DOCSLIB.ORG

Evidence Type Classification in Randomized Controlled Trials Tobias Mayer, Elena Cabrio, Serena Villata

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Evidence Type Classification in Randomized Controlled Trials Tobias Mayer, Elena Cabrio, Serena Villata Evidence Type Classification in Randomized Controlled Trials Tobias Mayer, Elena Cabrio, Serena Villata To cite this version: Tobias Mayer, Elena Cabrio, Serena Villata. Evidence Type Classification in Randomized Controlled Trials. 5th ArgMining@EMNLP 2018, Oct 2018, Brussels, Belgium. hal-01912157 HAL Id: hal-01912157 https://hal.archives-ouvertes.fr/hal-01912157 Submitted on 5 Nov 2018 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Evidence Type Classification in Randomized Controlled Trials Tobias Mayer and Elena Cabrio and Serena Villata Universite´ Coteˆ d’Azur, CNRS, I3S, Inria, France ftmayer,cabrio,[email protected] Abstract To answer this question, we propose to resort Randomized Controlled Trials (RCT) are a on Argument Mining (AM) (Peldszus and Stede, common type of experimental studies in the 2013; Lippi and Torroni, 2016a), defined as “the medical domain for evidence-based decision general task of analyzing discourse on the prag- making. The ability to automatically extract matics level and applying a certain argumentation the arguments proposed therein can be of valu- theory to model and automatically analyze the data able support for clinicians and practitioners in at hand” (Habernal and Gurevych, 2017). Two their daily evidence-based decision making ac- stages are crucial: (1) the detection of argument tivities. Given the peculiarity of the medical domain and the required level of detail, stan- components (e.g., claim, premises) and the iden- dard approaches to argument component de- tification of their textual boundaries, and (2) the tection in argument(ation) mining are not fine- prediction of the relations holding between the ar- grained enough to support such activities. In guments. In the AM framework, we propose a this paper, we introduce a new sub-task of the new task called evidence type classification, as a argument component identification task: evi- sub-task of the argument component identification dence type classification . To address it, we task. The distinction among different kinds of ev- propose a supervised approach and we test it on a set of RCT abstracts on different medical idence is crucial in evidence-based decision mak- topics. ing as different kinds of evidence are associated to different weights in the reasoning process. Such 1 Introduction information need to be extracted from raw text. Evidence-based decision making in medicine has To the best of our knowledge, this is the first the aim to support clinicians and practitioners to approach in AM targeting evidence type classifi- reason upon the arguments in support or against a cation in the medical domain. The main contribu- certain treatment, its effects, and the comparison tions of this paper are: (i) we propose four classes with other related treatments for the same disease. of evidence for RCT (i.e., comparative, signifi- These approaches (e.g., (Hunter and Williams, cance, side-effect, and other), and we annotate a 2012; Craven et al., 2012; Longo and Hederman, new dataset of 169 RCT abstracts with such labels, 2013; Qassas et al., 2015)) consider different kinds and (ii) we experiment with supervised classifiers of data, e.g., Randomized Controlled Trials or over such dataset obtaining satisfactory results. other observational studies, and they usually re- quire transforming the unstructured textual infor- mation into structured information as input of the 2 Evidence type classification reasoning framework. This paper proposes a pre- liminary step towards the issue of providing this In (Mayer et al., 2018), as a first step towards the transformation, starting from RCT, i.e., documents extraction of argumentative information from clin- reporting experimental studies in the medical do- ical data, we extended an existing corpus (Trenta main. More precisely, the research question we et al., 2015) on RCT abstracts, with the annota- answer in this paper is: how to distinguish differ- tions of the different argument components (evi- ent kinds of evidence in RCT, so that fine-grained dence, claim, major claim). The structure of RCTs evidence-based decision making activities are sup- should follow the CONSORT policies to ensure ported? a minimum consensus, which makes the studies comparable and ideal for building a corpus1. RCT risk of bias, when it comes to determining the abstracts were retrieved directly from PubMed2 by quality of the evidence. As stated by (Bellomo searching for the disease name and specifying that and Bagshaw, 2006) there are also other aspects it has to be a RCT. This version of the corpus with of the trial quality, which impinge upon the truth- coarse labels contains 927 argument components fulness of the findings. As a step forward, in this (679 evidence and 248 claims) from 159 abstracts work we extend the corpus annotation, specifying comprising 4 different diseases (glaucoma, hyper- four classes of evidence, which are most promi- tension, hepatitis b, diabetes). nent in our data and assist in assessing these com- In particular, an evidence in a RCT is an obser- plex quality dimensions, like reproducibility, gen- vation or measurement in the study (ground truth), eralizability or the estimate of effect: which supports or attacks another argument com- comparative: when there is some kind of com- ponent, usually a claim. Those observations com- parison between the control and intervention arms prise side effects and the measured outcome of the (Table1, example 2). Supporting the search for intervention and control arm. They are observed similarities in outcomes of different studies, which facts, and therefore credible without further justi- is an important measure for the reproducibility. fications, since this is the ground truth the argu- mentation is based on. In Example 1, evidence significance: for any sentence stating that the re- are in italic, underlined and surrounded by square sults are statistically significant (Table1, example brackets with subscripts, while claims are in bold. 3). Many comparative sentences also contain sta- tistical information. However, this class can be Example 1: To compare the intraocular pressure- seen more as a measure for the strength of ben- lowering effect of latanoprost with that eficial or potentially harmful outcomes. of dorzolamide when added to timolol. [. ] [The diurnal intraocular pressure side-effect: captures all evidence reporting any reduction was significant in both groups side-effect or adverse drug effect to see if poten- (P < 0:001)]1.[The mean intraocular pres- tial harms outweigh the benefits of an intervention sure reduction from baseline was 32% for the (Table1, example 4). latanoprost plus timolol group and 20% for other: all the evidence that do not fall under the the dorzolamide plus timolol group]2.[The least square estimate of the mean diurnal in- other categories, like non-comparative observa- traocular pressure reduction after 3 months tions, risk factors or limitations of the study (too was -7.06 mm Hg in the latanoprost plus rare occurrences to form new classes). Especially timolol group and -4.44 mm Hg in the dor- the latter can be relevant for the generalizabil- ity of the outcome of a study (Table1, example 5). zolamide plus timolol group (P < 0:001)]3. Drugs administered in both treatment groups were well tolerated. This study clearly Table2 shows the statistics of the obtained dataset. showed that [the additive diurnal intraocu- Three annotators have annotated the data after a lar pressure-lowering effect of latanoprost training phase. Inter Annotator Agreement has is superior to that of dorzolamide in pa- been calculated on 10 abstracts comprising 47 ev- idence, resulting in a Fleiss’ kappa of 0.88. tients treated with timolol]1. Example 1 shows different reports of the experi- 3 Proposed methods mental outcomes as evidence. Those can be re- In (Mayer et al., 2018), we addressed the argument sults without concrete measurement values (see component detection as a supervised text classifi- evidence 1), or exact measured values (see evi- cation problem: given a collection of sentences, dence 2 and 3). Different measures are annotated each labeled with the presence/absence of an argu- as multiple evidence. The reporting of side effects ment component, the goal is to train a classifier to and negative observations are also considered as detect the argumentative sentences. We retrained evidence. Traditionally evidence-based medicine an existing system, i.e. MARGOT (Lippi and Tor- (EBM) focuses mainly on the study design and roni, 2016b), to detect evidence and claims from 1http://www.consort-statement.org/ clinical data. The methods we used are SubSet 2https://www.ncbi.nlm.nih.gov/pubmed/ Tree Kernels (SSTK) (Collins and Duffy, 2002), 1. Brimonidine provides a sustained long-term ocular As a step forward - after the distinction be- hypotensive effect, is well tolerated, and has a low rate of allergic response. tween argumentative (claims and evidence) and 2. The overall success rates were 87% for the 350-mm2 non-argumentative sentences - we address the task group and 70% for the 500-mm2 group (P = 0:05). of distinguishing the different types of evidence 3. All regimens produced clinically relevant and statistically significant (P < :05) intraocular pressure (see Section2). We cast it as a multi-class classi- reductions from baseline. fication problem. For that we use Support Vector 4. Allergy was seen in 9 % of subjects treated with Machines (SVMs)3 with a linear kernel and dif- brimonidine. 5. Risk of all three outcomes was higher for participants ferent strategies to transform the multi-class into with chronic kidney disease or frailty.
Load more

Recommended publications
  • No-Decision Classification: an Alternative to Testing for Statistical
    The Journal of Socio-Economics 33 (2004) 631–650 No-decision classification: an alternative to testing for statistical significance Nathan Berga,b,∗ a School of Social Sciences, University of Texas at Dallas, GR 31 211300, Box 830688, Richardson, TX 75083-0688, USA b Center for Adaptive Behavior and Cognition, Max Planck Institute for Human Development, Berlin, Germany Abstract This paper proposes a new statistical technique for deciding which of two theories is better supported by a given set of data while allowing for the possibility of drawing no conclusion at all. Procedurally similar to the classical hypothesis test, the proposed technique features three, as opposed to two, mutually exclusive data classifications: reject the null, reject the alternative, and no decision. Referred to as No-decision classification (NDC), this technique requires users to supply a simple null and a simple alternative hypothesis based on judgments concerning the smallest difference that can be regarded as an economically substantive departure from the null. In contrast to the classical hypothesis test, NDC allows users to control both Type I and Type II errors by specifying desired probabilities for each. Thus, NDC integrates judgments about the economic significance of estimated magnitudes and the shape of the loss function into a familiar procedural form. © 2004 Elsevier Inc. All rights reserved. JEL classification: C12; C44; B40; A14 Keywords: Significance; Statistical significance; Economic significance; Hypothesis test; Critical region; Type II; Power ∗ Corresponding author. Tel.: +1 972 883 2088; fax +1 972 883 2735. E-mail address: [email protected]. 1053-5357/$ – see front matter © 2004 Elsevier Inc. All rights reserved.
    [Show full text]
  • Comparison of Machine Learning Techniques When Estimating Probability of Impairment
    Comparison of Machine Learning Techniques when Estimating Probability of Impairment Estimating Probability of Impairment through Identification of Defaulting Customers one year Ahead of Time Authors: Supervisors: Alexander Eriksson Prof. Oleg Seleznjev Jacob Långström Xun Su June 13, 2019 Student Master thesis, 30 hp Degree Project in Industrial Engineering and Management Spring 2019 Abstract Probability of Impairment, or Probability of Default, is the ratio of how many customers within a segment are expected to not fulfil their debt obligations and instead go into Default. This isakey metric within banking to estimate the level of credit risk, where the current standard is to estimate Probability of Impairment using Linear Regression. In this paper we show how this metric instead can be estimated through a classification approach with machine learning. By using models trained to find which specific customers will go into Default within the upcoming year, based onNeural Networks and Gradient Boosting, the Probability of Impairment is shown to be more accurately estimated than when using Linear Regression. Additionally, these models provide numerous real-life implementations internally within the banking sector. The new features of importance we found can be used to strengthen the models currently in use, and the ability to identify customers about to go into Default let banks take necessary actions ahead of time to cover otherwise unexpected risks. Key Words Classification, Imbalanced Data, Machine Learning, Probability of Impairment, Risk Management Sammanfattning Titeln på denna rapport är En jämförelse av maskininlärningstekniker för uppskattning av Probability of Impairment. Uppskattningen av Probability of Impairment sker genom identifikation av låntagare som inte kommer fullfölja sina återbetalningsskyldigheter inom ett år.
    [Show full text]
  • Binary Classification Models with “Uncertain” Predictions
    Binary classification models with “Uncertain” predictions Damjan Krstajic1§, Ljubomir Buturovic2, Simon Thomas3, David E Leahy4 1Research Centre for Cheminformatics, Jasenova 7, 11030 Beograd, Serbia 2Clinical Persona, 932 Mouton Circle, East Palo Alto, CA 94303, USA 3Cyprotex Discovery Ltd, No. 24 Mereside, Alderley Park, Macclesfield SK10 4TG, UK 4Discovery Bus Ltd, The Oakridge Centre, Gibhill Farm, Shrigley Rd, Macclesfield, SK10 5SE, UK §Corresponding author Email addresses: DK: [email protected] LB: [email protected] ST: [email protected] DEL: [email protected] - 1 - Abstract Binary classification models which can assign probabilities to categories such as “the tissue is 75% likely to be tumorous” or “the chemical is 25% likely to be toxic” are well understood statistically, but their utility as an input to decision making is less well explored. We argue that users need to know which is the most probable outcome, how likely that is to be true and, in addition, whether the model is capable enough to provide an answer. It is the last case, where the potential outcomes of the model explicitly include ‘don’t know’ that is addressed in this paper. Including this outcome would better separate those predictions that can lead directly to a decision from those where more data is needed. Where models produce an “Uncertain” answer similar to a human reply of “don’t know” or “50:50” in the examples we refer to earlier, this would translate to actions such as “operate on tumour” or “remove compound from use” where the models give a “more true than not” answer.
    [Show full text]
  • Social Dating: Matching and Clustering
    Social Dating: Matching and Clustering SangHyeon (Alex) Ahn Jin Yong Shin 3900 North Charles St 3900 North Charles St Baltimore, MD 21218, USA Baltimore, MD 21218, USA [email protected] [email protected] Abstract 1 Introduction Purpose of the paper was to apply machine learn- Social dating is a stage of interpersonal rela- ing algorithms for Social Dating problems and build tionship between two individuals for with the tools to be used for smarter decision making in aim of each assessing the other’s suitability as matching process. We used the data from Speed Dat- a partner in a more committed intimate rela- ing Experiment (of 21 waves) which includes each tionship or marriage. Today, many individ- candidate’s demographic attributes and preferences. uals spend a lot of money, time, and effort We have selected relevant features to provide the for the search of their true partners. Some most informative data and used SQL to inner join reasons for the inefficiency in seeking sexual partners include limited pool of candidates, missing feature variables. lack of transparency in uncovering personal- We implemented Machine Learning algorithms ities, and the nature of time consumption in (without the use of external libraries) to perform building relationships. Finding the right part- (1) binary classifications to predict a date match ner in a machine driven automated process can between a candidate and a potential partner, and be beneficial towards increasing efficiency in (2) clustering analysis on candidates to use narrow the following aspects: reduced time and ef- down a pool of candidates by demographic traits fort, a larger pool, and a level of quantita- and partner preferences.
    [Show full text]
  • How Will AI Shape the Future of Law?
    View metadata, citation and similar papers at core.ac.uk brought to you by CORE provided by Helsingin yliopiston digitaalinen arkisto How Will AI Shape the Future of Law? EDITED BY RIIKKA KOULU & LAURA KONTIAINEN 2019 Acknowledgements The editors and the University of Helsinki Legal Tech Lab would like to thank the authors and interviewees for the time and effort they put into their papers. We would also like to thank the Faculty of Law at University of Helsinki and particularly the continuous kind support of Professor Kimmo Nuotio, the former dean of the faculty and the Lab’s unofficial godfather, for facilitating the Lab’s development and for helping us make the second Legal Tech Conference happen. In addition, we would like to express our gratitude to the conference sponsors, Finnish Bar Association, the Association of Finnish Lawyers, Edita Publishing, Attorneys at Law Fondia and Attorneys at Law Roschier as well as the Legal Design Summit community for their support. It takes a village to raise a conference. Therefore, we would like to thank everyone whose time and commitment has turned the conference and this publication from an idea into reality. Thank you to the attendees, speakers, volunteers and Legal Tech Lab crew members. RIIKKA KOULU & LAURA KONTIAINEN Legal Tech Lab, University of Helsinki 2019 University of Helsinki Legal Tech Lab publications © Authors and Legal Tech Lab ISBN 978-951-51-5476-7 (print) ISBN 978-951-51-5477-4 (PDF) Print Veiters Helsinki 2019 Contents Foreword 009 KIMMO NUOTIO I Digital Transformation of
    [Show full text]
  • Gaussian Process Classification Using Privileged Noise
    Mind the Nuisance: Gaussian Process Classification using Privileged Noise Daniel Hernandez-Lobato´ Viktoriia Sharmanska Universidad Autonoma´ de Madrid IST Austria Madrid, Spain Klosterneuburg, Austria [email protected] [email protected] Kristian Kersting Christoph H. Lampert TU Dortmund IST Austria Dortmund, Germany Klosterneuburg, Austria [email protected] [email protected] Novi Quadrianto SMiLe CLiNiC, University of Sussex Brighton, United Kingdom [email protected] Abstract The learning with privileged information setting has recently attracted a lot of at- tention within the machine learning community, as it allows the integration of ad- ditional knowledge into the training process of a classifier, even when this comes in the form of a data modality that is not available at test time. Here, we show that privileged information can naturally be treated as noise in the latent function of a Gaussian process classifier (GPC). That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC probit likelihood function. Extensive experiments on public datasets show that the proposed GPC method using privileged noise, called GPC+, improves over a stan- dard GPC without privileged knowledge, and also over the current state-of-the-art SVM-based method, SVM+. Moreover, we show that advanced neural networks and deep learning methods can be compressed as privileged information. 1 Introduction Prior knowledge is a crucial component of any learning system as without a form of prior knowl- edge learning is provably impossible [1].
    [Show full text]
  • Binary Classification Approach to Ordinal Regression
    Binary Classification Approach to Ordinal Regression Jianhao Peng [email protected] Abstract In the lecture we mainly focus on questions about binary classification or regres- sion. However in many cases we may want the results to show preference in terms of several discrete, but ordered, values, like ratings of a restaurant, disease condition and students' letter grades. Such problems are usually known as ordinal regression or ordinal classification. Standard approaches to ordinal regression in statistics require a assumption on the distribution of a latent variable while many other learning methods treat this as a multiclass problem, which may lose the order information in the data. In this paper I first present the probability model of ordinal regression in traditional statistics, then briefly go through different types of loss function defined from two per- spectives in order to reduce the problem to simple binary case. From the loss function we can also get performance bounds similar to those we learnt in binary classification. 1 Introduction Compared to the standard machine learning tasks of classification or regression, there exist many other systems in which users specify preferences by giving each sample one of several discrete values, e.g. one through five stars in movie or restaurant rating and A through F in letter grades. Those problems are often considered as multiclass classification, which treated the labels as a finite unordered nominal set. However in that case the natural order structure of the data is ignored and may not be as accurate. Therefore one nature question arises: can we make use of the lost ordinal information to potentially improve the predictive performance of the classifier or simplify the learning algorithm? Such question has been studied in statistics for decades.
    [Show full text]
  • Analysis of Confirmed Cases of COVID-19
    sustainability Article Investigating a Serious Challenge in the Sustainable Development Process: Analysis of Confirmed cases of COVID-19 (New Type of Coronavirus) Through a Binary Classification Using Artificial Intelligence and Regression Analysis Behrouz Pirouz 1 , Sina Shaffiee Haghshenas 2,* , Sami Shaffiee Haghshenas 2 and Patrizia Piro 2 1 Department of Mechanical, Energy and Management Engineering, University of Calabria, 87036 Rende, Italy; [email protected] 2 Department of Civil Engineering, University of Calabria, 87036 Rende, Italy; Sami.shaffi[email protected] (S.S.H.); [email protected] (P.P.) * Correspondence: S.shaffi[email protected]; Tel.: +39-0984-496-542 Received: 5 March 2020; Accepted: 16 March 2020; Published: 20 March 2020 Abstract: Nowadays, sustainable development is considered a key concept and solution in creating a promising and prosperous future for human societies. Nevertheless, there are some predicted and unpredicted problems that epidemic diseases are real and complex problems. Hence, in this research work, a serious challenge in the sustainable development process was investigated using the classification of confirmed cases of COVID-19 (new version of Coronavirus) as one of the epidemic diseases. Hence, binary classification modeling was used by the group method of data handling (GMDH) type of neural network as one of the artificial intelligence methods. For this purpose, the Hubei province in China was selected as a case study to construct the proposed model, and some important factors, namely maximum, minimum, and average daily temperature, the density of a city, relative humidity, and wind speed, were considered as the input dataset, and the number of confirmed cases was selected as the output dataset for 30 days.
    [Show full text]
  • Estimating the Operating Characteristics of Ensemble Methods
    Estimating the Operating Characteristics of Ensemble Methods Anthony Gamst Jay-Calvin Reyes Alden Walker March 2017 Abstract Suppose we would like to compare the performance of two binary classi- fication algorithms. If we have their receiver operating characteristic (ROC) curves, then one might conclude that the algorithm corresponding to the higher ROC curve is better. This conclusion may not be correct due to vari- ability in the ROC curves. Two sources of variability are randomness in the procedure used to train each classifier and randomness in the sample of feature vectors that form the test data set. In this paper we present a technique for using the bootstrap to estimate the operating characteristics and their variability for certain types of ensem- ble methods. Bootstrapping a model can require a huge amount of work if the training data set is large. Fortunately in many cases the technique lets us determine the effect of infinite resampling without actually refitting a single model. We apply the technique to the study of meta-parameter selection for random forests. Wep demonstrate that alternatives to bootstrap aggregation and to considering d features to split each node, where d is the number of features, can produce improvements in predictive accuracy. arXiv:1710.08952v1 [stat.ML] 24 Oct 2017 1 Introduction Suppose we would like to compare the performance of two binary classification algorithms. The receiver operating characteristic (ROC) curve for each algorithm is shown in Figure 1. A ROC curve is simply a plot of the true positive rate (TPR) against the false positive rate (FPR) as the discrimination threshold is varied.
    [Show full text]
  • Binary Classification and Logistic Regression Models Application to Crash Severity
    BINARY CLASSIFICATION AND LOGISTIC REGRESSION MODELS APPLICATION TO CRASH SEVERITY GUILHERMINA A. TORRÃO, MSC. GRADUATE STUDENT, MECHANICAL ENGINEERING CENTRE FOR MECHANICAL TECHNOLOGY AND AUTOMATION AND DEPARTMENT OF MECHANICAL ENGINEERING, UNIVERSITY OF AVEIRO CAMPUS UNIVERSITÁRIO DE SANTIAGO, 3810-193 AVEIRO, PORTUGAL PHONE: (+351) 234 378 181 E-MAIL: [email protected] NAGUI M. ROUPHAIL, PH.D. DIRECTOR, INSTITUTE FOR TRANSPORTATION RESEARCH AND EDUCATION (ITRE) PROFESSOR OF CIVIL ENGINEERING, NORTH CAROLINA STATE UNIVERSITY RALEIGH, NC, 27695-8601, USA PHONE: (919) 515-1154 E-MAIL: [email protected] MARGARIDA C COELHO, PH.D. ASSISTANT PROFESSOR, MECHANICAL ENGINEERING CENTRE FOR MECHANICAL TECHNOLOGY AND AUTOMATION AND DEPARTMENT OF MECHANICAL ENGINEERING, UNIVERSITY OF AVEIRO CAMPUS UNIVERSITÁRIO DE SANTIAGO, 3810-193 AVEIRO, PORTUGAL PHONE: (+351) 234 370 830 EMAIL: [email protected] This is an abridged version of the paper presented at the conference. The full version is being submitted elsewhere. Details on the full paper can be obtained from the author. Binary Classification and Logistic Regression Models Application to Crash Severity TORRÃO, Guilhermina; ROUPHAIL, Nagui, COELHO, Margarida; BINARY CLASSIFICATION AND LOGISTIC REGRESSION MODELS APPLICATION TO CRASH SEVERITY Guilhermina A. Torrão, MSc. Graduate Student, Mechanical Engineering Centre for Mechanical Technology and Automation and Department of Mechanical Engineering, University of Aveiro Campus Universitário de Santiago, 3810-193 Aveiro, Portugal Phone: (+351) 234 378 181 E-mail: [email protected] Nagui M. Rouphail, Ph.D. Director, Institute for Transportation Research and Education (ITRE) Professor of Civil Engineering, North Carolina State University Raleigh, NC, 27695-8601, USA Phone: (919) 515-1154 E-mail: [email protected] Margarida C Coelho, Ph.D.
    [Show full text]
  • Benchmarking Machine Learning Models for the Analysis of Genetic Data Using FRESA.CAD Binary Classification Benchmarking
    bioRxiv preprint doi: https://doi.org/10.1101/733675; this version posted August 13, 2019. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under aCC-BY-ND 4.0 International license. de Velasco Oriol et al. SOFTWARE Benchmarking machine learning models for the analysis of genetic data using FRESA.CAD Binary Classification Benchmarking Javier de Velasco Oriol1*y, Antonio Martinez-Torteya2, Victor Trevino1, Israel Alanis1, Edgar E. Vallejo1^ and Jose Gerardo Tamez-Pena1y *Correspondence: [email protected] Abstract 1Escuela Nacional de Medicina y Ciencias de la Salud, Tecnologico Background: Machine learning models have proven to be useful tools for the de Monterrey, Ave. Morones analysis of genetic data. However, with the availability of a wide variety of such Prieto 3000, 64710 Monterrey, Nuevo Leon, Mexico methods, model selection has become increasingly difficult, both from the human Full list of author information is and computational perspective. available at the end of the article yEqual contributor^Deceased June Results: We present the R package FRESA.CAD Binary Classification 11,2019 Benchmarking that performs systematic comparisons between a collection of representative machine learning methods for solving binary classification problems on genetic datasets. Conclusions: FRESA.CAD Binary Benchmarking demonstrates to be a useful tool over a variety of binary classification problems comprising the analysis of genetic data showing both quantitative and qualitative advantages over similar packages. Keywords: Machine learning; model selection; R; FRESA.CAD Background There is an increasing interest in using Machine Learning (ML) models for address- ing questions on the analysis of genetic data [1, 2].
    [Show full text]
  • Measuring the Effects of Confounders in Medical Supervised Classification
    Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI) Elisa Ferraria,b, Alessandra Reticob, Davide Bacciuc aScuola Normale Superiore, Italy. bPisa Division, INFN, Italy. cDipartimento di Informatica, Universit`adi Pisa, Italy. Abstract Over the years, there has been growing interest in using Machine Learning tech- niques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called con- founders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to handle confounders, ranging from data selection, to normalization techniques, up to the use of training algorithm for learning with imbalanced data. However, all these solutions require the con- founders to be known a priori. To this aim, we introduce a novel index that is able to measure the confounding effect of a data attribute in a bias-agnostic way. This index can be used to quantitatively compare the confounding effects of different variables and to inform correction methods such as normalization procedures or ad-hoc-prepared learning algorithms. The effectiveness of this index is validated on both simulated data and real-world neuroimaging data. Keywords: Machine Learning, Confounding variables, Biomedical Data, Classification arXiv:1905.08871v2 [cs.LG] 3 Feb 2020 1. Introduction In the last years, there has been a growing interest in the use of super- vised learning in biomedical contexts.
    [Show full text]