Use of a Machine Learning Algorithm Improves Prediction of Progression to Diabetes

Cahn, Avivit; Shoshan, Avi; Sagiv, Tal; Yesharim, Rachel; Goshen, Ran

doi:10.2337/db18-1286-p

Cited by 7 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, a study comparing different machine learning techniques found that decision trees outperformed others in terms of accuracy 25 . Additionally, Cahn et al 26 demonstrated the prediction of diabetes risk using logistic regression and achieved commendable specificity rates. Various machine learning methods have also been explored for hypertension risk prediction.…”

Section: Discussionmentioning

confidence: 99%

FIT calculator: a multi-risk prediction framework for medical outcomes using cardiorespiratory fitness data

Elshawi,

Sakr,

Al-Mallah

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Accurately predicting patients' risk for specific medical outcomes is paramount for effective healthcare management and personalized medicine. While a substantial body of literature addresses the prediction of diverse medical conditions, existing models predominantly focus on singular outcomes, limiting their scope to one disease at a time. However, clinical reality often entails patients concurrently facing multiple health risks across various medical domains. In response to this gap, our study proposes a novel multi-risk framework adept at simultaneous risk prediction for multiple clinical outcomes, including diabetes, mortality, and hypertension. Leveraging a concise set of features extracted from patients' cardiorespiratory fitness data, our framework minimizes computational complexity while maximizing predictive accuracy. Moreover, we integrate a state-of-the-art instance-based interpretability technique into our framework, providing users with comprehensive explanations for each prediction. These explanations afford medical practitioners invaluable insights into the primary health factors influencing individual predictions, fostering greater trust and utility in the underlying prediction models. Our approach thus stands to significantly enhance healthcare decision-making processes, facilitating more targeted interventions and improving patient outcomes in clinical practice. Our prediction framework utilizes an automated machine learning framework, Auto-Weka, to optimize machine learning models and hyper-parameter configurations for the simultaneous prediction of three medical outcomes: diabetes, mortality, and hypertension. Additionally, we employ a local interpretability technique to elucidate predictions generated by our framework. These explanations manifest visually, highlighting key attributes contributing to each instance's prediction for enhanced interpretability. Using automated machine learning techniques, the models simultaneously predict hypertension, mortality, and diabetes risks, utilizing only nine patient features. They achieved an average AUC of 0.90 ± 0.001 on the hypertension dataset, 0.90 ± 0.002 on the mortality dataset, and 0.89 ± 0.001 on the diabetes dataset through tenfold cross-validation. Additionally, the models demonstrated strong performance with an average AUC of 0.89 ± 0.001 on the hypertension dataset, 0.90 ± 0.001 on the mortality dataset, and 0.89 ± 0.001 on the diabetes dataset using bootstrap evaluation with 1000 resamples.

show abstract

Section: Discussionmentioning

confidence: 99%

FIT calculator: a multi-risk prediction framework for medical outcomes using cardiorespiratory fitness data

Elshawi,

Sakr,

Al-Mallah

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Literature review indicates that mobile apps and related technology can positively affect health aspects, in particular weight loss, as well as diabetes prevention and treatment [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 ]. Similarly, an initial literature review indicates a significant number of publications on the use of Artificial Intelligence and Machine Learning techniques for diabetes prediction, prevention, and treatment [ 28 , 29 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 ].…”

Section: Methodology and Contextual Approachmentioning

confidence: 99%

Capacity Strengthening Undertaking—Farm Organized Response of Workers against Risk for Diabetes: (C.S.U.—F.O.R.W.A.R.D. with Cal Poly)—A Concept Approach to Tackling Diabetes in Vulnerable and Underserved Farmworkers in California

Sikalidis

Kristo

Reaves

et al. 2022

Sensors

View full text Add to dashboard Cite

In our project herein, we use the case of farmworkers, an underserved and understudied population at high risk for Type-2 Diabetes Mellitus (T2DM), as a paradigm of an integrated action-oriented research, education and extension approach involving the development of long-term equitable strategies providing empowerment and tailored-made solutions that support practical decision-making aiming to reduce risk of T2DM and ensuing cardiovascular disease (CVD). A Technology-based Empowerment Didactic module (TEDm) and an Informed Decision-Making enhancer (IDMe) coupled in a smart application (app) for farmworkers aiming to teach, set goals, monitor, and support in terms of nutrition, hydration, physical activity, sleep, and circadian rhythm towards lowering T2DM risk, is to be developed and implemented considering the particular characteristics of the population and setting. In parallel, anthropometric, biochemical, and clinical assessments will be utilized to monitor risk parameters for T2DM and compliance to dietary and wellness plans. The app incorporating anthropometric/clinical/biochemical parameters, dietary/lifestyle behavior, and extent of goal achievement can be continuously refined and improved through machine learning and re-programming. The app can function as a programmable tool constantly learning, adapting, and tailoring its services to user needs helping optimization of practical informed decision-making towards mitigating disease symptoms and associated risk factors. This work can benefit apart from the direct beneficiaries being farmworkers, the stakeholders who will be gaining a healthier, more vibrant workforce, and in turn the local communities.

show abstract

“…and Cahn et al [28] built risk models aiming for diabetes. Seyednasrollah et al and Chen et al achieved a high predictive power in obesity risk prediction [29] [30].…”

Section: Introductionmentioning

confidence: 99%

“…For example, there are risk estimation models for hypertension patients [22] , [23] , [24] , [25] . Also, Luo et al [26] , Casanova et al [27] , and Cahn et al [28] built risk models aiming for diabetes. Seyednasrollah et al and Chen et al achieved a high predictive power in obesity risk prediction [29] [30] .…”

Section: Introductionmentioning

confidence: 99%

Prediction for the Risk of Multiple Chronic Conditions Among Working Population in the United States With Machine Learning Models

Yang

Liu

et al. 2021

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

Chronic diseases have become the most prevalent and costly health conditions in the healthcare industry, deteriorating the quality of life, adversely affecting the work productivity, and costing astounding medical resources. However, few studies have been conducted on the predictive analysis of multiple chronic conditions (MCC) based on the working population. Results: Seven machine learning algorithms are used to support the decision making of healthcare practitioner on the risk of MCC. The models were developed and validated using checkup data from 451,425 working population collected by the healthcare providers. Our result shows that all proposed models achieved satisfactory performance, with the AUC values ranging from 0.826 to 0.850. Among the seven predictive models, the gradient boosting tree model outperformed other models, achieving an AUC of 0.850. Conclusions: Our risk prediction model shows great promise in automating real-time diagnosis, supporting healthcare practitioners to target high-risk individuals efficiently, and helping healthcare practitioners tailor proactive strategies to prevent the onset or delay the progression of the chronic diseases.INDEX TERMS Multiple Chronic Conditions, Machine Learning, Predictive Analysis, Health Informatics IMPACT STATEMENT A machine learning framework is implemented to automate the screening of high risk individuals for multiple chronic conditions in the working population.

show abstract

Use of a Machine Learning Algorithm Improves Prediction of Progression to Diabetes

Cited by 7 publications

References 0 publications

FIT calculator: a multi-risk prediction framework for medical outcomes using cardiorespiratory fitness data

FIT calculator: a multi-risk prediction framework for medical outcomes using cardiorespiratory fitness data

Capacity Strengthening Undertaking—Farm Organized Response of Workers against Risk for Diabetes: (C.S.U.—F.O.R.W.A.R.D. with Cal Poly)—A Concept Approach to Tackling Diabetes in Vulnerable and Underserved Farmworkers in California

Prediction for the Risk of Multiple Chronic Conditions Among Working Population in the United States With Machine Learning Models

Contact Info

Product

Resources

About