Predictive utilities of lipid traits, lipoprotein subfractions and other risk factors for incident diabetes: a machine learning approach in the Diabetes Prevention Program.
Trial report in BMJ open diabetes research & care, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. It reports registered trial NCT00004992. Cited by 2 papers.
0numbers the graph read from it
0cells of the map it votes in
2citing papers in PubMed
1.2field-weighted citation impact, top 21% of its field
1 · What the graph read from it
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
2 · The registry
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
5 · Who and what money
Authors and funding
11 authors at 7 institutions in 3 countries.
Tibor V VargaSection of Epidemiology, Department of Public Health, University of Copenhagen, Copenhagen, Denmark Tibor.Varga@sund.ku.dk ella@bsc.gwu.edu.ORCID 0000-0002-2383-699X
Jinxi LiuBiostatistics Center and Department of Biostatistics and Bioinformatics, Milken Institute School of Public Health, George Washington University, Rockville, Maryland, USA.
Ronald B GoldbergDepartment of Medicine, University of Miami, Miami, Florida, USA.ORCID 0000-0003-0924-1110
Guannan ChenBiostatistics Center and Department of Biostatistics and Bioinformatics, Milken Institute School of Public Health, George Washington University, Rockville, Maryland, USA.ORCID 0000-0002-6252-4673
Samuel Dagogo-JackUniversity of Tennessee Health Science Center, Memphis, Tennessee, USA.ORCID 0000-0001-5318-9677
Carlos LorenzoThe University of Texas Health Science Center at San Antonio, San Antonio, Texas, USA.ORCID 0000-0001-7080-765X
Kieren J MatherIndiana University School of Medicine, Indianapolis, Indiana, USA.
Xavier Pi-SunyerColumbia University Medical Center, New York City, New York, USA.
Søren BrunakNovo Nordisk Foundation Center for Protein Research, Translational Disease Systems Biology Group, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark.
Marinella TemprosaBiostatistics Center and Department of Biostatistics and Bioinformatics, Milken Institute School of Public Health, George Washington University, Rockville, Maryland, USA Tibor.Varga@sund.ku.dk ella@bsc.gwu.edu.ORCID 0000-0002-9976-745X
Diabetes Prevention Program Research Group
Milken Institute · USUniversity of Copenhagen · DKColumbia University Irving Medical Center · USIndiana University School of MedicineThe University of Texas Health Science Center at San Antonio · USUniversity of Miami · USUniversity of Tennessee Health Science Center · US
Funding
PRIMARY PREVENTION TRIAL--DATA COORDINATING CENTERU01DK048489 · NIDDK · GEORGE WASHINGTON UNIVERSITY · PI JABLONSKI, KATHLEEN ANN, TEMPROSA, MARINELLA · 1994 to 2021
$84.8M
Post-DDP Follow-up StudyU01DK048413 · NIDDK · UNIVERSITY OF WASHINGTON · PI KAHN, STEVEN EMANUEL · 1994 to 2021
$13.7M
PRIMARY PREVENTION TRIAL (DPT-2)U01DK048397 · NIDDK · MASSACHUSETTS GENERAL HOSPITAL · PI NATHAN, DAVID M · 1994 to 2021
$12.0M
NIDDM PRIMARY PREVENTION TRIAL (DPT 2)U01DK048404 · NIDDK · ST. LUKE'S-ROOSEVELT INST FOR HLTH SCIS · PI LAFERRERE, BLANDINE B · 1994 to 2021
$11.6M
PRIMARY PREVENTION TRIAL (DPT-2)U01DK048339 · NIDDK · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI ARANETA, MARIA ROSARIO GORREZ, MUDALIAR, SUNDER · 1994 to 2022
$11.4M
NIDDM PRIMARY PREVENTION TRIALU01DK048412 · NIDDK · UNIVERSITY OF PITTSBURGH AT PITTSBURGH · PI VENDITTI, ELIZABETH MARY · 1994 to 2021
$11.4M
PRIMARY PREVENTION TRIALU01DK048387 · NIDDK · MEDSTAR RESEARCH INSTITUTE · PI MAGEE, MICHELLE FISCHMANN · 1994 to 2022
$11.1M
TITLE OMITTEDU01DK048349 · NIDDK · YESHIVA UNIVERSITY · PI CRANDALL, JILL P · 1994 to 2021
$11.0M
PRIMARY PREVENTION TRIALU01DK048443 · NIDDK · UNIVERSITY OF SOUTHERN CALIFORNIA · PI WATSON, KAROL E · 1994 to 2021
$10.2M
Post-DPP Follow-up StudyU01DK048375 · NIDDK · UNIVERSITY OF COLORADO DENVER · PI DABELEA, DANA · 1994 to 2022
$10.0M
Post-Diabetes Prevention Program (DPP)U01DK048381 · NIDDK · UNIVERSITY OF CHICAGO · PI EHRMANN, DAVID A · 1994 to 2021
$9.6M
Post DPP Follow-up StudyU01DK048434 · NIDDK · UNIVERSITY OF MIAMI SCHOOL OF MEDICINE · PI GOLDBERG, RONALD B · 1994 to 2022
introductionAlthough various lipid and non-lipid analytes measured by nuclear magnetic resonance (NMR) spectroscopy have been associated with type 2 diabetes, a structured comparison of the ability of NMR-derived biomarkers and standard lipids to predict individual diabetes risk has not been undertaken in larger studies nor among individuals at high risk of diabetes. RESEARCH DESIGN AND
methodsCumulative discriminative utilities of various groups of biomarkers including NMR lipoproteins, related non-lipid biomarkers, standard lipids, and demographic and glycemic traits were compared for short-term (3.2 years) and long-term (15 years) diabetes development in the Diabetes Prevention Program, a multiethnic, placebo-controlled, randomized controlled trial of individuals with pre-diabetes in the USA (N=2590). Logistic regression, Cox proportional hazards model and six different hyperparameter-tuned machine learning algorithms were compared. The Matthews Correlation Coefficient (MCC) was used as the primary measure of discriminative utility.
resultsModels with baseline NMR analytes and their changes did not improve the discriminative utility of simpler models including standard lipids or demographic and glycemic traits. Across all algorithms, models with baseline 2-hour glucose performed the best (max MCC=0.36). Sophisticated machine learning algorithms performed similarly to logistic regression in this study.
conclusionsNMR lipoproteins and related non-lipid biomarkers were associated but did not augment discrimination of diabetes risk beyond traditional diabetes risk factors except for 2-hour glucose. Machine learning algorithms provided no meaningful improvement for discrimination compared with logistic regression, which suggests a lack of influential latent interactions among the analytes assessed in this study. TRIAL REGISTRATION NUMBER: Diabetes Prevention Program: NCT00004992; Diabetes Prevention Program Outcomes Study: NCT00038727.
Indexed as
Diabetes Mellitus, Type 2HumansLipidsLipoproteinsMachine LearningRisk FactorsLipidsLipoproteinsdiabetes mellituslipidslipoproteinsprediabetic statetype 2
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.
Predictive utilities of lipid traits, lipoprotein subfractions and other risk factors for incident diabetes: a machine learning approach in the Diabetes Prevention Program. · full record | OpenQuestion