer interpretation of clinical guidelines for primary and secondary care of chronic diseases. Details of the representation language and the execution model are presented. Guidelines for Tuberculosis, Hepatitis C, and Hypertension were developed using St-guide.
PMCID: PMC2244581
7.  The horizontal and vertical nature of patient phenotype retrieval: new directions for clinical text processing. 
The author reviews the historical problem of identifying appropriate patients for retrieval from a clinical repository of patient records, compares the competing features of document classification and natural language processing, and proposes an alternative approach. The alternative approach 1) codes inquiries in an ontology to lend a vertical axis to retrieval knowledge instead of coding the target body of notes, 2) invokes natural language indexing and lexical normalizations on the corpus of notes that is scalable and tractable, and 3) leverages thesauri of word-level synonyms and near-synonyms to expand term searches "horizontally" around the concept spaces drawn from the ontology in which the queries were "coded."
PMCID: PMC2244580  PMID: 12463808
8.  YMD: a microarray database for large-scale gene expression analysis. 
The use of microarray technology to perform parallel analysis of the expression pattern of a large number of genes in a single experiment has created a new frontier of medical research. The vast amount of gene expression data generated from multiple microarray experiments requires a robust database system that allows efficient data storage, retrieval, secure access, data dissemination, and integrated data analyses. To address the growing needs of microarray researchers at Yale and their collaborators, we have built the Yale Microarray Database (YMD). YMD is Web-accessible with the following features: (i) a Web program that tracks DNA samples between source plates and arrays, (ii) the capability of finding common genes/clones across different array platforms, (iii) an image file server, (iv) laboratory-based user management and access privileges, (v) project management, (vi) template data entry, (vii) linking gene expression data to annotation databases for functional analysis. YMD is currently being used on a pilot basis by several laboratories for different organisms and array platforms.
PMCID: PMC2244579  PMID: 12463803
9.  Outcome Prediction after Moderate and Severe Head Injury Using an Artificial Neural Network 
We conducted this study to determine if artificial neural network modeling would predict outcome in five levels of Glasgow Outcome Scale after moderate to severe head injury. The database was collected from a nation-wide epidemiological study of traumatic brain injury in Taiwan from July 1, 1995 to June 30, 1998. There were total 18583 records in this database and each record had thirty-two parameters. A step-wise logistic regression was applied to the data set and 10 variables were selected as being statistically significant in predicting outcome. These 10 variables were used as the input neurons for constructing neural network. Overall, 75.8% of predictions of this model were correct, 14.6% were pessimistic, and 9.6% optimistic. The prediction performance of dead or good recovery is best and the prediction of vegetative state is worst. An artificial neural network may assist neurosurgeons to predict outcome after traumatic brain injury.
PMCID: PMC2244578
11.  Maximum entropy modeling for mining patient medication status from free text. 
Using a classification scheme of patient medication status we sought to recognize and categorize medications mentioned in the unrestricted text of clinical documents generated in clinical practice. The categories refer to the patient's status with respect to the medication such as discontinuation, start or initiation, and continuation of a given medication. This categorization is performed with a machine learning technique, Maximum Entropy (ME), that is well suited to incorporating heterogeneous sources of information necessary for classifying patient's medication status. We use hand labeled training data to generate ME models and test 5 different training feature sets. Our results show that the most optimal feature set includes a combination of the following: two words preceding and following the mention of the drug, the subject of the sentence in which the drug mention occurs, the 2 words following the subject, and a binary feature vector of lexicalized semantic cues indicative of medication status or its change. The average predictive power of a model trained on these features is approximately 89%.
PMCID: PMC2244576  PMID: 12463891
12.  The SNOMED clinical terms development process: refinement and analysis of content. 
SNOMED Clinical Terms is a comprehensive concept-based health care terminology that was created by merging SNOMED RT and Clinical Terms Version 3. Following the mapping of concepts and descriptions into a merged database, the terminology was further refined by adding new content, modeling the relationships of individual concepts, and reviewing the hierarchical structure. A quality control process was performed to ensure integrity of the data. Additional features such as subsets, qualifiers, and mappings to other coding systems were added or updated to facilitate usability. We then analyzed the content of the completed work. This paper describes the refinement processes and compares the actual content of SNOMED CT with the early data obtained from analysis of the description mapping process. As predicted, the majority of concepts in SNOMED CT originated from SNOMED RT or CTV3, but not both.
PMCID: PMC2244575  PMID: 12463944
14.  Introducing information technology into the home: conducting a home assessment. 
Abstract As the home becomes an increasingly important site for health care, an increasing number of technology applications or devices are being introduced to support health at home. However, introducing new technology into a household raises a number of issues that must be considered prior to, during, and after the technology is implemented. This paper reviews the experiences of the UW-Madison Advanced Technologies for Health@Home Project, summarizing our assessment of household requirements that should be analyzed prior to introducing new technology. The overall goal of the Health@Home project is to improve the functionality and content of information technology innovations for the home. Using Venkatesh and Mazumdar's framework this article will summarize the relevant social, behavioral, technological, and physical dimensions of households that must be carefully assessed and understood to help ensure that the technology fits the needs of home residents.
PMCID: PMC2244573  PMID: 12463960
17.  Neural network modeling to predict the hypnotic effect of propofol bolus induction. 
Dose requirements of propofol to achieve loss of consciousness depend on the interindividual variability. Until now when propofol was administered by a single bolus, how to define the optimal individual dose and to assess its hypnotic effect have not been clearly studied. The goal of this study is to develop an artificial neural network model to predict the hypnotic effect of propofol on the basis of common clinical parameters. Ten parameters were chosen as the input factors based on the related literatures and clinical experiences. The bispectral index of EEG was used to record the consciousness level of patients and served as the output factor. The predictive results of neural net models were superior to that of clinician. This model could potentially help determine the optimal dose of propofol and thus reduce the anesthetic cost.
PMCID: PMC2244570  PMID: 12463864
18.  The Use of a Pharmacy Data Mart as a Patient Safety Tool 
The National Institute of Medicine's report, “To Err is Human, was extremely critical of the health care delivery system in the United States.1 Medication errors were a major contributor to the medical misadventures discussed in the report.
The pharmacy department of our facility began to use its data warehouse for identifying potential problems and discovering patients who may have “fallen through the cracks” of the traditional drug delivery system. To date, the system has been used to identify several areas of opportunity for the pharmacy department, for example identifying patients on quinidine who were supposed to have been prescribed quinine. The system also has been used to monitor patient safety issues as medication use guidelines are altered. The system provides fairly rapid access to information, with a typical search taking ten minutes or less.
PMCID: PMC2244569
20.  Development of a Wireless Web-based Infrastructure to Support Collection of Patient Self-reported QoL and Symptom Information in a Clinical Setting 
We have implemented a survey tool to collect patient-entered Quality of Life (QoL) and symptomology data for clinician use in an outpatient cancer treatment center. The system is currently implemented using a web infrastructure and delivered to patients in the waiting room via wireless laptops. The software assesses and records patient consent, delivers survey questions and records answers, and summarizes the results for clinical use in the during the patient's visit. Optionally, the data are recorded in a research database. The infrastructure can be expanded to support generalized survey delivery for future clinical and research purposes. (MESH: Internet, Data Collection, Quality of Life, Information Systems, Patient Participation, Data Display)
PMCID: PMC2244567
21.  Applying Axiomatic Design Methodology to Create Guidelines That Are Locally Adaptable 
Clinical guidelines developed at a national level are often difficult to use in specific-settings because of contextual factors. We have created a model for guideline representation that enables local adaptation of nationally developed guidelines. Guidelines are specified in a setting-independent manner and are then locally adapted by each practice. A guideline is represented hierarchically with the top level steps of the guideline specifying broad objectives and the lower level steps providing details of the recommendations. The axiomatic design framework provides a principled method for hierarchical design. The approach has been implemented by incorporation in the GLIF guideline modeling environment.
PMCID: PMC2244566
22.  MOPPDB: Database for Translational Investigations at H. Lee Moffitt Cancer Center and Research Institute 
The Molecular Oncology Program Project database (MOPPDB) at H. Lee Moffitt Cancer Center and Research Institute is being developed to house all of the data for a NCI Program Project grant for translational research. MOPPDB has a clinical side that includes several diseases and a research lab side for several assays. Important features of the database are: the system is web-delivered; has a user-friendly interface; emphasizes the use of electronic interfaces with other institutional systems; provides a method of de-identifying the data to insure patient confidentiality. This poster will discuss the different aspects of MOPPDB and the challenges of developing a system of this complexity.
PMCID: PMC2244565
23.  Assessment of a French Code of Ethics for Health Teaching Resources on the Internet 
Background: Constant assessment of the quality of health information on the Internet is an absolute necessity as peer review is often lacking on this media. Objective: To develop a simple and easy French Code of Ethics which will enable medical students to judge quality of health information in teaching material available on the Internet. Design: Three medical scientists selected nine criteria from previously established codes of ethics from Europe and the USA. This instrument was tested on a sample of 24 health French-speaking Internet teaching resources. Results: For the panel of experts, we analyzed assessments with non parametric tests. This analysis demonstrated a strong agreement among the raters. Conclusion: It seems possible to produce an analysis summary to evaluate teaching material available on the Internet.
PMCID: PMC2244564
24.  Pediatric Cancer CareLink--supporting home management of childhood leukemia. 
We conducted a descriptive evaluation of an Internet-based system designed to support home management of childhood leukemia (Pediatric Cancer CareLink). Twenty-five parents of children with ALL and thirty-four clinicians were interviewed to identify functional requirements and to demonstrate the system's potential to improve the experience and outcomes of children with acute lymphoblastic leukemia (ALL). Parental interviews focused on: medication and side effect management in the home; communication with the health care team; and the use of a computer for ALL home management. Results from these interviews provide strong evidence that parents of children with ALL are struggling to manage the complexity of their children's care in the home. Parents revealed an urgent need for tools that would help them to safely organize the medicines that their children receive while on ALL protocols. Forty percent of parents needed to know more about what to expect during their child's therapy and how to be prepared for it. Clinician interviews focused on the clinical impact and workflow issues associated with such a system. Decision support, prescription refill management, and educational and emotional support functions were considered key components. Clinicians were concerned that such a system would increase their already overburdened workload. Conversely, parents believed that access to such a system would eliminate unnecessary phone calls to the care team. Our findings show that parents would embrace collaborative Internet-based tools that would help with the home management of their child's leukemia.
PMCID: PMC2244563  PMID: 12463833
25.  NLM tele-educational application for radiologists to interpret mammography. 
The goal of this study was to provide unique tools for an educational program to improve the skills, namely consistency and accuracy, of radiology residents who interpret digital mammograms. The tele-educational tools, created at UNC, will be implemented locally and connected to the National Digital Mammography Archive (NDMA) through the Next Generation Internet (NGI). This application includes an annotation tool, as well as a teaching and testing tool. The annotation tool will allow radiologists to label all imaging findings including the specific location information in mammograms, and make lesion diagnosis based on pathology reports. The teaching tool will allow teachers to demonstrate cases of specific types and diagnoses. Trainees themselves will also be able to use the teaching tool for reviewing of cases of types of their choosing. Our testing tool can test radiology residents inverted exclamation mark performance in interpreting digital mammograms, and provides them detailed performance test results, such as, sensitivity, specificity, ROC curves, AUC values, etc. A local Oracle database was designed and implemented at UNC to support those tools. We developed a method to map information of cases from the local database to DICOM Structure Reports by using XML techniques.
PMCID: PMC2244562  PMID: 12463957

Results 1-25 (2069)