Dataset Information

Assessing the Performance of Clinical Natural Language Processing Systems: Development of an Evaluation Methodology.

ABSTRACT:

Background

Clinical natural language processing (cNLP) systems are of crucial importance due to their increasing capability in extracting clinically important information from free text contained in electronic health records (EHRs). The conversion of a nonstructured representation of a patient's clinical history into a structured format enables medical doctors to generate clinical knowledge at a level that was not possible before. Finally, the interpretation of the insights gained provided by cNLP systems has a great potential in driving decisions about clinical practice. However, carrying out robust evaluations of those cNLP systems is a complex task that is hindered by a lack of standard guidance on how to systematically approach them.

Objective

Our objective was to offer natural language processing (NLP) experts a methodology for the evaluation of cNLP systems to assist them in carrying out this task. By following the proposed phases, the robustness and representativeness of the performance metrics of their own cNLP systems can be assured.

Methods

The proposed evaluation methodology comprised five phases: (1) the definition of the target population, (2) the statistical document collection, (3) the design of the annotation guidelines and annotation project, (4) the external annotations, and (5) the cNLP system performance evaluation. We presented the application of all phases to evaluate the performance of a cNLP system called "EHRead Technology" (developed by Savana, an international medical company), applied in a study on patients with asthma. As part of the evaluation methodology, we introduced the Sample Size Calculator for Evaluations (SLiCE), a software tool that calculates the number of documents needed to achieve a statistically useful and resourceful gold standard.

Results

The application of the proposed evaluation methodology on a real use-case study of patients with asthma revealed the benefit of the different phases for cNLP system evaluations. By using SLiCE to adjust the number of documents needed, a meaningful and resourceful gold standard was created. In the presented use-case, using as little as 519 EHRs, it was possible to evaluate the performance of the cNLP system and obtain performance metrics for the primary variable within the expected CIs.

Conclusions

We showed that our evaluation methodology can offer guidance to NLP experts on how to approach the evaluation of their cNLP systems. By following the five phases, NLP experts can assure the robustness of their evaluation and avoid unnecessary investment of human and financial resources. Besides the theoretical guidance, we offer SLiCE as an easy-to-use, open-source Python library.

SUBMITTER: Canales L

PROVIDER: S-EPMC8367121 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:In recognition of potential barriers that may inhibit the widespread adoption of biomedical software, the 2014 i2b2 Challenge introduced a special track, Track 3 - Software Usability Assessment, in order to develop a better understanding of the adoption issues that might be associated with the state-of-the-art clinical NLP systems. This paper reports the ease of adoption assessment methods we developed for this track, and the results of evaluating five clinical NLP system submissions.A team of human evaluators performed a series of scripted adoptability test tasks with each of the participating systems. The evaluation team consisted of four "expert evaluators" with training in computer science, and eight "end user evaluators" with mixed backgrounds in medicine, nursing, pharmacy, and health informatics. We assessed how easy it is to adopt the submitted systems along the following three dimensions: communication effectiveness (i.e., how effective a system is in communicating its designed objectives to intended audience), effort required to install, and effort required to use. We used a formal software usability testing tool, TURF, to record the evaluators' interactions with the systems and 'think-aloud' data revealing their thought processes when installing and using the systems and when resolving unexpected issues.Overall, the ease of adoption ratings that the five systems received are unsatisfactory. Installation of some of the systems proved to be rather difficult, and some systems failed to adequately communicate their designed objectives to intended adopters. Further, the average ratings provided by the end user evaluators on ease of use and ease of interpreting output are -0.35 and -0.53, respectively, indicating that this group of users generally deemed the systems extremely difficult to work with. While the ratings provided by the expert evaluators are higher, 0.6 and 0.45, respectively, these ratings are still low indicating that they also experienced considerable struggles.The results of the Track 3 evaluation show that the adoptability of the five participating clinical NLP systems has a great margin for improvement. Remedy strategies suggested by the evaluators included (1) more detailed and operation system specific use instructions; (2) provision of more pertinent onscreen feedback for easier diagnosis of problems; (3) including screen walk-throughs in use instructions so users know what to expect and what might have gone wrong; (4) avoiding jargon and acronyms in materials intended for end users; and (5) packaging prerequisites required within software distributions so that prospective adopters of the software do not have to obtain each of the third-party components on their own.

Project description:BackgroundManually curating standardized phenotypic concepts such as Human Phenotype Ontology (HPO) terms from narrative text in electronic health records (EHRs) is time consuming and error prone. Natural language processing (NLP) techniques can facilitate automated phenotype extraction and thus improve the efficiency of curating clinical phenotypes from clinical texts. While individual NLP systems can perform well for a single cohort, an ensemble-based method might shed light on increasing the portability of NLP pipelines across different cohorts.MethodsWe compared four NLP systems, MetaMapLite, MedLEE, ClinPhen and cTAKES, and four ensemble techniques, including intersection, union, majority-voting and machine learning, for extracting generic phenotypic concepts. We addressed two important research questions regarding automated phenotype recognition. First, we evaluated the performance of different approaches in identifying generic phenotypic concepts. Second, we compared the performance of different methods to identify patient-specific phenotypic concepts. To better quantify the effects caused by concept granularity differences on performance, we developed a novel evaluation metric that considered concept hierarchies and frequencies. Each of the approaches was evaluated on a gold standard set of clinical documents annotated by clinical experts. One dataset containing 1,609 concepts derived from 50 clinical notes from two different institutions was used in both evaluations, and an additional dataset of 608 concepts derived from 50 case report abstracts obtained from PubMed was used for evaluation of identifying generic phenotypic concepts only.ResultsFor generic phenotypic concept recognition, the top three performers in the NYP/CUIMC dataset are union ensemble (F1, 0.634), training-based ensemble (F1, 0.632), and majority vote-based ensemble (F1, 0.622). In the Mayo dataset, the top three are majority vote-based ensemble (F1, 0.642), cTAKES (F1, 0.615), and MedLEE (F1, 0.559). In the PubMed dataset, the top three are majority vote-based ensemble (F1, 0.719), training-based (F1, 0.696) and MetaMapLite (F1, 0.694). For identifying patient specific phenotypes, the top three performers in the NYP/CUIMC dataset are majority vote-based ensemble (F1, 0.610), MedLEE (F1, 0.609), and training-based ensemble (F1, 0.585). In the Mayo dataset, the top three are majority vote-based ensemble (F1, 0.604), cTAKES (F1, 0.531) and MedLEE (F1, 0.527).ConclusionsOur study demonstrates that ensembles of natural language processing can improve both generic phenotypic concept recognition and patient specific phenotypic concept identification over individual systems. Among the individual NLP systems, each individual system performed best when they were applied in the dataset that they were primary designed for. However, combining multiple NLP systems to create an ensemble can generally improve the performance. Specifically, the ensemble can increase the results reproducibility across different cohorts and tasks, and thus provide a more portable phenotyping solution compared to individual NLP systems.

Project description:ContextIdentifying tranquil areas is important for landscape planning and policy-making. Research demonstrated discrepancies between modelled potential tranquil areas and where people experience tranquillity based on field surveys. Because surveys are resource-intensive, user-generated text data offers potential for extracting where people experience tranquillity.ObjectivesWe explore and model the relationship between landscape ecological measures and experienced tranquillity extracted from user-generated text descriptions.MethodsGeoreferenced, user-generated landscape descriptions from Geograph.UK were filtered using keywords related to tranquillity. We stratify resulting tranquil locations according to dominant land cover and quantify the influence of landscape characteristics including diversity and naturalness on explaining the presence of tranquillity. Finally, we apply natural language processing to identify terms linked to tranquillity keywords and compare the similarity of these terms across land cover classes.ResultsEvaluation of potential keywords yielded six keywords associated with experienced tranquillity, resulting in 15,350 extracted tranquillity descriptions. The two most common land cover classes associated with tranquillity were arable and horticulture, and improved grassland, followed by urban and suburban. In the logistic regression model across all land cover classes, freshwater, elevation and naturalness were positive predictors of tranquillity. Built-up area was a negative predictor. Descriptions of tranquillity were most similar between improved grassland and arable and horticulture, and most dissimilar between arable and horticulture and urban.ConclusionsThis study highlights the potential of applying natural language processing to extract experienced tranquillity from text, and demonstrates links between landscape ecological measures and tranquillity as a perceived landscape quality.Supplementary informationThe online version of this article (10.1007/s10980-020-01181-8) contains supplementary material, which is available to authorized users.

Project description:Natural language descriptions of organismal phenotypes, a principal object of study in biology, are abundant in the biological literature. Expressing these phenotypes as logical statements using ontologies would enable large-scale analysis on phenotypic information from diverse systems. However, considerable human effort is required to make these phenotype descriptions amenable to machine reasoning. Natural language processing tools have been developed to facilitate this task, and the training and evaluation of these tools depend on the availability of high quality, manually annotated gold standard data sets. We describe the development of an expert-curated gold standard data set of annotated phenotypes for evolutionary biology. The gold standard was developed for the curation of complex comparative phenotypes for the Phenoscape project. It was created by consensus among three curators and consists of entity-quality expressions of varying complexity. We use the gold standard to evaluate annotations created by human curators and those generated by the Semantic CharaParser tool. Using four annotation accuracy metrics that can account for any level of relationship between terms from two phenotype annotations, we found that machine-human consistency, or similarity, was significantly lower than inter-curator (human-human) consistency. Surprisingly, allowing curatorsaccess to external information did not significantly increase the similarity of their annotations to the gold standard or have a significant effect on inter-curator consistency. We found that the similarity of machine annotations to the gold standard increased after new relevant ontology terms had been added. Evaluation by the original authors of the character descriptions indicated that the gold standard annotations came closer to representing their intended meaning than did either the curator or machine annotations. These findings point toward ways to better design software to augment human curators and the use of the gold standard corpus will allow training and assessment of new tools to improve phenotype annotation accuracy at scale.