Temporal Trends Analysis for Dengue Outbreak and Network Threats Severity Prediction Accuracy Improvement

This paper focuses on predicting injury severity of a driver or rider by applying multi-layer perceptron (MLP), support vector machine (SVM), and a hybrid MLP-SVM method. By correlating the injury severity results and the influences that support their creation, this study was able to determine the key influences affecting the injury severity. The result indicated that the vehicle type, vehicle manoeuvre, lack of necessary crossing facilities for cyclists, 1st point of impact, and junction actions had a greater effect on the likelihood of injury severity. Following this indication, by maximising the prediction accuracies, a comparison between the models was made through exerting the most sensitive predictors in order to evaluate the models’ performance against each other. The outcomes specified that the proposed hybrid model achieved a significant improvement in terms of prediction accuracy compared with other models.

Download Full-text

Prediction Accuracy Improvement of Avoidance Driving Behavior Model Based on Game Theory: Introducing Jerk to Refine Acceleration

CICTP 2019 ◽

10.1061/9780784482292.051 ◽

2019 ◽

Author(s):

Jinghua Wang ◽

Zhao Zhang ◽

Guangquan Lu

Keyword(s):

Game Theory ◽

Prediction Accuracy ◽

Driving Behavior ◽

Behavior Model ◽

Accuracy Improvement ◽

Model Based

Download Full-text

Temporal Trends Analysis of the Characteristics, Management, and Outcomes of Women With Acute Coronary Syndrome (ACS): ACS Israeli Survey Registry 2000‐2016

Journal of the American Heart Association ◽

10.1161/jaha.119.014721 ◽

2020 ◽

Vol 9 (1) ◽

Cited By ~ 1

Author(s):

Avital Porter ◽

Anika Paradkar ◽

Ilan Goldenberg ◽

Nir Shlomo ◽

Tal Cohen ◽

...

Keyword(s):

Acute Coronary Syndrome ◽

Temporal Trends ◽

Coronary Syndrome ◽

Trends Analysis

Download Full-text

Timing of Hypoglycaemia in Patients with Hyperinsulinism (HI): Extension of the Digital Phenotype (Preprint)

10.2196/preprints.26957 ◽

2021 ◽

Author(s):

Chris Worth ◽

Simon Harper ◽

Maria Salomon-Estebanez ◽

Elaine O'Shea ◽

Paul W Nutter ◽

...

Keyword(s):

High Risk ◽

Prediction Accuracy ◽

Temporal Trends ◽

Computational Modelling ◽

Glucose Monitoring ◽

Significant Risk ◽

Genetic Mutations ◽

Glycaemic Variability ◽

Common Cause ◽

Future Work

BACKGROUND Hyperinsulinism (HI) due to excess and dysregulated insulin secretion is the most common cause of severe and recurrent hypoglycaemia in childhood. High cerebral glucose utilisation in the early hours results in high risk of hypoglycaemia for people with diabetes and carries a significant risk of brain injury. Prevention of hypoglycaemia is the cornerstone of management for HI but the risk of hypoglycaemia at night or indeed the timing of hypoglycaemia in children with HI have not been studied, and thus the digital phenotype remains incomplete and management suboptimal. OBJECTIVE We aimed to quantify the timing of hypoglycaemia in patients with HI, to describe glycaemic variability and to extend the digital phenotype. This will facilitate future work using computational modelling to enable behaviour change and reduce exposure of HI patients to injurious hypoglycaemia events. METHODS Patients underwent Continuous Glucose Monitoring (CGM) with a Dexcom G4 or G6 CGM device as part of their clinical assessment for either HI (n = 23) or Idiopathic Ketotic Hypoglycaemia (IKH) (n = 24). CGM data was analysed for temporal trends. Hypoglycaemia was defined as glucose < 3.5mmol/L. RESULTS 449 hypoglycaemia events totalling 15,610 minutes were captured over a total of 237 days from 47 patients (29 male, mean age 70 months). Mean length of hypoglycaemia event was 35 minutes. There was a clear tendency to hypoglycaemia in the early hours (0300H to 0700H), particularly for those HI patients over 10 months of age where 7.6% of time (1480/19370 minutes) in this period was in hypoglycaemia compared to 2.6% (2405/92840 minutes) outside (P < .001). This tendency was less pronounced in HI patients under 10 months and those negative for genetic mutations as well as those patients with IKH. Despite real-time CGM, there were 42 hypoglycaemia events from 13 separate HI patients lasting > 30 minutes. CONCLUSIONS In this study, we have taken the first step in extending the digital phenotype of HI by describing the glycaemic trends and identifying the timings of hypoglycaemia measured by CGM. We have identified the early hours as a time of high hypoglycaemia risk for patients with HI and demonstrated that simple provision of CGM data to patients is not sufficient to eliminate hypoglycaemia. Future work in HI should concentrate on the early hours as a period of high risk for hypoglycaemia and must target personalised hypoglycaemia predictions. Focus must move to the human-computer interaction as an aspect of the digital phenotype that is susceptible to change rather than simple mathematical modelling to produce small improvements in hypoglycaemia prediction accuracy. CLINICALTRIAL

Download Full-text