Predictive data mining in clinical medicine: Current issues and guidelines

By Riccardo Bellazzi, Blaz Zupan. 2008

870 citations recorded by the source corpus.

BACKGROUND The widespread availability of new computational methods and tools for data analysis and predictive modeling requires medical informatics researchers and practitioners to systematically select the most appropriate strategy to cope with clinical prediction problems. In particular, the collection of methods known as 'data mining' offers methodological and technical solutions to deal with the analysis of medical data and construction of prediction models. A large variety of these methods requires general and simple guidelines that may help practitioners in the appropriate selection of data mining tools, construction and validation of predictive models, along with the dissemination of predictive models within clinical environments. PURPOSE The goal of this review is to discuss the extent and role of the research area of predictive data mining and to propose a framework to cope with the problems of constructing, assessing and exploiting data mining models in clinical medicine. METHODS We review the recent relevant work published in the area of predictive data mining in clinical medicine, highlighting critical issues and summarizing the approaches in a set of learned lessons. RESULTS The paper provides a comprehensive review of the state of the art of predictive data mining in clinical medicine and gives guidelines to carry out data mining studies in this field. CONCLUSIONS Predictive data mining is becoming an essential instrument for researchers and clinical practitioners in medicine. Understanding the main issues underlying these methods and the application of agreed and standardized procedures is mandatory for their deployment and the dissemination of results. Thanks to the integration of molecular and clinical data taking place within genomic medicine, the area has recently not only gained a fresh impulse but also a new set of complex problems it needs to address.

Subfields: Artificial Intelligence, Health Informatics, Health Information Management

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Informatics

In Health Information Management

Citations in the corpus

Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records (2016, methodology): “However, predictive models and tools based on modern machine learning techniques have not been widely and reliably used in clinical decision support systems or workflows 6–9 .”
Data mining techniques and applications — A decade review (2017, background): “It solves many issues of medical field [31].”
Comprehensible classification models: a position paper (2014, background): “, it has been argued that modeling probabilities is very important in clinical practice [5].”
A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality (2017, background): “…among many possibilities, can be found in the following fields: neuroscience with the unveiling of secrets of the brain [70]; clinical medicine [71] by finding pathways to cure cancer [72–74]; biology with explanations for the presence of microbiota in the human gut [75] and termites [76],…”
Deep learning for healthcare: review, opportunities and challenges (2018, neutral): “Although existing models demonstrate great promises (e.g. [7–11]), predictive tools based on machine learning techniques have not been widely applied in medicine [12].”
Performance Evaluation of Machine Learning Algorithms in Post-operative Life Expectancy in the Lung Cancer Patients (2015, background): “Each node in the directed acyclic graph represents a stochastic variable and arcs represent a probabilistic dependency between a node and its parents [9].”
Mining electronic health records: towards better research applications and clinical care (2012, background): “…in the next sections, exploring this knowledge-discovery potential from multivariate health data increasingly involves a suite of statistical, machine-learning and computational methods that are often referred to as data-mining methods or knowledge discovery in databases (KDD) methods 35–37 .”
Interactive knowledge discovery with the doctor-in-the-loop: a practical example of cerebral aneurysms research (2016, background): “This is also supported by Bellazi and Zupan [6], who stress the safety aspect of medical knowledge discovery, which is an often neglected part, as the expert-in-the-loop (in the biomedical sciences, we speak of a ‘‘doctor-in-the-loop’’) is a new paradigm in information-driven medicine, seating the…”
A survey on Data Mining approaches for Healthcare (2013, background): “Data Mining offers novel information regarding healthcare which in turn helpful for making administrative as well as medical decision such as estimation of medical staff, decision regarding health insurance policy, selection of treatments, disease prediction etc. , [8-11].”
Medical big data: promise and challenges (2017, background): “The tasks of data mining can be summarized as description, finding human-interpretable patterns and associations, and prediction, foretelling some response of interest [10].”
Comparison of Variable Selection Methods for Clinical Predictive Modeling (2018, background): “The prediction of clinical outcomes is a common medical information need that is particularly adept to the use of large clinical datasets, making clinical predictive modeling a promising area of study in this era of digital healthcare [3].”
Data Mining for the Internet of Things: Literature Review and Challenges (2015, background): “Treatment record data can be mined to explore ways to cut costs and deliver better medicine [124, 125].”
Machine Learning for Survival Analysis (2019, methodology): “Its uses are legion; for example, Bellazzi and Zupan (2008) built a naïve Bayesian classifier to make predictions in clinical medicine by estimating various probabilities from the data, while Fard et al. (2016) effectively integrated Bayesian methods with an AFT model by extrapolating the prior…”