Phastar's Statistics Manager, Stephen Corson, wins prestigious DIA Award

Phastar's Statistics Manager, Stephen Corson, has been chosen by the Board of Directors and the Fellows of DIA to receive the DIA 2023 Global Inspire Award for Community Engagement. This prestigious award recognises the outstanding contribution of the DIA Community Chairs who consistently drive engagement and promote knowledge sharing, while advancing thought leadership within the membership community.

Stephen has been part of the DIA’s Statistics and Data Science Community, presenting at the DIA Global Annual Meetings for the past three years and sharing his vast knowledge of statistics. He will be delivering a half-day virtual workshop on 14th June from 13:00 – 16:00 and presenting at the upcoming DIA Annual Conference in Boston on 29th June from 8:30 – 9:30 track 11 statistics, providing a deeper understanding of the interpretation of common statistical terminology and knowledge to have effective discussions with statistical colleagues. Find out more about Stephen's presentation here.

This award is a testament to Stephen’s commitment to DIA’s mission, their stakeholders, and the patients they serve. Stephen will be presented with the award at the DIA Annual Conference on the evening of June 26th, 2023. Congratulations, Stephen!

Data science collaboration with Ishango.ai - part two

Click here to read part one 

Phastar embarked on a collaboration project with Ishango.ai to work on a data science project to automate the medical coding process for adverse events using machine learning approaches.

In clinical trials adverse events are coded using the MedDRA coding dictionary to standardize and allow consistent interpretation of results. There are five MedDRA classifications that each verbatim term (the term reported during the trial) needs to be mapped. Even with the aid of auto-coders this is a manual and time-consuming process that is prone to human error. The recent wider adoption of machine learning within clinical trials has led to the semi-automation of certain tasks to increase efficiency in the clinical trial process. The focus of this project was the verbatim mapping to the Lowest Level Term (LLT) in the MedDRA hierarchy.

The goal of the 8-week project was to ascertain if the auto-coding process could be improved with the application of Natural Language Processing (NLP) to the verbatim terms that would suggest a list of the most appropriate LLT for the verbatim term with a confidence interval for adjudication by the data manager.

Continue Reading

Season's greetings from Phastar's SAS Art competition winners!

Season's greetings from PHASTAR

Each year Phastar holds an internal competition among its programmers to create a work of festive art, using only their imagination and SAS software!

With so many exciting entries this year, our panel of judges was unable to choose a single winner, and decided to pick two winners instead! 

Take a look at our 2022 winners, and scroll down to reveal the SAS code if you'd like to try something similar yourself!

Continue Reading

Data science collaboration with Ishango.ai - part one

PHASTAR recently embarked on a collaboration with Ishango.ai to host two aspiring data scientists to work on an innovative data science project. Ishango is a social enterprise that provides graduates from Africa the opportunity to gain the specialized skills required to work within the data science industry through fellowships with global companies.

This was a great opportunity for the fellows to gain experience within the CRO world, but also for experts from within PHASTAR to gain input and insight from a different perspective.

After providing the project brief to Ishango, PHASTAR were introduced to candidate fellows and were able to discuss the project concept and high level expectations. From the start, the fellows were engaged and enthusiastic about the project and keen to get started.

Continue Reading

Smart signal detection - Part two

Image of a woman typing on a keyboard

In a previous blog post, we described how, as part of the Centre for Analytical Excellence, PHASTAR delivered a project looking at detecting signals from historical clinical trial data and developing models to enable predictions of signals from new trials. Over a 3-month period, experts from within PHASTAR were provided with a large amount of historical clinical trial data to digest, generate signals and create predictive models from.

The team explored different machine learning methods and demonstrated good performance at predicting an efficacy signal based on baseline data.

Continue Reading