Neural Translation and Automated Recognition of ICD-10 Medical Entities From Natural Language: Model Development and Performance Assessment

Abstract

Background The recognition of medical entities from natural language is a ubiquitous problem in the medical field, with applications ranging from medical coding to the analysis of electronic health data for public health. It is, however, a complex task usually requiring human expert intervention, thus making it expansive and time-consuming. Recent advances in artificial intelligence, specifically the rise of deep learning methods, have enabled computers to make efficient decisions on a number of complex problems, with the notable example of neural sequence models and their powerful applications in natural language processing. However, they require a considerable amount of data to learn from, which is typically their main limiting factor. The Centre for Epidemiology on Medical Causes of Death (CépiDc) stores an exhaustive database of death certificates at the French national scale, amounting to several millions of natural language examples provided with their associated human-coded medical entities available to the machine learning practitioner. Objective The aim of this paper was to investigate the application of deep neural sequence models to the problem of medical entity recognition from natural language. Methods The investigated data set included every French death certificate from 2011 to 2016. These certificates contain information such as the subject’s age, the subject’s gender, and the chain of events leading to his or her death, both in French and encoded as International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) medical entities, for a total of around 3 million observations in the data set. The task of automatically recognizing ICD-10 medical entities from the French natural language–based chain of events leading to death was then formulated as a type of predictive modeling problem known as a sequence-to-sequence modeling problem. A deep neural network–based model, known as the Transformer, was then slightly adapted and fit to the data set. Its performance was then assessed on an external data set and compared to the current state-of-the-art approach. CIs for derived measurements were estimated via bootstrapping. Results The proposed approach resulted in an F-measure value of 0.952 (95% CI 0.946-0.957), which constitutes a significant improvement over the current state-of-the-art approach and its previously reported F-measure value of 0.825 as assessed on a comparable data set. Such an improvement makes possible a whole field of new applications, from nosologist-level automated coding to temporal harmonization of death statistics. Conclusions This paper shows that a deep artificial neural network can directly learn from voluminous data sets in order to identify complex relationships between natural language and medical entities, without any explicit prior knowledge. Although not entirely free from mistakes, the derived model constitutes a powerful tool for automated coding of medical entities from medical language with promising potential applications.

Real-Time Classification of Causes of Death Using AI: Sensitivity Analysis

“…These results are aligned with those of previous studies using AUTOCOD [ 12 , 13 ] and, in general, with the literature on deep neural networks applied to the automatic classification of DCs [ 14 , 27 , 28 ]. Falissard et al [ 14 ] developed a deep neural network for automated coding of the underlying cause of death with a test accuracy of 0.978 (95% CI 0.977-0.979) and an F -measure value of 0.952 (95% CI 0.946-0.957) [ 27 ].…”

“…These results are aligned with those of previous studies using AUTOCOD [ 12 , 13 ] and, in general, with the literature on deep neural networks applied to the automatic classification of DCs [ 14 , 27 , 28 ]. Falissard et al [ 14 ] developed a deep neural network for automated coding of the underlying cause of death with a test accuracy of 0.978 (95% CI 0.977-0.979) and an F -measure value of 0.952 (95% CI 0.946-0.957) [ 27 ]. The proposed approach by Della Mea et al [ 28 ] for automated coding of causes of death had an accuracy of 0.990 (95% CI 0.990-0.991) and a macroaveraged accuracy and F 1 -score of 0.974 and 0.968, respectively.…”

Year 2022 in Medical Natural Language Processing: Availability of Language Models as a Step in the Democratization of NLP in the Biomedical Area

“…Nevertheless, the trends observed within this set of keywords are also reflected in the analysis provided in the following sections. [23], construction of cohorts of similar patients [24], processing of electronic medical records [25], understanding of patient's answers in a French medical chatbot [26]; • German: evaluation of Transformers on clinical notes [27]; • Greek: improving the performance of localized healthcare virtual assistants [28]; • Hindi: classification of COVID-19 texts [29], chatbot for information sexual and reproductive health for young people [30]; • Italian: analysis of social media for quality of life in Parkinson's patients [31], sentiment analysis of opinion on COVID-19 vaccines [32,33], estimation of the incidence of infectious disease cases [34]; • Japanese: understanding psychiatric illness [35], detection of adverse events from narrative clinical documents [36]; • Korean: BERT model for processing med-ical documents [37], sentiment analysis of tweets about COVID-19 vaccines [38];…”

“…and institutions (like MIMIC-III), as well as data from social media, hospitals, bibliographical datasets, clinical trials, etc. The research in other languages is possible mainly thanks to the availability of data from social media [7,9,19,20,22,38,43,47] and documents from local hospitals [10,13,14,17,18,23,25,27,36,37,40,42]. Besides, this set of works in languages other than English relies on the dedicated language models, which cover a great variety of languages by now.…”

Automated ICF Coding of Rehabilitation Notes for Low-Resource Languages via Continual Training of Language Models

“…Yet, the need for coding electronic health records also with ICF has been recognized as useful [4]. Thus, the use of tools to support this task is welcomed, although not yet researched as much as for other biomedical classifications like ICD, e.g., in [5,6,7,8].…”