Initial Validation of a Machine Learning-Derived Prognostic Test (KidneyIntelX) Integrating Biomarkers and Electronic Health Record Data To Predict Longitudinal Kidney Outcomes

BackgroundIndividuals with type 2 diabetes (T2D) or the apolipoprotein L1 high-risk (APOL1-HR) genotypes are at increased risk of rapid kidney function decline (RKFD) and kidney failure. We hypothesized that a prognostic test using machine learning integrating blood biomarkers and longitudinal electronic health record (EHR) data would improve risk stratification.MethodsWe selected two cohorts from the Mount Sinai BioMe Biobank: T2D (n=871) and African ancestry with APOL1-HR (n=498). We measured plasma tumor necrosis factor receptors (TNFR) 1 and 2 and kidney injury molecule-1 (KIM-1) and used random forest algorithms to integrate biomarker and EHR data to generate a risk score for a composite outcome: RKFD (eGFR decline of ≥5 ml/min per year), or 40% sustained eGFR decline, or kidney failure. We compared performance to a validated clinical model and applied thresholds to assess the utility of the prognostic test (KidneyIntelX) to accurately stratify patients into risk categories.ResultsOverall, 23% of those with T2D and 18% of those with APOL1-HR experienced the composite kidney end point over a median follow-up of 4.6 and 5.9 years, respectively. The area under the receiver operator characteristic curve (AUC) of KidneyIntelX was 0.77 (95% CI, 0.75 to 0.79) in T2D, and 0.80 (95% CI, 0.77 to 0.83) in APOL1-HR, outperforming the clinical models (AUC, 0.66 [95% CI, 0.65 to 0.67] and 0.72 [95% CI, 0.71 to 0.73], respectively; P<0.001). The positive predictive values for KidneyIntelX were 62% and 62% versus 46% and 39% for the clinical models (P<0.01) in high-risk (top 15%) stratum for T2D and APOL1-HR, respectively. The negative predictive values for KidneyIntelX were 92% in T2D and 96% for APOL1-HR versus 85% and 93% for the clinical model, respectively (P=0.76 and 0.93, respectively), in low-risk stratum (bottom 50%).ConclusionsIn patients with T2D or APOL1-HR, a prognostic test (KidneyIntelX) integrating biomarker levels with longitudinal EHR data significantly improved prediction of a composite kidney end point of RKFD, 40% decline in eGFR, or kidney failure over validated clinical models.

CanAssist breast: An affordable breast cancer prognostic test validated on Asian patients.

541 Background: Treatment decisions for early stage HR+/HER2neu- breast cancer patients in the West routinely depend on prognostic tests that predict risk of recurrence. However, such tests are rarely used in Asia due to prohibitive costs and lack of validation data on Asian patients. Chemotherapy is thus often a default treatment leading to physiological and financial toxicity. To address these, we have developed CanAssist Breast (CAB) as an affordable IHC-based prognostic test, retrospectively validated on ~1400 patients, 63% South Asians and rest Caucasians. To date CAB has been prescribed by 180+ doctors across 30 cities in India for ~600 patients in clinics, enabling personalized treatment decisions. Methods: Primary surgical FFPE blocks and clinical follow-up data were obtained from hospitals. GraphPad Prism and MedCalc were respectively used for Kaplan-Meier survival analyses and Cox logistic regression to calculate hazard ratios. Results: The median age of diagnosis in the validation cohort was 56 years, 63% patients with stage II disease and 60% node negative tumors. Distant Metastasis Free Survival (DMFS) in the low-risk category of the validation cohort was 95%, and 84% in high-risk (P < 0.0001). Similar results were obtained with the Caucasian subgroup, as also with the chemotherapy-naive subgroup (30% of the cohort), demonstrating that risk stratification by CAB is unaffected by race or chemotherapy. Next, the performance of CAB was compared with Oncotype DX (ODX). 83% patients stratified as low risk by ODX (RS 0-25) in a sub-cohort of 109 were also stratified as low-risk by CAB. To assess the impact of CAB in treatment decision making, we assessed the data of 589 patients who have undergone CAB testing so far, 288 were identified as low-risk. 93% of these CAB low-risk patients were not given chemotherapy, demonstrating the clinical impact of CAB. Conclusions: CAB is the first test of its kind to be retrospectively validated in Asia. It shows high concordance with ODX in risk stratification of patients. CAB has been in clinical practice in India and near-India markets for 2 years and is helping clinicians and patients in making affordable treatment decisions.