scholarly journals Clinically applicable machine learning approaches to identify attributes of Chronic Kidney Disease (CKD) for use in low-cost diagnostic screening

Author(s):  
Md. Rashed-Al-Mahfuz ◽  
Abedul Haque ◽  
AKM Azad ◽  
Salem A. Alyami ◽  
Julian M.W. Quinn ◽  
...  
2020 ◽  
Author(s):  
Ada Admin ◽  
Jialing Huang ◽  
Cornelia Huth ◽  
Marcela Covic ◽  
Martina Troll ◽  
...  

Early and precise identification of individuals with pre-diabetes and type 2 diabetes (T2D) at risk of progressing to chronic kidney disease (CKD) is essential to prevent complications of diabetes. Here, we identify and evaluate prospective metabolite biomarkers and the best set of predictors of CKD in the longitudinal, population-based Cooperative Health Research in the Region of Augsburg (KORA) cohort by targeted metabolomics and machine learning approaches. Out of 125 targeted metabolites, sphingomyelin (SM) C18:1 and phosphatidylcholine diacyl (PC aa) C38:0 were identified as candidate metabolite biomarkers of incident CKD specifically in hyperglycemic individuals followed during 6.5 years. Sets of predictors for incident CKD developed from 125 metabolites and 14 clinical variables showed highly stable performances in all three machine learning approaches and outperformed the currently established clinical algorithm for CKD. The two metabolites in combination with five clinical variables were identified as the best set of predictors and their predictive performance yielded a mean area value under the receiver operating characteristic curve of 0.857. The inclusion of metabolite variables in the clinical prediction of future CKD may thus improve the risk prediction in persons with pre- and T2D. The metabolite link with hyperglycemia-related early kidney dysfunction warrants further investigation.


2020 ◽  
Author(s):  
Ada Admin ◽  
Jialing Huang ◽  
Cornelia Huth ◽  
Marcela Covic ◽  
Martina Troll ◽  
...  

Early and precise identification of individuals with pre-diabetes and type 2 diabetes (T2D) at risk of progressing to chronic kidney disease (CKD) is essential to prevent complications of diabetes. Here, we identify and evaluate prospective metabolite biomarkers and the best set of predictors of CKD in the longitudinal, population-based Cooperative Health Research in the Region of Augsburg (KORA) cohort by targeted metabolomics and machine learning approaches. Out of 125 targeted metabolites, sphingomyelin (SM) C18:1 and phosphatidylcholine diacyl (PC aa) C38:0 were identified as candidate metabolite biomarkers of incident CKD specifically in hyperglycemic individuals followed during 6.5 years. Sets of predictors for incident CKD developed from 125 metabolites and 14 clinical variables showed highly stable performances in all three machine learning approaches and outperformed the currently established clinical algorithm for CKD. The two metabolites in combination with five clinical variables were identified as the best set of predictors and their predictive performance yielded a mean area value under the receiver operating characteristic curve of 0.857. The inclusion of metabolite variables in the clinical prediction of future CKD may thus improve the risk prediction in persons with pre- and T2D. The metabolite link with hyperglycemia-related early kidney dysfunction warrants further investigation.


2020 ◽  
Author(s):  
Ada Admin ◽  
Jialing Huang ◽  
Cornelia Huth ◽  
Marcela Covic ◽  
Martina Troll ◽  
...  

Early and precise identification of individuals with pre-diabetes and type 2 diabetes (T2D) at risk of progressing to chronic kidney disease (CKD) is essential to prevent complications of diabetes. Here, we identify and evaluate prospective metabolite biomarkers and the best set of predictors of CKD in the longitudinal, population-based Cooperative Health Research in the Region of Augsburg (KORA) cohort by targeted metabolomics and machine learning approaches. Out of 125 targeted metabolites, sphingomyelin (SM) C18:1 and phosphatidylcholine diacyl (PC aa) C38:0 were identified as candidate metabolite biomarkers of incident CKD specifically in hyperglycemic individuals followed during 6.5 years. Sets of predictors for incident CKD developed from 125 metabolites and 14 clinical variables showed highly stable performances in all three machine learning approaches and outperformed the currently established clinical algorithm for CKD. The two metabolites in combination with five clinical variables were identified as the best set of predictors and their predictive performance yielded a mean area value under the receiver operating characteristic curve of 0.857. The inclusion of metabolite variables in the clinical prediction of future CKD may thus improve the risk prediction in persons with pre- and T2D. The metabolite link with hyperglycemia-related early kidney dysfunction warrants further investigation.


Diabetes ◽  
2020 ◽  
Vol 69 (12) ◽  
pp. 2756-2765
Author(s):  
Jialing Huang ◽  
Cornelia Huth ◽  
Marcela Covic ◽  
Martina Troll ◽  
Jonathan Adam ◽  
...  

2021 ◽  
Vol 9 (2) ◽  
pp. e002364
Author(s):  
Cynthia Ciwei Lim ◽  
Feng He ◽  
Jialiang Li ◽  
Yih Chung Tham ◽  
Chieh Suai Tan ◽  
...  

IntroductionChronic kidney disease (CKD) is increasing in Asia, but there are sparse data on incident CKD among different ethnic groups. We aimed to describe the incidence and risk factors associated with CKD in the three major ethnic groups in Asia: Chinese, Malays and Indians.Research design and methodsProspective cohort study of 5580 general population participants age 40–80 years (2234 Chinese, 1474 Malays and 1872 Indians) who completed both baseline and 6-year follow-up visits. Incident CKD was defined as an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2 in those free of CKD at baseline.ResultsThe 6-year incidence of CKD was highest among Malays (10.0%), followed by Chinese (6.1%) and Indians (5.8%). Logistic regression showed that older age, diabetes, higher systolic blood pressure and lower eGFR were independently associated with incident CKD in all three ethnic groups, while hypertension and cardiovascular disease were independently associated with incident CKD only in Malays. The same factors were identified by machine learning approaches, gradient boosted machine and random forest to be the most important for incident CKD. Adjustment for clinical and socioeconomic factors reduced the excess incidence in Malays by 60% compared with Chinese but only 13% compared with Indians.ConclusionIncidence of CKD is high among the main Asian ethnic groups in Singapore, ranging between 6% and 10% over 6 years; differences were partially explained by clinical and socioeconomic factors.


2021 ◽  
Vol 10 (3) ◽  
Author(s):  
Shreya Nag ◽  
Nimitha Jammula

The diagnosis of a disease to determine a specific condition is crucial in caring for patients and furthering medical research. The timely and accurate diagnosis can have important implications for both patients and healthcare providers. An earlier diagnosis allows doctors to consider more methods of treatment, allowing them to have a greater flexibility of tailoring their decisions, and ultimately improving the patient’s health. Additionally, a timely detection allows patients to have a greater control over their health and their decisions, allowing them to plan ahead. As advancements in computer science and technology continue to improve, these two factors can play a major role in aiding healthcare providers with medical issues. The emergence of artificial intelligence and machine learning can aid in addressing the challenge of completing timely and accurate diagnosis. The goal of this research work is to design a system that utilizes machine learning and neural network techniques to diagnose chronic kidney disease with more than 90% accuracy based on a clinical data set, and to do a comparative study of the performance of the neural network versus supervised machine learning approaches. Based on the results, all the algorithms performed well in prediction of chronic kidney disease (CKD) with more that 90% accuracy. The neural network system provided the best performance (accuracy = 100%) in prediction of chronic kidney disease in comparison with the supervised Random Forest algorithm (accuracy = 99%) and the supervised Decision Tree algorithm (accuracy = 97%).


Sign in / Sign up

Export Citation Format

Share Document