Search

Background: Standardized coding of plays an important role in radiology reports' secondary use such as data analytics, data-driven decision support, and personalized medicine. RadLex, a standard radiological lexicon, can reduce subjective variability and improve clarity in radiology reports. RadLex coding of radiology reports is widely used in many countries, but translation and localization of RadLex in China are far from being established. Although automatic RadLex coding is a common way for non-standard radiology reports, the high-accuracy cross-language RadLex coding is hardly achieved due to the limitation of up-to-date auto-translation and text similarity algorithms and still requires further research.Methods: We present an effective approach that combines a hybrid translation and a Multilayer Perceptron weighting text similarity ensemble algorithm for automatic RadLex coding of Chinese structured radiology reports. Firstly, a hybrid way to integrate Google neural machine translation and dictionary translation helps to optimize the translation of Chinese radiology phrases to English. The dictionary is made up of 21,863 Chinese-English radiological term pairs extracted from several free medical dictionaries. Secondly, four typical text similarity algorithms are introduced, which are Levenshtein distance, Jaccard similarity coefficient, Word2vec Continuous bag-of-words model, and WordNet Wup similarity algorithms. Lastly, the Multilayer Perceptron model has been used to synthesize the contextual, lexical, character and syntactical information of four text similarity algorithms to promote precision, in which four similarity scores of two terms are taken as input and the output presents whether the two terms are synonyms.Results: The results show the effectiveness of the approach with an F1-score of 90.15%, a precision of 91.78% and a recall of 88.59%. The hybrid translation algorithm has no negative effect on the final coding, F1-score has increased by 21.44% and 8.12% compared with the GNMT algorithm and dictionary translation. Compared with the single similarity, the result of the MLP weighting similarity algorithm is satisfactory that has a 4.48% increase compared with the best single similarity algorithm, WordNet Wup.Conclusions: The paper proposed an innovative automatic cross-language RadLex coding approach to solve the standardization of Chinese structured radiology reports, that can be taken as a reference to automatic cross-language coding. [ABSTRACT FROM AUTHOR]

Background: It has been shown that the entities in everyday clinical text are often expressed in a way that varies from how they are expressed in the nomenclature. Owing to lots of synonyms, abbreviations, medical jargons or even misspellings in the daily used physician notes in clinical information system (CIS), the terminology without enough synonyms may not be adequately suitable for the task of Chinese clinical term recognition.Methods: This paper demonstrates a validated system to retrieve the Chinese term of clinical finding (CTCF) from CIS and map them to the corresponding concepts of international clinical nomenclature, such as SNOMED CT. The system focuses on the SNOMED CT with Chinese synonyms enrichment (SCCSE). The literal similarity and the diagnosis-related similarity metrics were used for concept mapping. Two CTCF recognition methods, the rule- and terminology-based approach (RTBA) and the conditional random field machine learner (CRF), were adopted to identify the concepts in physician notes. The system was validated against the history of present illness annotated by clinical experts. The RTBA and CRF could be combined to predict new CTCFs besides SCCSE persistently.Results: Around 59,000 CTCF candidates were accepted as valid and 39,000 of them occurred at least once in the history of present illness. 3,729 of them were accordant with the description in referenced Chinese clinical nomenclature, which could cross map to other international nomenclature such as SNOMED CT. With the hybrid similarity metrics, another 7,454 valid CTCFs (synonyms) were succeeded in concept mapping. For CTCF recognition in physician notes, a series of experiments were performed to find out the best CRF feature set, which gained an F-score of 0.887. The RTBA achieved a better F-score of 0.919 by the CTCF dictionary created in this research.Conclusions: This research demonstrated that it is feasible to help the SNOMED CT with Chinese synonyms enrichment based on physician notes in CIS. With continuous maintenance of SCCSE, the CTCFs could be precisely retrieved from free text, and the CTCFs arranged in semantic hierarchy of SNOMED CT could greatly improve the meaningful use of electronic health record in China. The methodology is also useful for clinical synonyms enrichment in other languages. [ABSTRACT FROM AUTHOR]

Background: Administrative healthcare databases are widespread and are often standardized with regard to their content and data coding, thus they can be used also as data sources for surveillance and epidemiological research. Chronic dialysis requires patients to frequently access hospital and clinic services, causing a heavy burden to healthcare providers. This also means that these patients are routinely tracked on administrative databases, yet very few case definitions for their identification are currently available. The aim of this study was to develop two algorithms derived from administrative data for identifying incident chronic dialysis patients and test their validity compared to the reference standard of the regional dialysis registry.Methods: The algorithms are based on data retrieved from hospital discharge records (HDR) and ambulatory specialty visits (ASV) to identify incident chronic dialysis patients in an Italian region. Subjects are included if they have at least one event in the HDR or ASV databases based on the ICD9-CM dialysis-related diagnosis or procedure codes in the study period. Exclusion criteria comprise non-residents, prevalent cases, or patients undergoing temporary dialysis, and are evaluated only on ASV data by the first algorithm, on both ASV and HDR data by the second algorithm. We validated the algorithms against the Emilia-Romagna regional dialysis registry by searching for incident patients in 2014 and performed sensitivity analyses by modifying the criteria to define temporary dialysis.Results: Algorithm 1 identified 680 patients and algorithm 2 identified 676 initiating dialysis in 2014, compared to 625 patients included in the regional dialysis registry. Sensitivity for the two algorithms was respectively 90.8 and 88.4%, positive predictive value 84.0 and 82.0%, and percentage agreement was 77.4 and 74.1%.Conclusions: Algorithms relying on retrieval of administrative records have high sensitivity and positive predictive value for the identification of incident chronic dialysis patients. Algorithm 1, which showed the higher accuracy and has a simpler case definition, can be used in place of regional dialysis registries when they are not present or sufficiently developed in a region, or to improve the accuracy and timeliness of existing registries. [ABSTRACT FROM AUTHOR]

Background: Patient stratification is a critical task in clinical decision making since it can allow physicians to choose treatments in a personalized way. Given the increasing availability of electronic medical records (EMRs) with longitudinal data, one crucial problem is how to efficiently cluster the patients based on the temporal information from medical appointments. In this work, we propose applying the Temporal Needleman-Wunsch (TNW) algorithm to align discrete sequences with the transition time information between symbols. These symbols may correspond to a patient's current therapy, their overall health status, or any other discrete state. The transition time information represents the duration of each of those states. The obtained TNW pairwise scores are then used to perform hierarchical clustering. To find the best number of clusters and assess their stability, a resampling technique is applied.Results: We propose the AliClu, a novel tool for clustering temporal clinical data based on the TNW algorithm coupled with clustering validity assessments through bootstrapping. The AliClu was applied for the analysis of the rheumatoid arthritis EMRs obtained from the Portuguese database of rheumatologic patient visits (Reuma.pt). In particular, the AliClu was used for the analysis of therapy switches, which were coded as letters corresponding to biologic drugs and included their durations before each change occurred. The obtained optimized clusters allow one to stratify the patients based on their temporal therapy profiles and to support the identification of common features for those groups.Conclusions: The AliClu is a promising computational strategy to analyse longitudinal patient data by providing validated clusters and by unravelling the patterns that exist in clinical outcomes. Patient stratification is performed in an automatic or semi-automatic way, allowing one to tune the alignment, clustering, and validation parameters. The AliClu is freely available at https://github.com/sysbiomed/AliClu. [ABSTRACT FROM AUTHOR]

Background: The objective of this research is to compare the relational and non-relational (NoSQL) database systems approaches in order to store, recover, query and persist standardized medical information in the form of ISO/EN 13606 normalized Electronic Health Record XML extracts, both in isolation and concurrently. NoSQL database systems have recently attracted much attention, but few studies in the literature address their direct comparison with relational databases when applied to build the persistence layer of a standardized medical information system.Methods: One relational and two NoSQL databases (one document-based and one native XML database) of three different sizes have been created in order to evaluate and compare the response times (algorithmic complexity) of six different complexity growing queries, which have been performed on them. Similar appropriate results available in the literature have also been considered.Results: Relational and non-relational NoSQL database systems show almost linear algorithmic complexity query execution. However, they show very different linear slopes, the former being much steeper than the two latter. Document-based NoSQL databases perform better in concurrency than in isolation, and also better than relational databases in concurrency.Conclusion: Non-relational NoSQL databases seem to be more appropriate than standard relational SQL databases when database size is extremely high (secondary use, research applications). Document-based NoSQL databases perform in general better than native XML NoSQL databases. EHR extracts visualization and edition are also document-based tasks more appropriate to NoSQL database systems. However, the appropriate database solution much depends on each particular situation and specific problem. [ABSTRACT FROM AUTHOR]

Background: Clinical data repositories (CDR) have great potential to improve outcome prediction and risk modeling. However, most clinical studies require careful study design, dedicated data collection efforts, and sophisticated modeling techniques before a hypothesis can be tested. We aim to bridge this gap, so that clinical domain users can perform first-hand prediction on existing repository data without complicated handling, and obtain insightful patterns of imbalanced targets for a formal study before it is conducted. We specifically target for interpretability for domain users where the model can be conveniently explained and applied in clinical practice.Methods: We propose an interpretable pattern model which is noise (missing) tolerant for practice data. To address the challenge of imbalanced targets of interest in clinical research, e.g., deaths less than a few percent, the geometric mean of sensitivity and specificity (G-mean) optimization criterion is employed, with which a simple but effective heuristic algorithm is developed.Results: We compared pattern discovery to clinically interpretable methods on two retrospective clinical datasets. They contain 14.9% deaths in 1 year in the thoracic dataset and 9.1% deaths in the cardiac dataset, respectively. In spite of the imbalance challenge shown on other methods, pattern discovery consistently shows competitive cross-validated prediction performance. Compared to logistic regression, Naïve Bayes, and decision tree, pattern discovery achieves statistically significant (p-values < 0.01, Wilcoxon signed rank test) favorable averaged testing G-means and F1-scores (harmonic mean of precision and sensitivity). Without requiring sophisticated technical processing of data and tweaking, the prediction performance of pattern discovery is consistently comparable to the best achievable performance.Conclusions: Pattern discovery has demonstrated to be robust and valuable for target prediction on existing clinical data repositories with imbalance and noise. The prediction results and interpretable patterns can provide insights in an agile and inexpensive way for the potential formal studies. [ABSTRACT FROM AUTHOR]

Background: Risk calculation is increasingly used in lipid management, congestive heart failure, and atrial fibrillation. The risk scores are then used for decisions about statin use, anticoagulation, and implantable defibrillator use. Calculating risks for patients and making decisions based on these risks is often done at the point of care and is an additional time burden for clinicians that can be decreased by automating the tasks and using clinical decision-making support.Methods: Using Morae Recorder software, we timed 30 healthcare providers tasked with calculating the overall risk of cardiovascular events, sudden death in heart failure, and thrombotic event risk in atrial fibrillation. Risk calculators used were the American College of Cardiology Atherosclerotic Cardiovascular Disease risk calculator (AHA-ASCVD risk), Seattle Heart Failure Model (SHFM risk), and CHA2DS2VASc. We also timed the 30 providers using Ask Mayo Expert care process models for lipid management, heart failure management, and atrial fibrillation management based on the calculated risk scores. We used the Mayo Clinic primary care panel to estimate time for calculating an entire panel risk.Results: Mean provider times to complete the CHA2DS2VASc, AHA-ASCVD risk, and SHFM were 36, 45, and 171 s respectively. For decision making about atrial fibrillation, lipids, and heart failure, the mean times (including risk calculations) were 85, 110, and 347 s respectively.Conclusion: Even under best case circumstances, providers take a significant amount of time to complete risk assessments. For a complete panel of patients this can lead to hours of time required to make decisions about prescribing statins, use of anticoagulation, and medications for heart failure. Informatics solutions are needed to capture data in the medical record and serve up automatically calculated risk assessments to physicians and other providers at the point of care. [ABSTRACT FROM AUTHOR]