Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Implicit data crimes: Machine learning bias arising from misuse of public data.

ABSTRACT: SignificancePublic databases are an important resource for machine learning research, but their growing availability sometimes leads to "off-label" usage, where data published for one task are used for another. This work reveals that such off-label usage could lead to biased, overly optimistic results of machine-learning algorithms. The underlying cause is that public data are processed with hidden processing pipelines that alter the data features. Here we study three well-known algorithms developed for image reconstruction from magnetic resonance imaging measurements and show they could produce biased results with up to 48% artificial improvement when applied to public databases. We relate to the publication of such results as implicit "data crimes" to raise community awareness of this growing big data problem.

SUBMITTER: Shimron E

PROVIDER: S-EPMC9060447 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Implicit data crimes: Machine learning bias arising from misuse of public data.

Shimron Efrat E Tamir Jonathan I JI Wang Ke K Lustig Michael M

Proceedings of the National Academy of Sciences of the United States of America 20220321 13

SignificancePublic databases are an important resource for machine learning research, but their growing availability sometimes leads to "off-label" usage, where data published for one task are used for another. This work reveals that such off-label usage could lead to biased, overly optimistic results of machine-learning algorithms. The underlying cause is that public data are processed with hidden processing pipelines that alter the data features. Here we study three well-known algorithms devel ...[more]

PMID: 35312366

Similar Datasets

Machine-learning media bias.

Project description:We present an automated method for measuring media bias. Inferring which newspaper published a given article, based only on the frequencies with which it uses different phrases, leads to a conditional probability distribution whose analysis lets us automatically map newspapers and phrases into a bias space. By analyzing roughly a million articles from roughly a hundred newspapers for bias in dozens of news topics, our method maps newspapers into a two-dimensional bias landscape that agrees well with previous bias classifications based on human judgement. One dimension can be interpreted as traditional left-right bias, the other as establishment bias. This means that although news bias is inherently political, its measurement need not be.

| S-EPMC9365193 | biostudies-literature

Forecasting of digital financial crimes in Russia based on machine learning methods

Project description:In the modern world, economic relations, business, and markets are increasingly being transferred to the online world. Accordingly, the percentage of a new type of financial fraud – digital crimes – is also growing. In Russia, they are one of the leaders in economic crimes. Constant development and improvement of digital technologies make for the emergence of increasingly sophisticated types of digital fraud. Information security management systems are among the most important parts of both public and private internal policy of the enterprises that use them. Every year, the issue of combating cyber attacks is becoming more acute. For example, in 2021, the volume of transactions without the consent of bank customers increased by 38.8% compared to 2020. For cyber risks not to lead to such serious consequences, it is necessary to determine the influence of external factors on the dynamics of digital financial crimes in Russia. We will develop a predictive system based on machine learning methods to predict the number of digital financial crimes. Supplementary Information The online version contains supplementary material available at 10.1007/s11416-023-00480-3.

| S-EPMC10159233 | biostudies-literature

MLIMC: Machine Learning-Based Implicit-Solvent Monte Carlo.

Project description:Monte Carlo (MC) methods are important computational tools for molecular structure optimizations and predictions. When solvent effects are explicitly considered, MC methods become very expensive due to the large degree of freedom associated with the water molecules and mobile ions. Alternatively implicit-solvent MC can largely reduce the computational cost by applying a mean field approximation to solvent effects and meanwhile maintains the atomic detail of the target molecule. The two most popular implicit-solvent models are the Poisson-Boltzmann (PB) model and the Generalized Born (GB) model in a way such that the GB model is an approximation to the PB model but is much faster in simulation time. In this work, we develop a machine learning-based implicit-solvent Monte Carlo (MLIMC) method by combining the advantages of both implicit solvent models in accuracy and efficiency. Specifically, the MLIMC method uses a fast and accurate PB-based machine learning (PBML) scheme to compute the electrostatic solvation free energy at each step. We validate our MLIMC method by using a benzene-water system and a protein-water system. We show that the proposed MLIMC method has great advantages in speed and accuracy for molecular structure optimization and prediction.

| S-EPMC8752096 | biostudies-literature

Reducing Peptide Sequence Bias in Quantitative Mass Spectrometry Data with Machine Learning.

Project description:Quantitative mass spectrometry measurements of peptides necessarily incorporate sequence-specific biases that reflect the behavior of the peptide during enzymatic digestion and liquid chromatography and in a mass spectrometer. These sequence-specific effects impair quantification accuracy, yielding peptide quantities that are systematically under- or overestimated. We provide empirical evidence for the existence of such biases, and we use a deep neural network, called Pepper, to automatically identify and reduce these biases. The model generalizes to new proteins and new runs within a related set of tandem mass spectrometry experiments, and the learned coefficients themselves reflect expected physicochemical properties of the corresponding peptide sequences. The resulting adjusted abundance measurements are more correlated with mRNA-based gene expression measurements than the unadjusted measurements. Pepper is suitable for data generated on a variety of mass spectrometry instruments and can be used with labeled or label-free approaches and with data-independent or data-dependent acquisition.

| S-EPMC9531543 | biostudies-literature

The Effect of Implicit Bias and Role Misidentification in the Learning Environment.

Project description:BackgroundLittle is known about the impact of implicit bias our trainees experience in the form of role misidentification in the clinical learning environment.ActivityWe surveyed 540 residents and clinical medical students to determine the frequency and impact of role misidentification.Results and discussionMost respondents (85%, n = 162) experienced role misidentification, directly resulting in heightened emotions that led to guarded behavior. An additional indirect impact for trainees is transmitted through frequent non-promotional role misidentification and personalizing the incidents. Women and trainees with marginalized identities had significant impacts. These findings present an opportunity to improve our understanding of the trainee experience.Supplementary informationThe online version contains supplementary material available at 10.1007/s40670-021-01475-9.

| S-EPMC8814075 | biostudies-literature

Predicting Mouse Liver Microsomal Stability with "Pruned" Machine Learning Models and Public Data.

Project description:PurposeMouse efficacy studies are a critical hurdle to advance translational research of potential therapeutic compounds for many diseases. Although mouse liver microsomal (MLM) stability studies are not a perfect surrogate for in vivo studies of metabolic clearance, they are the initial model system used to assess metabolic stability. Consequently, we explored the development of machine learning models that can enhance the probability of identifying compounds possessing MLM stability.MethodsPublished assays on MLM half-life values were identified in PubChem, reformatted, and curated to create a training set with 894 unique small molecules. These data were used to construct machine learning models assessed with internal cross-validation, external tests with a published set of antitubercular compounds, and independent validation with an additional diverse set of 571 compounds (PubChem data on percent metabolism).Results"Pruning" out the moderately unstable / moderately stable compounds from the training set produced models with superior predictive power. Bayesian models displayed the best predictive power for identifying compounds with a half-life ≥1 h.ConclusionsOur results suggest the pruning strategy may be of general benefit to improve test set enrichment and provide machine learning models with enhanced predictive value for the MLM stability of small organic molecules. This study represents the most exhaustive study to date of using machine learning approaches with MLM data from public sources.

| S-EPMC4712113 | biostudies-literature

Enhanced SARS-CoV-2 case prediction using public health data and machine learning models

Project description: Not available

| S-EPMC10913390 | biostudies-literature

Implicit Bias and Patient Care: Mitigating Bias, Preventing Harm.

Project description:IntroductionSimulation is a valuable and novel tool in the expanding approach to racism and bias education for medical practitioners. We present a simulation case focused on identifying and addressing the implicit bias of a consultant to teach bias mitigation skills and limit harm to patients and families.MethodsLearners were presented with a case of a classic toddler's fracture in an African American child. The learners interacted with an orthopedic resident who insisted on child welfare involvement, with nonspecific and increasingly biased concerns about the child/family. The learners were expected to identify that this case was not concerning for nonaccidental trauma and that the orthopedic resident was demonstrating bias. They were expected to communicate with both the resident and the parent effectively to defuse the situation and prevent harm from reaching the family. A debrief and an anonymous survey followed the case.ResultsSeventy-five learners participated, including pediatric and emergency medicine residents, fellows, attendings, and medical students. After the case, the majority of learners expressed confidence that they could recognize racial bias in the care of a patient (90%), ensure patient care was not influenced by racial bias (88%), and utilize a tool to frame a concern about bias (79%).DiscussionParticipants felt that this simulation was relevant and effective and overall left the experience feeling confident in their abilities to identify and manage racially biased patient care. This anti-racist simulation offers an important skill-building opportunity that has been well received by learners.

| S-EPMC10507144 | biostudies-literature

Implicit and explicit learning of Bayesian priors differently impacts bias during perceptual decision-making.

Project description:Knowledge without awareness, or implicit knowledge, influences a variety of behaviors. It is unknown however, whether implicit knowledge of statistical structure informs visual perceptual decisions or whether explicit knowledge of statistical probabilities is required. Here, we measured visual decision-making performance using a novel task in which humans reported the orientation of two differently colored translational Glass patterns; each color associated with different orientation probabilities. The task design allowed us to assess participants' ability to learn and use a general orientation prior as well as a color specific feature prior. Classifying decision-makers based on a questionnaire revealed that both implicit and explicit learners implemented a general orientation bias by adjusting the starting point of evidence accumulation in the drift diffusion model framework. Explicit learners additionally adjusted the drift rate offset. When subjects implemented a stimulus specific bias, they did so by adjusting primarily the drift rate offset. We conclude that humans can learn priors implicitly for perceptual decision-making and depending on awareness implement the priors using different mechanisms.

| S-EPMC8379185 | biostudies-literature

Propranolol reduces implicit negative racial bias.

Project description:BackgroundImplicit negative attitudes towards other races are important in certain kinds of prejudicial social behaviour. Emotional mechanisms are thought to be involved in mediating implicit "outgroup" bias but there is little evidence concerning the underlying neurobiology. The aim of the present study was to examine the role of noradrenergic mechanisms in the generation of implicit racial attitudes.MethodsHealthy volunteers (n = 36) of white ethnic origin, received a single oral dose of the β-adrenoceptor antagonist, propranolol (40 mg), in a randomised, double-blind, parallel group, placebo-controlled, design. Participants completed an explicit measure of prejudice and the racial implicit association test (IAT), 1-2 h after propranolol administration.ResultsRelative to placebo, propranolol significantly lowered heart rate and abolished implicit racial bias, without affecting the measure of explicit racial prejudice. Propranolol did not affect subjective mood.ConclusionsOur results indicate that β-adrenoceptors play a role in the expression of implicit racial attitudes suggesting that noradrenaline-related emotional mechanisms may mediate negative racial bias. Our findings may also have practical importance given that propranolol is a widely used drug. However, further studies will be needed to examine whether a similar effect can be demonstrated in the course of clinical treatment.

| S-EPMC3395337 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data