The Promise of Machine Learning: When Will it be Delivered?

Research output: Contribution to journalEditorial

1 Citation (Scopus)

Abstract

Background: The real-life applications of machine learning clinical decision making is currently lagging behind its promise. One of the critics on machine learning is that it doesn't outperform more traditional statistical approaches in every problem. Methods and Results: Authors of “Predictive Abilities of Machine Learning Techniques May Be Limited by Dataset Characteristics: Insights From the UNOS Database” presented in the current issue of the Journal of Cardiac Failure that machine learning approaches do not provide significantly higher performance when compared to more traditional statistical approaches in predicting mortality following heart transplant. In this brief report, we provide an insight on the possible reasons for why machine learning methods do not outperform more traditional approaches for every problem and every dataset. Conclusions: Most of the performance-focused critics on machine learning are because the bar is set unfairly too high for machine learning. In most cases, machine learning methods provides at least as good results as traditional statistical methods do. It is normal for machine learning models to provide similar performance with linear models if the actual underlying input-outcome relationship is linear. Moreover, machine learning methods outperforms linear statistical models when the underlying input-output relationship is not linear and if the dataset is large enough and include predictors capturing that nonlinear relationship.

Original languageEnglish (US)
Pages (from-to)484-485
Number of pages2
JournalJournal of Cardiac Failure
Volume25
Issue number6
DOIs
StatePublished - Jun 1 2019

Fingerprint

Linear Models
Machine Learning
Statistical Models
Heart Failure
Databases
Transplants
Mortality
Datasets
Clinical Decision-Making

All Science Journal Classification (ASJC) codes

  • Cardiology and Cardiovascular Medicine

Cite this

The Promise of Machine Learning : When Will it be Delivered? / Akbilgic, Oguz; Davis, Robert.

In: Journal of Cardiac Failure, Vol. 25, No. 6, 01.06.2019, p. 484-485.

Research output: Contribution to journalEditorial

@article{13921bbdb93249fabf63076a015878ef,
title = "The Promise of Machine Learning: When Will it be Delivered?",
abstract = "Background: The real-life applications of machine learning clinical decision making is currently lagging behind its promise. One of the critics on machine learning is that it doesn't outperform more traditional statistical approaches in every problem. Methods and Results: Authors of “Predictive Abilities of Machine Learning Techniques May Be Limited by Dataset Characteristics: Insights From the UNOS Database” presented in the current issue of the Journal of Cardiac Failure that machine learning approaches do not provide significantly higher performance when compared to more traditional statistical approaches in predicting mortality following heart transplant. In this brief report, we provide an insight on the possible reasons for why machine learning methods do not outperform more traditional approaches for every problem and every dataset. Conclusions: Most of the performance-focused critics on machine learning are because the bar is set unfairly too high for machine learning. In most cases, machine learning methods provides at least as good results as traditional statistical methods do. It is normal for machine learning models to provide similar performance with linear models if the actual underlying input-outcome relationship is linear. Moreover, machine learning methods outperforms linear statistical models when the underlying input-output relationship is not linear and if the dataset is large enough and include predictors capturing that nonlinear relationship.",
author = "Oguz Akbilgic and Robert Davis",
year = "2019",
month = "6",
day = "1",
doi = "10.1016/j.cardfail.2019.04.006",
language = "English (US)",
volume = "25",
pages = "484--485",
journal = "Journal of Cardiac Failure",
issn = "1071-9164",
publisher = "Churchill Livingstone",
number = "6",

}

TY - JOUR

T1 - The Promise of Machine Learning

T2 - When Will it be Delivered?

AU - Akbilgic, Oguz

AU - Davis, Robert

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Background: The real-life applications of machine learning clinical decision making is currently lagging behind its promise. One of the critics on machine learning is that it doesn't outperform more traditional statistical approaches in every problem. Methods and Results: Authors of “Predictive Abilities of Machine Learning Techniques May Be Limited by Dataset Characteristics: Insights From the UNOS Database” presented in the current issue of the Journal of Cardiac Failure that machine learning approaches do not provide significantly higher performance when compared to more traditional statistical approaches in predicting mortality following heart transplant. In this brief report, we provide an insight on the possible reasons for why machine learning methods do not outperform more traditional approaches for every problem and every dataset. Conclusions: Most of the performance-focused critics on machine learning are because the bar is set unfairly too high for machine learning. In most cases, machine learning methods provides at least as good results as traditional statistical methods do. It is normal for machine learning models to provide similar performance with linear models if the actual underlying input-outcome relationship is linear. Moreover, machine learning methods outperforms linear statistical models when the underlying input-output relationship is not linear and if the dataset is large enough and include predictors capturing that nonlinear relationship.

AB - Background: The real-life applications of machine learning clinical decision making is currently lagging behind its promise. One of the critics on machine learning is that it doesn't outperform more traditional statistical approaches in every problem. Methods and Results: Authors of “Predictive Abilities of Machine Learning Techniques May Be Limited by Dataset Characteristics: Insights From the UNOS Database” presented in the current issue of the Journal of Cardiac Failure that machine learning approaches do not provide significantly higher performance when compared to more traditional statistical approaches in predicting mortality following heart transplant. In this brief report, we provide an insight on the possible reasons for why machine learning methods do not outperform more traditional approaches for every problem and every dataset. Conclusions: Most of the performance-focused critics on machine learning are because the bar is set unfairly too high for machine learning. In most cases, machine learning methods provides at least as good results as traditional statistical methods do. It is normal for machine learning models to provide similar performance with linear models if the actual underlying input-outcome relationship is linear. Moreover, machine learning methods outperforms linear statistical models when the underlying input-output relationship is not linear and if the dataset is large enough and include predictors capturing that nonlinear relationship.

UR - http://www.scopus.com/inward/record.url?scp=85065023500&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065023500&partnerID=8YFLogxK

U2 - 10.1016/j.cardfail.2019.04.006

DO - 10.1016/j.cardfail.2019.04.006

M3 - Editorial

C2 - 30978508

AN - SCOPUS:85065023500

VL - 25

SP - 484

EP - 485

JO - Journal of Cardiac Failure

JF - Journal of Cardiac Failure

SN - 1071-9164

IS - 6

ER -