Phase I Human Analytics (HALO) Study

Discover, optimize, standardize, and validate clinical-trial measures and biomarkers used to diagnose and differentiate cardiovascular, oncologic, neurologic, and other diseases and disorders. Specifically, our research study endeavors to improve disease and disorder diagnosis to the earliest clinical states, in preclinical states, and to develop ensemble multivariate biomarker risk scores leading to cardiovascular, oncologic, neurologic, and other diseases and disorders. Additionally, the study aims to: * Evaluate data analysis techniques to improve diagnostic accuracy and reduce time to diagnosis. * Evaluate data analysis techniques to improve risk stratification for participants through machine learning algorithms. * Direct participants to relevant and applicable clinical trials.

Sex

Male

Minimum age

45 Years

Maximum age

90 Years

Inclusion Criteria:

Treatment Naïve patients:

* Male, 45 years of age or older.
* Diagnosis of prostate adenocarcinoma.
* Clinical stage T1c or T2a.
* Gleason score of 7 (3+4 or 4+3) or less.
* Three or fewer biopsy cores with prostate cancer.
* PSA density not exceeding 0.375.
* One, two, or three tumor suspicious regions identified on multiparametric MRI.
* Negative radiographic indication of extra-capsular extent.
* Karnofsky performance status of at least 70.
* Estimated survival of 5 years or greater, as determined by treating physician.
* Tolerance for anesthesia/sedation.
* Ability to give informed consent.
* At least 6 weeks since any previous prostate biopsy.
* MR-guided biopsy confirmation of one or more MRI-visible prostate lesion(s) with Gleason score of 7 (3+4 or 4+3) or less.

Salvage candidates will be accepted upon physician referral.

Exclusion Criteria:

* Presence of any condition (e.g., metal implant, shrapnel) not compatible with MRI.
* Severe lower urinary tract symptoms as measured by an International Prostate Symptom Score (IPSS) of 20 or greater
* History of other primary non-skin malignancy within previous three years.
* Diabetes
* Smoker

• BACKGROUNDWeng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS One. 2017 Apr 4;12(4):e0174944. doi: 10.1371/journal.pone.0174944. eCollection 2017. PMID 28376093
• BACKGROUNDWang X, Oldani MJ, Zhao X, Huang X, Qian D. A review of cancer risk prediction models with genetic variants. Cancer Inform. 2014 Sep 21;13(Suppl 2):19-28. doi: 10.4137/CIN.S13788. eCollection 2014. PMID 25288876