[Artificial intelligence for medical information departments : construction and evaluation of a decision-making tool to identify and prioritize stays of which the PMSI coding could be optimized, and to ensure the revenues generated by activity-based pricing]. / L'intelligence artificielle au service des départements d'information médicale : construction et évaluation d'un outil d'aide à la décision pour cibler et prioriser les séjours à contrôler et fiabiliser les recettes hospitalières générées par la tarification à l'activité.

BACKGROUND: Medical Information Departments help to optimize the hospital revenues generated by activity-based pricing. A review of medical files, selected after the targeting of coding summaries, is organized. The aim is to make any corrections to the diagnoses or coded procedures with a potential impact on the pricing of the stay. Targeting is of major importance as a means of concentrating resources on the files for which coding can be effectively improved. The tools available for targeting can be optimized. We have developed a decision-making support tool to make targeting more efficient. The objective of our study was to evaluate the performance of this tool. METHODS: The tool combines an artificial intelligence module with a rule-based expert module. A predictive score is assigned to each coding summary that reflects the probability of a revalued stay. Evaluation of the performance of this tool was based on a sample of 400 stays of at least 3 nights of patients hospitalized at the Paris Saint-Joseph Hospital from 1st November to 31st December 2019. Each stay was reviewed by a coding expert, without knowledge of the score assigned and without help from expert queries. Two main assessment criteria were used: area under the ROC curve and positive predictive value (PPV). RESULTS: The area under the ROC curve was 0.70 (CI 95% [0.64-0.76]). With a revalued coding rate of 32%, PPV was 41% for scores above 5, 65% for scores above 8, 88% for scores above 9. CONCLUSION: The study made it possible to validate the performance of the tool. The implementation of new variables could further increase its performance. This is an area of development to be considered, particularly with in view of generalizing individual invoicing in hospitals.

Prevalence and management of antivitamin K overdose in a hospital setting.

INTRODUCTION: Vitamin K antagonist (VKA) related adverse events are the first cause for iatrogenic events in France, particularly due to the narrow therapeutic margin. The risk of bleeding increases significantly when the INR level is ≥5. The main objective of this study was to assess the prevalence of VKA overdose in a hospital setting (at D2 of hospital entry) and to evaluate physicians' adherence to clinical practice guidelines for the management of VKA overdose according to French National Authority for Health recommendations. METHODS: This single-center retrospective observational study consisted in querying the computerized database of a Parisian hospital on 21275INR determinations (3995 patients, 6813 hospital stays) performed between 2013 and 2018. RESULTS: An INR level ≥5 was noted during 350 (6%) of the hospital stays, in 331 patients (of whom 57% were women). The mean age of the patient population with an INR≥5 was 81.1 years. Infection, heart failure and renal failure were the most frequent acute medical conditions for hospital admission. Twenty-three patients (7%) had a bleeding complication, 11 of which were major bleeding complications. Older age was associated with the severity of bleeding complications. Fifteen in-hospital deaths (4%) were reported, not related to bleeding events. The management of VKA overdose did not comply with the recommendations in 43% of cases, in particular for the highest INRs (50% of noncompliance for an INR>6.4). Non-compliance with recommendations for VKA overdose was related to: the delay until the INR was checked (44% of cases); the indication for prescribing vitamin K (34% of cases); the dose or route of administration of vitamin K therapy (19% of cases); and the interruption or not of VKA therapy (12% of cases). CONCLUSION: The management of VKA overdose in a hospital setting remains non-compliant with the recommendations in almost half of the cases, mainly due to the delayed INR control and inappropriate management of vitamin K therapy. Computerized alert system would be helpful for personalized patient management and improved pharmacovigilance to prevent iatrogenic VKA events.