ECElsa Cécilia-Joseph

Elsa Cécilia-Joseph

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Elsa Cécilia-Joseph has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Machine Learning Algorithms for the Prediction of Dengue Epidemics in Martinique: A Prediction Model Study (Preprint)

    by Sophie Flobinus, Elsa Cecilia-Joseph, André Cabié, Guillaume Bouzillé, Morgane Pierre-Jean, Amélie Brejot, Thomas Jaylet, Fatiha Najioullah, Manuel Etienne, Fabrice Malouines, et al.

  • Open Access

    Machine Learning Algorithms for the Prediction of Dengue Epidemics in Martinique: a prediction Model Study (Preprint)

    by Sophie Flobinus, Elsa Cecilia-Joseph, André Cabié, Guillaume Bouzillé, Morgane Pierre-Jean, Amélie Bréjot, Thomas Jaylet, Fatiha Najioullah, Manuel Etienne, Fabrice Malouines, et al.

    BACKGROUND Dengue fever, also known as “tropical flu”, is an infectious disease caused by the dengue virus, which most often occurs in tropical and subtropical regions. To combat this virus and prevent dengue epidemics in France, Santé publique France (SpFrance) has set up both individual and collective actions. In Martinique, the Programme de Surveillance, d'Alerte et de Gestion des Epidémies de dengue (PSAGE dengue), set up by SpFrance in 2006, coordinates these collective actions. It brings together a few local players involved in both clinical surveillance (general practitioners, Martinique University Hospital, laboratories, etc.) and vector surveillance (Centre de Démoustication et de Recherches Entomologiques - Lutte Antivectorielle; CEDRE-LAV). OBJECTIVE At present, there is a delay of several weeks between the increase in the number of dengue cases detected in the field and the declaration of the epidemic phase by the PSAGE. The main objective of this study is to use Machine Learning algorithms to predict dengue epidemics in Martinique. METHODS Different Machine Learning algorithms using heterogeneous real-life data (administrative and clinical data, laboratory data, Google Trends data and entomological data) were evaluated and compared on their ability to predict the 2019-2021 dengue epidemic. RESULTS The best-performing model was the random forest model (correlation at 0.933 [0.915 ;0.947]). CONCLUSIONS This study highlighted the value of integrating real-life data into the surveillance and prediction of dengue epidemics in Martinique. The results show that the use of multiple data sources, such as clinical, entomological and Google Trends data, improves disease surveillance. Thus, the implementation of these different sources can contribute to the prediction of future epidemics.

  • Open Access

    Thoracic Endometriosis Syndrome (TES) in Martinique, a French West Indies Island

    by Moustapha Agossou, Bruno-Gilbert Sanchez, Paul-Henri Alauzen, Maud Olivier, Elsa Cécilia-Joseph, Ludivine Chevallier, Mehdi Jean-Laurent, Aude Aline-Fardin, Moustapha Dramé, Nicolas Venissac

    Introduction: Endometriosis is a female disease that affects 5–10% of women of childbearing age, with predominantly pelvic manifestations. It is currently declared as a public health priority in France. Thoracic endometriosis syndrome (TES) is the most common extra-pelvic manifestation. Objective: The objective of this study was to describe the epidemiological and clinical characteristics, and outcomes of patients with TES in Martinique. Patients and Methods: We performed a descriptive, retrospective study including all patients managed at the University Hospital of Martinique for TES between 1 January 2004 and 31 December 2020. Results: During the study period, we identified 479 cases of pneumothorax, of which 212 were women (44%). Sixty-three patients (30% of all female pneumothorax) were catamenial pneumothorax (CP) including 49 pneumothoraxes alone (78% of catamenial pneumothorax) and 14 hemopneumothorax (22% of catamenial pneumothorax). There were 71 cases of TES, including 49 pneumothoraxes (69%), 14 hemopneumothoraxes (20%) and 8 hemothorax (11%). The annual incidence of TES was 1.1 cases/100,000 inhabitants. The prevalence of TES was 1.2/1000 women aged from 15 to 45 years and the annual incidence of TES for this group was 6.9/100,000. The annual incidence of CP was 1 case/100,000 inhabitants. The average age at diagnosis was 36 ± 6 years. Eight patients (11%) had no prior diagnosis of pelvic endometriosis (PE). The mean age at pelvic endometriosis diagnosis was 29 ± 6 years. The mean time from symptom onset to diagnosis was 24 ± 50 weeks, and 53 ± 123 days from diagnosis to surgery. Thirty-two patients (47%) had prior abdominopelvic surgery. Seventeen patients (24%) presented other extra-pelvic localizations. When it came to management, 69/71 patients (97%) underwent surgery. Diaphragmatic nodules or perforations were found in 68/69 patients (98.5%). Histological confirmation was obtained in 55/65 patients who underwent resection (84.6%). Forty-four patients (62%) experienced recurrence. The mean time from the initial treatment to recurrence was 20 ± 33 months. The recurrence rate was 16/19 (84.2%) in patients who received medical therapy only, 11/17 (64.7%) in patients treated by surgery alone, and 17/31 (51.8%) in patients treated with surgery and medical therapy (p = 0.03). Conclusions: We observed a very high incidence of TES in Martinique. The factors associated with this high incidence in this specific geographical area remain to be elucidated. The frequency of recurrence was lower in patients who received both hormone therapy and surgery.


  • Open Access

    Early Discharge, Outpatient Evaluation, and Home Management of Acute Respiratory Failure from COVID-19 in Martinique

    by Moustapha Agossou, Mathilde Provost, José-Luis Barnay, Jean-Marie Turmel, Elsa Cécilia-Joseph, Dabor Resiere, Moustapha Dramé

    : A worldwide pandemic of viral infection due to SARS-CoV-2 (and its resultant disease, COVID-19) has been ongoing since 2019. Martinique was affected by a major wave in summer 2021, with saturation of the health system forcing the implementation of home care management. We conducted a retrospective, observational study that included patients treated in the KOVIDHOM 972 program. We included adult patients with SARS-CoV2 hypoxemic pneumonia and requiring 4 L per minute or less of oxygen. In total, 418 were discharged to home with oxygen therapy after hospitalization for SARS-CoV-2 hypoxemic acute pneumonia, and 416 were analyzed. Half (50.2%) were women. Mean age was 58.8 ± 13.0 years. Time from onset of symptoms to hospitalization was 9.1 ± 3.5 days, and average length of stay was 10.5 ± 7.4 days. Maximum oxygen flow during hospitalization was 6.9 ± 4.5 L/min in patients who did not require intensive care. Average oxygen flow at discharge was 1.8 ± 07 L/min. At 30 days after discharge, the readmission rate was 0.5% (95% CI: 0–1.18), and the death rate was 0.5% (95% CI 0–1.18). Our study shows a very low rate of readmission or death in COVID-19 patients discharged to home with oxygen therapy. These results highlight the possibility of safe home care in carefully selected patients. Such programs could be useful in pandemic or wide-scale emergency situations.


  • Open Access

    The Role of Heterogenous Real-world Data for Dengue Surveillance in Martinique: Observational Retrospective Study

    by Emmanuelle Sylvestre, Elsa Cécilia-Joseph, Guillaume Bouzillé, Fatiha Najioullah, Manuel Etienne, Fabrice Malouines, Jacques Rosine, Sandrine Julié, André Cabié, Marc Cuggia

    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.


  • Open Access

    Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review

    by Emmanuelle Sylvestre, Clarisse Joachim, Elsa Cécilia-Joseph, Guillaume Bouzillé, Boris Campillo-Gimenez, Marc Cuggia, André Cabié

    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.


  • Open Access

    Health informatics support for outbreak management: How to respond without an electronic health record?

    by Emmanuelle Sylvestre, René-Michel Thuny, Elsa Cecilia-Joseph, Papa Gueye, Cyrille Chabartier, Yannick Brouste, Hossein Mehdaoui, Fatiha Najioullah, Sandrine Pierre-François, Sylvie Abel, et al.