Skip to Main Content

An official website of the United States government

Improving diagnosis, treatment approach, and quality-of-life of patients with prostate cancer using A.I.

Principal Investigator
Name
Frank Sullivan
Degrees
M.B., M.R.C.P.I., F.F.R.R.C.S.I., M.Sc.,
Institution
Galway Clinic
Position Title
Professor, Director-Prostate Cancer Institute Galway, National Director-Prostate Brachytherapy(NCCP)
Email
About this CDAS Project
Study
PLCO (Learn more about this study)
Project ID
PLCO-842
Initial CDAS Request Approval
Oct 29, 2021
Title
Improving diagnosis, treatment approach, and quality-of-life of patients with prostate cancer using A.I.
Summary
Prostate cancer is the second leading cancer and the third leading cause of cancer death among men. 30 million men in Europe are confronted with a diagnosis of prostate cancer in their lifetime and each year 75,000 men die from prostate cancer. Prostate cancer patients have multiple treatment options, and treatment choices are influenced by for several factors, including tumor stage, patient’s age, and comorbidity. We wish to use the prostate cancer component of the PLCO dataset to leverage A.I in aiding diagnosis, selection of treatment approach, and improving quality-of-life. We aim to develop the machine learning models for pre-diagnosis, identification of best treatment for the patient, and post - diagnosis for prostate cancer patients. We have already checked the data dictionary of the PLCO dataset and have found that the important features which we need to train our Machine learning models.
Aims

- What is the probability for a patient to develop prostate cancer where a family member has a history of such cancer?
- Evaluating features, risk factors, and clinical tests on their importance for an early diagnosis of prostate cancer.
- Assessing the relationship between patient clinical history (i.e. other medical conditions), drug exposure, and its likelihood of developing prostate cancer.
- Patient profile based risk assessment and analysis to identify the best medical intervention for patients with prostate cancer. (Possibility for sub-therapies of Brachy)
- Stratification of patients into risk groups, and predicting the mortality rate and side-effects of patients based on treatment approach.
- Predicting the likelihood of biochemical recurrence after prostate cancer treatment and diagnosis for patients.
- Classifying the patients who need aggressive follow up after the prostate cancer treatment reduces the chance of relapse.
- Predicting the risk of prostate cancer mortality within 10 years after diagnosis.
- Predicting the probability of occurrence of 1) tumor, node, and metastasis (TNM) staging, 2) extracapsular extension, 3) seminal vesicle invasion, and 4) lymph node metastasis for the patient treated with Brachytherapy.

Collaborators

Dr. Vivek Mahato, Postgraduate Researcher | Data Scientist at I-Form DCU and WhyzeHealth