RESUMEN
Rationale and objectives: The study aims to propose an optimal workflow in patients with a PI-RADS 3 (PR-3) assessment category (AC) through determining the timing and type of pathology interrogation used for the detection of clinically significant prostate cancer (csPCa) in these men based upon a 5-year retrospective review in a large academic medical center. Materials and methods: This United States Health Insurance Probability and Accountability Act (HIPAA)-compliant, institutional review board-approved retrospective study included men without prior csPCa diagnosis who received PR-3 AC on magnetic resonance (MR) imaging (MRI). Subsequent incidence and time to csPCa diagnosis and number/type of prostate interventions was recorded. Categorical data were compared using Fisher's exact test and continuous data using ANOVA omnibus F-test. Results: Our cohort of 3238 men identified 332 who received PR-3 as their highest AC on MRI, 240 (72.3%) of whom had pathology follow-up within 5 years. csPCa was detected in 76/240 (32%) and non-csPCa in 109/240 (45%) within 9.0 ± 10.6 months. Using a non-targeted trans-rectal ultrasound biopsy as the initial approach (n = 55), another diagnostic procedure was required to diagnose csPCa in 42/55 (76.4%) of men, compared with 3/21(14.3%) men with an initial MR targeted-biopsy approach (n = 21); (p < 0.0001). Those with csPCa had higher median serum prostate-specific antigen (PSA) and PSA density, and lower median prostate volume (p < 0.003) compared with non-csPCa/no PCa. Conclusion: Most patients with PR-3 AC underwent prostate pathology exams within 5 years, 32% of whom were found to have csPCa within 1 year of MRI, most often with a higher PSA density and a prior non-csPCa diagnosis. Addition of a targeted biopsy approach initially reduced the need for a second biopsy to reach a for csPCa diagnosis. Thus, a combination of systematic and targeted biopsy is advised in men with PR-3 and a co-existing abnormal PSA and PSA density.
RESUMEN
OBJECTIVE: This work aims to provide a review of the existing literature in the field of automated machine learning (AutoML) to help healthcare professionals better utilize machine learning models "off-the-shelf" with limited data science expertise. We also identify the potential opportunities and barriers to using AutoML in healthcare, as well as existing applications of AutoML in healthcare. METHODS: Published papers, accompanied with code, describing work in the field of AutoML from both a computer science perspective or a biomedical informatics perspective were reviewed. We also provide a short summary of a series of AutoML challenges hosted by ChaLearn. RESULTS: A review of 101 papers in the field of AutoML revealed that these automated techniques can match or improve upon expert human performance in certain machine learning tasks, often in a shorter amount of time. The main limitation of AutoML at this point is the ability to get these systems to work efficiently on a large scale, i.e. beyond small- and medium-size retrospective datasets. DISCUSSION: The utilization of machine learning techniques has the demonstrated potential to improve health outcomes, cut healthcare costs, and advance clinical research. However, most hospitals are not currently deploying machine learning solutions. One reason for this is that health care professionals often lack the machine learning expertise that is necessary to build a successful model, deploy it in production, and integrate it with the clinical workflow. In order to make machine learning techniques easier to apply and to reduce the demand for human experts, automated machine learning (AutoML) has emerged as a growing field that seeks to automatically select, compose, and parametrize machine learning models, so as to achieve optimal performance on a given task and/or dataset. CONCLUSION: While there have already been some use cases of AutoML in the healthcare field, more work needs to be done in order for there to be widespread adoption of AutoML in healthcare.
