A further look into the PLCO data with open questions on PSA, active surveillance, and risk factors in prostate cancer
Most prostate cancer remains asymptomatic and most patients with low-grade early-stage prostate cancer do not eventually die of prostate cancer. Active surveillance becomes a common option other than aggressive treatments like the radical prostatectomy or radiation therapy. These patients will be closely followed up with PSA and repeated biopsies. Only 18% of this patient population will die of prostate cancer. How to stratify this patient population and screen relatively high-risk patients becomes highly clinically-relevant.
In recent years, more patients have been diagnosed with prostate cancer before the age of 55. Data have shown that these patients are more likely to die of prostate cancer, compared to patients diagnosed with prostate cancer after the age of 55. It is possible that prostate cancer in these young patients is more aggressive than usual. However, the underlying molecular mechanism and risk factors remain unknown.
With these considerations and questions, we are interested in accessing the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial (PLCO) datasets – data only (no images or biospecimens). We would like to use statistical methods and machine learning techniques to further study these cancer screening data.
We hope to get more insights to the above-mentioned open questions in the following aspects, which will bring high clinical-relevant impacts in the prostate cancer field.
1. Will PSA screening help to improve the actual overall survival of prostate cancer patients?
2. What are the risk factors for prostate cancer patients under active surveillance?
3. What are the risk factors associated with mortality among prostate cancer patients?
Zhiming Yang, MidLantic Urology
Alexander B. Chen, Conestoga High School
Jefferey Wang, Conestoga High School