Center for Advanced Diagnostic Research (CADRe)

Research Projects

3D medical illustration of a cross-sectioned kidney with a digital technology background

CADRe supports research projects across the diagnostic spectrum by designing and conducting clinical translational research studies designed to bring new tools and technology into the clinic more rapidly. Explore some examples of active research projects supported by the center.

Tailored Screening for Urinary System Cancers in Patients with Chronic Kidney Disease 

Principal Investigator: Stella Kang, MD, MS 

Chronic kidney disease is a highly prevalent condition, found in 20% of people aged 50 years and older. While it is well known that chronic kidney disease is strongly associated with cardiovascular mortality, recent work has also demonstrated an association with cancers of the urinary system. The lack of clear cancer screening recommendations represents an important gap in chronic kidney disease practice guidelines and may be due to the complex weighing of benefits and harms for a population with wide-ranging health status. For example, middle-aged adults without other significant cardiovascular comorbidities and multiple established risk factors may warrant more intensive screening, whereas patients with cardiovascular disease and few risk factors may warrant less intensive screening. In addition, Black men and women with chronic kidney disease have been shown repeatedly to suffer higher all-cause and cancer-specific mortality compared to non-Black patients, an important consideration in forming screening recommendations. 

Here, we bring together experts in decision science, epidemiology, urologic oncology, nephrology, radiology, and internal medicine to assess the potential of screening strategies for patients with chronic kidney disease. We previously developed a computer simulation model of kidney tumors and comorbidities, capable of simulating outcomes of subpopulations defined by chronic kidney disease severity and kidney tumor natural history. We are transforming the model to incorporate bladder cancer natural history as well as kidney and bladder screening pathways.  

Our goal is to assess whether cancer screening pathways benefit life expectancy and quality-adjusted life expectancy based on age, kidney disease stage, co-existing risk factors, and comorbidity burden. Cost-effectiveness will also be explored for key factors that affect or elevate the value of screening. We aim to establish the context in which urinary tract screening recommendations could benefit the large population with chronic kidney disease. 

Publications 

Oral Cavity Cancer Precision Imaging 

Principal Investigator: Stella Kang, MD, MS 

Oral cancers and precancers are currently under-detected at an early stage, leading to costly and disfiguring therapy as well as poor overall outcomes for patients with oral cancer. Screening with conventional visual-tactile examination is limited in accuracy, and standard practice entails referral and scalpel biopsy of most potentially malignant oral lesions. Detractors of oral screening cite the high prevalence of benign oral lesions and mild dysplasia as circumstances placing patients at risk of harm from over-testing and over-treatment. 

Computer vision-assisted precision imaging tests have recently shown strong diagnostic performance for oral lesion characterization, but their potential pitfalls and promises must be thoroughly investigated before clinical application. Similarly, machine learning could bolster optical tests for visualizing potentially malignant lesions. If successful, these artificial intelligence devices could aid decision-making, preventing unnecessary scalpel biopsies for low-risk lesions and enabling risk-stratified surveillance or treatment.   

In this project, our team of experts in computer disease simulation modeling, machine learning, oral medicine, and economic evaluation is transforming a disease simulation model to provide analysis at the point of care and evaluate the different potential uses of precision imaging diagnostics for translation to clinical care. We are expanding our existing disease model of potentially malignant oral lesions to represent lesion characteristics and clinical risk categories (e.g., based on tobacco and alcohol use) through incorporation of large longitudinal datasets in order to evaluate whether artificial intelligence-assisted cytologic testing can improve the effectiveness and cost-effectiveness of screening for low, moderate, or high-risk categories. Finally, we are evaluating whether adjuncts for lesion visualization render favorable effectiveness and cost-effectiveness of screening across risk categories, with or without artificial intelligence support, and developing a user interface for the model. This work will produce an analytic engine to guide clinical translation of artificial intelligence-aided diagnostics for oral lesion detection and characterization, to overcome insufficient screening reliability. 

Publications 

Decision Support and Risk Analysis for Management of Small Renal Tumors 

Principal Investigator: Stella Kang, MD, MS 

Kidney tumors are most often diagnosed at an early stage as incidental lesions on imaging tests performed for unrelated reasons. Most of these small renal masses are malignant, however only a small minority of tumors metastasize, and approximately 20% are benign. Despite earlier detection and aggressive treatment with surgical resection, the current treatment paradigm for small renal tumors (≤ 4 cm) has resulted in worsened overall survival. Less aggressive treatment alternatives must be more widely adopted into decision-making to prevent unnecessary surgeries in patients with indolent or benign tumors or risk factors for poor post-surgical outcomes.  

Here, we are constructing a decision-analytic model to determine the optimal management strategies for patients with small kidney tumors, incorporating small renal tumor histology and anatomy, and patient comorbidities (including renal function) in treatment selection. We are creating tools to communicate personalized harms and benefits of treatment options and promote shared decision-making. The result is an interactive decision aid to improve patients' knowledge of small renal tumors, communicate personalized harms and benefits, and elicit patient preferences in treatment selection. 

Publications 

Back to top