Key result
Smartphone machine learning app predicts diabetes risk with 95% accuracy based on simple patient questions.
Why the study?
Diabetes screening is challenging due to asymptomatic early stages, invasive risk factor measurement, and complex physiological relations, creating a need for non-invasive early-stage assessment tools.
Does a Random Forest machine learning model embedded in a smartphone application accurately assess early-stage diabetes risk based on patient-reported symptoms?
Does a Random Forest machine learning model embedded in a smartphone application accurately assess early-stage diabetes risk based on patient-reported symptoms?
A Random Forest machine learning model embedded in a smartphone app can predict early-stage diabetes risk with 95% accuracy using non-invasive symptom questionnaires.
May support preliminary app-based diabetes screening; leaves open prospective validation before clinical adoption.
Diabetes Mellitus (DM) is a metabolic disease that hampers the function of glucose in the human body. DM screening remains challenging due to its initial asymptotic be-havior, invasive nature of risk factor measurement, and complex physiological relation with other diseases. An efficient early-stage diagnosis tool that provides a diabetes risk assessment via non-invasive means is imperative to mitigate the lingering risk as well as to take preventive measures. In this paper, a highly accurate diabetes risk assessment pipeline using medical health records is presented. The dataset obtained from the University of California Irvine (UCI) Machine Learning Repository consists of 520 samples of both male and female subjects, each having 16 attributes related to signs and symptoms of diabetes. Different su-pervised machine learning (ML) models have been implemented to predict the probabilities of the diabetic and non-diabetic classes for a given record. A comparative analysis of different ML methods confirms that the Random Forest is best suited for this problem with an accuracy of 95%. The best performing pre-trained machine learning predictive model is embedded into a smartphone application to generate a recommendation on the risk of DM based on simple patient-related questions and answers. Therefore, the outcome of this research will help improve early diagnosis, monitoring, and clinical screening of DM.
No takes yet. Share an insight, caveat, or question.
Shuvo et al. (2022) studied Diabetes Mellitus (n=520). Random Forest machine learning model embedded in a smartphone application vs. Other supervised machine learning models was evaluated on Prediction accuracy of diabetic and non-diabetic classes. A Random Forest machine learning model embedded in a smartphone application predicted diabetes risk with an accuracy of 95% based on simple patient-related questions.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: