Predicting poor glycemic control during Ramadan among non-fasting patients with diabetes using artificial intelligence based machine learning models

Motaib, Imane; Aitlahbib, Faiçal; Fadil, Abdelhamid; Tlemcani, Fatima Z Rhmari; Elamari, Saloua; Laidi, Soukaina; Chadli, Asma

doi:10.1016/j.diabres.2022.109982

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This variation could be attributed to the implementation of different ML models and the inclusion of different features as the main risk factors of UDM in the previous study [ 36 ]. Our prediction finding is contrary to that of Motaib, I. et al (2022) who predicted poor glycemic control during Ramadan using the extra tree classifier (accuracy = 0.87, AUC = 0.87), which is relatively higher in prediction accuracy as compared with our study findings [ 37 ]. This rather contradictory result might be due to the inclusion of baseline caloric intake as an important factor in their study.…”

Section: Discussioncontrasting

confidence: 99%

Application of Machine Learning Algorithms to Predict Uncontrolled Diabetes Using the All of Us Research Program Data

et al. 2023

View full text Add to dashboard Cite

There is a paucity of predictive models for uncontrolled diabetes mellitus. The present study applied different machine learning algorithms on multiple patient characteristics to predict uncontrolled diabetes. Patients with diabetes above the age of 18 from the All of Us Research Program were included. Random forest, extreme gradient boost, logistic regression, and weighted ensemble model algorithms were employed. Patients who had a record of uncontrolled diabetes based on the international classification of diseases code were identified as cases. A set of features including basic demographic, biomarkers and hematological indices were included in the model. The random forest model demonstrated high performance in predicting uncontrolled diabetes, yielding an accuracy of 0.80 (95% CI: 0.79–0.81) as compared to the extreme gradient boost 0.74 (95% CI: 0.73–0.75), the logistic regression 0.64 (95% CI: 0.63–0.65) and the weighted ensemble model 0.77 (95% CI: 0.76–0.79). The maximum area under the receiver characteristics curve value was 0.77 (random forest model), while the minimum value was 0.7 (logistic regression model). Potassium levels, body weight, aspartate aminotransferase, height, and heart rate were important predictors of uncontrolled diabetes. The random forest model demonstrated a high performance in predicting uncontrolled diabetes. Serum electrolytes and physical measurements were important features in predicting uncontrolled diabetes. Machine learning techniques may be used to predict uncontrolled diabetes by incorporating these clinical characteristics.

show abstract

Section: Discussioncontrasting

confidence: 99%

Application of Machine Learning Algorithms to Predict Uncontrolled Diabetes Using the All of Us Research Program Data

et al. 2023

View full text Add to dashboard Cite

show abstract

“…CGM iPro2 (Medtronic) was used before and during Ramadan, complemented by Machine learning models were used to predict poor glycemic control during Ramadan among non-fasting patients with diabetes. 29 First, they conducted three consultations, before, during, and after Ramadan, to assess demographics, diabetes history, caloric intake, and anthropometric and metabolic parameters. Second, machine learning techniques were trained using the data to predict poor glycemic control among patients.…”

Section: Diabetes Technology In Ramadanmentioning

confidence: 99%

“…There was a large interest in studies involving technology during Ramadan fasting. 9,[23][24][25][26][27][28][29] These studies are summarized in ►Table 3. The highlights of these studies are discussed briefly below.…”

Section: Diabetes Technology In Ramadanmentioning

confidence: 99%

Ramadan Fasting and Diabetes (2022): The Year in Review

Hafidh

Besheya

Elmehdawi

et al. 2023

Journal of Diabetes and Endocrine Practice

View full text Add to dashboard Cite

Objectives The literature on the impact of Ramadan fasting (RF) on metabolic control and health in people with diabetes is widely spread in many journals making it not readily accessible to those interested in the subject. We aimed to provide a narrative overview of the global literature production in 1 year (2022) on diabetes and RF. Materials and Methods It is a narrative, non-systematic review of the international literature from a single major medical online database (i.e., PubMed) in one calendar year (2022). Relevant literature was narrated in a concise thematic account. Results Themes emerged from the review of the literature on RF published in 2022, including a couple of studies on the epidemiology of fasting in the real world by adults and children. Three studies involved some pathophysiological observations of metabolic and other biochemical markers. Several studies assessed the use and safety of different pharmacological therapeutic agents. Certain sulfonylureas, such as modified-release gliclazide, were considered safer than other sulfonylureas. Newer basal insulin analogs were studied in different geographical and socioeconomic settings (Gulf vs. South East Asia). The role of diabetes technology in Ramadan was the focus of several studies of insulin pumps and monitoring. Special themes were high-risk groups, pregnancy, acute complications, postbariatric surgery, and COVID-19 in Ramadan. Few studies examined the safety of sodium-glucose co-transporter-2 inhibitors as a class and individually during RF. Professional and patient perspectives released in 2022 included updated guidelines for adults and adolescents. Conclusions In 2022's medical literature, RF and diabetes continue to address epidemiology, the burden of diabetes care on fasting patients, and discussions of concerns of patients and healthcare professionals. Risk stratification and issues of high-risk patients are still in focus for children, adolescents, and adults. Approaches to effective management still gather evidence for newer pharmacological agents and diabetes technology.

show abstract

Identification of influence factors in overweight population through an interpretable risk model based on machine learning: a large retrospective cohort

Lin,

Shi,

Lan

et al. 2023

Endocrine

View full text Add to dashboard Cite

Predicting poor glycemic control during Ramadan among non-fasting patients with diabetes using artificial intelligence based machine learning models

Cited by 4 publications

References 19 publications

Application of Machine Learning Algorithms to Predict Uncontrolled Diabetes Using the All of Us Research Program Data

Application of Machine Learning Algorithms to Predict Uncontrolled Diabetes Using the All of Us Research Program Data

Ramadan Fasting and Diabetes (2022): The Year in Review

Identification of influence factors in overweight population through an interpretable risk model based on machine learning: a large retrospective cohort

Contact Info

Product

Resources

About