Scientific Research
As part of CapeStart’s work with the life science industry’s top innovators, we regularly co-author scientific research published in leading clinical journals and at industry conferences. This section shares those publications.
Treatment Patterns and Survival in Men with Metastatic Castration-Resistant Prostate Cancer (mCRPC): A Systematic Literature Review of 35 Real-World Observational Studies. (Research Sponsor: Bayer)
Treatment landscapes have changed dramatically in prostate cancer in the past decade. Therapies like androgen receptor pathways inhibitors (ARPIs), which were initially approved for mCRPC are now approved in the earlier disease spectrum, including biochemical recurrence (BCR), non-metastatic castration-resistant prostate cancer (nmCRPC), and hormone-sensitive metastatic prostate cancer (mHSPC).
Insights Into the Burden and Unmet Needs of Patients With Hereditary Angioedema: A Retrospective Social Media Listening Study (Research Sponsor: CSL Behring)
Hereditary angioedema (HAE) is a rare genetic disease characterized by recurrent, painful, unpredictable, and debilitating attacks of angioedema which are detrimental to patients’ quality of life. Understanding the experience of patients living with HAE and existing unmet medical needs is critical for HAE management optimization.
How Can Explainable Artificial Intelligence Accelerate the Systematic Literature Review Process? (Research Sponsor: Roche)
Systematic literature reviews (SLRs) are key evidence requirements for health technology agency decision-making. However, the exponential increase in published articles makes a thorough and practical literature review increasingly challenging. To help researchers conduct an SLR, we developed a machine learning (ML)-based pipeline to accelerate the title and abstract screening (TIABS) step. We assessed this ML-based TIABS using various human-labeled SLRs to ensure its reproducibility.
Training Models for Machine-Enabled Systematic Literature Reviews: Do Large Datasets Always Give Better Results? (Research Sponsor: Roche)
Artificial intelligence (AI) model fitting by supervised learning suggests that larger training datasets tend to produce more accurate predictions. This can be demonstrated by evaluating the final tuned model on a labeled test dataset. However, it is not clear what the minimum number of records is for training such models and whether larger training datasets will produce significantly better results. We investigated these issues using an example of randomized controlled trial data of oncology patients.