Research Assistant in Biostatistics: Focus on Clinical Accuracy of AI models for breast cancer radiology

Do you want to contribute to top quality medical research?

Artificial intelligence (AI) will change the daily work of doctors, make diagnoses more accurate and treatment choices more likely to succeed. Our group has curated a large dataset of hundreds of thousands of mammograms, thousands of ultrasound images and MRI exams, linked to clinical outcome data and radiologist image labels. We have collaborations with several medical AI companies and academic research groups whose AI models we evaluate.

Do you have a recent Master's degree in Epidemiology, Medicine, Biomedical Science, Biostatistics, Bioinformatics or similar field? Have you written a thesis or have other experience related to evaluating clinical tests for any disease?

Our group

Our goal, related to this position, is to facilitate a safe and optimized introduction of established AI models in breast imaging and breast cancer care. Our research group is part of the Department of Oncology and Pathology at Karolinska Institutet, and the research leader Fredrik Strand is a breast radiologist at Karolinska University Hospital.

We have internationally well-established research in developing and evaluating AI for radiological breast cancer diagnosis. Our group has expertise in radiology, biostatistics and machine learning. In addition, we have a strong collaboration with research groups at KTH, the Royal Institute of Technology, the University of California San Francisco and Berkeley.

We are now looking for our biostatistical research assistant focused on assessing the clinical validity of AI models for radiological diagnostics and simulating the potential clinical impact. Clinical validity analysis includes estimating the common metrics of sensitivity, specificity, false positive rates, false negative rates. Clinical impact simulation includes taking alternative combinations between AI and radiologists into account, to assess how the diagnoses could have been made earlier or more accurately.

Your mission

Your major duty will be part of the Swedish cross-institutional VAIB (Validation of AI for Breast imaging) team, responsible for conducting and developing biostatistical evaluations and simulations of the clinical use of AI models for breast cancer detection and diagnosis. You will work with Swedish hospitals and international AI companies. In addition, you will be involved in the EUCAIM (European federation for Cancer IMaging) project where we aim to contribute data and validation and simulation methods.  You are expected to be part of writing research papers, and to produce written test reports for the parties providing the AI models.

Your profile

Qualifications

In your personal letter, please specify what concretely in your history support that you meet, and excel in, each of the qualifications listed below.

You must have:

• a university-level Master's degree in Epidemiology, Medicine, Biostatistics, Bioinformatics, Biomedical Science or similar field
• knowledge about evaluating medical diagnostic tests, and how to calculate common metrics
• coding skills in R
• coding skills in Python (or willingness to learn)
• excellent communication skills in English
  
  

It is a merit if:

• you have experience from evaluating disease screening tests
• you have experience from working with statistical analysis based on radiology or pathology reports and images
• understanding of the the clinical workflow for cancer patients and the preceding screening of cancer
• you have experience from interacting with non-sql databases, especially MongoDB
• you have experience from automating statistical reporting

What do we offer?

A creative and inspiring environment with wide-ranging expertise and interests. Karolinska Institutet is one of the world's leading medical universities. Our vision is to pursue the development of knowledge about life and to promote a better health for all. At Karolinska Institutet, we conduct successful medical research and hold the largest range of medical education in Sweden. Karolinska Institutet is also a state university, which entitles you to several good benefits through our collective agreement. And you get to practice freely in our modern wellness facilities, where trained staff are on site.

Location: Solna

Choose to work at KI – Ten reasons why

Application

Welcome to apply at the latest 11^th January. 

The application is to be submitted through the Varbi recruitment system.In this recruitment, you will apply with your CV without a personal letter. Instead, you will answer some questions about why you are applying for the job in the application form. 

Duration is approximately 12 months, with possibility of extension.

Want to make a difference? Join us and contribute to better health for all