Initial Validation of a Machine Learning-Derived Prognostic Test (KidneyIntelX) Integrating Biomarkers and Electronic Health Record Data To Predict Longitudinal Kidney Outcomes
Copyright © 2020 by the American Society of Nephrology..
Background: Individuals 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.
Methods: We 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.
Results: Overall, 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%).
Conclusions: In 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.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
Zur Gesamtaufnahme - volume:1 |
---|---|
Enthalten in: |
Kidney360 - 1(2020), 8 vom: 27. Aug., Seite 731-739 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Chauhan, Kinsuk [VerfasserIn] |
---|
Links: |
---|
Anmerkungen: |
Date Completed 07.04.2022 Date Revised 31.05.2022 published: Electronic-eCollection Citation Status MEDLINE |
---|
doi: |
10.34067/KID.0002252020 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM339028289 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM339028289 | ||
003 | DE-627 | ||
005 | 20231226002011.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2020 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.34067/KID.0002252020 |2 doi | |
028 | 5 | 2 | |a pubmed24n1130.xml |
035 | |a (DE-627)NLM339028289 | ||
035 | |a (NLM)35372952 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Chauhan, Kinsuk |e verfasserin |4 aut | |
245 | 1 | 0 | |a Initial Validation of a Machine Learning-Derived Prognostic Test (KidneyIntelX) Integrating Biomarkers and Electronic Health Record Data To Predict Longitudinal Kidney Outcomes |
264 | 1 | |c 2020 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 07.04.2022 | ||
500 | |a Date Revised 31.05.2022 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2020 by the American Society of Nephrology. | ||
520 | |a Background: Individuals 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 | ||
520 | |a Methods: We 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 | ||
520 | |a Results: Overall, 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%) | ||
520 | |a Conclusions: In 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 | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, N.I.H., Extramural | |
650 | 4 | |a Validation Study | |
650 | 4 | |a APOL1 protein | |
650 | 4 | |a HAVCR1 protein | |
650 | 4 | |a TNFRSF1A protein | |
650 | 4 | |a apolipoprotein L1 | |
650 | 4 | |a area under curve | |
650 | 4 | |a biologic specimen banks | |
650 | 4 | |a clinical nephrology | |
650 | 4 | |a diabetes mellitus | |
650 | 4 | |a electronic health records | |
650 | 4 | |a follow-up studies | |
650 | 4 | |a glomerular filtration rate | |
650 | 4 | |a hepatitis A virus cellular receptor 1 | |
650 | 4 | |a human | |
650 | 4 | |a prognosis | |
650 | 4 | |a receptors | |
650 | 4 | |a tumor necrosis factor | |
650 | 4 | |a tumor necrosis factors | |
650 | 4 | |a type 2 | |
650 | 4 | |a type I | |
650 | 7 | |a APOL1 protein, human |2 NLM | |
650 | 7 | |a Apolipoprotein L1 |2 NLM | |
650 | 7 | |a Biomarkers |2 NLM | |
700 | 1 | |a Nadkarni, Girish N |e verfasserin |4 aut | |
700 | 1 | |a Fleming, Fergus |e verfasserin |4 aut | |
700 | 1 | |a McCullough, James |e verfasserin |4 aut | |
700 | 1 | |a He, Cijiang J |e verfasserin |4 aut | |
700 | 1 | |a Quackenbush, John |e verfasserin |4 aut | |
700 | 1 | |a Murphy, Barbara |e verfasserin |4 aut | |
700 | 1 | |a Donovan, Michael J |e verfasserin |4 aut | |
700 | 1 | |a Coca, Steven G |e verfasserin |4 aut | |
700 | 1 | |a Bonventre, Joseph V |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Kidney360 |d 2020 |g 1(2020), 8 vom: 27. Aug., Seite 731-739 |w (DE-627)NLM311083633 |x 2641-7650 |7 nnns |
773 | 1 | 8 | |g volume:1 |g year:2020 |g number:8 |g day:27 |g month:08 |g pages:731-739 |
856 | 4 | 0 | |u http://dx.doi.org/10.34067/KID.0002252020 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 1 |j 2020 |e 8 |b 27 |c 08 |h 731-739 |