Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comment
. 2018 Nov;23(11):2114-2115.
doi: 10.1038/mp.2017.181.

Overestimation of the classification accuracy of a biomarker for assessing heavy alcohol use

M W Hattab  1 , S L Clark  1 , E J C G van den Oord  2
Affiliations
Comment

Overestimation of the classification accuracy of a biomarker for assessing heavy alcohol use

M W Hattab et al. Mol Psychiatry. 2018 Nov.
No abstract available

PubMed Disclaimer

Conflict of interest statement

CONFLICT OF INTEREST

The authors declare no conflict of interest.

Figures

Figure
Figure. Area under the curve for simulated methylation data without effects
A) We simulated 10,000 data-sets with parameters mimicking the Lothian Birth Cohort 1936 (LBC1936) that has 574 individuals who are light drinkers and 61 heavy drinkers (Table 1 in Liu et al.). We first simulated age, sex, and BMI so that logistic regression produced an average AUC of 0.57, which is approximately the value of the “Null” model (right panel of Figure 2 in Liu et al.). Next, we added simulated CpG data to the model that was independent of the outcome. To illustrate the effect of the number of predictors\variables on the AUC, we increased the number of CpGs included from 0 to 144 in steps of 4 (i.e., 0, 4, 8,…,144). To maximize compatibility with Figure 2 in Liu et al., the x-axis displays only the sets of 5, 23, 78, and 144 CpGs. In the figure we plotted the average AUC (red solid curve) with the 95% confidence intervals (red dashed lines). The black triangles indicate the values reported by Liu at al. B) The above simulation was repeated for all other replication cohorts comparing non- vs Heavy drinkers. Sample sizes were: LBC 1936:181 vs. 61, MESA: 691 vs. 51, KORA F4: 534 vs. 230, ARIC: 1519 vs. 348. Only the results for the full model with 144 CpGs are reported. We did not include the FHS cohort because, as mentioned by Liu et al., this cohort was also used in the discovery stage to find the 144 CpGs. In the figure we plotted the average AUC (red solid point) with the 95% confidence intervals (red dashed lines). The black triangles indicate the values reported by Liu at al. C) We also performed simulations using the sample sizes for the analysis comparing light vs heavy drinkers are: LBC 1936: 574 vs. 61, MESA: 444 vs. 51, KORA F4: 751 vs. 230, ARIC: 67 vs. 348. See panel B for explanation of legend etc.
See this image and copyright information in PMC

Comment on

  • A DNA methylation biomarker of alcohol consumption.
    Liu C, Marioni RE, Hedman ÅK, Pfeiffer L, Tsai PC, Reynolds LM, Just AC, Duan Q, Boer CG, Tanaka T, Elks CE, Aslibekyan S, Brody JA, Kühnel B, Herder C, Almli LM, Zhi D, Wang Y, Huan T, Yao C, Mendelson MM, Joehanes R, Liang L, Love SA, Guan W, Shah S, McRae AF, Kretschmer A, Prokisch H, Strauch K, Peters A, Visscher PM, Wray NR, Guo X, Wiggins KL, Smith AK, Binder EB, Ressler KJ, Irvin MR, Absher DM, Hernandez D, Ferrucci L, Bandinelli S, Lohman K, Ding J, Trevisi L, Gustafsson S, Sandling JH, Stolk L, Uitterlinden AG, Yet I, Castillo-Fernandez JE, Spector TD, Schwartz JD, Vokonas P, Lind L, Li Y, Fornage M, Arnett DK, Wareham NJ, Sotoodehnia N, Ong KK, van Meurs JBJ, Conneely KN, Baccarelli AA, Deary IJ, Bell JT, North KE, Liu Y, Waldenberger M, London SJ, Ingelsson E, Levy D. Liu C, et al. Mol Psychiatry. 2018 Feb;23(2):422-433. doi: 10.1038/mp.2016.192. Epub 2016 Nov 15. Mol Psychiatry. 2018. PMID: 27843151 Free PMC article.

References

    1. Liu C, Marioni RE, Hedman AK, Pfeiffer L, Tsai PC, Reynolds LM, et al. A DNA methylation biomarker of alcohol consumption. Mol Psychiatry. 2016 - PMC - PubMed
    1. Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Verlag; New York: 2001.

Substances