Management of immune thrombocytopenia in adults: a population-based analysis of the French hospital discharge database from 2009 to 2012

2015 ◽  
Vol 170 (2) ◽  
pp. 218-222 ◽  
Author(s):  
Marc Michel ◽  
Florence Suzan ◽  
Daniel Adoue ◽  
Dominique Bordessoule ◽  
Jean-Pierre Marolleau ◽  
...  
Keyword(s):  
Hospital Discharge ◽  
Immune Thrombocytopenia ◽  
Population Based ◽  
Hospital Discharge Database ◽  
French Hospital ◽  
Discharge Database

scholarly journals Type 2 diabetes and postoperative pneumonia: An observational, population-based study using the Spanish Hospital Discharge Database, 2001-2015

PLoS ONE ◽  
2019 ◽  
Vol 14 (2) ◽  
pp. e0211230 ◽  
Author(s):  
Ana López-de-Andrés ◽  
Napoleon Perez-Farinos ◽  
Javier de Miguel-Díez ◽  
Valentín Hernández-Barrera ◽  
Isabel Jiménez-Trujillo ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Hospital Discharge ◽  
Population Based ◽  
Postoperative Pneumonia ◽  
Population Based Study ◽  
Hospital Discharge Database ◽  
Spanish Hospital ◽  
Discharge Database

scholarly journals Challenges of a French Hospital Discharge algorithm to detect non-accidental paediatric burns

2019 ◽  
Vol 29 (Supplement_4) ◽  
Author(s):  
C Hermetet ◽  
E Laurent ◽  
Y El Allali ◽  
C Gaborit ◽  
A-I Lecuyer ◽  
...  
Keyword(s):  
Child Maltreatment ◽  
Hospital Discharge ◽  
Healthcare Professionals ◽  
Qualitative Studies ◽  
Hospital Discharge Database ◽  
Paediatric Burns ◽  
Icd 10 ◽  
Judicial Authority ◽  
French Hospital ◽  
Discharge Database

Abstract Background Child maltreatment includes physical, psychological, sexual abuse and acts of neglect. Among the resulting non-accidental injuries, burns are responsible for an important morbi-mortality. The main objective was to build a detection algorithm of non-accidental paediatric burns (NAB), using ICD-10 codes in the hospital resumes from the French Hospital Discharge Database (HDD). Methods Children aged 0 to 16 years old hospitalised at the University Hospital of Tours from 2012 to 2017 with a coded burn were included. “Probable” or “possible” HDD cases of NAB were defined based on specific ICD-10 codes during the inclusion stay or the previous year. A chart review was performed on all the HDD cases and HDD non cases matched on sex and age with a 1:2 ratio. Performance parameters were estimated for three clinical definitions of suspected child maltreatment: excluding neglect, including neglect with restriction then broad definition. For clinical cases, report to the judicial authority (RJA) or worrying information (WI) was searched. Results Among the 253 included children, 83 “probable” cases and 153 non cases were analysed. Sensitivity varied from 48% (95%CI [36-60]) to 90% [55-100] when excluding neglect, specificity from 70% [63;77] to 68% [61;74]. The positive and negative likelihood ratios varied respectively from 1,6 [1,2;2,3] to 2,8 [2,1;3,7] and from 0,7 [0,6;0,9] to 0,1 [0,0;0,9]. The proportion of clinical cases with no RJA/WI without reason varied from 0 (when excluding neglect) to > 85% (with broadest definition); all corresponded to a possible isolated neglect. Conclusions The performances of the algorithm varied tremendously according to the clinical definition level of child maltreatment. Neglect is obviously difficult to clinically detect. Training for healthcare professionals and qualitative studies on obstacles to RJA/WI should be added to this work. Key messages The performances of an algorithm to detect non-accidental pediatric burns (maltreatment) using the French hospital discharge database dropped when including neglect, difficult to diagnose clinically. Training for healthcare professionals and qualitative studies on obstacles to the judicial authority (RJA) or worrying information (WI) should be added to this diagnostic study.

scholarly journals Prediction of In-Hospital Mortality from Administrative Data: A Sequential Pattern Mining Approach

2021 ◽  
Author(s):  
Jessica Pinaire ◽  
Etienne Chabert ◽  
Jérôme Azé ◽  
Sandra Bringay ◽  
Pascal Poncelet ◽  
...  
Keyword(s):  
Hospital Mortality ◽  
Hospital Discharge ◽  
Pattern Mining ◽  
Model Complexity ◽  
Sequential Patterns ◽  
Machine Model ◽  
Hospital Discharge Database ◽  
String Distance ◽  
French Hospital ◽  
Discharge Database

Study of trajectory of care is attractive for predicting medical outcome. Models based on machine learning (ML) techniques have proven their efficiency for sequence prediction modeling compared to other models. Introducing pattern mining techniques contributed to reduce model complexity. In this respect, we explored methods for medical events’ prediction based on the extraction of sets of relevant event sequences of a national hospital discharge database. It is illustrated to predict the risk of in-hospital mortality in acute coronary syndrome (ACS). We mined sequential patterns from the French Hospital Discharge Database. We compared several predictive models using a text string distance to measure the similarity between patients’ patterns of care. We computed combinations of similarity measurements and ML models commonly used. A Support Vector Machine model coupled with edit-based distance appeared as the most effective model. Indeed discrimination ranged from 0.71 to 0.99, together with a good overall accuracy. Thus, sequential patterns mining appear motivating for event prediction in medical settings as described here for ACS.

Sign in / Sign up

Export Citation Format

Share Document