A tutorial on variable selection for clinical prediction models: feature selection methods in data mining could improve the results

Bagherzadeh‐Khiabani, Farideh; Ramezankhani, Azra; Azizi, Fereidoun; Hadaegh, Farzad; Steyerberg, Ewout W.; Khalili, Davood

doi:10.1016/j.jclinepi.2015.10.002

Cited by 131 publications

(94 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first category deals with biomarker discovery, which is a task mainly performed through feature selection techniques [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34]. Following a feature selection step, a classification algorithm is employed to assess the prediction accuracy of the selected features.…”

Section: Dm Through Machine Learning and Data Miningmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning and Data Mining Methods in Diabetes Research

Kavakiotis

Tsave

Salifoglou

et al. 2017

Computational and Structural Biotechnology Journal

1,021

530

View full text Add to dashboard Cite

The remarkable advances in biotechnology and health sciences have led to a significant production of data, such as high throughput genetic data and clinical information, generated from large Electronic Health Records (EHRs). To this end, application of machine learning and data mining methods in biosciences is presently, more than ever before, vital and indispensable in efforts to transform intelligently all available information into valuable knowledge. Diabetes mellitus (DM) is defined as a group of metabolic disorders exerting significant pressure on human health worldwide. Extensive research in all aspects of diabetes (diagnosis, etiopathophysiology, therapy, etc.) has led to the generation of huge amounts of data. The aim of the present study is to conduct a systematic review of the applications of machine learning, data mining techniques and tools in the field of diabetes research with respect to a) Prediction and Diagnosis, b) Diabetic Complications, c) Genetic Background and Environment, and e) Health Care and Management with the first category appearing to be the most popular. A wide range of machine learning algorithms were employed. In general, 85% of those used were characterized by supervised learning approaches and 15% by unsupervised ones, and more specifically, association rules. Support vector machines (SVM) arise as the most successful and widely used algorithm. Concerning the type of data, clinical datasets were mainly used. The title applications in the selected articles project the usefulness of extracting valuable knowledge leading to new hypotheses targeting deeper understanding and further investigation in DM.

show abstract

Section: Dm Through Machine Learning and Data Miningmentioning

confidence: 99%

“…In [25], the authors used a clinical dataset comprised of 803 prediabetic females with 55 features and compared several common feature selection algorithms (both wrapper and filter methods) to predict DM. They concluded that the best overall performance had been achieved through wrapper methods.…”

Section: Dm Through Machine Learning and Data Miningmentioning

confidence: 99%

Machine Learning and Data Mining Methods in Diabetes Research

Kavakiotis

Tsave

Salifoglou

et al. 2017

Computational and Structural Biotechnology Journal

1,021

530

View full text Add to dashboard Cite

show abstract

“…Here, the input gate of the ith LSTM unit will be connected to the signal value at the time point + ( , 5 ), which is a row vector with 9 features as the input of each LSTM unit. We can formulate the prediction function as: ∆ e 1 = ( , 8 , , j , … , , k ) where the output ∆ e 1 is the estimated change of a patient's HbA1c after one year, and the function f represents the proposed model. The desired output of the function f is a single value of ∆ e 1 .…”

Section: Long Short-term Memory Networkmentioning

confidence: 99%

Multi-modal Predictive Models of Diabetes Progression

Ramazi

Perndorfer

Soriano

et al. 2019

Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

View full text Add to dashboard Cite

With the increasing availability of wearable devices, continuous monitoring of individuals' physiological and behavioral patterns has become significantly more accessible. Access to these continuous patterns about individuals' statuses offers an unprecedented opportunity for studying complex diseases and health conditions such as type 2 diabetes (T2D). T2D is a widely common chronic disease that its roots and progression patterns are not fully understood. Predicting the progression of T2D can inform timely and more effective interventions to prevent or manage the disease. In this study, we have used a dataset related to 63 patients with T2D that includes the data from two different types of wearable devices worn by the patients: continuous glucose monitoring (CGM) devices and activity trackers (ActiGraphs). Using this dataset, we created a model for predicting the levels of four major biomarkers related to T2D after a one-year period. We developed a wide and deep neural network and used the data from the demographic information, lab tests, and wearable sensors to create the model. The deep part of our method was developed based on the long short-term memory (LSTM) structure to process the time-series dataset collected by the wearables. In predicting the patterns of the four biomarkers, we have obtained a root mean square error of ±1.67% for HBA1c, ±6.22 mg/dl for HDL cholesterol, ±10.46 mg/dl for LDL cholesterol, and ±18.38 mg/dl for Triglyceride. Compared to existing models for studying T2D, our model offers a more comprehensive tool for combining a large variety of factors that contribute to the disease. CCS CONCEPTS•Applied computing •Life and medical sciences •Health informatics

show abstract

“…So stopping criteria is necessary based on evaluation function. Some of the commonly used criteria such as search is complete or next iteration fails to produce a better subset [30][31][32].…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Developing Diabetes Disease Classification Model using Sequential Forward Selection Algorithm

Hashi¹,

Zaman²,

Hasan³

2017

IJCA

View full text Add to dashboard Cite

Data mining techniques are being used extensively in healthcare sector to discover hidden pattern and relationship between patients' record and their medical diagnosis dataset. In the concept of disease prediction, high classification accuracy can be obtained from accurately pre-processed and trained model. But existence of unimportant and irrelevant attributes in the training dataset may decrease the predictive accuracy and increase the time complexity in training phase. To increase the accuracy and efficiency, feature selection technique is frequently used in data mining. In this paper, a sequential forward selection based wrapper approach is proposed to select optimal and informative feature subset. It is known that diabetes mellitus is the most serious health problem and the complications lead to cause of death. So the aim of this research is to identify the significant attributes and classify diabetes dataset. The proposed approach is used to build the classifier models like Decision tree, K-Nearest Neighbor and Support Vector Machine produces the accuracies of 81.17%, 86.36% and 87.01% respectively. Finally, from results it is clear that the proposed model is performing better with high accuracy comparing the similar existing models. In the research, the Pima Indian diabetes dataset is used.

show abstract

A tutorial on variable selection for clinical prediction models: feature selection methods in data mining could improve the results

Cited by 131 publications

References 26 publications

Machine Learning and Data Mining Methods in Diabetes Research

Machine Learning and Data Mining Methods in Diabetes Research

Multi-modal Predictive Models of Diabetes Progression

Developing Diabetes Disease Classification Model using Sequential Forward Selection Algorithm

Contact Info

Product

Resources

About