Patient level analytics using self-organising maps: A case study on Type-1 Diabetes self-care survey responses

Tirunagari, Santosh; Poh, Norman; Aliabadi, Kouros; Windridge, David; Cooke, Debbie

doi:10.1109/cidm.2014.7008682

Cited by 10 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A dimensional reduction in heterogeneous diabetes dataset using Self Organizing Map (SOM) clustering was performed and established similarities among patients using (Unified distance) U-Matrix [ 6 ]. Questionnaires consisting of both text as well as numeric responses were used.…”

Section: Literature Reviewmentioning

confidence: 99%

EAGA-MLP—An Enhanced and Adaptive Hybrid Classification Model for Diabetes Diagnosis

Mishra

Tripathy

Mallick

et al. 2020

Sensors

138

View full text Add to dashboard Cite

Disease diagnosis is a critical task which needs to be done with extreme precision. In recent times, medical data mining is gaining popularity in complex healthcare problems based disease datasets. Unstructured healthcare data constitutes irrelevant information which can affect the prediction ability of classifiers. Therefore, an effective attribute optimization technique must be used to eliminate the less relevant data and optimize the dataset for enhanced accuracy. Type 2 Diabetes, also called Pima Indian Diabetes, affects millions of people around the world. Optimization techniques can be applied to generate a reliable dataset constituting of symptoms that can be useful for more accurate diagnosis of diabetes. This study presents the implementation of a new hybrid attribute optimization algorithm called Enhanced and Adaptive Genetic Algorithm (EAGA) to get an optimized symptoms dataset. Based on readings of symptoms in the optimized dataset obtained, a possible occurrence of diabetes is forecasted. EAGA model is further used with Multilayer Perceptron (MLP) to determine the presence or absence of type 2 diabetes in patients based on the symptoms detected. The proposed classification approach was named as Enhanced and Adaptive-Genetic Algorithm-Multilayer Perceptron (EAGA-MLP). It is also implemented on seven different disease datasets to assess its impact and effectiveness. Performance of the proposed model was validated against some vital performance metrics. The results show a maximum accuracy rate of 97.76% and 1.12 s of execution time. Furthermore, the proposed model presents an F-Score value of 86.8% and a precision of 80.2%. The method is compared with many existing studies and it was observed that the classification accuracy of the proposed Enhanced and Adaptive-Genetic Algorithm-Multilayer Perceptron (EAGA-MLP) model clearly outperformed all other previous classification models. Its performance was also tested with seven other disease datasets. The mean accuracy, precision, recall and f-score obtained was 94.7%, 91%, 89.8% and 90.4%, respectively. Thus, the proposed model can assist medical experts in accurately determining risk factors of type 2 diabetes and thereby help in accurately classifying the presence of type 2 diabetes in patients. Consequently, it can be used to support healthcare experts in the diagnosis of patients affected by diabetes.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

EAGA-MLP—An Enhanced and Adaptive Hybrid Classification Model for Diabetes Diagnosis

Mishra

Tripathy

Mallick

et al. 2020

Sensors

138

View full text Add to dashboard Cite

show abstract

“…SOM is used an un-supervised learning framework to cluster the profiles He used 7×12 hexagonal grid mapping with Gaussian neighborhood functions to detect the similarities and variations in the variables. In another research, conducted by author [2] have used the techniques of SOM to study the behavior of type 1 diabetic patients. From his research outcomes, there were suggestions provided to change or adjust the life style to control diabetics.…”

Section: Introductionmentioning

confidence: 99%

Diabetic analytics: proposed conceptual data mining approaches in type 2 diabetes dataset

Alalwan

2019

IJEECS

View full text Add to dashboard Cite

Diabetes is a fast spreading illness, which makes to worry millions of people around the globe. The people affected by type-2 diabetes are rapidly increasing and there are no effective diagnostic systems to control the diabetics. As per global health statistics, in western countries, population effected by type 2 diabetics are higher in rate and cost factor for treatment is increasing. There are no effective methods to eradicate the diabetes and it leads to carry out an investigative study on this disease. In existing reviews, researchers are using data analysis approaches to link the cause for diabetes with the patients based on the diet, life style, inheritance details, age factor, medical history, etc. to identify the root cause of the problem. By having multiple key factors and historical datasets, there are some data mining tools were developed, to generate new rules on the root cause of the disease and discover new knowledge from the past data’s, but the accuracy was not promising. The main objective of this paper is to carry out a detail literature review and design a conceptual data mining method at initial stage and implement it to improve the result accuracy compared to other classifiers. In this research, two data-mining algorithm were proposed at conceptual level: Self Organizing Map (SOM) and Random Forest Algorithm, which is applied on adult population datasets. The data set used for this research are from UCI machine Learning Repository: Diabetes Dataset. In this paper, data mining algorithms were discussed and implementation results were evaluated. Based on the result performance evaluation, Self-organizing maps have performed better compared to the Random Forest and other data mining algorithms such as naïve Bayes, decision tree, SVM and MLP for diagnosing the diabetes with better accuracy. In future, once system is implemented, it can be integrated with diabetic detector device for faster diagnosis of TYPE 2 diabetes disease.

show abstract

“…Previously, SOMs have been used to visually explore financial [2], gene expression [3], linguistics [4] and medical survey [5] datasets. Toronen et al [6] used SOMs to analyse yeast gene expression data, and demonstrated its suitability for analysing and visualising gene expression profiles.…”

Section: Introductionmentioning

confidence: 99%

“…It has also been shown that SOMs can be used to identify co-morbidities, link self-care factors that are dependent on each other and to visualise individual patient profiles in clinically useful ways, e.g. by giving a visual summary of individual patient profiles and enabling patients to be grouped together [5]. SOMs are therefore a potentially valuable tool for visually analysing high-dimensional medical questionnaire responses, as well as a means to visually summarise an individual patient's data.…”

Section: Introductionmentioning

confidence: 99%

Visualisation of survey responses using self-organising maps: A case study on diabetes self-care factors

Tirunagari

Bull

Kouchaki³

et al. 2016

2016 IEEE Symposium Series on Computational Intelligence (SSCI)

Self Cite

View full text Add to dashboard Cite

Due to the chronic nature of diabetes, patient selfcare factors play an important role in any treatment plan. In order to understand the behaviour of patients in response to medical advice on self-care, clinicians often conduct crosssectional surveys. When analysing the survey data, statistical machine learning methods can potentially provide additional insight into the data either through deeper understanding of the patterns present or making information available to clinicians in an intuitive manner. In this study, we use self-organising maps (SOMs) to visualise the responses of patients who share similar responses to survey questions, with the goal of helping clinicians understand how patients are managing their treatment and where action should be taken. The principle behavioural patterns revealed through this are that: patients who take the correct dose of insulin also tend to take their injections at the correct time, patients who eat on time also tend to correctly manage their food portions and patients who check their blood glucose with a monitor also tend to adjust their insulin dosage and carry snacks to counter low blood glucose. The identification of these positive behavioural patterns can also help to inform treatment by exploiting their negative corollaries. arXiv:1609.05716v1 [q-bio.QM]

show abstract

Patient level analytics using self-organising maps: A case study on Type-1 Diabetes self-care survey responses

Cited by 10 publications

References 16 publications

EAGA-MLP—An Enhanced and Adaptive Hybrid Classification Model for Diabetes Diagnosis

EAGA-MLP—An Enhanced and Adaptive Hybrid Classification Model for Diabetes Diagnosis

Diabetic analytics: proposed conceptual data mining approaches in type 2 diabetes dataset

Visualisation of survey responses using self-organising maps: A case study on diabetes self-care factors

Contact Info

Product

Resources

About