Suicide and All-Cause Mortality Within 1 Year After a Suicide Attempt in the VigilanS Cohort.

Objective: Obtaining better knowledge on the outcomes of patients who attempt suicide is crucial for suicide prevention. The aim of our study was to determine the causes of death 1 year after a suicide attempt (SA) in the VigilanS program, mortality rates, and risk factors associated with any cause of death and suicide.Methods: A prospective cohort of 7,406 people who had attempted suicide between January 1, 2017, and December 31, 2018, was included in the study. The vital status of each participant was sought, and the cause of death was established through a phone call to their general practitioner or psychiatrist. Second, the relationship between sociodemographic and clinical factors and death by suicide within 1 year of an SA was assessed using a multivariable Cox model.Results: At 1 year, 125 (1.7%) participants had died, 77 of whom died by suicide. Half of the deaths occurred within the first 4 months after an SA. Hanging (20.3%; 24/125) and self-poisoning (19.5%; 23/125) were the methods the most often used for suicide. We demonstrated that male sex (HR = 1.79 [1.13-2.82], P = .01) and being 45 years of age or older (between 45 and 64 years old, HR = 2.08 [1.21-3.56], P < .01; 65 years or older, HR = 5.36 [2.72-10.54], P < .01) were associated with a higher risk of death by suicide 1 year after an SA and that being younger than 25 years was associated with a lower risk (HR = 0.22 [0.07-0.76], P = .02).Conclusions: One out of 100 people who attempted suicide died by suicide within 1 year after an SA. Greater vigilance is required in the first months following an SA, especially for males older than 45 years.Trial Registration: ClinicalTrials.gov identifier: NCT03134885.

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

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.

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.

Causes of deaths data, linkages and big data perspectives.

The study of cause-specific mortality data is one of the main sources of information for public health monitoring. In most industrialized countries, when a death occurs, it is a legal requirement that a medical certificate based on the international form recommended by World Health Organization's (WHO) is filled in by a physician. The physician reports the causes of death that directly led or contributed to the death on the death certificate. The death certificate is then forwarded to a coding office, where each cause is coded, and one underlying cause is defined, using the rules of the International Classification of Diseases and Related Health Problems, now in its 10th Revision (ICD-10). Recently, a growing number of countries have adopted, or have decided to adopt, the coding software Iris, developed and maintained by an international consortium1. This whole standardized production process results in a high and constantly increasing international comparability of cause-specific mortality data. While these data could be used for international comparisons and benchmarking of global burden of diseases, quality of care and prevention policies, there are also many other ways and methods to explore their richness, especially when they are linked with other data sources. Some of these methods are potentially referring to the so-called "big data" field. These methods could be applied both to the production of the data, to the statistical processing of the data, and even more to process these data linked to other databases. In the present note, we depict the main domains in which this new field of methods could be applied. We focus specifically on the context of France, a 65 million inhabitants country with a centralized health data system. Finally we will insist on the importance of data quality, and the specific problematics related to death certification in the forensic medicine domain.