Dynamic categorization of clinical research eligibility criteria by hierarchical clustering

Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States.
Journal of Biomedical Informatics (Impact Factor: 2.19). 06/2011; 44(6):927-35. DOI: 10.1016/j.jbi.2011.06.001
Source: PubMed


To semi-automatically induce semantic categories of eligibility criteria from text and to automatically classify eligibility criteria based on their semantic similarity.
The UMLS semantic types and a set of previously developed semantic preference rules were utilized to create an unambiguous semantic feature representation to induce eligibility criteria categories through hierarchical clustering and to train supervised classifiers.
We induced 27 categories and measured the prevalence of the categories in 27,278 eligibility criteria from 1578 clinical trials and compared the classification performance (i.e., precision, recall, and F1-score) between the UMLS-based feature representation and the "bag of words" feature representation among five common classifiers in Weka, including J48, Bayesian Network, Naïve Bayesian, Nearest Neighbor, and instance-based learning classifier.
The UMLS semantic feature representation outperforms the "bag of words" feature representation in 89% of the criteria categories. Using the semantically induced categories, machine-learning classifiers required only 2000 instances to stabilize classification performance. The J48 classifier yielded the best F1-score and the Bayesian Network classifier achieved the best learning efficiency.
The UMLS is an effective knowledge source and can enable an efficient feature representation for semi-automated semantic category induction and automatic categorization for clinical research eligibility criteria and possibly other clinical text.

Download full-text


Available from: Chunhua Weng
  • Source
    • "Köpcke et al. analyzed eligibility criteria from 15 clinical trials performed in 5 tertiary care hospitals in Germany. Köpcke et al. categorized the eligibility criteria based on the semantic categories identified by Luo et al. and found distribution among semantic categories similar to the results of Luo et al. [22, 23]. A similar more recent study by Doods et al. evaluated eligibility criteria from 40 clinical trials to identify the most common data elements used for patient identification in pharmaceutical clinical trials. "
    [Show abstract] [Hide abstract]
    ABSTRACT: An increasing number of clinical trials are conducted in primary care settings. Making better use of existing data in the electronic health records to identify eligible subjects can improve efficiency of such studies. Our study aims to quantify the proportion of eligibility criteria that can be addressed with data in electronic health records and to compare the content of eligibility criteria in primary care with previous work. Eligibility criteria were extracted from primary care studies downloaded from the UK Clinical Research Network Study Portfolio. Criteria were broken into elemental statements. Two expert independent raters classified each statement based on whether or not structured data items in the electronic health record can be used to determine if the statement was true for a specific patient. Disagreements in classification were discussed until 100 % agreement was reached. Statements were also classified based on content and the percentages of each category were compared to two similar studies reported in the literature. Eligibility criteria were retrieved from 228 studies and decomposed into 2619 criteria elemental statements. 74 % of the criteria elemental statements were considered likely associated with structured data in an electronic health record. 79 % of the studies had at least 60 % of their criteria statements addressable with structured data likely to be present in an electronic health record. Based on clinical content, most frequent categories were: “disease, symptom, and sign”, “therapy or surgery”, and “medication” (36 %, 13 %, and 10 % of total criteria statements respectively). We also identified new criteria categories related to provider and caregiver attributes (2.6 % and 1 % of total criteria statements respectively). Electronic health records readily contain much of the data needed to assess patients’ eligibility for clinical trials enrollment. Eligibility criteria content categories identified by our study can be incorporated as data elements in electronic health records to facilitate their integration with clinical trial management systems.
    Full-text · Article · Dec 2015 · BMC Medical Informatics and Decision Making
  • Source
    • "Weng et al. [12] and Luo et al. [13] describe in related publications, a semi-automatic approach that allows annotating free text eligibility criteria using semantic representation. In contrast to our expert-driven simplification approach - intended to reduce complexity with a focus on trial feasibility - those methods aim at semi-automatically extracting the complete information out of free text. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Clinical studies are a necessity for new medications and therapies. Many studies, however, struggle to meet their recruitment numbers in time or have problems in meeting them at all. With increasing numbers of electronic health records (EHRs) in hospitals, huge databanks emerge that could be utilized to support research. The Innovative Medicine Initiative (IMI) funded project 'Electronic Health Records for Clinical Research' (EHR4CR) created a standardized and homogenous inventory of data elements to support research by utilizing EHRs. Our aim was to develop a Data Inventory that contains elements required for site feasibility analysis. The Data Inventory was created in an iterative, consensus driven approach, by a group of up to 30 people consisting of pharmaceutical experts and informatics specialists. An initial list was subsequently expanded by data elements of simplified eligibility criteria from clinical trial protocols. Each element was manually reviewed by pharmaceutical experts and standard definitions were identified and added. To verify their availability, data exports of the source systems at eleven university hospitals throughout Europe were conducted and evaluated. The Data Inventory consists of 75 data elements that, on the one hand are frequently used in clinical studies, and on the other hand are available in European EHR systems. Rankings of data elements were created from the results of the data exports. In addition a sub-list was created with 21 data elements that were separated from the Data Inventory because of their low usage in routine documentation. The data elements in the Data Inventory were identified with the knowledge of domain experts from pharmaceutical companies. Currently, not all information that is frequently used in site feasibility is documented in routine patient care.
    Full-text · Article · Jan 2014 · Trials
  • Source
    • "We examined how many and what type of trial eligibility criteria were mapped into the patient characteristics and corresponding data elements of the EMRs to evaluate the completeness of our mapping. We assigned patient characteristics, as mentioned above, to one of the 27 semantic categories defined by Luo et al. [22]. One author, a medical doctor, broke up and assigned the eligibility criteria to one of the semantic categories, and another medical doctor validated the results. "
    [Show abstract] [Hide abstract]
    ABSTRACT: A number of clinical trials have encountered difficulties enrolling a sufficient number of patients upon initiating the trial. Recently, many screening systems that search clinical data warehouses for patients who are eligible for clinical trials have been developed. We aimed to estimate the number of eligible patients using routine electronic medical records (EMRs) and to predict the difficulty of enrolling sufficient patients prior to beginning a trial. Investigator-initiated clinical trials that were conducted at Kyoto University Hospital between July 2004 and January 2011 were included in this study. We searched the EMRs for eligible patients and calculated the eligible EMR patient index by dividing the number of eligible patients in the EMRs by the target sample size. Additionally, we divided the trial eligibility criteria into corresponding data elements in the EMRs to evaluate the completeness of mapping clinical manifestation in trial eligibility criteria into structured data elements in the EMRs. We evaluated the correlation between the index and the accrual achievement with Spearman's rank correlation coefficient. Thirteen of 19 trials did not achieve their original target sample size. Overall, 55% of the trial eligibility criteria were mapped into data elements in EMRs. The accrual achievement demonstrated a significant positive correlation with the eligible EMR patient index (r = 0.67, 95% confidence interval (CI), 0.42 to 0.92). The receiver operating characteristic analysis revealed an eligible EMR patient index cut-off value of 1.7, with a sensitivity of 69.2% and a specificity of 100.0%. Our study suggests that the eligible EMR patient index remains exploratory but could be a useful component of the feasibility study when planning a clinical trial. Establishing a step to check whether there are likely to be a sufficient number of eligible patients enables sponsors and investigators to concentrate their resources and efforts on more achievable trials.
    Full-text · Article · Dec 2013 · Trials
Show more