Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

OBJECTIVES: The primary objective of this study was to determine if the number of missing teeth could be predicted by oral disease pathogens, and the secondary objective was to assess whether deep learning is a better way of predicting the number of missing teeth than multivariable linear regression (MLR).METHODS: Data were collected through review of patient’s initial medical records. A total of 960 participants were cross-sectionally surveyed. MLR analysis was performed to assess the relationship between the number of missing teeth and the results of real-time PCR assay (done for quantification of 11 oral disease pathogens). A convolutional neural network (CNN) was used as the deep learning model and compared with MLR models. Each model was performed five times to generate an average accuracy rate and mean square error (MSE). The accuracy of predicting the number of missing teeth was evaluated and compared between the CNN and MLR methods.RESULTS: Model 1 had the demographic information necessary for the prediction of periodontal diseases in addition to the red and the orange complex bacteria that are highly predominant in oral diseases. The accuracy of the convolutional neural network in this model was 65.0%. However, applying Model 4, which added yellow complex bacteria to the total bacterial load, increased the expected extractions of dental caries to 70.2%.On the other hand, the accuracy of the MLR was about 50.0% in all models. The mean square error of the CNN was considerably smaller than that of the MLR, resulting in better predictability.CONCLUSIONS: Oral disease pathogens can be used as a predictor of missing teeth and deep learning can be a more accurate analysis method to predict the number of missing teeth as compared to MLR.
Bacteria ; Bacterial Load ; Citrus sinensis ; Dental Caries ; Hand ; Learning ; Linear Models ; Medical Records ; Methods ; Periodontal Diseases ; Periodontitis ; Pilot Projects ; Real-Time Polymerase Chain Reaction ; Tooth