A Lightweight API-Based Approach for Building Flexible Clinical NLP Systems

Abstract

Natural language processing (NLP) has become essential for secondary use of clinical data. Over the last two decades, many clinical NLP systems were developed in both academia and industry. However, nearly all existing systems are restricted to specific clinical settings mainly because they were developed for and tested with specific datasets, and they often fail to scale up. Therefore, using existing NLP systems for one’s own clinical purposes requires substantial resources and long-term time commitments for customization and testing. Moreover, the maintenance is also troublesome and time-consuming. This research presents a lightweight approach for building clinical NLP systems with limited resources. Following the design science research approach, we propose a lightweight architecture which is designed to be composable, extensible, and configurable. It takes NLP as an external component which can be accessed independently and orchestrated in a pipeline via web APIs. To validate its feasibility, we developed a web-based prototype for clinical concept extraction with six well-known NLP APIs and evaluated it on three clinical datasets. In comparison with available benchmarks for the datasets, three high F1 scores (0.861, 0.724, and 0.805) were obtained from the evaluation. It also gained a low F1 score (0.373) on one of the tests, which probably is due to the small size of the test dataset. The development and evaluation of the prototype demonstrates that our approach has a great potential for building effective clinical NLP systems with limited resources.

Revolutionizing Accessibility: Smart Wheelchair Robot and Mobile Application for Mobility, Assistance, and Home Management

“…The third article, [83], delves into the impact of intelligent speech recognition (ISR) systems on English learning, presenting a study affirming the enhancement of English listening and speaking skills among Chinese students. The article [84] [98] [100] proposes a lightweight API-based approach for flexible clinical NLP systems, aiming to simplify the development and deployment of clinical NLP systems, accompanied by a case study on adverse drug event identification. The final article [85] delves into the technical considerations of using oligonucleotide solution APIs, pivotal in synthesizing DNA or RNA strands for diverse applications, providing an extensive overview of available APIs and essential technical aspects for their use.…”

Automatic Extraction of Adverse Drug Reactions from Summary of Product Characteristics

“…Specifically, we simplify the extraction process by using the IBM Watson Natural Language Understanding API that offers sophisticated NLP techniques in extracting meta-data from content such as concepts, entities, keywords, and others. Benchmarking studies have shown that IBM Watson Natural Language Understanding API is a simple and useful NLP tool in solving various clinical NLP problems [12,13]. A demonstration of how the API works is available [14].…”