Dataset Information

Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease.

ABSTRACT:

Aim

Predicting progression in diabetic kidney disease (DKD) is critical to improving outcomes. We sought to develop/validate a machine-learned, prognostic risk score (KidneyIntelX™) combining electronic health records (EHR) and biomarkers.

Methods

This is an observational cohort study of patients with prevalent DKD/banked plasma from two EHR-linked biobanks. A random forest model was trained, and performance (AUC, positive and negative predictive values [PPV/NPV], and net reclassification index [NRI]) was compared with that of a clinical model and Kidney Disease: Improving Global Outcomes (KDIGO) categories for predicting a composite outcome of eGFR decline of ≥5 ml/min per year, ≥40% sustained decline, or kidney failure within 5 years.

Results

In 1146 patients, the median age was 63 years, 51% were female, the baseline eGFR was 54 ml min^-1 [1.73 m]^-2, the urine albumin to creatinine ratio (uACR) was 6.9 mg/mmol, follow-up was 4.3 years and 21% had the composite endpoint. On cross-validation in derivation (n = 686), KidneyIntelX had an AUC of 0.77 (95% CI 0.74, 0.79). In validation (n = 460), the AUC was 0.77 (95% CI 0.76, 0.79). By comparison, the AUC for the clinical model was 0.62 (95% CI 0.61, 0.63) in derivation and 0.61 (95% CI 0.60, 0.63) in validation. Using derivation cut-offs, KidneyIntelX stratified 46%, 37% and 17% of the validation cohort into low-, intermediate- and high-risk groups for the composite kidney endpoint, respectively. The PPV for progressive decline in kidney function in the high-risk group was 61% for KidneyIntelX vs 40% for the highest risk strata by KDIGO categorisation (p < 0.001). Only 10% of those scored as low risk by KidneyIntelX experienced progression (i.e., NPV of 90%). The NRI_event for the high-risk group was 41% (p < 0.05).

Conclusions

KidneyIntelX improved prediction of kidney outcomes over KDIGO and clinical models in individuals with early stages of DKD.

SUBMITTER: Chan L

PROVIDER: S-EPMC8187208 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background and objectivesOsmotic demyelination syndrome is the most concerning complication of severe hyponatremia, occurring with an overly rapid rate of serum sodium correction. There are limited clinical tools to aid in identifying individuals at high risk of overcorrection with severe hyponatremia.Design, setting, participants, & measurementsWe identified all patients who presented to a tertiary-care hospital emergency department in Ottawa, Canada (catchment area 1.2 million) between January 1, 2003 and December 31, 2015, with serum sodium (corrected for glucose levels) <116 mmol/L. Overcorrection was determined using 14 published criteria. Latent class analysis measured the independent association of baseline factors with a consensus overcorrection status on the basis of the 14 criteria, and was summarized as a risk score, which was validated in two cohorts.ResultsA total of 623 patients presented with severe hyponatremia (mean initial value 112 mmol/L; SD 3.2). The prevalence of no, unlikely, possible, and definite overcorrection was 72%, 4%, 10%, and 14%, respectively. Overcorrection was independently associated with decreased level of consciousness (2 points), vomiting (2 points), severe hypokalemia (1 point), hypotonic urine (4 points), volume overload (-5 points), chest tumor (-5 points), patient age (-1 point per decade, over 50 years), and initial sodium level (<110 mmol/L: 4 points; 110-111 mmol/L: 2 points; 112-113 mmol/L: 1 point). These points were summed to create the Severe Hyponatremic Overcorrection Risk (SHOR) score, which was significantly associated with overcorrection status (Spearman correlation 0.45; 95% confidence interval, 0.36 to 0.49) and was discriminating (average dichotomized c-statistic 0.77; 95% confidence interval, 0.73 to 0.81). The internal (n=119) and external (n=95) validation cohorts had significantly greater use of desmopressin, which was significantly associated with the SHOR score. The SHOR score was significantly associated with overcorrection status in the internal (P<0.001) but not external (P=0.39) validation cohort.ConclusionsIn patients presenting with severe hyponatremia, overcorrection was common and predictable using baseline information. Further external validation of the SHOR is required before generalized use.

Project description:BackgroundRheumatoid arthritis (RA) patients have increased risk for cardiovascular disease (CVD). Accurate CVD risk prediction could improve care for RA patients. Our goal is to develop and validate a biomarker-based model for predicting CVD risk in RA patients.MethodsMedicare claims data were linked to multi-biomarker disease activity (MBDA) test results to create an RA patient cohort with age ??40?years that was split 2:1 for training and internal validation. Clinical and RA-related variables, MBDA score, and its 12 biomarkers were evaluated as predictors of a composite CVD outcome: myocardial infarction (MI), stroke, or fatal CVD within 3?years. Model building used Cox proportional hazard regression with backward elimination. The final MBDA-based CVD risk score was internally validated and compared to four clinical CVD risk prediction models.Results30,751 RA patients (904 CVD events) were analyzed. Covariates in the final MBDA-based CVD risk score were age, diabetes, hypertension, tobacco use, history of CVD (excluding MI/stroke), MBDA score, leptin, MMP-3 and TNF-R1. In internal validation, the MBDA-based CVD risk score was a strong predictor of 3-year risk for a CVD event, with hazard ratio (95% CI) of 2.89 (2.46-3.41). The predicted 3-year CVD risk was low for 9.4% of patients, borderline for 10.2%, intermediate for 52.2%, and high for 28.2%. Model fit was good, with mean predicted versus observed 3-year CVD risks of 4.5% versus 4.4%. The MBDA-based CVD risk score significantly improved risk discrimination by the likelihood ratio test, compared to four clinical models. The risk score also improved prediction, reclassifying 42% of patients versus the simplest clinical model (age + sex), with a net reclassification index (NRI) (95% CI) of 0.19 (0.10-0.27); and 28% of patients versus the most comprehensive clinical model (age + sex + diabetes + hypertension + tobacco use + history of CVD + CRP), with an NRI of 0.07 (0.001-0.13). C-index was 0.715 versus 0.661 to 0.696 for the four clinical models.ConclusionA prognostic score has been developed to predict 3-year CVD risk for RA patients by using clinical data, three serum biomarkers and the MBDA score. In internal validation, it had good accuracy and outperformed clinical models with and without CRP. The MBDA-based CVD risk prediction score may improve RA patient care by offering a risk stratification tool that incorporates the effect of RA inflammation.

Project description: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.

Project description:ImportanceAcute kidney injury (AKI) is associated with increased morbidity and mortality in hospitalized patients. Current methods to identify patients at high risk of AKI are limited, and few prediction models have been externally validated.ObjectiveTo internally and externally validate a machine learning risk score to detect AKI in hospitalized patients.Design, setting, and participantsThis diagnostic study included 495 971 adult hospital admissions at the University of Chicago (UC) from 2008 to 2016 (n = 48 463), at Loyola University Medical Center (LUMC) from 2007 to 2017 (n = 200 613), and at NorthShore University Health System (NUS) from 2006 to 2016 (n = 246 895) with serum creatinine (SCr) measurements. Patients with an SCr concentration at admission greater than 3.0 mg/dL, with a prior diagnostic code for chronic kidney disease stage 4 or higher, or who received kidney replacement therapy within 48 hours of admission were excluded. A simplified version of a previously published gradient boosted machine AKI prediction algorithm was used; it was validated internally among patients at UC and externally among patients at NUS and LUMC.Main outcomes and measuresPrediction of Kidney Disease Improving Global Outcomes SCr-defined stage 2 AKI within a 48-hour interval was the primary outcome. Discrimination was assessed by the area under the receiver operating characteristic curve (AUC).ResultsThe study included 495 971 adult admissions (mean [SD] age, 63 [18] years; 87 689 [17.7%] African American; and 266 866 [53.8%] women) across 3 health systems. The development of stage 2 or higher AKI occurred in 15 664 of 48 463 patients (3.4%) in the UC cohort, 5711 of 200 613 (2.8%) in the LUMC cohort, and 3499 of 246 895 (1.4%) in the NUS cohort. In the UC cohort, 332 patients (0.7%) required kidney replacement therapy compared with 672 patients (0.3%) in the LUMC cohort and 440 patients (0.2%) in the NUS cohort. The AUCs for predicting at least stage 2 AKI in the next 48 hours were 0.86 (95% CI, 0.86-0.86) in the UC cohort, 0.85 (95% CI, 0.84-0.85) in the LUMC cohort, and 0.86 (95% CI, 0.86-0.86) in the NUS cohort. The AUCs for receipt of kidney replacement therapy within 48 hours were 0.96 (95% CI, 0.96-0.96) in the UC cohort, 0.95 (95% CI, 0.94-0.95) in the LUMC cohort, and 0.95 (95% CI, 0.94-0.95) in the NUS cohort. In time-to-event analysis, a probability cutoff of at least 0.057 predicted the onset of stage 2 AKI a median (IQR) of 27 (6.5-93) hours before the eventual doubling in SCr concentrations in the UC cohort, 34.5 (19-85) hours in the NUS cohort, and 39 (19-108) hours in the LUMC cohort.Conclusions and relevanceIn this study, the machine learning algorithm demonstrated excellent discrimination in both internal and external validation, supporting its generalizability and potential as a clinical decision support tool to improve AKI detection and outcomes.