Combining deep neural networks, a rule-based expert system and targeted manual coding for ICD-10 coding causes of death of French death certificates from 2018 to 2019.

OBJECTIVE: For ICD-10 coding causes of death in France in 2018 and 2019, predictions by deep neural networks (DNNs) are employed in addition to fully automatic batch coding by a rule-based expert system and to interactive coding by the coding team focused on certificates with a special public health interest and those for which DNNs have a low confidence index. METHODS: Supervised seq-to-seq DNNs are trained on previously coded data to ICD-10 code multiple causes and underlying causes of death. The DNNs are then used to target death certificates to be sent to the coding team and to predict multiple causes and underlying causes of death for part of the certificates. Hence, the coding campaign for 2018 and 2019 combines three modes of coding and a loop of interaction between the three. FINDINGS: In this campaign, 62% of the certificates are automatically batch coded by the expert system, 3% by the coding team, and the remainder by DNNs. Compared to a traditional campaign that would have relied on automatic batch coding and manual coding, the present campaign reaches an accuracy of 93.4% for ICD-10 coding of the underlying cause (95.6% at the European shortlist level). Some limitations (risks of under- or overestimation) appear for certain ICD categories, with the advantage of being quantifiable. CONCLUSION: The combination of the three coding methods illustrates how artificial intelligence, automated and human codings are mutually enriching. Quantified limitations on some chapters of ICD codes encourage an increase in the volume of certificates sent for manual coding from 2021 onward.

GP responses to price regulation: evidence from a French nationwide reform.

This paper uses a French reform to evaluate the impacts of overbilling restrictions on general practitioner (GP) care provision, fees and incomes. Since 1990, this reform has introduced conditions self-employed GPs must fulfil to be permitted to bill freely. We exploit 2005 and 2008 public health insurance administrative data on GP activity and fees. We use fuzzy regression discontinuity techniques to estimate local causal impacts for GPs who established practices in 1990 and who were constrained by the new regulation to charge regulated prices (compliers). We find that those GPs practices to income effects. In the regulated fee regime, GPs face prices lower by 42% and provide 50% more care than they would do in the unregulated fee regime. Male care provision increasing reaction is larger than the female one, which results in a higher male labour income in the regulated fee regime than with unregulated fees, whereas it is the opposite for women. With regulated fees, GPs limit side-salaried activities, use more lump-sum payment schemes and occupy more often gatekeeper positions.