Event type
Lectures and seminars
Sfo Epi Seminar in Biostatistics: Distributed Privacy-Preserving Estimation of Time-to-Event Models

17-09-2021 3:00 pm Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/68906707686
Lead

Welcome to attend the SfoEpi Seminar Series in Biostatistics!
Title: Distributed Privacy-Preserving Estimation of Time-to-Event Models

Content

Speaker:

Dr. C Jason Liang PhD, Biostatistics Research Branch, NIAID, NIH, USA

Abstract:

There has been a proliferation of EHR data in recent years. However, the data tends to be splintered across institutional silos. Integration of the data across silos at the patient level has many challenges, including patient privacy and the practical necessities of minimizing the rounds of communication between sites.

Informally, there is a trade-off between efficiency and privacy. Freely sharing patient-level information across silos is efficient but impractical. Restricting information sharing to coarse aggregate summaries (e.g. meta-analytic approaches that essentially average treatment effects across different studies) preserves privacy but is inefficient and may lead to bias. There is a need to identify approaches that lie between these two extremes of privacy and efficiency.

Building on the communication-efficient surrogate likelihood work of Jordan et al. (2018 JASA), we outline approaches for fitting Cox models and its extensions when data is distributed among multiple sites. We show that our approaches are more accurate than naive meta-analytic approaches while preserving privacy and minimizing the frequency of communication required between separate data sites.

Zoom Link: https://ki-se.zoom.us/j/68906707686

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

If you have any questions, please contact Erin Gabriel.

Contact

Event type
Conferences and symposiums
NorPEN 2021

10-11-2021 to
12-11-2021 Add to iCal
Campus Solna
Location
to be posted
NorPen 2021
Photo: N/A
Lead

The 13th Annual Nordic Pharmacoepidemiological Network (NorPEN) meeting. Hosted by the Centre for Pharmacoepidemiology at Karolinska Institutet.

Content

Theme: Sustainability of Nordic Collaboration

November 11-12th 2021

Hosted by the Centre for Pharmacoepidemiology at Karolinska Institutet

Questions? Contact us at norpen@meds.ki.se

 

Registration is now open!

For more information visit:https://ki.se/en/meds/norpen-2021

Format

The NorPEN 2021 meeting will be held online with live participation capability by attendees

Abstracts

  • Abstract submissions for the 10-minute oral presentations and 3-minute PharmacoepiSLAMs are now welcome
  • The submission form is available here https://ki.se/en/meds/norpen-2021
  • Deadline Friday September 10th

Pre-conference course: A general overview of G methods in relation to pharmacoepidemiology

Wednesday November 10th 2021, afternoon, time: TBA

Funded by SFO Epi (The Strategic Research Area in Epidemiology and Biostatistics, KI)

*Note that registration for the course is separate from the conference

Contact

Event type
Lectures and seminars
Sfo Epi Seminar in Biostatistics: Reconsideration of the Kaplan-Meier Estimator: Censoring and Time-varying Covariates

11-06-2021 3:00 pm Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/65377392771
Lead

Welcome to attend the SfoEpi Seminar Series in Biostatistics!
Title: Reconsideration of the Kaplan-Meier Estimator: Censoring and Time-varying Covariates

Content

Speaker:

Professor Rebecca Betensky, Chair of the Department of Biostatistics, School of Global Public Health at New York University

Abstract:

In this talk I will present two extensions of the Kaplan-Meier estimator that address a nuance of censoring and incorporation of time-varying covariates. Clinical studies with time to event endpoints typically report the median follow-up (i.e., censoring) time for the subjects in the trial, alongside the median time to event.  The reason for this is to provide information about the opportunity for subjects in the study to experience the event of interest.  In most clinical studies, the censoring time is a composite measure, defined as the minimum of the time to drop-out from the study and time to the administrative end of study.  The time to drop-out component may or may not be observed, while the time to the end of study is observed for each subject. I consider whether this decomposition of the censoring time into a time that is itself potentially censored and a time that is fully observed offers any improvement of the estimation of the censoring distribution.

Extensions of the Kaplan-Meier estimator have been developed to illustrate the relationship between a time-varying covariate of interest and survival, however they are limited to displaying survival for patients who always have a certain value of a time-varying covariate.  I present extensions of these estimators that provide crude and covariate-adjusted estimates of the survival function for patients defined by covariate paths. 

Zoom Link: https://ki-se.zoom.us/j/65377392771

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

If you have any questions, please contact Erin Gabriel.

Contact

Event type
Lectures and seminars
Sfo Epi Seminar in Biostatistics: Using EHR to Extend Understanding of Treatment Effectiveness Beyond Clinical Trials

10-05-2021 3:30 pm Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/65923678214
Lead

Welcome to attend the SfoEpi Seminar Series in Biostatistics!
Title: Using EHR to Extend Understanding of Treatment Effectiveness Beyond Clinical Trials

Content

Speakers:

Professor Rebecca Hubbard PhD, Division of Biostatistics, Perelman School of Medicine, University of Pennsylvania and

Dr. Ronac Mamtani MD, Assistant Professor, Division of Hematology/Oncology, Abramson Cancer Center, Perelman School of Medicine, University of Pennsylvania 

Abstract:

Randomized clinical trials (RCTs) are considered the gold standard for evaluating efficacy of novel treatments but suffer from limitations. Some treatments cannot be ethically or feasibly allocated via random assignment. Moreover, vulnerable populations are under-represented in RCTs, raising concerns about equity and the external validity of results. Clinical trial treatment settings may not reflect care and outcomes as they are experienced in routine practice. Real-world data (RWD) sources, including electronic health records (EHR), have the potential to address many of these concerns. However, limitations of RWD necessitate careful attention to study design and application of appropriate statistical methods. In this talk, we will discuss sources of RWD, their strengths and limitations, and their potential to supplement RCT evidence on treatment efficacy. We present two novel statistical developments aimed at extending evidence on treatment efficacy beyond clinical trials: (1) a method for addressing data quality issues in EHR data to obtain valid treatment effectiveness estimates in the presence of differential outcome misclassification without requiring specification of the measurement error models and (2) an approach to combining clinical trial and EHR-derived effectiveness estimates. The overarching objective of this presentation is to introduce data sources, study design considerations, and statistical challenges arising in the analysis of RWD. Through judicious application of these methods RWD have the potential to aid clinical decision making through the creation of evidence on treatment effectiveness that would not be possible using RCTs alone.

Zoom Link: https://ki-se.zoom.us/j/65923678214

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

If you have any questions, please contact Erin Gabriel.

Contact

Event type
Lectures and seminars
SFOepi Seminar in Biostatistics: New Approaches for Inference on Optimal Treatment Regimes

16-04-2021 3:00 pm Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/65431068521
Lead

Welcome to attend the SFOepi Seminar Series in Biostatistics!
Title: New Approaches for Inference on Optimal Treatment Regimes

Content

Speaker: Professor Lan Wang, Department of Management Science, University of Miami

Abstract: 

Finding the optimal treatment regime (or a series of sequential treatment regimes)based on individual characteristics has important applications in precision medicine. We propose two new approaches to quantify uncertainty in optimal treatment regime estimation. First, we consider inference in the model-free setting, which does not require to specify an outcome regression model. Existing model-free estimators for optimal treatment regimes are usually not suitable for the purpose of inference, because they either have nonstandard asymptotic distributions or do not necessarily guarantee consistent estimation of the parameter indexing the Bayes rule due to the use of surrogate loss. We study a smoothed robust estimator that directly targets the parameter corresponding to the Bayes decision rule for optimal treatment regimes estimation. We verify that a resampling procedure provides asymptotically accurate inference for both the parameter indexing the optimal treatment regime and the optimal value function. Next, we consider the high-dimensional setting and propose a semiparametric model-assisted approach for simultaneous inference. Simulations results and real data examples are used for illustration.

Zoom Link: https://ki-se.zoom.us/j/65431068521

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

If you have any questions, please contact Erin Gabriel.

Contact

Event type
Lectures and seminars
Sfo Epi Seminar in Biostatistics: Marginalized Frailty-Based Illness-Death Model: Application to the UK-Biobank Survival Data

19-03-2021 11:00 am Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/61853985168
Lead

Welcome to attend the SfoEpi Seminar Series in Biostatistics!
Title: Marginalized Frailty-Based Illness-Death Model: Application to the UK-Biobank Survival Data

Content

Speaker: Professor Malka Gorfine, Department of Statistics at Tel Aviv University, Israel

Abstract: The UK Biobank is a large-scale health resource comprising genetic, environmental, and medical information on approximately 500,000 volunteer participants in the United Kingdom, recruited at ages 40–69 during the years 2006–2010. The project monitors the health and well-being of its participants. This work demonstrates how these data can be used to yield the building blocks for an interpretable risk-prediction model, in a semiparametric fashion, based on known genetic and environmental risk factors of various chronic diseases, such as colorectal cancer. An illness-death model is adopted, which inherently is a semi-competing risks model, since death can censor the disease, but not vice versa. Using a shared-frailty approach to account for the dependence between time to disease diagnosis and time to death, we provide a new illness-death model that assumes Cox models for the marginal hazard functions. The recruitment procedure used in this study introduces delayed entry to the data. An additional challenge arising from the recruitment procedure is that information coming from both prevalent and incident cases must be aggregated. Lastly, we do not observe any deaths prior to the minimal recruitment age, 40. In this work, we provide an estimation procedure for our new illness-death model that overcomes all the above challenges. This talk will cover the work recently published online at JASA https://doi.org/10.1080/01621459.2020.1831922.

Zoom Link: https://ki-se.zoom.us/j/61853985168

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

If you have any questions, please contact Erin Gabriel.

Contact

Event type
Lectures and seminars
Sfo Epi Seminar in Biostatistics: Panel on Artificial Intelligence in Epidemiology

12-02-2021 3:00 pm Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/61164688056
Lead

Welcome to attend the SfoEpi Seminar Series in Biostatistics!
Title: Panel on Artificial Intelligence in Epidemiology

Content

Panelists

Dr. Mattias Rantalainen, Senior Lecturer of Epidemiology at the Department of Medical Epidemiology Karolinska Institutet.

Dr. Sema Sgaier, Co-Founder and Executive Director of Surgo Foundation, Adjunct Assistant Professor of Global Health, Harvard T.H. Chan School of Public Health, and  Adjunct Assistant Professor of Global Health University of Washington. 

Dr. Andrea Ganna, FIMM-EMBL group leader, Institute for Molecular Medicine, University of Helsinki, Finland and Instructor, Harvard Medical School.

Dr. Christian Guttman, Vice president, global head of Artificial Intelligence and Chief Artificial Intelligence and Data officer at TietoEVRY, adjunct associate professor at the University of New South Wales, Australia, and Adjunct researcher at Department of Learning, Informatics, Management, and Ethics and the Karolinska Institutet.

Chair

Dr. Elizabeth Arkema, Clinical Epidemiology Unit, Department of Medicine, Karolinska Institutet.

Zoom Link: https://ki-se.zoom.us/j/61164688056

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

If you have any questions, please contact Erin Gabriel.

Contact

Published: 2021-02-01 16:22 | Updated: 2021-02-01 16:22

President of National Health Research Institutes of Taiwan Speaks About Importance of Biostatistics

Portrait of Dr Kung-Lee Liang, President at the National Health Research Institutes of Taiwan
Dr Kung-Lee Liang, President at the National Health Research Institutes of Taiwan Photo: National Health Research Institutes

Dr Kung-Lee Liang, a pioneer in the field of biostatistics, gave a webinar via zoom with more than 100 attendees, including the President of KI, Ole Petter Ottersen. Dr. Liang spoke about how biostatistics contributed to medical science in the 20th century, and how we can rise to meet the current and future challenges in public health.

On Friday, January 29, 2021 at 9 local time, Dr Kung-Lee Liang virtually visited Karolinska Institutet to give a seminar about his views on the impacts of biostatistics on advancing human health in the 20th century and beyond. Dr Liang was scheduled to visit KI in person earlier this spring to speak at the Sfo Epi-Biostat Expo, which was cancelled due to the ongoing coronavirus pandemic. Instead, he joined our community via Zoom, welcomed by the panelists Dr Erin Gabriel, Professors Juni Palmgren, Paul Dickman, Rachel Fisher, and KI’s President, Ole Petter Ottersen. Dr Gabriel organized and hosted the seminar, with generous financial support from the Strategic Research Area in Epidemiology and Biostatistics.

Dr Liang is the current president of the National Health Research Institutes of Taiwan, which serves the dual role of monitoring and conducting research on human health. Recently, Dr Liang was appointed by Taiwan’s federal government to lead a research and development group focused on finding COVID-19 vaccines, treatments and diagnostics. He is a biostatistician who earned his doctorate in biostatistics from the University of Washington, and was a professor of biostatistics at Johns Hopkins University for over 20 years.

After a welcome and introduction from President Ottersen and Professor Palmgren, Dr Liang described the birth and history of biostatistics at academic departments in the United States. The first biostatistics department in the world was founded in 1918 at Johns Hopkins University, where Dr Liang was later a professor. He went on to define the field of biostatistics as the combination of principles of statistical reasoning and methods for data analysis. Together, these enable us to use data to create knowledge and make sound scientific conclusions.

Health risks of smoking

As a running example, Dr Liang spoke about the health risks of smoking. While the risks of smoking are well known today, in the 1950s and 1960s there was a vigorous debate on the issue. Two giants of statistics at the time clashed, with RA Fisher on one side claiming that the observed association between smoking and lung cancer was due to unmeasured genetic factors. On the other side, WG Cochran used sound statistical and causal reasoning to explain that the genetic component would have to be so large as to be implausible.

The debate continued with biostatisticians serving key roles in the national committees who reviewed the thousands of scientific articles on smoking, and more or less ended with the 1964 Surgeon General Report on the deleterious health consequences of tobacco use. The subsequent policies on advertising and sales of tobacco, and the increase in public awareness led to a continual decline in the smoking rate and therefore decrease in death and morbidity due to smoking. Dr Liang highlighted this as the sort of profound impact that biostatistician can have on human health, despite not often directly treating individual patients.

Future challenges

Dr Liang gave several more examples of scientific challenges and the biostatistical methods designed to solve them, including survival analysis, and longitudinal data analysis. He closed with discussion of some future challenges in science, and how biostatisticians can step up to meet them. The key recommendations are for biostatisticians to be more engaging with collaborators and the public, and to invest in the training of young and energetic researchers. The panelists discussed the future of biostatistics at Karolinska Institutet, and President Ottersen stated that “biostatistics really is the backbone of medical research.”

About Kung-Lee Liang

Kung-Yee Liang is the current President of the National Health Research Institutes of Taiwan (NHRI) and Professor of Biostatistics at Johns Hopkins University. Liang has served as the Vice President, NHRI, Taiwan from July, 2003 to August, 2006 and was the Acting President for six months beginning in January, 2006. In August, 2010, Liang became the sixth President of the National Yang-Ming University, the first medical university in Taiwan. In December, 2017, Liang stepped down from the post to become the sixth President of NHRI and his primary appointment is with the Institute of Population Health Science which focuses on clinical and public health research to build healthier communities. Today, Dr Liang leads a research and development group focused on finding COVID-19 vaccines, treatments and diagnostics. 

He is well-known from a pair of papers in 1986 (Liang & Zeger Biometrika, Zeger & Liang Biometrics) in which he developed the theory and methods for generalized linear models for longitudinal data, now commonly known as GEE (generalized estimating equations). He has spent his career collaborating with researchers in a variety of fields, and making pioneering contributions in biostatistical methods. His brilliance and dedication has been recognized widely, including the Snedecor Award in 1987, the Spiegelman Award in 1990, the Rema Lapouse Award by the American Public Health Association in 2010 for significant contributions to the scientific understanding of the epidemiology and control of mental disorders, the Karl Pearson Prize in 2015, and most recently, one of the 50 alumni from the University of Washington School of Public Health recognized as changemakers.

Event type
Lectures and seminars
Sfo Epi Seminar in Biostatistics: Professor Sonia Hernández-Díaz

05-02-2021 3:00 pm Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/69658391166
Lead

Welcome to attend the SfoEpi Seminar Series in Biostatistics!
Title: Target Trial Emulation to Study the Effects of Treatments and Vaccines During Pregnancy
Speaker: Sonia Hernández-Díaz, Professor of Epidemiology, Department of Epidemiology Harvard T.C. Chan school of public health

Content

Zoom Link: https://ki-se.zoom.us/j/69658391166

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

Abstract

Questions on the comparative effectiveness or safety of treatments and vaccines during pregnancy are often answered using observational data. Causal inference from observational data can be conceptualized as an attempt to emulate a hypothetical pragmatic randomized trial: the target trial.  In this seminar, I will propose a protocol framework that makes the target trial explicit. Emulating a trial forces the investigators to specify the causal question, the study population and eligibility criteria, the exposure and reference groups, and the start and end of follow-up. In addition, investigators must consider which assumptions are necessary for specific analyses. I will discuss how this process itself can be enlightening and can help describe and avoid biases including confounding, immortal person-time bias, and prevalent user bias. I will present applications to different causal questions in the setting of treatment decisions before, early, and late in pregnancy that emphasize specific protocol components, challenges, and solutions.

If you have any questions, please contact Erin Gabriel.

Contact

Event type
Lectures and seminars
Sfo Epi Seminar in Biostatistics: Professor Kung-Yee Liang

29-01-2021 9:00 am Add to iCal
Campus Solna
Location
https://ki-se.zoom.us/j/65152688563
Lead

Welcome to attend the SfoEpi Seminar Series in Biostatistics!
Title: Impacts of biostatistics on advancing human health in the 20th century and beyond: My personal view
Speaker: President Kung-Yee Liang, Institute of Population Health Sciences, National Health Research Institutes, Taiwan, R.O.C. and Professor of Biostatistics, Johns Hopkins University, Department of Biostatistics

Content

Zoom Link: https://ki-se.zoom.us/j/65152688563

*Webinar format: unless you are on the panel you will be muted and with no video. Participants can raise their hands during the Q&A to be recognized to ask questions.

Abstract

In this talk, I will discuss in what way the field of biostatistics has impacted human health in the 20th century. Focus will be on chronic diseases including cancers, diabetes, which has drawn a great deal of attentions among the health community in the 1940’s.  Specifically, we discuss three major statistical challenges pertained to dealing with chronic diseases: (1) Assessing efficacy of new treatments, (2) Identifying risk factors for prevention and (3) Utilizing biomarkers for pre- and post-designs. I will end the talk with what I perceive important challenges for the scientific and biostatistical communities in the near future.  

If you have any questions, please contact Erin Gabriel.

Contact

Subscribe to SfoEpi (eng)