Neural translation and automated recognition of ICD-10 medical entities from natural language: Algorithm Development and Validation (Preprint)

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.

Contacts with health services during the year prior to suicide death in France (2013-2015)

Background

This study was designed to describe contacts with health services during the year before suicide death in France, and to compare the prevalent mental and physical conditions in these people to those of the general population.

Methods

Data were extracted from the French National Health Data System (SNDS), which comprises comprehensive claims data for inpatient and outpatient care linked to the national causes-of-death registry. Individuals, national health insurance general scheme beneficiaries (i.e. 76% of the population living in France), aged 15 years or older, who died from suicide in France in 2013-2015 were included. Medical consultations, emergency room visits, and hospitalisations during the year preceding death were collected. Conditions were identified, and standardised prevalence ratios (SPRs) were estimated to compare prevalence rates in suicide decedents with those of the general population.

Results

The study included 19,144 suicide decedents. Overall, 8.5% of suicide decedents consulted a physician or attended an emergency room on the day of death, 34.1% during the week before death, 60.9% during the month before death. Most contacts involved a general practitioner or an emergency room (46.2% of suicide decedents consulted a general practitioner during the month before death, 16.7% attended an emergency room). During the month preceding suicide, 24.4% of individuals were hospitalised at least once. Mental conditions (36.8% of cases) were 7.9-fold (SPR 95% CI: 7.7-8.1) more prevalent in suicide decedents than in the general population. The highest SPRs among physical conditions were for liver/pancreatic diseases (SPR=3.3, 95% CI: 3.1-3.6) and epilepsy (SPR=2.7, 95% CI: 2.4-3.0).

Conclusions

General practitioners and emergency departments have frequent contacts with suicide decedents during the last weeks before death and are at the forefront of suicide risk identification and prevention in individuals with mental, but also physical conditions.

Key messages

Mental and physical conditions are more common among suicide decedents than in the general population, and contacts with primary care services are frequent in the last weeks prior to suicide. Primary care services (general practitioners and emergency rooms) should be targeted for suicide preventive interventions.

Contacts with Health Services During the Year Prior to Suicide Death and Prevalent Conditions A Nationwide Study

BACKGROUND

This study was designed to describe contacts with health services during the year before suicide death in France, and prevalent mental and physical conditions.

METHODS

Data were extracted from the French National Health Data System (SNDS), which comprises comprehensive claims data for inpatient and outpatient care linked to the national causes-of-death registry. Individuals aged ≥15 years who died from suicide in France in 2013-2015 were included. Medical consultations, emergency room visits, and hospitalisations during the year preceding death were collected. Conditions were identified, and standardised prevalence ratios (SPRs) were estimated to compare prevalence rates in suicide decedents with those of the general population.

RESULTS

The study included 19,144 individuals. Overall, 8.5% of suicide decedents consulted a physician or attended an emergency room on the day of death, 34.1% during the week before death, 60.9% during the month before death. Most contacts involved a general practitioner or an emergency room. During the month preceding suicide, 24.4% of individuals were hospitalised at least once. Mental conditions (36.8% of cases) were 7.9-fold more prevalent in suicide decedents than in the general population. The highest SPRs among physical conditions were for liver/pancreatic diseases (SPR=3.3) and epilepsy (SPR=2.7).

LIMITATIONS

The study population was restricted to national health insurance general scheme beneficiaries (76% of the population living in France).

CONCLUSIONS

Suicide decedents have frequent contacts with general practitioners and emergency departments during the last weeks before death. Improving suicide risk identification and prevention in these somatic healthcare settings is needed.

A Deep Artificial Neural Network-Based Model for Prediction of Underlying Cause of Death From Death Certificates: Algorithm Development and Validation

Background

Coding of underlying causes of death from death certificates is a process that is nowadays undertaken mostly by humans with potential assistance from expert systems, such as the Iris software. It is, consequently, an expensive process that can, in addition, suffer from geospatial discrepancies, thus severely impairing the comparability of death statistics at the international level. The recent advances in artificial intelligence, specifically the rise of deep learning methods, has enabled computers to make efficient decisions on a number of complex problems that were typically considered out of reach without human assistance; they require a considerable amount of data to learn from, which is typically their main limiting factor. However, the CépiDc (Centre d’épidémiologie sur les causes médicales de Décès) stores an exhaustive database of death certificates at the French national scale, amounting to several millions of training examples available for the machine learning practitioner.

Objective

This article investigates the application of deep neural network methods to coding underlying causes of death.

Methods

The investigated dataset was based on data contained from every French death certificate from 2000 to 2015, containing information such as the subject’s age and gender, as well as the chain of events leading to his or her death, for a total of around 8 million observations. The task of automatically coding the subject’s underlying cause of death was then formulated as a predictive modelling problem. A deep neural network−based model was then designed and fit to the dataset. Its error rate was then assessed on an exterior test dataset and compared to the current state-of-the-art (ie, the Iris software). Statistical significance of the proposed approach’s superiority was assessed via bootstrap.

Results

The proposed approach resulted in a test accuracy of 97.8% (95% CI 97.7-97.9), which constitutes a significant improvement over the current state-of-the-art and its accuracy of 74.5% (95% CI 74.0-75.0) assessed on the same test example. Such an improvement opens up a whole field of new applications, from nosologist-level batch-automated coding to international and temporal harmonization of cause of death statistics. A typical example of such an application is demonstrated by recoding French overdose-related deaths from 2000 to 2010.

Conclusions

This article shows that deep artificial neural networks are perfectly suited to the analysis of electronic health records and can learn a complex set of medical rules directly from voluminous datasets, without any explicit prior knowledge. Although not entirely free from mistakes, the derived algorithm constitutes a powerful decision-making tool that is able to handle structured medical data with an unprecedented performance. We strongly believe that the methods developed in this article are highly reusable in a variety of settings related to epidemiology, biostatistics, and the medical sciences in general.

[Development of multidisciplinary community-based health care centres in Germany]

MVZ provide community-based health care services improving integrated primary care and specialist care and allow hospital to outsource outpatient activities. They also provide patient-centered care and promote internal and external multidisciplinary coordination.</ce:para> <ce:para>MVZ can provide an example for possible changes to private specialist organisation and structuring of hospital services in France, while MSP mainly focus on primary care and only a few specialist CS have been created.</ce:para>.