Novel Data Mining Methodology for Healthcare Applied to a New Model to Diagnose Metabolic Syndrome without a Blood Test

Barrios, Maite; Jimeno, Miguel; Villalba, Pedro; Navarro, Édgar

doi:10.3390/diagnostics9040192

Cited by 5 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the diagnosis of Type II DM, it was shown that a possible diagnosis can be made without the physician based on the physiological findings of the patient [25]. In a study about diagnosing metabolic syndrome without blood tests, the rate of making the correct diagnosis was determined as 85.12% [45]. The analysis of adipocytokines and anthropometric levels obtained from obese women (diabetic and non-diabetic) with experimental data set and the probability of having DM in women with obesity was tried to be determined.…”

Section: Discussionmentioning

confidence: 99%

Nursing Strategies for Diabetic Patient Management: Predicting Parameter Values Post-Exenatide Treatment with Machine Learning Algorithm

Ersoy,

Gürfidan

2024

Süleyman Demirel Üniversitesi Sağlık Bilimleri Dergisi

View full text Add to dashboard Cite

The global escalation of DM parallels the rise in obesity rates, with Turkey experiencing a prevalence of 13.7% for diabetes and 32% for obesity among adults. Managing diabetic patients necessitates a comprehensive approach due to the intertwined nature of diabetes and obesity, along with the heightened risk of additional chronic illnesses. Diabet nurses play a pivotal role in diabetic care, encompassing regular assessments, blood glucose monitoring, medication management, patient education. Incretin-mimetic glucagon-like peptide-1 receptor-agonists (GLP-1A) have demonstrated superiority in diabetes, weight control, positioning them as second-line treatments. Weight management remains fundamental in diabetes care, with Diabet nurses providing vital support through dietary guidance, physical activity promotion, and weight loss assistance for diabetic patients. Predicting patient responses to GLP-1A therapy is crucial for optimizing treatment outcomes, streamlining decisions, averting potential complications. Artificial intelligence (AI) and machine learning (ML) offer promising avenues for enhancing healthcare delivery. Our study aimed to forecast fasting blood sugar levels, HbA1C values, and weight loss outcomes in diabetic patients using exenatide, utilizing the random forest algorithm. Analyzing real patient data from the Western-Mediterranean, this study achieved substantial success rates of %99.9, %99.9 and %97.3 in predicting weight loss, fasting blood sugar levels, and HbA1C values, respectively. Our findings underscore the potential of AI-driven approaches in nursing, particularly in prognostic modeling for diabetic patient management. By leveraging ML, nurses can anticipate treatment responses, streamline decision-making, and elevate patient care quality. As AI applications evolve, integrating these technologies into nursing roles promises to advance patient-centered care and optimize health outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

Nursing Strategies for Diabetic Patient Management: Predicting Parameter Values Post-Exenatide Treatment with Machine Learning Algorithm

Ersoy,

Gürfidan

2024

Süleyman Demirel Üniversitesi Sağlık Bilimleri Dergisi

View full text Add to dashboard Cite

show abstract

“…However, connected AI doctors could make their own independent decisions, considering the other AI doctors’ opinions. For example, a single patient living in a small village in Siberia or Tibet could benefit from comparing diagnosis coming from a thousand AI doctors [ 116 , 117 , 118 ]. AI could provide more accurate, faster, and cheaper health care for everyone.…”

Section: Challenges and Prospectsmentioning

confidence: 99%

How Do Machines Learn? Artificial Intelligence as a New Era in Medicine

Koteluk

Wartecki

Mazurek

et al. 2021

JPM

View full text Add to dashboard Cite

With an increased number of medical data generated every day, there is a strong need for reliable, automated evaluation tools. With high hopes and expectations, machine learning has the potential to revolutionize many fields of medicine, helping to make faster and more correct decisions and improving current standards of treatment. Today, machines can analyze, learn, communicate, and understand processed data and are used in health care increasingly. This review explains different models and the general process of machine learning and training the algorithms. Furthermore, it summarizes the most useful machine learning applications and tools in different branches of medicine and health care (radiology, pathology, pharmacology, infectious diseases, personalized decision making, and many others). The review also addresses the futuristic prospects and threats of applying artificial intelligence as an advanced, automated medicine tool.

show abstract

Framework to Diagnose the Metabolic Syndrome Types without Using a Blood Test Based on Machine Learning

et al. 2020

View full text Add to dashboard Cite

Metabolic Syndrome (MetS) is a set of risk factors that increase the probability of heart disease or even diabetes mellitus. The diagnosis of the pathology implies compliance with at least three of five risk factors. Doctors obtain two of those factors in a medical consultation: waist circumference and blood pressure. The other three factors are biochemical variables that require a blood test to determine triglyceride, high-density lipoprotein cholesterol, and fasting plasma glucose. Consequently, scientists are developing technology for non-invasive diagnostics, but medical personnel also need the risk factors involved in MetS to start a treatment. This paper describes the segmentation of MetS into ten types based on harmonized Metabolic Syndrome criteria. It proposes a framework to diagnose the types of MetS based on Artificial Neural Networks and Random undersampling Boosted tree using non-biochemical variables such as anthropometric and clinical information. The framework works over imbalanced and balanced datasets using the Synthetic Minority Oversampling Technique and for validation uses random subsampling to get performance evaluation indicators between the classifiers. The results showed an excellent framework for diagnosing the 10 MetS types that have Area under Receiver Operating Characteristic (AROC) curves with a range of 71% to 93% compared with AROC 82.86% from traditional MetS.

show abstract

Novel Data Mining Methodology for Healthcare Applied to a New Model to Diagnose Metabolic Syndrome without a Blood Test

Cited by 5 publications

References 44 publications

Nursing Strategies for Diabetic Patient Management: Predicting Parameter Values Post-Exenatide Treatment with Machine Learning Algorithm

Nursing Strategies for Diabetic Patient Management: Predicting Parameter Values Post-Exenatide Treatment with Machine Learning Algorithm

How Do Machines Learn? Artificial Intelligence as a New Era in Medicine

Framework to Diagnose the Metabolic Syndrome Types without Using a Blood Test Based on Machine Learning

Contact Info

Product

Resources

About