Biomedical subjects

George Hripcsak

Publications and source records attributed to George Hripcsak.

At least 37 records · Page 2Linked to original sources

PubMed2004

Modeling electronic discharge summaries as a simple temporal constraint satisfaction problem.

OBJECTIVE: To model the temporal information contained in medical narrative reports as a simple temporal constraint satisfaction problem. DESIGN: A constraint satisfaction problem is defined by time points and constraints (inequalities between points). A time interval comprises a pair of points and a constraint. Five complete electronic discharge summaries and paragraphs from 226 other discharge summaries were studied. Medical events were represented as intervals, and assertions about events were represented as constraints. Through a consensus process, a set of encoding procedures and a list of issues related to encoding were generated. MEASUREMENTS: Instances of temporal disjunction and contradiction and distribution of temporal constraints were used. RESULTS: An average of 95 medical events (range, 46-151) and 234 temporal assertions (range, 118-388) were identified per complete discharge summary. Nondefinitional assertions were explicit (36%) or implicit (64%) and absolute (17%), qualitative (72%), or metric (11%). Implicit assertions were based on domain knowledge and assumptions, e.g., the section of the report determined the ordering of events. Issues included linking events, intermittence, periodicity, granularity, vagueness, ambiguity, uncertainty, and plans. ions such as intermittence were not represented explicitly. The temporal network was sparse: Only 0.80% (range, 0.42%-1.38%) of possible constraints were instantiated. No instances of discontinuous temporal disjunction were found in the complete summaries or the 226 paragraphs. One instance of temporal contradiction was found (intrareport rate of 0.2 with a 95% confidence interval of 0.005-1.114). CONCLUSION: A simple temporal constraint satisfaction problem appears sufficient to represent most temporal assertions in discharge summaries and may be useful for encoding electronic medical records.

Algorithms↗

PubMed2004

Automated encoding of clinical documents based on natural language processing.

OBJECTIVE: The aim of this study was to develop a method based on natural language processing (NLP) that automatically maps an entire clinical document to codes with modifiers and to quantitatively evaluate the method. METHODS: An existing NLP system, MedLEE, was adapted to automatically generate codes. The method involves matching of structured output generated by MedLEE consisting of findings and modifiers to obtain the most specific code. Recall and precision applied to Unified Medical Language System (UMLS) coding were evaluated in two separate studies. Recall was measured using a test set of 150 randomly selected sentences, which were processed using MedLEE. Results were compared with a reference standard determined manually by seven experts. Precision was measured using a second test set of 150 randomly selected sentences from which UMLS codes were automatically generated by the method and then validated by experts. RESULTS: Recall of the system for UMLS coding of all terms was .77 (95% CI.72-.81), and for coding terms that had corresponding UMLS codes recall was .83 (.79-.87). Recall of the system for extracting all terms was .84 (.81-.88). Recall of the experts ranged from .69 to .91 for extracting terms. The precision of the system was .89 (.87-.91), and precision of the experts ranged from .61 to .91. CONCLUSION: Extraction of relevant clinical information and UMLS coding were accomplished using a method based on NLP. The method appeared to be comparable to or better than six experts. The advantage of the method is that it maps text to codes along with other related information, rendering the coded output suitable for effective retrieval.

Abstracting and Indexing↗

PubMed2004

Using the Federated Council for Internal Medicine curricular guide and administrative codes to assess IM residents' breadth of experience.

PURPOSE: To estimate internal medicine residents' breadth of experience using a published curricular guide and an electronic medical record. METHOD: A cohort of 41 internal medicine residents at Columbia University Medical Center, a large, inner-city, primary and tertiary care center, were followed over their three years of training in the late 1990s. Residents were mapped to the patients they cared for, the diagnoses those patients were assigned, and the Federated Council for Internal Medicine (FCIM) competencies covered. The proportion and distribution of competencies covered (potential to achieve a competency) were measured. RESULTS: Residents covered 76% of priority 1 competencies (those identified by FCIM as optimally learned through direct responsibility for patients) and 67% of all competencies. Although the number of patients cared for was correlated with breadth of experience, the effect was small. Rare diagnoses appear to have been distributed well. CONCLUSION: Internal medicine residents had the potential to achieve the majority of competencies via direct patient care, but no residents achieved full coverage. The electronic medical record may provide a mechanism to track residents and study training programs.

Academic Medical Centers↗

PubMed2004

Promoting patient safety and enabling evidence-based practice through informatics.

OBJECTIVES: The purposes of this article are to highlight the role of informatics in promoting patient safety and enabling evidence-based practice (EBP), 2 significant aspects for assuring healthcare quality; to delineate some challenges for the future; and to provide key recommendations for education, practice, policy, and research. METHODS: First, we describe the components of an informatics infrastructure for patient safety and evidence-based practice. Second, we address the role of informatics in 4 areas: 1) information access; 2) automated surveillance for real-time error detection and prevention; 3) communication among members of the healthcare team; and 4) standardization of practice patterns. Last, we delineate some future challenges for nursing and for informatics and provide key recommendations for education, practice, policy, and research. RESULTS: The components of an informatics infrastructure are available and applications that bring together these components to promote patient safety and enable EBP have demonstrated positive or promising results. CONCLUSIONS: Challenges must be addressed so that an informatics infrastructure and related applications that promote patient safety and enable EBP can be realized.

Equipment Safety↗

PubMed2003

The role of domain knowledge in automating medical text report classification.

OBJECTIVE: To analyze the effect of expert knowledge on the inductive learning process in creating classifiers for medical text reports. DESIGN: The authors converted medical text reports to a structured form through natural language processing. They then inductively created classifiers for medical text reports using varying degrees and types of expert knowledge and different inductive learning algorithms. The authors measured performance of the different classifiers as well as the costs to induce classifiers and acquire expert knowledge. MEASUREMENTS: The measurements used were classifier performance, training-set size efficiency, and classifier creation cost. RESULTS: Expert knowledge was shown to be the most significant factor affecting inductive learning performance, outweighing differences in learning algorithms. The use of expert knowledge can affect comparisons between learning algorithms. This expert knowledge may be obtained and represented separately as knowledge about the clinical task or about the data representation used. The benefit of the expert knowledge is more than that of inductive learning itself, with less cost to obtain. CONCLUSION: For medical text report classification, expert knowledge acquisition is more significant to performance and more cost-effective to obtain than knowledge discovery. Building classifiers should therefore focus more on acquiring knowledge from experts than trying to learn this knowledge inductively.

Algorithms↗

PubMed2003

GESDOR - a generic execution model for sharing of computer-interpretable clinical practice guidelines.

We developed the Guideline Execution by Semantic Decomposition of Representation (GESDOR) model to share guidelines encoded in different formats at the execution level. For this purpose, we extracted a set of generalized guideline execution tasks from the existing guideline representation models. We then created the mappings between specific guideline representation models and the set of the common guideline execution tasks. Finally, we developed a generic task-scheduling model to harmonize the existing approaches to guideline task scheduling. The evaluation has shown that the GESDOR model can be used for the effective execution of guidelines encoded in different formats, and thus realizes guideline sharing at the execution level.

Decision Making, Computer-Assisted↗

PubMed2003

Assessing explicit error reporting in the narrative electronic medical record using keyword searching.

In this study, we assessed the explicit reporting of medical errors in the electronic record. We looked for cases in which the provider explicitly stated that he or she or another provider had committed an error. The advantage of the technique is that it is not limited to a specific type of error. Our goals were to 1) measure the rate at which medical errors were documented in medical records, and 2) characterize the types of errors that were reported.

Humans↗

PubMed2003

Automated identification of shortcuts to patient data for a wireless handheld clinical information system.

Inadequate access to patient information at the point of care has been identified as an impediment to the health care process. To create clinical computing tools that are useful to and used by clinicians, developers of clinical information systems must have accurate models of the users for whom their systems are intended. To create these models, the information needs of clinicians must be understood. While the wireless handheld environment offers many advantages such as the ability to provide mobile access to information, there are a number of challenges. Developing for this environment differs from the laptop and desktop environments due to features such as processing power, screen size, input mechanism, and bandwidth. PalmCIS (Palm-based Clinical Information System) is a clinical application being developed at New York Presbyterian Hospital (NYPH) that provides clinicians with access to patient data via a wireless handheld device. We are using an automated technique to uncover patient-specific information needs of clinicians while using a patient record system. With the results, we can enhance PalmCIS.

Computers, Handheld↗

PubMed2003

An experimental system for comparing speed, accuracy, and completeness of physician data entry using electronic and paper methods.

Electronic medical record (EMR) systems have important potential advantages over traditional paper-based systems, but they require that physicians assume responsibility for data entry. However, little is known about the quality of physician data entry in electronic systems. This study describes a system for comparing the speed, accuracy, and completeness of examination data entry using electronic and paper methods. Data will be shown to demonstrate that this may be a simple, reproducible, and useful technique.

Humans↗

PubMed2003

A native XML database design for clinical document research.

Health-care institutions are gaining an increasing interest in exploiting the data that are gathered through electronic medical records. Narrative data, generated by transcription or direct entry, represents a far greater challenge for analytic tasks. Moreover, a small number of institutions are beginning to explore deeper structuring of narrative data using natural language processing (NLP). The data produced by NLP systems has a complex, nested structure. Current electronic medical records do not have the ability to store and retrieve data of this complexity in a suitable way.

Database Management Systems↗

PubMed2002

Measuring agreement in medical informatics reliability studies.

Agreement measures are used frequently in reliability studies that involve categorical data. Simple measures like observed agreement and specific agreement can reveal a good deal about the sample. Chance-corrected agreement in the form of the kappa statistic is used frequently based on its correspondence to an intraclass correlation coefficient and the ease of calculating it, but its magnitude depends on the tasks and categories in the experiment. It is helpful to separate the components of disagreement when the goal is to improve the reliability of an instrument or of the raters. Approaches based on modeling the decision making process can be helpful here, including tetrachoric correlation, polychoric correlation, latent trait models, and latent class models. Decision making models can also be used to better understand the behavior of different agreement metrics. For example, if the observed prevalence of responses in one of two available categories is low, then there is insufficient information in the sample to judge raters' ability to discriminate cases, and kappa may underestimate the true agreement and observed agreement may overestimate it.

Decision Making↗

PubMed2002

Of truth and pathways: chasing bits of information through myriads of articles.

Knowledge on interactions between molecules in living cells is indispensable for theoretical analysis and practical applications in modern genomics and molecular biology. Building such networks relies on the assumption that the correct molecular interactions are known or can be identified by reading a few research articles. However, this assumption does not necessarily hold, as truth is rather an emerging property based on many potentially conflicting facts. This paper explores the processes of knowledge generation and publishing in the molecular biology literature using modelling and analysis of real molecular interaction data. The data analysed in this article were automatically extracted from 50000 research articles in molecular biology using a computer system called GeneWays containing a natural language processing module. The paper indicates that truthfulness of statements is associated in the minds of scientists with the relative importance (connectedness) of substances under study, revealing a potential selection bias in the reporting of research results. Aiming at understanding the statistical properties of the life cycle of biological facts reported in research articles, we formulate a stochastic model describing generation and propagation of knowledge about molecular interactions through scientific publications. We hope that in the future such a model can be useful for automatically producing consensus views of molecular interaction data.

Algorithms↗

PubMed2002

Use of natural language processing to translate clinical information from a database of 889,921 chest radiographic reports.

PURPOSE: To evaluate translation of chest radiographic reports by using natural language processing and to compare the findings with those in the literature. MATERIALS AND METHODS: A natural language processor coded 10 years of narrative chest radiographic reports from an urban academic medical center. Coding for 150 reports was compared with manual coding. Frequencies and co-occurrences of 24 clinical conditions (diseases, abnormalities, and clinical states) were estimated. The ratio of right to left lung mass, association of pleural effusion with other conditions, and frequency of bullet and stab wounds were compared with independent observations. The sensitivity and specificity of the system's pneumothorax coding were compared with those of manual financial coding. RESULTS: The system coded 889,921 reports on 251,186 patients. On the basis of manual coding of 150 reports, the processor's sensitivity (0.81) and specificity (0.99) were comparable to those previously reported for natural language processing and for expert coders. The frequencies of the selected conditions ranged from 0.22 for pleural effusion to 0.0004 for tension pneumothorax. The database confirmed earlier observations that lung cancer occurs in a 3:2 right-to-left ratio. The association of pleural effusion with other conditions mirrored that in the literature. Bullet and stab wounds decreased during 10 years at a rate consistent with crime statistics. A review of pneumothorax cases showed that the database (sensitivity, 1.00; specificity, 0.996) was more accurate than financial discharge coding (sensitivity, 0.17; P =.002; specificity, 0.996; not significant). CONCLUSION: Internal and external validation in this study confirmed the accuracy of natural language processing for translating chest radiographic narrative reports into a large database of information.

Databases, Factual↗

PubMed2002

A comparison of the Charlson comorbidities derived from medical language processing and administrative data.

The objective of this study was to develop a medical language processing (MLP) system, which consisted of MedLEE and a set of inference rules, to identify 19 Charlson comorbidities from discharge summaries and chest x-ray reports. We used 233 cases to learn the patterns that were indicative of comorbidities for developing the inference rules. We then used an independent data set of 3,662 pneumonia patients to identify comorbidities by MLP compared with administrative data (ICD-9 codes). A stratified random sample of 190 records from disagreement cases was manually reviewed. The sensitivity, specificity, and accuracy for the MLP system/ICD-9 codes in this testing set were 0.84/0.16, 0.70/0.30, and 0.77/0.23 respectively. Thirteen of the 19 comorbidities studied were underreported in the administrative data. The kappa values ranged from 0.19 for peptic ulcer to 0.70 for lymphoma. We conclude that comorbidities derived from natural language processing of medical records can improve ICD-9-based approaches.

Adult↗

PubMed2002

Representing nested semantic information in a linear string of text using XML.

XML has been widely adopted as an important data interchange language. The structure of XML enables sharing of data elements with variable degrees of nesting as long as the elements are grouped in a strict tree-like fashion. This requirement potentially restricts the usefulness of XML for marking up written text, which often includes features that do not properly nest within other features. We encountered this problem while marking up medical text with structured semantic information from a Natural Language Processor. Traditional approaches to this problem separate the structured information from the actual text mark up. This paper introduces an alternative solution, which tightly integrates the semantic structure with the text. The resulting XML markup preserves the linearity of the medical texts and can therefore be easily expanded with additional types of information.

Programming Languages↗

PubMed2002

The effect of sample size and disease prevalence on supervised machine learning of narrative data.

This paper examines the independent effects of outcome prevalence and training sample sizes on inductive learning performance. We trained 3 inductive learning algorithms (MC4, IB, and Naïve-Bayes) on 60 simulated datasets of parsed radiology text reports labeled with 6 disease states. Data sets were constructed to define positive outcome states at 4 prevalence rates (1, 5, 10, 25, and 50%) in training set sizes of 200 and 2,000 cases. We found that the effect of outcome prevalence is significant when outcome classes drop below 10% of cases. The effect appeared independent of sample size, induction algorithm used, or class label. Work is needed to identify methods of improving classifier performance when output classes are rare.

Algorithms↗

PubMed2002

The sublanguage of cross-coverage.

At Columbia-Presbyterian Medical Center, free-text "Signout" notes are typed into the electronic record by clinicians for the purpose of cross-coverage. We plan to "unlock" information about adverse events contained in these notes in a subsequent project using Natural Language Processing (NLP). To better understand the requirements for parsing, Signout notes were compared to other common medical notes (ambulatory clinic notes and discharge summaries) on a series of quantitative metrics. They are shorter (mean length 59.25 words vs. 144.11 and 340.85 for ambulatory and discharge notes respectively) and use more abbreviations (26.88% vs. 20.07% and 3.57%). Despite being terser, Signout notes use less ambiguous abbreviations (8.34% vs. 9.09% and 18.02%). Differences were found using Relative Entropy and Squared Chi-square Distance in a novel fashion to compare these medical corpora. Signout notes appear to constitute a unique sublanguage of medicine. The implications for parsing free-text cross-coverage notes into coded medical data are discussed.

Linguistics↗

PubMedDate not supplied

Mining complex clinical data for patient safety research: a framework for event discovery.

Successfully addressing patient safety requires detecting medical events effectively. Given the volume of patients seen at medical centers, detecting events automatically from data that are already available electronically would greatly facilitate patient safety work. We have created a framework for electronic detection. Key steps include: selecting target events, assessing what information is available electronically, transforming raw data such as narrative notes into a coded format, querying the transformed data, verifying the accuracy of event detection, characterizing the events using systems and cognitive approaches, and using what is learned to improve detection.

Database Management Systems↗