Catalog Advanced Search

Search by Category
Search by Format
Sort By
Search by Category
Search by Format
Search by Date Range
Products are filtered by different dates, depending on the combination of live and on-demand components that they contain, and on whether any live components are over or not.
Start
End
Search by Keyword
Sort By
  • Contains 1 Component(s)

    This tutorial aims to give a practical introduction tailored for pharmacoepidemiologists on how to set up, structure, and implement analytic workflows using Git, the most frequently used distributed version-control system to date.

    Presented by Janick Weberpals, Transparency and reproducibility in pharmacoepidemiology research 

    Transparency and reproducibility in conducting healthcare database studies in pharmacoepidemiology are critical scientific requirements for meaningful research. While many advances have been made in the documentation and reporting of study protocols and results, the principles for version control and sharing of analytic code in real-world evidence are not yet as established as in other quantitative disciplines like computational biology and health informatics. 

    This tutorial aims to give a practical introduction tailored for pharmacoepidemiologists on how to set up, structure, and implement analytic workflows using Git, the most frequently used distributed version-control system to date. 


  • Contains 1 Component(s)

    Presented by Kathryn Rough, IQVIA - This webinar will discuss what it means for machine learning algorithms to be fair, explore potential issues, and share concrete steps for creating fair algorithms, as part of our larger goal of promoting equity in health systems.

    Machine learning has the potential to transform aspects of how healthcare and medicine are delivered, yet we know these technologies have the capacity to exacerbate existing inequalities (or introduce new ones). 

    This webinar will discuss what it means for machine learning algorithms to be fair, explore potential issues, and share concrete steps for creating fair algorithms, as part of our larger goal of promoting equity in health systems. Special attention will be paid to fairness and bias considerations for large language models (e.g., ChatGPT/GPT-4, Bard/LaMDA). 


  • Contains 1 Component(s)

    This webinar was presented on behalf of the ISPE Vaccines Special Interest Group (SIG) and the ISPE Student Council (SISPE).

    This webinar was presented on behalf of the ISPE Vaccines Special Interest Group (SIG) and the ISPE Student Council (SISPE). Event highlights included: engaging with top professionals from pharmaceuticals, consulting, academia, and government; exploring various career paths within the vaccine industry; and participating in a dynamic agenda that included panelist introductions, a moderated Q&A session, and an open Q&A forum. This is an excellent platform for professionals and students alike to gain insights and network with industry leaders.

  • Contains 1 Component(s)

    Synthetic data is a form of model generated data that shares the same patterns and characteristics as real ‎data. The applications of synthetic data in pharmacoepidemiology are still emerging, but can offer new ‎ways for us to:‎ ‎1. Enable the internal reuse of datasets and sharing data with external parties in a privacy-preserving ‎manner (i.e., it can be seen as anonymization 2.0)‎ ‎2. Augment and expand datasets that are small for training machine learning models‎ ‎3. Mitigate bias in datasets by simulating observations from the under-represented groups ‎4. Simulate patients for clinical trials that are experiencing problems, including under-recruitment Synthetic data can be created when a generative AI model is trained on source data, such as claims ‎database or an EMR database. This AI-generated data would not have a one-to-one mapping to the ‎original data, and therefore will have strong privacy preserving characteristics, and the generated data ‎can be much larger than the original data. Some of these use cases have already been applied in practice ‎and some are still in the formative stage of development. This webinar will give an overview of synthetic ‎data generation and walk through some of the above applications.‎ This webinar is sponsored by the Digital Epidemiology Special Interest Group.‎

    Methods and Applications of Synthetic Data in Pharmacoepidemiology (November 15, 2023)

    Synthetic data is a form of model generated data that shares the same patterns and characteristics as real data. The applications of synthetic data in pharmacoepidemiology are still emerging, but can offer new ways for us to:

    1. Enable the internal reuse of datasets and sharing data with external parties in a privacy-preserving manner (i.e., it can be seen as anonymization 2.0)

    2. Augment and expand datasets that are small for training machine learning models

    3. Mitigate bias in datasets by simulating observations from the under-represented groups

    4. Simulate patients for clinical trials that are experiencing problems, including under-recruitment

    Synthetic data can be created when a generative AI model is trained on source data, such as claims database or an EMR database. This AI-generated data would not have a one-to-one mapping to the original data, and therefore will have strong privacy preserving characteristics, and the generated data can be much larger than the original data. Some of these use cases have already been applied in practice and some are still in the formative stage of development. This webinar will give an overview of synthetic data generation and walk through some of the above applications.
    This webinar is sponsored by the Digital Epidemiology Special Interest Group.

    This webinar is aimed towards industry/service providers, academia, government/regulatory and students.

    .

  • Contains 1 Component(s)

    This webinar covers key concepts in designing and conducting pragmatic randomized trials in electronic ‎databases, like electronic health record systems and administrative claims databases. These designs are ‎often referred to as "database-randomized trials", which may be increasingly possible within electronic ‎databases used in pharmacoepidemiology. Content will include conceptual differences from traditional ‎pragmatic trials, advantages and disadvantages of these types of trials, and relevant examples.‎

    Designing and Conducting Pragmatic Randomized Trials in Electronic Databases in ‎Pharmacoepidemiology (October 12, 2023)

    This webinar covers key concepts in designing and conducting pragmatic randomized trials in electronic databases, like electronic health record systems and administrative claims databases. These designs are often referred to as "database-randomized trials", which may be increasingly possible within electronic databases used in pharmacoepidemiology. Content will include conceptual differences from traditional pragmatic trials, advantages and disadvantages of these types of trials, and relevant examples.

    This webinar is aimed towards industry/service providers, academia and students.

    .

  • Contains 1 Component(s)

    Pharmacoepidemiology and Drug Safety (PDS), the official journal of ISPE, presents the Ronald D. Mann ‎Best Paper Award each year to the strongest contribution within a given volume of the journal. The award ‎for 2022 is presented to Dr. Elizabeth A. Suarez and collaborators for their paper ”Novel Methods for ‎Pregnancy Drug Safety Surveillance in the FDA Sentinel System.”‎ The paper discussed the application of TreeScan™, a statistical data mining tool, within the FDA Sentinel ‎System to simultaneously identify multiple potential adverse neonatal and infant outcomes after ‎maternal medication exposure. This method could supplement existing approaches to enhance the ‎surveillance of medication safety during pregnancy.‎ In this webinar, Dr. Suarez will present findings of their study, followed by comments by PDS regional ‎editor for the Americas, Dr. Vincent Lo Re. Audience will not only have the opportunity to discuss the ‎paper with Dr. Suarez and but also ask questions regarding manuscript submission to PDS with Dr. Lo Re.‎

    Pharmacoepidemiology and Drug Safety Best Paper of 2022 --- Novel Methods for Pregnancy Drug Safety Surveillance in the FDA Sentinel System (September 15, 2023)

    Pharmacoepidemiology and Drug Safety (PDS), the official journal of ISPE, presents the Ronald D. Mann Best Paper Award each year to the strongest contribution within a given volume of the journal. The award for 2022 is presented to Dr. Elizabeth A. Suarez and collaborators for their paper ”Novel Methods for Pregnancy Drug Safety Surveillance in the FDA Sentinel System.”

    The paper discussed the application of TreeScan™, a statistical data mining tool, within the FDA Sentinel System to simultaneously identify multiple potential adverse neonatal and infant outcomes after maternal medication exposure. This method could supplement existing approaches to enhance the surveillance of medication safety during pregnancy.

    In this webinar, Dr. Suarez will present findings of their study, followed by comments by PDS regional editor for the Americas, Dr. Vincent Lo Re. Audience will not only have the opportunity to discuss the paper with Dr. Suarez and but also ask questions regarding manuscript submission to PDS with Dr. Lo Re.

    This webinar is aimed towards industry/service providers, academia, government/regulatory, and students.
    .

  • Contains 1 Component(s)

    Opportunities and Challenges Surrounding the Incorporation of Laboratory Test-Result Information ‎within High-Dimensional Confounder Adjustment Procedures ‎ Comparison of Stable Balancing Weights Vs. Propensity Score Weighting for RWE or External Clinical ‎Study Comparison Arms to Single Arm Clinical Trials ‎ Standardization Over Disease Risk Score Versus Propensity Score for Confounding Control When Using ‎Random Forests for Model Fitting ‎ High-dimensional Iterative Causal Forest (hdiCF): A Novel Algorithm for Subgroup Identification in ‎Claims Data ‎ Can Machine Learning Approaches Help Accelerating Rare Diseases Diagnosis? The Acromegaly Case ‎Study ‎ Severity Score Extraction from Clinical Notes Using Natural Language Processing: Applications to ‎Dermatology ‎

    MODERATORS: Jeremy Rassen | Katia Verhamme

    Opportunities and Challenges Surrounding the Incorporation of Laboratory Test-Result Information within High-Dimensional Confounder Adjustment Procedures [279]

    AUTHORS: John Tazare | Jeremy Brown | Daniel Morales | Elizabeth Williamson Ian Douglas (United Kingdom)

    Comparison of Stable Balancing Weights Vs. Propensity Score Weighting for RWE or External Clinical Study Comparison Arms to Single Arm Clinical Trials [280]

    AUTHORS: Stephen Johnston | Pranjal Tewari | Paul Coplan (United States)

    Standardization Over Disease Risk Score Versus Propensity Score for Confounding Control When Using Random Forests for Model Fitting [281]

    AUTHORS: Yi Li | Tibor Schuster | Kazuki Yoshida | Robert Platt (Canada)

    High-dimensional Iterative Causal Forest (hdiCF): A Novel Algorithm for Subgroup Identification in Claims Data [282]

    AUTHORS: Tiansheng Wang | Virginia Pate | John Buse | Richard Wyss Til Stürmer (United States)

    Can Machine Learning Approaches Help Accelerating Rare Diseases Diagnosis? The Acromegaly Case Study [283]

    AUTHORS: Salvatore Crisafulli | Luca L'Abbate | Andrea Fontana Giacomo Vitturi | Daniele Gianfrilli | Alessia Cozzolino Maria Cristina De Martino | Gianluca Trifirò (Italy)

    Severity Score Extraction from Clinical Notes Using Natural Language Processing: Applications to Dermatology [284]

    AUTHORS: Vikas Kumar | Lawrence Rasouliyan | Amanda Althoff Stella Chang | Stacey Long (United States)

  • Contains 1 Component(s)

    Case Validation in Electronic Health Records Linked with a Disease-Specific Clinical Database: Use Case ‎in Pulmonary Arterial Hypertension Does Misclassification Due to Electronic Health Record Discontinuity Cause Biased Effect Estimates in ‎Comparative Effectiveness Research? International Classification of Diseases (ICD-10) Code Identification of Lab-Confirmed SARS-CoV-2 ‎within Electronic Health Data Using Tree-Based Scan Statistics for Signal Identification: Screening for Elevated Congenital ‎Malformation Risk Following Prenatal Antipsychotic Exposure How to Underpower Your Real-World Data Study: Examples and Ways to Avoid Them Using ‎Quantitative Bias Analysis A Methodology Study to Evaluate External Comparator Arm Study Results Versus Randomised ‎Controlled Trial Results: Metastatic Hormone-Sensitive Prostate Cancer Case Study‎

    MODERATORS: Stanley Edlavitch | Anick Bérard

    Case Validation in Electronic Health Records Linked with a Disease-Specific Clinical Database: Use Case in Pulmonary Arterial Hypertension [149]
    AUTHORS: Eva-Maria Didden | Di Lu | Haley Hedlin | Andrew Hsi |Monika Brand | Roham Zamanian (Switzerland)

    Does Misclassification Due to Electronic Health Record Discontinuity Cause Biased Effect Estimates in Comparative Effectiveness Research? [150]
    AUTHORS: Yinzhu Jin | Richard Wyss | Shirley Wang | Rishi Desai | Kueiyu Joshua Lin (United States)

    International Classification of Diseases (ICD-10) Code Identification of Lab-Confirmed SARS-CoV-2 within Electronic Health Data [151]
    AUTHORS: Sasha Bernatsky | Marina Birck | Autumn Neville | Louise Pilote | Erik Youngson | James King | Anick Bérard | Sherif Eltonsy | Cristiano Moura (Canada)

    Using Tree-Based Scan Statistics for Signal Identification: Screening for Elevated Congenital Malformation Risk Following Prenatal Antipsychotic Exposure [152]
    AUTHORS: Loreen Straub | Shirley Wang | Sonia Hernandez-Diaz | Seanna Vine | Massimiliano Russo | Brian Bateman | Yanmin Zhu | Krista Huybrechts (United States)

    How to Underpower Your Real-World Data Study: Examples and Ways to Avoid Them Using Quantitative Bias Analysis [153]
    AUTHORS: Sudhir Venkatesan | Christen Gray (United Kingdom)

    A Methodology Study to Evaluate External Comparator Arm Study Results Versus Randomised Controlled Trial Results: Metastatic Hormone-Sensitive Prostate Cancer Case Study [154]
    AUTHORS: Wilhelmina Hoogendoorn | Héctor Sanz | Chantal Quinten | Joan Largent | Gerd Rippin (Netherlands)

  • Contains 1 Component(s)

    Breast Cancer Cohort Comparison Among Four Real-World Databases [119] ‎ ‎Comparison of EHR Data-Completeness in Patients with Different Types of Medical Insurance ‎Coverage in the United States [120] ‎ ‎Variation in Mother-Infant Linkage Rates by Jurisdiction in U.S. Medicaid Data [121] ‎Developing Clinically Interpretable Machine Learning Algorithms for Pressure Injury Safety ‎Surveillance with Explainable AI [122] Brain Metastasis Prediction in Patients with Metastatic Breast Cancer using a U.S. Nationwide ‎Clinico-genomic Database [123] ‎ ‎Prevalence of Probable Alzheimer’s Disease in Veteran Patients Based on Clinical Notes from ‎Electronic Health Records [124]

    MODERATORS: Julie Lauffenburger | Rosa Gini

    Breast Cancer Cohort Comparison Among Four Real-World Databases

    AUTHORS: Xinyue Liu | Golnoosh Alipour Haris | Changxia Shao | Mehmet Burcu | Edward Bortnichak | Sarah Markt | Thao Vo Chu-Ling Yu (United States)

    Comparison of EHR Data-Completeness in Patients with Different Types of Medical Insurance Coverage in the United States

    AUTHORS: Priyanka Anand | Yichi Zhang | David Merola | Yinzhu Jin | Shirley Wang | Joyce Lii | Jun Liu | Kueiyu Joshua Lin (United States)

    Variation in Mother-Infant Linkage Rates by Jurisdiction in U.S. Medicaid Data 

    AUTHORS: Bradley Hammill | Michael Stagner | Judith Maro | Sarah Dutcher | David Moeny | Robert Rosofsky | Daniel Kiernan | Laura Shockro | Alexander Mai | Jessica Pritchard | Steven Lippmann | Pratap Adhikari (United States)

    Developing Clinically Interpretable Machine Learning Algorithms for Pressure Injury Safety Surveillance with Explainable AI 

    AUTHORS: Andy Wilson | Jenny Alderden | Jace Johnny (United States)

    Brain Metastasis Prediction in Patients with Metastatic Breast Cancer using a U.S. Nationwide Clinico-genomic Database

    AUTHORS: Yunru Huang | Tianyi Sun | Thibaut Sanglier | Chiara Lambertini | Adam Knott | Yolande Du Toit | Raf Poppe | Eleonora Restuccia | Sanne de Haas | Patricia Luhn (United States)

    Prevalence of Probable Alzheimer’s Disease in Veteran Patients Based on Clinical Notes from Electronic Health Records

    AUTHORS: Donald Miller | Guneet Jasuja | Byron Aguilar | Xuyang Li | Ekaterina Shishova | Dan Berlowitz | Peter Morin | Maureen O'Conner | Andrew Nguyen | Cindy Christiansen Raymond Zhang | Amir Abbas | Tahami Monfared | Quanwu Zhang | Weiming Xia (United States) 

  • Contains 1 Component(s)

    The global COVID-19 pandemic has generated enormous morbidity and mortality, as well as large health system disruptions including changes in use of prescription medications, outpatient encounters, emergency department admissions, and hospitalizations. These pandemic-related disruptions are reflected in real-world data derived from electronic medical records, administrative claims, disease or medication registries, and mobile devices. This webinar will discuss how pandemic-related disruptions in healthcare utilization may impact the conduct of noninterventional studies designed to characterize the utilization and estimate the effects of medical interventions on health-related outcomes, including possible threats to external validity (participant selection) and internal validity (for example, confounding, selection bias, missing data bias).

    Methodological Considerations for Designing Pharmacoepidemiology Studies in the COVID-19 Era  (June 23, 2023)

    The global COVID-19 pandemic has generated enormous morbidity and mortality, as well as large health system disruptions including changes in use of prescription medications, outpatient encounters, emergency department admissions, and hospitalizations. These pandemic-related disruptions are reflected in real-world data derived from electronic medical records, administrative claims, disease or medication registries, and mobile devices. This webinar will discuss how pandemic-related disruptions in healthcare utilization may impact the conduct of noninterventional studies designed to characterize the utilization and estimate the effects of medical interventions on health-related outcomes, including possible threats to external validity (participant selection) and internal validity (for example, confounding, selection bias, missing data bias).

    This webinar is aimed towards students, trainees, young professionals, anyone interested in methodology and pharmacoepidemiologic research.