Tags

Type your tag names separated by a space and hit enter

A Deep Artificial Neural Network-Based Model for Prediction of Underlying Cause of Death From Death Certificates: Algorithm Development and Validation.
JMIR Med Inform. 2020 Apr 28; 8(4):e17125.JM

Abstract

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.

Authors+Show Affiliations

Inserm (Institut National de la Santé et de la Recherche Médicale) - CépiDc (Centre d'epidémiologie sur les causes médicales de Décès), Le Kremlin Bicêtre, France. Université Paris Saclay, Le Kremlin Bicêtre, France.Inserm (Institut National de la Santé et de la Recherche Médicale) - CépiDc (Centre d'epidémiologie sur les causes médicales de Décès), Le Kremlin Bicêtre, France.Inserm (Institut National de la Santé et de la Recherche Médicale) - CépiDc (Centre d'epidémiologie sur les causes médicales de Décès), Le Kremlin Bicêtre, France.Inserm (Institut National de la Santé et de la Recherche Médicale) - CépiDc (Centre d'epidémiologie sur les causes médicales de Décès), Le Kremlin Bicêtre, France.Inserm (Institut National de la Santé et de la Recherche Médicale) - CépiDc (Centre d'epidémiologie sur les causes médicales de Décès), Le Kremlin Bicêtre, France.Inserm (Institut National de la Santé et de la Recherche Médicale) - CépiDc (Centre d'epidémiologie sur les causes médicales de Décès), Le Kremlin Bicêtre, France.Inserm (Institut National de la Santé et de la Recherche Médicale) - CépiDc (Centre d'epidémiologie sur les causes médicales de Décès), Le Kremlin Bicêtre, France.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

32343252

Citation

Falissard, Louis, et al. "A Deep Artificial Neural Network-Based Model for Prediction of Underlying Cause of Death From Death Certificates: Algorithm Development and Validation." JMIR Medical Informatics, vol. 8, no. 4, 2020, pp. e17125.
Falissard L, Morgand C, Roussel S, et al. A Deep Artificial Neural Network-Based Model for Prediction of Underlying Cause of Death From Death Certificates: Algorithm Development and Validation. JMIR Med Inform. 2020;8(4):e17125.
Falissard, L., Morgand, C., Roussel, S., Imbaud, C., Ghosn, W., Bounebache, K., & Rey, G. (2020). A Deep Artificial Neural Network-Based Model for Prediction of Underlying Cause of Death From Death Certificates: Algorithm Development and Validation. JMIR Medical Informatics, 8(4), e17125. https://doi.org/10.2196/17125
Falissard L, et al. A Deep Artificial Neural Network-Based Model for Prediction of Underlying Cause of Death From Death Certificates: Algorithm Development and Validation. JMIR Med Inform. 2020 Apr 28;8(4):e17125. PubMed PMID: 32343252.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - A Deep Artificial Neural Network-Based Model for Prediction of Underlying Cause of Death From Death Certificates: Algorithm Development and Validation. AU - Falissard,Louis, AU - Morgand,Claire, AU - Roussel,Sylvie, AU - Imbaud,Claire, AU - Ghosn,Walid, AU - Bounebache,Karim, AU - Rey,Grégoire, Y1 - 2020/04/28/ PY - 2019/11/19/received PY - 2020/02/04/accepted PY - 2020/01/31/revised PY - 2020/4/29/entrez PY - 2020/4/29/pubmed PY - 2020/4/29/medline KW - deep learning KW - machine learning KW - mortality statistics KW - underlying cause of death SP - e17125 EP - e17125 JF - JMIR medical informatics JO - JMIR Med Inform VL - 8 IS - 4 N2 - 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. SN - 2291-9694 UR - https://www.unboundmedicine.com/medline/citation/32343252/A_Deep_Artificial_Neural_Network-Based_Model_for_Prediction_of_Underlying_Cause_of_Death_From_Death_Certificates:_Algorithm_Development_and_Validation L2 - https://medinform.jmir.org/2020/4/e17125/ DB - PRIME DP - Unbound Medicine ER -
Try the Free App:
Prime PubMed app for iOS iPhone iPad
Prime PubMed app for Android
Prime PubMed is provided
free to individuals by:
Unbound Medicine.