Ensemble learning methods for decision making: Status and future prospects

Abstract Background Machine learning is a broad term encompassing a number of methods that allow the investigator to learn from the data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient-provider decision making. Methods This systematic literature review was conducted to identify published observational research of employed machine learning to inform decision making at the patient-provider level. The search strategy was implemented and studies meeting eligibility criteria were evaluated by two independent reviewers. Relevant data related to study design, statistical methods and strengths and limitations were identified; study quality was assessed using a modified version of the Luo checklist. Results A total of 34 publications from January 2014 to September 2020 were identified and evaluated for this review. There were diverse methods, statistical packages and approaches used across identified studies. The most common methods included decision tree and random forest approaches. Most studies applied internal validation but only two conducted external validation. Most studies utilized one algorithm, and only eight studies applied multiple machine learning algorithms to the data. Seven items on the Luo checklist failed to be met by more than 50% of published studies. Conclusions A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of machine learning methods to inform patient-provider decision making. There is a need to ensure that multiple machine learning approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that decisions for patient care are being made with the highest quality evidence. Future work should routinely employ ensemble methods incorporating multiple machine learning algorithms.

Download Full-text

Prediction of hERG potassium channel blockage using ensemble learning methods and molecular fingerprints

Toxicology Letters ◽

10.1016/j.toxlet.2020.07.003 ◽

2020 ◽

Vol 332 ◽

pp. 88-96 ◽

Cited By ~ 1

Author(s):

Miao Liu ◽

Li Zhang ◽

Shimeng Li ◽

Tianzhou Yang ◽

Lili Liu ◽

...

Keyword(s):

Potassium Channel ◽

Ensemble Learning ◽

Learning Methods ◽

Molecular Fingerprints ◽

Channel Blockage

Download Full-text

Targeting Customers for Profit: An Ensemble Learning Framework to Support Marketing Decision Making

SSRN Electronic Journal ◽

10.2139/ssrn.3130661 ◽

2018 ◽

Cited By ~ 1

Author(s):

Stefan Lessmann ◽

Kristof Coussement ◽

Koen De Bock ◽

Johannes Haupt

Keyword(s):

Decision Making ◽

Ensemble Learning ◽

For Profit ◽

Learning Framework ◽

Marketing Decision

Download Full-text

Digital Education, Work and Artificial Intelligence: Health and Law

EDEN Conference Proceedings ◽

10.38069/edenconf-2020-ac0026 ◽

2020 ◽

pp. 277-288

Author(s):

Abílio Azevedo ◽

Patricia Anjos Azevedo

Keyword(s):

Artificial Intelligence ◽

Decision Making ◽

Qualitative Methodology ◽

Learning Methods ◽

Digital Education ◽

Ethical Concerns ◽

Application Potential ◽

New Challenges ◽

Formal Application ◽

Daily Application

The use and possibilities of artificial intelligence (AI) have been assuming great importance in recent years. This fact led to a greater attention on the topic in various fields, especially in health and law, both in its daily application potential and in learning methods. The aim of this article was to present a brief perspective of the challenges and effects of the AI use in teaching and application on health and law domains. Therefore, to better define the theme it was performed a qualitative methodology of bibliographic review. The applications of artificial intelligence have a great potential in clinical and legal use, facilitating the tasks of those involved by helping to reduce workflow, to avoid errors and in decision-making. However, despite these benefits and new opportunities, there are still obstacles regarding regulation and ethical concerns, as well as some reluctance from professionals in their adoption and formal application. In addition, there also the need to proper implement these technologies in learning to keep up the change and the new challenges currently posed, so there is a path that still needs to be followed.

Download Full-text