Blog

We are excited to present our latest achievement: an enhanced version of our eCRF tool that redefines how you collect and manage clinical data. These notable improvements are designed to provide an even more intuitive, intelligent, and efficient experience for our users.

We are thrilled to announce the release of our latest feature: Propensity Score Matching (PSM). This groundbreaking tool revolutionizes the field of clinical research by empowering researchers to enhance the quality and comparability of their studies. In this blog post, we will delve into the significance of PSM, its relevance in clinical research, and how to access this game-changing feature on EasyMedStat. The First Propensity Score Matching Guided Tool for Clinical Research We are proud to be the pioneers in introducing a guided tool for propensity score matching in the realm of clinical research. Our team of experts has developed a robust algorithm that facilitates the identification and pairing of subjects based on key characteristics, ensuring a more balanced and rigorous comparative analysis. With our PSM Guided Tool, researchers can now conduct propensity score matching analyses with confidence , knowing that the tool automates the critical checks for the required assumptions . These include ensuring the appropriate number of covariates, assessing group comparability, validating the common support assumption, and more. By streamlining and automating these crucial steps, we empower researchers to focus on their analysis and interpretation, knowing that the tool has their back. What is PSM? And Why Does It Matter? Propensity Score Matching (PSM) is a statistical technique used to control for potential confounding variables in non-randomized studies . It aims to create comparable groups by balancing the distribution of covariates between treatment and control groups. By doing so, PSM helps minimize the impact of confounding factors, thereby improving the internal validity of the study and strengthening the evidence obtained. PSM matters because it allows researchers to address the inherent limitations of non-randomized studies . It enables researchers to account for differences in patient characteristics and minimize bias, leading to more reliable and meaningful results. How to Perform a Propensity Score Matching? To access the propensity score matching feature on EasyMedStat, follow these simple steps: Navigate to the menu "Statistics" and Click on "Compare groups" to initiate the comparative analysis. Choose the groups you want to compare Click on "Match groups to improve comparability." Select the covariates you want to base the matching on, ensuring they are relevant to your research question. Verify the methodology with our built-in methodology tool, which provides transparency and ensures the accuracy of the matching process. With EasyMedStat's user-friendly interface and step-by-step guidance, researchers can seamlessly incorporate propensity score matching into their study design, ultimately enhancing the reliability and validity of their findings. Propensity Score Matching (PSM) is a powerful tool that significantly contributes to the advancement of clinical research. EasyMedStat's guided PSM feature empowers researchers to tackle the challenges of non-randomized studies and improve the quality of their research. By leveraging the benefits of PSM, researchers can obtain more robust and reliable results, leading to better-informed medical decisions and improved patient care. Unlock the potential of Propensity Score Matching with EasyMedStat and take your clinical research to new heights!

During a clinical investigation on a medical device, it is crucial to select the appropriate clinical scores to accurately assess its effectiveness. Clinical scores provide quantifiable and standardized measurements, enabling an objective evaluation of clinical outcomes. In this article, we explore the different steps to choose the suitable clinical scores for your clinical investigation on medical devices. Analyze the Scientific Literature A fundamental step in selecting the appropriate clinical scores is to conduct an in-depth analysis of the existing scientific literature. This analysis helps discover validated clinical scores used in previous studies on similar medical devices. By relying on the accumulated knowledge and expertise in the field, one can ensure the relevance of the selected clinical scores. Consult Your Investigators! Working closely with investigators ensures that the chosen clinical scores align with the needs of the clinical investigation. Their expertise and practical experience are invaluable in selecting the most appropriate clinical scores based on the medical device and study context. Another advantage of co-constructing the observation form with investigators is that they are often familiar with certain clinical scores used in their daily medical practice. Hence, they can more easily collect the same scores for your clinical investigations. Limit the Number of Scores to the Minimum It is essential to limit the number of clinical scores in the observation form. By avoiding information overload, data collection and statistical analysis are simplified. Typically, one to two relevant clinical scores are sufficient to evaluate the effectiveness of a medical device. By focusing on the most significant and directly related measures to the study's objective, clearer and more actionable data are obtained. Patient-Reported Outcome Measures (PROMs) Patient-reported outcome measures, or PROMs, are valuable tools for gathering data directly from patients. They provide information about their health status, symptoms, and quality of life. However, it is important to consider the potential fatigue associated with repeated completion of these questionnaires , especially if using redundant questionnaires or sending them at a high frequency. To minimize fatigue, it is necessary to use concise and targeted patient questionnaires, avoiding redundant or irrelevant information. A well-designed questionnaire encourages patient participation and ensures more comprehensive data. Choose the Questionnaire Requiring Fewer Responses in Case of Equivalence When faced with two highly correlated questionnaires, it is advisable to choose the one that requires fewer responses from patients or investigators. This simplifies data collection, encourages patient and investigator participation, and reduces monitoring efforts. By ensuring simplicity and user-friendliness in questionnaires, more complete and higher-quality data are obtained. The Importance of Subscales in Clinical Scores Some clinical scores include specific subscales that evaluate particular aspects of a medical device's effectiveness. For example, a functional score may provide subscores evaluating pain, mobility, or daily activities. A quality of life questionnaire may provide subscores on the mental health of patients. These subscales provide detailed and in-depth information on specific domains. Including these relevant subscales allows for a more comprehensive evaluation of the impact of the medical device. Conclusion Choosing the right clinical scores is crucial for a successful clinical investigation. By following the outlined steps, including analyzing scientific literature, consulting investigators, limiting the number of scores, and considering patient questionnaires and subscales, high-quality data can be obtained to assess the performance of your medical device. Close collaboration with investigators and attention to patient questionnaires and subscales contribute to a precise and comprehensive evaluation of the effectiveness of medical devices.

Why can a CRF template be relevant for your clinical investigation?

Like you, we are always happy when we can validate the hypothesis of our clinical study by obtaining a p-value < 0.05 on our main hypothesis. But is this result robust? Could the fate of a single patient modify the p-value and cause it to pass beyond the sacrosanct threshold of “significance”? You will now be able to answer this question very easily thanks to EasyMedStat. We also have new features on the ROC curves side. Read on carefully to find out more…

Connect your information system or medical device to EasyMedStat with the API.

New on EMS: Data Cleaner, a tool to clean your data before statistical analysis. Clean data for a more accurate analysis. [Product Update 3.20]

Enrich your patient data with our new e-PRO functionality!

Thanks to EasyMedStat the next version of SciPy will ship with a faster Wilcoxon signed-rank exact test.