Log transformation: application and interpretation in biomedical research

Feng, Changyong; Wang, Hongyue; Lu, Naiji; Tu, Xin

doi:10.1002/sim.5486

Cited by 201 publications

(163 citation statements)

References 23 publications

(29 reference statements)

Supporting

Mentioning

148

Contrasting

Order By: Relevance

“…2.2. Although logarithmic transformations are common, they are not always acceptable; see [14] for some examples of when logarithmic transformations can actually introduce skew. However, as noted in [3], for many practical problems logarithmic transformations can be very useful.…”

Section: Although We Developed τ (ŷ ) [And Hence (Yŷ )]mentioning

confidence: 99%

Improving predictions of pediatric surgical durations with supervised learning

Master

Zhou

Miller

et al. 2017

Int J Data Sci Anal

View full text Add to dashboard Cite

Effective management of operating room resources relies on accurate predictions of surgical case durations. This prediction problem is known to be particularly difficult in pediatric hospitals due to the extreme variation in pediatric patient populations. We pursue two supervised learning approaches: (1) We directly predict the surgical case durations using features derived from electronic medical records and from hospital operational information. For this regression problem, we propose a novel metric for measuring accuracy of predictions which captures key issues relevant to hospital operations. We evaluate several prediction models; some are automated (they do not require input from surgeons) while others are semi-automated (they do require input from surgeons). We see that many of our automated (2) We consider a classification problem in which each prediction provided by a surgeon is predicted to be correct, an overestimate, or an underestimate. This classification mechanism builds on the metric mentioned above and could potentially be useful for detecting human errors. Both supervised learning approaches give insights into the feature engineering process while creating the basis for decision support tools.

show abstract

Section: Although We Developed τ (ŷ ) [And Hence (Yŷ )]mentioning

confidence: 99%

Improving predictions of pediatric surgical durations with supervised learning

Master

Zhou

Miller

et al. 2017

Int J Data Sci Anal

View full text Add to dashboard Cite

show abstract

“…In both analyses, participants and target items were included concurrently as random factors (Brysbaert, 2007;Quené & Van den Bergh, 2008). To remove the intrinsic positive skew and the non-normality of the distribution, a logarithmic transformation was applied to the RTs (Keene, 1995;Limpert, Stahel, & Abbt, 2001;Quené & Van den Bergh, 2008).…”

Section: Behavioural Datamentioning

confidence: 99%

Trial by trial: selecting first or second language phonology of a visually masked word

Timmer

Ganushchak

Mitlina

et al. 2013

Language, Cognition and Neuroscience

View full text Add to dashboard Cite

“…Studies with weak or negative results often lack detailed descriptions of protocols used to collect samples323334, used heparin-treated tubes35 or measured MPO from serum36. In a notable negative study with MPO measured in EDTA-treated samples collected from heparin-naïve patients37, MPO concentration was log-transformed due to its skewed distribution; not only is such a transformation unnecessary, but it can obfuscate the true underlying relationships between covariates and outcomes38. These issues in methodology and analysis underscore the need for more investigation of MPO and its clinical utility.…”

Section: Discussionmentioning

confidence: 99%

A rapid bioluminescence assay for measuring myeloperoxidase activity in human plasma

2015

View full text Add to dashboard Cite

Myeloperoxidase (MPO) is a circulating cardiovascular disease (CVD) biomarker used to estimate clinical risk and patient prognosis. Current enzyme-linked immunosorbent assays (ELISA) for MPO concentration are costly and time-intensive. Here we report a novel bioluminescence assay, designated MPO activity on a polymer surface (MAPS), for measuring MPO activity in human plasma samples using the bioluminescent substrate L-012. The method delivers a result in under an hour and is resistant to confounding effects from endogenous MPO inhibitors. In a pilot clinical study, we compared MAPS and two clinical ELISAs using 72 plasma samples from cardiac catheterization patients. Results from parallel MAPS and ELISAs were concordant within 2±11 μg l−1 MPO with similar uncertainty and reproducibility. Results between parallel MAPS and ELISA were in better agreement than those between independent ELISAs. MAPS may provide an inexpensive and rapid assay for determining MPO activity in plasma samples from patients with CVD or potentially other immune and inflammatory disorders.

show abstract

Log transformation: application and interpretation in biomedical research

Cited by 201 publications

References 23 publications

Improving predictions of pediatric surgical durations with supervised learning

Improving predictions of pediatric surgical durations with supervised learning

Trial by trial: selecting first or second language phonology of a visually masked word

A rapid bioluminescence assay for measuring myeloperoxidase activity in human plasma

Contact Info

Product

Resources

About