ABSTRACT
Introduction: During the recent covid-19 vaccination campaign, the number of ICSRs reported by patients and professionals has dramatically increased, reaching up to almost 1 M declarations only in Europe (EMA numbers). To deal with such growing amount of data, Synapse Medicine-, in collaboration with The French National Agency for Medicines and Health Products Safety (ANSM), have developed an artificial intelligence (AI) tool, the Medication Shield, which, based on a natural language processing algorithm, is able to detect ADRs from patients' reports and to code them into an appropriate MedDRA preferred term (PT). Before the covid-19 pandemic, this system was successful in detecting ADRs from the patient reports declared through the French web national reporting system (1, 2). However, how it behaves in conditions of higher reporting flow rate is unknown at present. Objective(s): To evaluate the performance of the Medication Shield in detecting vaccine-related ADRs from patients' ICSRs declared across the covid-19 vaccination campaign. Method(s): A machine learning (ML) pipeline composed by a light Gradient Boosting Machine ensemble model was employed to detect and code covid-19 vaccine-related ADRs from patients' ICSRs declared through the web reporting system during the vaccination campaign (Jan 2021-Apr 2022). The encoding of regional pharmacovigilance centers was employed as the reference ground truth to train the algorithm in a supervised manner. Moreover, a panel of three pharmacologists, with significant experience in ADRs encoding, was set-up to perform a case-by-case analysis of 200 hundreds reports for which the algorithm provided improper encoding. Result(s): Overall, 65.191 ICSRs were extracted and used to train our ML algorithm. Of this, 54.987 were employed to validate the system. Importantly, almost 86% of the ICSRs were related to covid vaccines. Because the percentage of newly reported ADRs increased over time and was higher for vaccine than not-vaccine related reports, we split the training and validation sets in batches with similar ADRs distribution. Performance evaluation is currently under process. Initial feedbacks from the analysis performed by the experts are showing an uneven distribution of false positive and false negative across samples. Results from the other experts are needed to confirm this finding. Conclusion(s): The core findings of this study will be gathered in the forthcoming weeks and be ready for the ISoP meeting in September. This work will provide new insights about the effectiveness of deploying AI as a support to treat real world data in a context of sanitary crisis.
ABSTRACT
Introduction: During the recent covid-19 vaccination campaign, the number of ICSRs reported by patients and professionals has dramatically increased, reaching up to almost 1 M declarations only in Europe (EMA numbers). To deal with such growing amount of data, Synapse Medicine®, in collaboration with The French National Agency for Medicines and Health Products Safety (ANSM), have developed an artificial intelligence (AI) tool, the Medication Shield, which, based on a natural language processing algorithm, is able to detect ADRs from patients' reports and to code them into an appropriate MedDRA preferred term (PT). Before the covid-19 pandemic, this system was successful in detecting ADRs from the patient reports declared through the French web national reporting system (1, 2). However, how it behaves in conditions of higher reporting flow rate is unknown at present. Objective: To evaluate the performance of the Medication Shield in detecting vaccine-related ADRs from patients' ICSRs declared across the covid-19 vaccination campaign. Methods: A machine learning (ML) pipeline composed by a light Gradient Boosting Machine ensemble model was employed to detect and code covid-19 vaccine-related ADRs from patients' ICSRs declared through the web reporting system during the vaccination campaign (Jan 2021-Apr 2022). The encoding of regional pharmacovigilance centers was employed as the reference ground truth to train the algorithm in a supervised manner. Moreover, a panel of three pharmacologists, with significant experience in ADRs encoding, was set-up to perform a case-by-case analysis of 200 hundreds reports for which the algorithm provided improper encoding. Results: Overall, 65.191 ICSRs were extracted and used to train our ML algorithm. Of this, 54.987 were employed to validate the system. Importantly, almost 86% of the ICSRs were related to covid vaccines. Because the percentage of newly reported ADRs increased over time and was higher for vaccine than not-vaccine related reports, we split the training and validation sets in batches with similar ADRs distribution. Performance evaluation is currently under process. Initial feedbacks from the analysis performed by the experts are showing an uneven distribution of false positive and false negative across samples. Results from the other experts are needed to confirm this finding. Conclusion: The core findings of this study will be gathered in the forthcoming weeks and be ready for the ISoP meeting in September. This work will provide new insights about the effectiveness of deploying AI as a support to treat real world data in a context of sanitary crisis.
ABSTRACT
Background: Onco-haematological patients are considered a vulnerable group with early access to SARS-CoV-2 vaccination. The Onco-Hematological Department of Piacenza has activated a dedicated vaccination program, with appropriate timing. We selected patients on active injection therapy with extreme immune fragility or undergoing haematopoietic stem cell transplantation. The project has created a path for access to vaccination, with reservations on a dedicated agenda and departmental vaccination point, has allowed patients to be vaccinated before starting therapies, start a clinical study of immunological surveillance, feed a departmental database by recording the number of vaccinated patients and any adverse events, favor vaccination in a known, familiar, comfortable context. Materials and methods: The staff underwent training on the preparation, administration, registration of the vaccine, observation and management of any adverse events. On the basis of the identified criteria, the patients who had to carry out the vaccination were selected. The programming was carried out by the referring physician who delivered the informed consent and who checked the medical history. During the vaccination sessions, the patients were managed by the Department team who took care of all the planned vaccination phases. The data were recorded on a regional IT platform. Each vaccination session was coordinated by a nurse and a vaccinating doctor. Results: The vaccination sessions were organized from 20/03/2021 for a total of 13 vax days. 426 patients were vaccinated, 230 F (53.99%) and 196 M (46.01%), mean age 63.38 ± 11.35, range 20-86, of these 415 (97.42%) completed the two scheduled vaccination doses, 11 patients (2.58%) did not receive the second administration due to worsening of the clinical picture. To evaluate the perceived quality and make suggestions, 10 posts were published on the FB page, totaling 2217 likes, 93 comments and 97 shares. The comments were positive, in particular the family environment, the presence of the treating team and the adequate waiting times were appreciated. Conclusions: Experience has made it possible to vaccinate the category of vulnerable patients ensuring safety, appropriateness, effectiveness, efficiency, satisfaction and user loyalty, without delaying or interrumpting oncological treatment.
ABSTRACT
OBJECTIVE: To identify epidemiological and clinical characteristics of multisystemic inflammatory syndrome associated with coronavirus infection as one of the severe forms of COVID-19 involvement in children and adolescents. METHODS: review was based on articles published in 2020 in the PubMed, Medline, Scopus, SciELO and Cochrane databases. SUMMARY: Multisystemic inflammatory syndrome is a serious clinical disorder that affects children and adolescents and is associated with the detection of previous exposure to SARS-CoV-2. It is characterized by the installation of a shock picture, with a significant increase in inflammatory markers such as presentations of Kawasaki Disease or shock syndrome related to Kawasaki Disease, or even toxic shock syndrome, with the clinical picture being characterized by fever of difficult control, rash, conjunctivitis, peripheral edema, generalized pain in the extremities and gastrointestinal symptoms. CONCLUSIONS: Although the vast majority of children with COVID-19 have mild symptoms, it is necessary to consider that some have a hyperinflammatory response. It is essential that health professionals receive information that can assist in the recognition of this clinical condition, differentiating it from other diagnoses, so that early and appropriate treatment is instituted.