Search

Purpose: Mapping clinical observations and medical test results into the standardized vocabulary LOINC is a prerequisite for exchanging clinical data between health information systems and ensuring efficient interoperability., Methods: We present a comparison of three approaches for LOINC transcoding applied to French data collected from real-world settings. These approaches include both a state-of-the-art language model approach and a classifier chains approach., Results: Our study demonstrates that we successfully improve the performance of the baselines using the classifier chains approach and compete effectively with state-of-the-art language models., Conclusions: Our approach proves to be efficient, cost-effective despite reproducibility challenges and potential for future optimizations and dataset testing.

Today, social media is increasingly used by patients to openly discuss their health. Mining automatically such data is a challenging task because of the non-structured nature of the text and the use of many abbreviations and the slang terms. Our goal is to use Patient Authored Text to build a French Consumer Health Vocabulary on breast cancer field, by collecting various kinds of non-experts' expressions that are related to their diseases and then compare them to biomedical terms used by health care professionals. We combine several methods of the literature based on linguistic and statistical approaches to extract candidate terms used by non-experts and to link them to expert terms. We use messages extracted from the forum on ' cancerdusein.org ' and a vocabulary dedicated to breast cancer elaborated by the Institut National Du Cancer. We have built an efficient vocabulary composed of 192 validated relationships and formalized in Simple Knowledge Organization System ontology.

Background: Currently, cardiovascular disease (CVD) is widely acknowledged to be the first leading cause of fatality in the world with 31% of all deaths worldwide and is predicted to remain as such in 2030. Furthermore, CVD is also a major cause of morbidity in adults worldwide. Among these diseases, the coronary artery disease (CAD) is the most common cause, accounting for over 40% of CVD deaths. Despite a decline in mortality rates, the consequences of more effective preventive and management programs, the burden of CAD remains significant. Indeed, the rise in the prevalence of modifiable risk factors due to changes in lifestyle and health behaviors has further increased the burden of this epidemic. Our objective was to evaluate the hospital burden of CAD via MI trends and Percutaneous Coronary Intervention (PCI) in the French Prospective Payment System (PPS)., Methods: MI/PCI were identified in the national PPS database from 2009 to 2014 for patients aged 20 to 99, living in metropolitan France. We examined hospitalisation, readmission and mortality trends using standardised rates., Results: Over the six-year period, we identified 678,021 patients, representing 900,121 stays of which, 215,224 had a MI and a PCI. Admission trends increased by nearly 25%. Acute MI cases increased every year, with an alarming increase in women, and more specifically in young women. Men were 3 times more hospitalised than women, who were older. A North-South divide was noted. Twenty seven percent of patients experienced readmission within 1 month. Trajectories of care were significantly different by sex and age. Overall in-hospital death was 3.3%, decreasing by 15% during the period. The highest adjusted mortality rates were observed for inpatients aged <40 or >80., Conclusion: We outlined the public health burden of this condition and the importance of improving the trajectories of care as an aid for better care., Competing Interests: Pr. Cayla reports research Grants to the Institution or Consulting/Lecture Fees from, Amgen, Abbott, AstraZeneca, Bayer, Boehringer Ingelheim, Biotronik, Bristol-Myers Squibb, Daiichi-Sankyo, Eli-Lilly, Medtronic, MSD, Pfizer, Sanofi-Aventis. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

More and more health websites hire medical experts (physicians, medical students, experienced volunteers, etc.) and indicate explicitly their medical role in order to notify that they provide high-quality answers. However, medical experts may participate in forum discussions even when their role is not officially indicated. Detecting posts written by medical experts facilitates the quick access to posts that have more chances of being correct and informative. The main objective of this work is to learn classification models that can be used to detect posts written by medical experts in any health forum discussions. Two French health forums have been used to discover the best features and methods for this text categorization task. The obtained results confirm that models learned on appropriate websites may be used efficiently on other websites (more than 98% of F1-measure has been obtained using a Random Forest classifier). A study of misclassified posts highlights the participation of medical experts in forum discussions even if their role is not explicitly indicated.

Online health forums are increasingly used by patients to get information and help related to their health. However, information reliability in these forums is unfortunately not always guaranteed. Obviously, consequences of self-diagnosis may be severe on the patient's health if measures are taken without consulting a doctor. Many works on trust issues related to social media have been proposed, but most of them mainly focus only on the structure part of the social network (number of posts, number of likes, etc.). In the case of online health forums, a lot of trust and distrust is expressed inside the posted messages and cannot be inferred by only considering the structure. In this study, we rather suggest inferring the user's trustworthiness from the replies he receives in the forum. The proposed method is divided into three main steps: First, the recipient(s) of each post must be identified. Next, the trust or distrust expressed in these posts is evaluated. Finally, the user's reputation is computed by aggregating all the posts he received. Conducted experiments using a manually annotated corpus are encouraging.

Although Health Professionals HPs are aware of the interest of the Electronic Medical Record EMR, most of them still use a Paper Medical Record PMR. In the French DocPatient project, we work on documentary functionalities to improve the use of the EMR. We made the assumption that a best integration of the way they use these paper medical documents in the EMR design will improve its utility, its use and its acceptance. We propose in this paper to add a functionality of annotations in the EMR to reinforce collaboration, coordination and awareness.

Introduction: To build relevant tools for Health Care Professionals, we must study and understand their practices. This paper discusses the way they leave traces in the Patient Record to help asynchronous collaboration, elaborating new documents or adding annotations., Methods: We compared the results of two studies about the various writing strategies used by the Health Care Professionals to capture knowledge in the Patient Records. The first study deals with the information written by the nurses in a textbook during homecare situations. The second one deals with the annotations left by all the practitioners to complete the documents of the patient record in a hospital ward., Results: We have found some invariants in these two situations. An interpretation model based on four levels: Communication Context, Communication Object, Value of Communication and Value of Cooperation, is proposed in order to describe and to index the characteristics of the Communication Notes.