Search

Introduction Cyclosporine and methotrexate are the two preferred first-line immunosuppressive treatments in atopic dermatitis. The aim of this study was to compare the treatment profiles of methotrexate and cyclosporine in daily practice as the first-line immunosuppressive treatment in atopic dermatitis, using two survival analyses, 'drug survival' (time on the drug) and 'postdrug survival' (time between two drugs). Methods Retrospective study including patients with moderate-to-severe atopic dermatitis treated with methotrexate or cyclosporine as the first-line immunosuppressive treatment. The reasons for discontinuation of treatment were collected as follows: controlled disease, treatment failure, side event pregnancy and non-compliance. 'Drug survival' and 'postdrug survival' analyses were performed using the Kaplan-Meier method and predictive factors were analysed using uni- and multivariate Cox regression analyses. Results Fifty-six patients, among whom 25 patients treated with cyclosporine and 31 with methotrexate (median age: 34 ± 15 years), were included between 2007 and 2016. Reasons for discontinuation were not significantly different between 'controlled disease' and other reasons (P = 0.11). The median 'drug survival' was significantly longer for methotrexate (23 months) than for cyclosporine (8 months) (P < 0.0001). Six months from baseline, 93% of patients treated with methotrexate were still being treated vs 63% among patients treated with cyclosporine. The median of 'postdrug survival' was significantly longer for methotrexate (12 months) than for cyclosporine (2 months). Only treatment with CYC was a predictive factor for decreased 'drug survival' and 'postdrug survival'. Conclusion This is the first direct comparison between methotrexate and cyclosporine as first-line immunosuppressive treatments for moderate-to-severe atopic dermatitis in daily practice. We evidenced two different treatment profiles: the duration of methotrexate administration is longer than that of cyclosporine. 'Postdrug survival' could be a new tool to assess the maintenance of effect of a drug after withdrawal in atopic dermatitis, and more broadly in chronic skin disease. [ABSTRACT FROM AUTHOR]

Objectives: Oocyte donation pregnancies are more frequently complicated by preeclampsia (PE), which cause significant fetal-maternal morbidity and mortality. Our objective was to determine risk factors for PE in oocyte recipients (OR). Our secondary objective was to describe the course of pregnancy and the neonatal outcome in this group. Methods: This was a historical-prospective study. One hundred and fifty OR who gave birth to children at over 22 weeks of amenorrhea between January 2010 and June 2018 were included in the study. Results: Risk factors for PE in OR found in univariate analysis were as follows: primiparity, primipaternity, body mass index (BMI), and anti-Müllerian hormone (AMH) of the OR and age and AMH of the oocyte donors (OD). In multivariate analysis, the BMI of the OR (odds ratio [OR]: 1.2, 95% confidence interval [CI]: [1.1–1.4], P = 0.0474) and the AMH of the OD (OR: 1.2, 95% CI: [1.2–1.4], P = 0.0481) were found to be statistically significant risk factors for PE. In addition, we observed an increase in the rate of prematurity in the OR that were not associated with fetal growth retardation, despite the occurrence of PE. Conclusion: In OR, the allogeneic nature of pregnancy induces an increased risk of PE, the pathophysiology of which seems different from that in other methods of conception. Thus, risk factors for PE should be reconsidered to take into account the impact of certain characteristics of OD such as age and AMH.

Objectives: SLE is a systemic autoimmune disease characterized by heterogeneous manifestations and severity, with frequent lung involvement. Among pulmonary function tests, the measure of the diffusing capacity of the lungs for carbon monoxide (DLCO) is a noninvasive and sensitive tool assessing pulmonary microcirculation. Asymptomatic and isolated DLCO alteration has frequently been reported in SLE, but its clinical relevance has not been established., Methods: This retrospective study focused on 232 SLE patients fulfilling the 2019 EULAR/ACR classification criteria for SLE. Data were collected from the patient's medical record, including demographic, clinical and immunological characteristics, while DLCO was measured when performing pulmonary function tests as part of routine patient follow-up., Results: At the end of follow-up, DLCO alteration (<70% of predicted value) was measured at least once in 154 patients (66.4%), and was associated with a history of smoking as well as interstitial lung disease, but was also associated with renal and neurological involvement. History of smoking, detection of anti-nucleosome autoantibodies and clinical lymphadenopathy at diagnosis were independent predictors of DLCO alteration, while early cutaneous involvement with photosensitivity was a protective factor. DLCO alteration, at baseline or any time during follow-up, was predictive of admission in intensive care unit and/or of all-cause death, both mainly due to severe disease flares and premature cardiovascular complications., Conclusion: This study suggests a link between DLCO alteration and disease damage, potentially related to SLE vasculopathy, and a prognostic value of DLCO on death or intensive care unit admission in SLE., (© The Author(s) 2023. Published by Oxford University Press on behalf of the British Society for Rheumatology. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Background: Antibiotics play a central role in infection management. In older patients, antibiotics are frequently administered subcutaneously. Ceftriaxone pharmacokinetics after subcutaneous administration is well documented, but little data are available on its safety., Methods: We compared the occurrence of adverse events associated with ceftriaxone administered subcutaneously versus intravenously in ≥75-year-old patients. We used data from a single-center, retrospective, clinical-administrative database to compare the occurrence of adverse events at day 14 and outcome at day 21 in older patients who received ceftriaxone via the subcutaneous route or the intravenous route at Rennes University Hospital, France, from May 2020 to February 2023., Results: The subcutaneous and intravenous groups included 402 and 3387 patients, respectively. Patients in the subcutaneous group were older and more likely to receive palliative care. At least one adverse event was reported for 18% and 40% of patients in the subcutaneous and intravenous group, respectively (RR = 2.21). Mortality at day 21 was higher in the subcutaneous route group, which could be linked to between-group differences in clinical and demographic features., Conclusions: In ≥75-year-old patients, ceftriaxone administered by the subcutaneous route is associated with less-adverse events than by the intravenous route. The subcutaneous route, which is easier to use, has a place in infection management in geriatric settings., (© 2024 The American Geriatrics Society.)

Background: Electronic health records (EHRs) contain valuable information for clinical research; however, the sensitive nature of healthcare data presents security and confidentiality challenges. De-identification is therefore essential to protect personal data in EHRs and comply with government regulations. Named entity recognition (NER) methods have been proposed to remove personal identifiers, with deep learning-based models achieving better performance. However, manual annotation of training data is time-consuming and expensive. The aim of this study was to develop an automatic de-identification pipeline for all kinds of clinical documents based on a distant supervised method to significantly reduce the cost of manual annotations and to facilitate the transfer of the de-identification pipeline to other clinical centers., Methods: We proposed an automated annotation process for French clinical de-identification, exploiting data from the eHOP clinical data warehouse (CDW) of the CHU de Rennes and national knowledge bases, as well as other features. In addition, this paper proposes an assisted data annotation solution using the Prodigy annotation tool. This approach aims to reduce the cost required to create a reference corpus for the evaluation of state-of-the-art NER models. Finally, we evaluated and compared the effectiveness of different NER methods., Results: A French de-identification dataset was developed in this work, based on EHRs provided by the eHOP CDW at Rennes University Hospital, France. The dataset was rich in terms of personal information, and the distribution of entities was quite similar in the training and test datasets. We evaluated a Bi-LSTM + CRF sequence labeling architecture, combined with Flair + FastText word embeddings, on a test set of manually annotated clinical reports. The model outperformed the other tested models with a significant F1 score of 96,96%, demonstrating the effectiveness of our automatic approach for deidentifying sensitive information., Conclusions: This study provides an automatic de-identification pipeline for clinical notes, which can facilitate the reuse of EHRs for secondary purposes such as clinical research. Our study highlights the importance of using advanced NLP techniques for effective de-identification, as well as the need for innovative solutions such as distant supervision to overcome the challenge of limited annotated data in the medical domain., (© 2024. The Author(s).)

Aims: Patients presenting symptoms of heart failure with preserved ejection fraction (HFpEF) are not a homogenous population. Different phenotypes can differ in prognosis and optimal management strategies. We sought to identify phenotypes of HFpEF by using the medical information database from a large university hospital centre using machine learning., Methods and Results: We explored the use of clinical variables from electronic health records in addition to echocardiography to identify different phenotypes of patients with HFpEF. The proposed methodology identifies four phenotypic clusters based on both clinical and echocardiographic characteristics, which have differing prognoses (death and cardiovascular hospitalization)., Conclusion: This work demonstrated that artificial intelligence-derived phenotypes could be used as a tool for physicians to assess risk and to target therapies that may improve outcomes., Competing Interests: Conflict of interest: CHU Rennes and Erwan DONAL are receiving research facilities from Abbott structural and General Electric Healthcare., (© The Author(s) 2023. Published by Oxford University Press on behalf of the European Society of Cardiology.)

Background: Amoxicillin (AMX)-induced neurotoxicity is well described and may be associated with AMX overexposure. No neurotoxic concentration threshold has been determined thus far. A better knowledge of maximum tolerable AMX concentrations is of importance to improve the safety of high doses of AMX., Methods: We conducted a retrospective study using the local hospital data warehouse EhOP ® to generate a specific query related to AMX neurotoxicity symptomatology. All patient medical reports containing a mention of neurotoxicity clinical symptoms coupled with AMX plasma concentration measurements were explored. Patients were classified into two groups according to the imputability of AMX in the onset of their neurotoxicity, on the basis of chronological and semiological criteria. A receiver-operating characteristic curve was performed to identify an AMX neurotoxic steady-state concentration (Css) threshold., Results: The query identified 101 patients among 2054 patients benefiting from AMX TDM. Patients received a median daily dose of 9 g AMX, with a median creatinine clearance of 51 mL/min. A total of 17 of the 101 patients exhibited neurotoxicity attributed to AMX. The mean Css was higher for patients with neurotoxicity attributed to AMX (118 ± 62 mg/L) than those without 74 ± 48 mg/L ( p = 0.002). A threshold AMX concentration of 109.7 mg/L predicted the occurrence of neurotoxicity., Conclusions: This study identified, for the first time, an AMX Css threshold of 109.7 mg/L associated with an excess risk of neurotoxicity. This approach needs to be confirmed by a prospective study with systematic neurological evaluation and TDM.

Background: Disease surveillance systems capable of producing accurate real-time and short-term forecasts can help public health officials design timely public health interventions to mitigate the effects of disease outbreaks in affected populations. In France, existing clinic-based disease surveillance systems produce gastroenteritis activity information that lags real time by 1 to 3 weeks. This temporal data gap prevents public health officials from having a timely epidemiological characterization of this disease at any point in time and thus leads to the design of interventions that do not take into consideration the most recent changes in dynamics., Objective: The goal of this study was to evaluate the feasibility of using internet search query trends and electronic health records to predict acute gastroenteritis (AG) incidence rates in near real time, at the national and regional scales, and for long-term forecasts (up to 10 weeks)., Methods: We present 2 different approaches (linear and nonlinear) that produce real-time estimates, short-term forecasts, and long-term forecasts of AG activity at 2 different spatial scales in France (national and regional). Both approaches leverage disparate data sources that include disease-related internet search activity, electronic health record data, and historical disease activity., Results: Our results suggest that all data sources contribute to improving gastroenteritis surveillance for long-term forecasts with the prominent predictive power of historical data owing to the strong seasonal dynamics of this disease., Conclusions: The methods we developed could help reduce the impact of the AG peak by making it possible to anticipate increased activity by up to 10 weeks., (©Canelle Poirier, Guillaume Bouzillé, Valérie Bertaud, Marc Cuggia, Mauricio Santillana, Audrey Lavenu. Originally published in JMIR Public Health and Surveillance (https://publichealth.jmir.org), 31.01.2023.)

Background: Traditionally, dengue prevention and control rely on vector control programs and reporting of symptomatic cases to a central health agency. However, case reporting is often delayed, and the true burden of dengue disease is often underestimated. Moreover, some countries do not have routine control measures for vector control. Therefore, researchers are constantly assessing novel data sources to improve traditional surveillance systems. These studies are mostly carried out in big territories and rarely in smaller endemic regions, such as Martinique and the Lesser Antilles., Objective: The aim of this study was to determine whether heterogeneous real-world data sources could help reduce reporting delays and improve dengue monitoring in Martinique island, a small endemic region., Methods: Heterogenous data sources (hospitalization data, entomological data, and Google Trends) and dengue surveillance reports for the last 14 years (January 2007 to February 2021) were analyzed to identify associations with dengue outbreaks and their time lags., Results: The dengue hospitalization rate was the variable most strongly correlated with the increase in dengue positivity rate by real-time reverse transcription polymerase chain reaction (Pearson correlation coefficient=0.70) with a time lag of -3 weeks. Weekly entomological interventions were also correlated with the increase in dengue positivity rate by real-time reverse transcription polymerase chain reaction (Pearson correlation coefficient=0.59) with a time lag of -2 weeks. The most correlated query from Google Trends was the "Dengue" topic restricted to the Martinique region (Pearson correlation coefficient=0.637) with a time lag of -3 weeks., Conclusions: Real-word data are valuable data sources for dengue surveillance in smaller territories. Many of these sources precede the increase in dengue cases by several weeks, and therefore can help to improve the ability of traditional surveillance systems to provide an early response in dengue outbreaks. All these sources should be better integrated to improve the early response to dengue outbreaks and vector-borne diseases in smaller endemic territories., (©Emmanuelle Sylvestre, Elsa Cécilia-Joseph, Guillaume Bouzillé, Fatiha Najioullah, Manuel Etienne, Fabrice Malouines, Jacques Rosine, Sandrine Julié, André Cabié, Marc Cuggia. Originally published in JMIR Public Health and Surveillance (https://publichealth.jmir.org), 22.12.2022.)

Objective: To describe the management of pathogenic CDH1 variant carriers (pCDH1vc) within the FREGAT (FRench Eso-GAsTric tumor) network. Primary objective focused on clinical outcomes and pathological findings, Secondary objective was to identify risk factor predicting postoperative morbidity (POM)., Background: Prophylactic total gastrectomy (PTG) remains the recommended option for gastric cancer risk management in pCDH1vc with, however, endoscopic surveillance as an alternative., Methods: A retrospective observational multicenter study was carried out between 2003 and 2021. Data were reported as median (interquartile range) or as counts (proportion). Usual tests were used for univariate analysis. Risk factors of overall and severe POM (ie, Clavien-Dindo grade 3 or more) were identified with a binary logistic regression., Results: A total of 99 patients including 14 index cases were reported from 11 centers. Median survival among index cases was 12.0 (7.6-16.4) months with most of them having peritoneal carcinomatosis at diagnosis (71.4%). Among the remaining 85 patients, 77 underwent a PTG [median age=34.6 (23.7-46.2), American Society of Anesthesiologists score 1: 75%] mostly via a minimally invasive approach (51.9%). POM rate was 37.7% including 20.8% of severe POM, with age 40 years and above and low-volume centers as predictors ( P =0.030 and 0.038). After PTG, the cancer rate on specimen was 54.5% (n=42, all pT1a) of which 59.5% had no cancer detected on preoperative endoscopy (n=25)., Conclusions: Among pCDH1vc, index cases carry a dismal prognosis. The risk of cancer among patients undergoing PTG remained high and unpredictable and has to be balanced with the morbidity and functional consequence of PTG., Competing Interests: The authors report no conflicts of interest., (Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.)

Background: Often missing from or uncertain in a biomedical data warehouse (BDW), vital status after discharge is central to the value of a BDW in medical research. The French National Mortality Database (FNMD) offers open-source nominative records of every death. Matching large-scale BDWs records with the FNMD combines multiple challenges: absence of unique common identifiers between the 2 databases, names changing over life, clerical errors, and the exponential growth of the number of comparisons to compute., Objective: We aimed to develop a new algorithm for matching BDW records to the FNMD and evaluated its performance., Methods: We developed a deterministic algorithm based on advanced data cleaning and knowledge of the naming system and the Damerau-Levenshtein distance (DLD). The algorithm's performance was independently assessed using BDW data of 3 university hospitals: Lille, Nantes, and Rennes. Specificity was evaluated with living patients on January 1, 2016 (ie, patients with at least 1 hospital encounter before and after this date). Sensitivity was evaluated with patients recorded as deceased between January 1, 2001, and December 31, 2020. The DLD-based algorithm was compared to a direct matching algorithm with minimal data cleaning as a reference., Results: All centers combined, sensitivity was 11% higher for the DLD-based algorithm (93.3%, 95% CI 92.8-93.9) than for the direct algorithm (82.7%, 95% CI 81.8-83.6; P<.001). Sensitivity was superior for men at 2 centers (Nantes: 87%, 95% CI 85.1-89 vs 83.6%, 95% CI 81.4-85.8; P=.006; Rennes: 98.6%, 95% CI 98.1-99.2 vs 96%, 95% CI 94.9-97.1; P<.001) and for patients born in France at all centers (Nantes: 85.8%, 95% CI 84.3-87.3 vs 74.9%, 95% CI 72.8-77.0; P<.001). The DLD-based algorithm revealed significant differences in sensitivity among centers (Nantes, 85.3% vs Lille and Rennes, 97.3%, P<.001). Specificity was >98% in all subgroups. Our algorithm matched tens of millions of death records from BDWs, with parallel computing capabilities and low RAM requirements. We used the Inseehop open-source R script for this measurement., Conclusions: Overall, sensitivity/recall was 11% higher using the DLD-based algorithm than that using the direct algorithm. This shows the importance of advanced data cleaning and knowledge of a naming system through DLD use. Statistically significant differences in sensitivity between groups could be found and must be considered when performing an analysis to avoid differential biases. Our algorithm, originally conceived for linking a BDW with the FNMD, can be used to match any large-scale databases. While matching operations using names are considered sensitive computational operations, the Inseehop package released here is easy to run on premises, thereby facilitating compliance with cybersecurity local framework. The use of an advanced deterministic matching algorithm such as the DLD-based algorithm is an insightful example of combining open-source external data to improve the usage value of BDWs., (©Vianney Guardiolle, Adrien Bazoge, Emmanuel Morin, Béatrice Daille, Delphine Toublant, Guillaume Bouzillé, Youenn Merel, Morgane Pierre-Jean, Alexandre Filiot, Marc Cuggia, Matthieu Wargny, Antoine Lamer, Pierre-Antoine Gourraud. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 01.11.2022.)

Background: Despite the many opportunities data reuse offers, its implementation presents many difficulties, and raw data cannot be reused directly. Information is not always directly available in the source database and needs to be computed afterwards with raw data for defining an algorithm., Objective: The main purpose of this article is to present a standardized description of the steps and transformations required during the feature extraction process when conducting retrospective observational studies. A secondary objective is to identify how the features could be stored in the schema of a data warehouse., Methods: This study involved the following 3 main steps: (1) the collection of relevant study cases related to feature extraction and based on the automatic and secondary use of data; (2) the standardized description of raw data, steps, and transformations, which were common to the study cases; and (3) the identification of an appropriate table to store the features in the Observation Medical Outcomes Partnership (OMOP) common data model (CDM)., Results: We interviewed 10 researchers from 3 French university hospitals and a national institution, who were involved in 8 retrospective and observational studies. Based on these studies, 2 states (track and feature) and 2 transformations (track definition and track aggregation) emerged. "Track" is a time-dependent signal or period of interest, defined by a statistical unit, a value, and 2 milestones (a start event and an end event). "Feature" is time-independent high-level information with dimensionality identical to the statistical unit of the study, defined by a label and a value. The time dimension has become implicit in the value or name of the variable. We propose the 2 tables "TRACK" and "FEATURE" to store variables obtained in feature extraction and extend the OMOP CDM., Conclusions: We propose a standardized description of the feature extraction process. The process combined the 2 steps of track definition and track aggregation. By dividing the feature extraction into these 2 steps, difficulty was managed during track definition. The standardization of tracks requires great expertise with regard to the data, but allows the application of an infinite number of complex transformations. On the contrary, track aggregation is a very simple operation with a finite number of possibilities. A complete description of these steps could enhance the reproducibility of retrospective studies., (©Antoine Lamer, Mathilde Fruchart, Nicolas Paris, Benjamin Popoff, Anaïs Payen, Thibaut Balcaen, William Gacquer, Guillaume Bouzillé, Marc Cuggia, Matthieu Doutreligne, Emmanuel Chazard. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 17.10.2022.)

Introduction: While pirfenidone and nintedanib have greatly influenced the treatment of idiopathic pulmonary fibrosis (IPF), both drugs have significant early adverse drug reactions (ADRs) and almost nothing is known of their rare and delayed ADRs. We collected and analyzed pirfenidone- or nintedanib-related ADRs identified in a French rare lung disease center, recorded their profiles and identified potential safety signals., Methods: We analyzed the medical records of IPF patients treated with pirfenidone or nintedanib between January 2011 and January 2020 at the Rennes University Hospital to estimate the incidence of serious and non-serious ADRs cases due to each drug and the incidence of ADRs involving the cardiovascular, hepatobiliary, gastro-intestinal, dermatological, and metabolic/nutritional systems., Results: The 176 patients included 115 (65%) initially treated with pirfenidone and 61 (35%) given nintedanib. ADRs occurred in 78.3% of those given pirfenidone and in 70.5% of those given nintedanib. The incidence of first serious ADRs cases was about 33 per 100 person-years (100 PY) for both drugs; first non-serious pirfenidone ADRs cases were 102 per 100 PY and 130 per 100 PY for nintedanib. The incidence involving each organ system were quite similar, except for the gastro-intestinal and skin disorders. Cardiovascular disorders occurred in about 10 cases per 100 PY in both pirfenidone and nintedanib patients., Discussion: Most ADRs were consistent with the expected antifibrotic drug safety profiles. As arterial and venous thromboembolic events are rare, it is important to assess the risk associated with using antifibrotics by a dedicated pharmacoepidemiological study., Competing Interests: Declaration of competing interest DF, GB, EP, MNO, LMS: none. SJ has received fees, funding or reimbursement for national and international conferences, boards, expert or opinion groups, research projects over the past 5 years from Actelion, AIRB, Astra Zeneca, Bellorophon Therapeutics, Biogen, BMS, Boehringer Ingelheim, Chiesi, Fibrogen, Galecto Biotech, Genzyme, Gilead, GSK, LVL, Mundipharma, Novartis, Olam Pharm, Pfizer, Pliant Therapeutics, Roche, Sanofi, Savara-Serendex., (Copyright © 2022 Elsevier Ltd. All rights reserved.)

Direct oral anticoagulants and vitamin K antagonists are considered as potentially inappropriate medications (PIM) in several situations according to Beers Criteria. Drug-drug interactions (DDI) occurring specifically with these oral anticoagulants considered PIM (PIM-DDI) is an issue since it could enhance their inappropriate character and lead to adverse drug events, such as bleeding events. The aim of this study was (1) to describe the prevalence of oral anticoagulants as PIM, DDI and PIM-DDI in elderly patients in primary care and during hospitalization and (2) to evaluate their potential impact on the clinical outcomes by predicting hospitalization for bleeding events using machine learning methods. This retrospective study based on the linkage between a primary care database and a hospital data warehouse allowed us to display the oral anticoagulant treatment pathway. The prevalence of PIM was similar between primary care and hospital setting (22.9% and 20.9%), whereas the prevalence of DDI and PIM-DDI were slightly higher during hospitalization (47.2% vs. 58.9% and 19.5% vs. 23.5%). Concerning mechanisms, combined with CYP3A4-P-gp interactions as PIM-DDI, were among the most prevalent in patients with bleeding events. Although PIM, DDI and PIM-DDI did not appeared as major predictors of bleeding events, they should be considered since they are the only factors that can be optimized by pharmacist and clinicians.

The ReMIAMes project proposes a methodological framework to provide a reliable and reproducible measurement of the frequency of drug-drug interactions (DDI) when performed on real-world data. This framework relies on (i) a fine-grained and contextualized definition of DDIs, (ii) a shared minimum information model to select the appropriate data for the correct interpretation of potential DDIs, (iii) an ontology-based inference module able to handle missing data to classify prescription lines with potential DDIs, (iv) a report generator giving the value of the measurement and explanations when potential false positive are detected due to a lack of available data. All the tools developed are intended to be publicly shared under open license.

Patients suffering from heart failure (HF) symptoms and a normal left ventricular ejection fraction (LVEF 50%) present very different clinical phenotypes that could influence their survival. This study aims to identify phenotypes of this type of HF by using the medical information database from Rennes University Hospital Center. We present a preliminary work, where we explore the use of clinical variables from health electronic records (HER) in addition to echocardiography to identify several phenotypes of patients suffering from heart failure with preserved ejection fraction. The proposed methodology identifies 4 clusters with various characteristics (both clinical and echocardiographic) that are linked to survival (death, surgery, hospitalization). In the future, this work could be deployed as a tool for the physician to assess risks and contribute to support better care for patients.

Introduction: Out-of-hospital cardiac arrest (OHCA) is a major public health issue. The prognosis is closely related to the time from collapse to return of spontaneous circulation. Resuscitation efforts are frequently initiated at the request of emergency call center professionals who are specifically trained to identify critical conditions over the phone. However, 25% of OHCAs are not recognized during the first call. Therefore, it would be interesting to develop automated computer systems to recognize OHCA on the phone. The aim of this study was to build and evaluate machine learning models for OHCA recognition based on the phonetic characteristics of the caller's voice., Methods: All patients for whom a call was done to the emergency call center of Rennes, France, between 01/01/2017 and 01/01/2019 were eligible. The predicted variable was OHCA presence. Predicting variables were collected by computer-automatized phonetic analysis of the call. They were based on the following voice parameters: fundamental frequency, formants, intensity, jitter, shimmer, harmonic to noise ratio, number of voice breaks, and number of periods. Three models were generated using binary logistic regression, random forest, and neural network. The area under the curve (AUC) was the primary outcome used to evaluate each model performance., Results: 820 patients were included in the study. The best model to predict OHCA was random forest (AUC=74.9, 95% CI=67.4-82.4)., Conclusion: Machine learning models based on the acoustic characteristics of the caller's voice can recognize OHCA. The integration of the acoustic parameters identified in this study will help to design decision-making support systems to improve OHCA detection over the phone.

New use cases and the need for quality control and imaging data sharing in health studies require the capacity to align them to reference terminologies. We are interested in mapping the local terminology used at our center to describe imaging procedures to reference terminologies for imaging procedures (RadLex Playbook and LOINC/RSNA Radiology Playbook). We performed a manual mapping of the 200 most frequent imaging report titles at our center (i.e. 73.2% of all imaging exams). The mapping method was based only on information explicitly stated in the titles. The results showed 57.5% and 68.8% of exact mapping to the RadLex and LOINC/RSNA Radiology Playbooks, respectively. We identified the reasons for the mapping failure and analyzed the issues encountered.

Objective: The main objective was to assess the feasibility of the trigger tool method for the retrospective detection of adverse drug reactions (ADRs) in the Rennes University Hospital. The secondary objective was to describe the performance of the method in terms of positive predictive values (PPVs) and severity or preventability of ADRs., Methods: Using the Rennes University Hospital clinical data warehouse, pharmacovigilance experts performed a retrospective review of a random sample of 30 inpatient hospital medical records per month using the triggers "fall" and "delirium" to identify related ADRs among patients 65 years and older in 2018 in the geriatrics department. Using the Z test, we compared the proportion of medical records with a positive (identified) trigger related to an ADR, which were reviewed within 20 minutes using the reference of 50% reviewed within 20 minutes., Results: Among the 355 medical records reviewed, 222 had at least 1 trigger and 98 at least 1 related ADR. Among the 222 positive trigger medical records, 99.6% were reviewed in under 20 minutes (P < 0.001). The pharmacovigilance assessment took 3 months. The PPVs reached 53.9% (46.0%-61.7%) for falls and 21.0% (14.3%-27.5%) for delirium. Among the ADRs, 80% were serious and 53% were preventable., Conclusions: Given the low PPV of the triggers used and the considerable need for technical and human resources, the trigger tool method cannot be used as a routine tool at the pharmacovigilance center. However, it could be implemented occasionally for specific purposes such as monitoring the impact of risk minimization measures to prevent ADRs., Competing Interests: The authors disclose no conflict of interest., (Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.)

Background: Traditionally, dengue surveillance is based on case reporting to a central health agency. However, the delay between a case and its notification can limit the system responsiveness. Machine learning methods have been developed to reduce the reporting delays and to predict outbreaks, based on non-traditional and non-clinical data sources. The aim of this systematic review was to identify studies that used real-world data, Big Data and/or machine learning methods to monitor and predict dengue-related outcomes., Methodology/principal Findings: We performed a search in PubMed, Scopus, Web of Science and grey literature between January 1, 2000 and August 31, 2020. The review (ID: CRD42020172472) focused on data-driven studies. Reviews, randomized control trials and descriptive studies were not included. Among the 119 studies included, 67% were published between 2016 and 2020, and 39% used at least one novel data stream. The aim of the included studies was to predict a dengue-related outcome (55%), assess the validity of data sources for dengue surveillance (23%), or both (22%). Most studies (60%) used a machine learning approach. Studies on dengue prediction compared different prediction models, or identified significant predictors among several covariates in a model. The most significant predictors were rainfall (43%), temperature (41%), and humidity (25%). The two models with the highest performances were Neural Networks and Decision Trees (52%), followed by Support Vector Machine (17%). We cannot rule out a selection bias in our study because of our two main limitations: we did not include preprints and could not obtain the opinion of other international experts., Conclusions/significance: Combining real-world data and Big Data with machine learning methods is a promising approach to improve dengue prediction and monitoring. Future studies should focus on how to better integrate all available data sources and methods to improve the response and dengue management by stakeholders., Competing Interests: The authors have declared that no competing interests exist.

Background: Linking different sources of medical data is a promising approach to analyze care trajectories. The aim of the INSHARE (Integrating and Sharing Health Big Data for Research) project was to provide the blueprint for a technological platform that facilitates integration, sharing, and reuse of data from 2 sources: the clinical data warehouse (CDW) of the Rennes academic hospital, called eHOP (entrepôt Hôpital), and a data set extracted from the French national claim data warehouse (Système National des Données de Santé [SNDS])., Objective: This study aims to demonstrate how the INSHARE platform can support big data analytic tasks in the health field using a pharmacovigilance use case based on statin consumption and statin-drug interactions., Methods: A Spark distributed cluster-computing framework was used for the record linkage procedure and all analyses. A semideterministic record linkage method based on the common variables between the chosen data sources was developed to identify all patients discharged after at least one hospital stay at the Rennes academic hospital between 2015 and 2017. The use-case study focused on a cohort of patients treated with statins prescribed by their general practitioner or during their hospital stay., Results: The whole process (record linkage procedure and use-case analyses) required 88 minutes. Of the 161,532 and 164,316 patients from the SNDS and eHOP CDW data sets, respectively, 159,495 patients were successfully linked (98.74% and 97.07% of patients from SNDS and eHOP CDW, respectively). Of the 16,806 patients with at least one statin delivery, 8293 patients started the consumption before and continued during the hospital stay, 6382 patients stopped statin consumption at hospital admission, and 2131 patients initiated statins in hospital. Statin-drug interactions occurred more frequently during hospitalization than in the community (3800/10,424, 36.45% and 3253/14,675, 22.17%, respectively; P<.001). Only 121 patients had the most severe level of statin-drug interaction. Hospital stay burden (length of stay and in-hospital mortality) was more severe in patients with statin-drug interactions during hospitalization., Conclusions: This study demonstrates the added value of combining and reusing clinical and claim data to provide large-scale measures of drug-drug interaction prevalence and care pathways outside hospitals. It builds a path to move the current health care system toward a Learning Health System using knowledge generated from research on real-world health data., (©Aurélie Bannay, Mathilde Bories, Pascal Le Corre, Christine Riou, Pierre Lemordant, Pascal Van Hille, Emmanuel Chazard, Xavier Dode, Marc Cuggia, Guillaume Bouzillé. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 13.12.2021.)

Background: Despite cases of factitious disorder imposed on self being documented in the literature for decades, it appears to remain an under-identified and under-diagnosed problem. The present study aimed to explore factitious disorder imposed on self in a series of French patients., Methods: Patients 18 years old and over with factitious disorder imposed on self were retrospectively included by two independent reviewers according to DSM-5 criteria in Rennes University Hospital for the period 1995 to 2019. Patients were identified from a clinical data warehouse., Results: 49 patients with factitious disorder imposed on self were included. Among them, 36 (73.5%) were female. The average age at diagnosis was 38.4 years. The 16 patients with a health-related profession were all female. Direct evidence of falsification was found in 20.4% of cases. Falsification was mainly diagnosed on the basis of indirect arguments: history of factitious disorder diagnosed in another hospital (12.2%), extensive use of healthcare services (22.4%), investigations that were normal or inconclusive (69.4%), inconsistent or incomplete anamnesis and/or patient refusal to allow access to outside information sources (20.4%), atypical presentation (59.2%), evocative patient behaviour or comments (32.7%), and/or treatment failure (28.6%). Dermatology and neurology were the most frequently involved specialities (24.5%). Nine patients were hospitalized in intensive care. Some of them received invasive treatments, such as intubations, because of problems that were only reported or feigned. The diagnosis of factitious disorder imposed on self was discussed with the patient in 28 cases (57.1%). None of them admitted to making up the disorder intentionally. Two suicide attempts occurred within 3 months after the discussion of the diagnosis. No deaths were recorded. 44.9% of the patients returned to the same hospital at least once in relation to factitious disorder imposed on self., Conclusions: The present study reinforces data in favour of a predominance of females among patients with factitious disorder imposed on self. This diagnosis is difficult and is based on a range of arguments. While induced cases can be of low severity, cases that are only feigned can lead to extreme medical interventions, such as intubation., (© 2021. The Author(s).)

Introduction: Data collection automation through the reuse of real-world digital data from clinical data warehouses (CDW) could represent a great opportunity to improve medical device monitoring. For instance, this approach is starting to be used for the design of automated decision support systems for joint replacement monitoring. However, a number of obstacles remains, such as data quality and interoperability through the use of common and regularly updated terminologies, and the use of a Unique Device Identifier (UDI)., Areas Covered: To present the existing models of automated surveillance of orthopedic devices, a systematic review of initiatives using real-world digital health data to monitor joint replacement surgery was performed following the PRISMA 2020 guidelines. The main objective was to identify the data sources, the target populations, the population size, the device location, and the main results of studies on such initiatives., Expert Opinion: Analysis of the identified studies showed that real-world digital data offer many opportunities for improving the automation of monitoring in orthopedics. The contribution of real-world data, especially through natural language processing, UDI use in CDW and the integration of device databases, is needed for automated and more robust health surveillance.

There are few studies in humans dealing with the relationship between physico-chemical properties of drugs and their systemic bioavailability after administration via oral inhalation route (Fpulm). Getting further insight in the determinants of Fpulm after oral pulmonary inhalation could be of value for drugs considered for a systemic delivery as a result of poor oral bioavailability, as well as for drugs considered for a local delivery to anticipate their undesirable systemic effects. To better delineate the parameters influencing the systemic delivery after oral pulmonary inhalation in humans, we studied the influence of physico-chemical and permeability properties obtained in silico on the rate and extent of Fpulm in a series of 77 compounds with or without marketing approval for pulmonary delivery, and intended either for local or for systemic delivery. Principal component analysis (PCA) showed mainly that Fpulm was positively correlated with Papp and negatively correlated with %TPSA, without a significant influence of solubility and ionization fraction, and no apparent link with lipophilicity and drug size parameters. As a result of the small sample set, the performance of the different models as predictive of Fpulm were quite average with random forest algorithm displaying the best performance. As a whole, the different models captured between 50 and 60% of the variability with a prediction error of less than 20%. Tmax data suggested a significant positive influence of lipophilicity on absorption rate while charge apparently had no influence. A significant linear relationship between Cmax and dose (R 2 = "0.79) highlighted that Cmax was primarily dependent on dose and absorption rate and could be used to estimate Cmax in humans for new inhaled drugs., (Copyright © 2021 Elsevier B.V. All rights reserved.)

Effective and timely disease surveillance systems have the potential to help public health officials design interventions to mitigate the effects of disease outbreaks. Currently, healthcare-based disease monitoring systems in France offer influenza activity information that lags real-time by one to three weeks. This temporal data gap introduces uncertainty that prevents public health officials from having a timely perspective on the population-level disease activity. Here, we present a machine-learning modeling approach that produces real-time estimates and short-term forecasts of influenza activity for the twelve continental regions of France by leveraging multiple disparate data sources that include, Google search activity, real-time and local weather information, flu-related Twitter micro-blogs, electronic health records data, and historical disease activity synchronicities across regions. Our results show that all data sources contribute to improving influenza surveillance and that machine-learning ensembles that combine all data sources lead to accurate and timely predictions., Competing Interests: The authors have declared that no competing interests exist.

The reverse transcription-polymerase chain reaction (RT-PCR) assay is the accepted standard for coronavirus disease 2019 (COVID-19) diagnosis. As any test, RT-PCR provides false negative results that can be rectified by clinicians by confronting clinical, biological and imaging data. The combination of RT-PCR and chest-CT could improve diagnosis performance, but this would requires considerable resources for its rapid use in all patients with suspected COVID-19. The potential contribution of machine learning in this situation has not been fully evaluated. The objective of this study was to develop and evaluate machine learning models using routine clinical and laboratory data to improve the performance of RT-PCR and chest-CT for COVID-19 diagnosis among post-emergency hospitalized patients. All adults admitted to the ED for suspected COVID-19, and then hospitalized at Rennes academic hospital, France, between March 20, 2020 and May 5, 2020 were included in the study. Three model types were created: logistic regression, random forest, and neural network. Each model was trained to diagnose COVID-19 using different sets of variables. Area under the receiving operator characteristics curve (AUC) was the primary outcome to evaluate model's performances. 536 patients were included in the study: 106 in the COVID group, 430 in the NOT-COVID group. The AUC values of chest-CT and RT-PCR increased from 0.778 to 0.892 and from 0.852 to 0.930, respectively, with the contribution of machine learning. After generalization, machine learning models will allow increasing chest-CT and RT-PCR performances for COVID-19 diagnosis.