scholarly journals Data Homogeneity Effect in Deep Learning-Based Prediction of Type 1 Diabetic Retinopathy

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Jui-En Lo ◽  
Eugene Yu-Chuan Kang ◽  
Yun-Nung Chen ◽  
Yi-Ting Hsieh ◽  
Nan-Kai Wang ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Model Performance ◽  
Area Under The Curve ◽  
Retinal Hemorrhage ◽  
High Variability ◽  
Chang Gung Memorial Hospital ◽  
Predominant Type ◽  
Wrong Prediction ◽  
Homogeneity Effect

This study is aimed at evaluating a deep transfer learning-based model for identifying diabetic retinopathy (DR) that was trained using a dataset with high variability and predominant type 2 diabetes (T2D) and comparing model performance with that in patients with type 1 diabetes (T1D). The Kaggle dataset, which is a publicly available dataset, was divided into training and testing Kaggle datasets. In the comparison dataset, we collected retinal fundus images of T1D patients at Chang Gung Memorial Hospital in Taiwan from 2013 to 2020, and the images were divided into training and testing T1D datasets. The model was developed using 4 different convolutional neural networks (Inception-V3, DenseNet-121, VGG1, and Xception). The model performance in predicting DR was evaluated using testing images from each dataset, and area under the curve (AUC), sensitivity, and specificity were calculated. The model trained using the Kaggle dataset had an average (range) AUC of 0.74 (0.03) and 0.87 (0.01) in the testing Kaggle and T1D datasets, respectively. The model trained using the T1D dataset had an AUC of 0.88 (0.03), which decreased to 0.57 (0.02) in the testing Kaggle dataset. Heatmaps showed that the model focused on retinal hemorrhage, vessels, and exudation to predict DR. In wrong prediction images, artifacts and low-image quality affected model performance. The model developed with the high variability and T2D predominant dataset could be applied to T1D patients. Dataset homogeneity could affect the performance, trainability, and generalization of the model.

Predictors of Purchasing a Hearing Aid After an Evaluation Period: A Prospective Study in Dutch Older Hearing Aid Candidates

2019 ◽  
Vol 28 (3S) ◽  
pp. 802-805 ◽  
Author(s):  
Marieke Pronk ◽  
Janine F. J. Meijerink ◽  
Sophia E. Kramer ◽  
Martijn W. Heymans ◽  
Jana Besser
Keyword(s):  
Help Seeking ◽  
Hearing Aid ◽  
Model Performance ◽  
Area Under The Curve ◽  
Secondary Data ◽  
Support Program ◽  
Evaluation Period ◽  
A Prospective Study ◽  
Study Participants ◽  
Baseline Covariates

Purpose The current study aimed to identify factors that distinguish between older (50+ years) hearing aid (HA) candidates who do and do not purchase HAs after having gone through an HA evaluation period (HAEP). Method Secondary data analysis of the SUpport PRogram trial was performed ( n = 267 older, 1st-time HA candidates). All SUpport PRogram participants started an HAEP shortly after study enrollment. Decision to purchase an HA by the end of the HAEP was the outcome of interest of the current study. Participants' baseline covariates (22 in total) were included as candidate predictors. Multivariable logistic regression modeling (backward selection and reclassification tables) was used. Results Of all candidate predictors, only pure-tone average (average of 1, 2, and 4 kHz) hearing loss emerged as a significant predictor (odds ratio = 1.03, 95% confidence interval [1.03, 1.17]). Model performance was weak (Nagelkerke R 2 = .04, area under the curve = 0.61). Conclusions These data suggest that, once HA candidates have decided to enter an HAEP, factors measured early in the help-seeking journey do not predict well who will and will not purchase an HA. Instead, factors that act during the HAEP may hold this predictive value. This should be examined.

Polymorphisms of the Plasminogen Activator Inhibitor- 1 Gene in Type 1 and Type 2 Diabetes, and in Patients with Diabetic Retinopathy

1994 ◽  
Vol 71 (06) ◽  
pp. 731-736 ◽  
Author(s):  
M W Mansfield ◽  
M H Stickland ◽  
A M Carter ◽  
P J Grant
Keyword(s):  
Diabetic Retinopathy ◽  
Plasminogen Activator Inhibitor ◽  
Allelic Frequency ◽  
Repeat Sequence ◽  
Dinucleotide Repeat ◽  
Plasminogen Activator Inhibitor 1 ◽  
The Difference ◽  
Pai 1

SummaryTo identify whether genotype contributes to the difference in PAI-1 levels in type 1 and type 2 diabetic subjects and whether genotype relates to the development of retinopathy, a Hind III restriction fragment length polymorphism and two dinucleotide repeat polymorphisms were studied. In 519 Caucasian diabetic subjects (192 type 1, 327 type 2) and 123 Caucasian control subjects there were no differences in the frequency of the Hind III restriction alleles (type 1 vs type 2 vs control: allele 1 0.397 vs 0.420 vs 0.448; allele 2 0.603 vs 0.580 vs 0.552) nor in the allelic frequency at either dinucleotide repeat sequence. In 86 subjects with no retinopathy at 15 years or more from diagnosis of diabetes and 190 subjects with diabetic retinopathy there was no difference in the frequency of Hind III restriction alleles (retinopathy present vs retinopathy absent: allele 1 0.400 vs 0.467; allele 2 0.600 vs 0.533) nor in the allelic frequencies at either dinucleotide repeat sequence. The results indicate that there is no or minimal influence of the PAI-1 gene on either PAI-1 levels or the development of diabetic retinopathy in patients with diabetes mellitus.

Venular oxygen saturation is increased in young patients with type 1 diabetes and mild nonproliferative diabetic retinopathy

2020 ◽  
Vol 98 (8) ◽  
pp. 800-807 ◽  
Author(s):  
Nina C.B.B. Veiby ◽  
Aida Simeunovic ◽  
Martin Heier ◽  
Cathrine Brunborg ◽  
Naila Saddique ◽  
...  
Keyword(s):  
Type 1 Diabetes ◽  
Diabetic Retinopathy ◽  
Oxygen Saturation ◽  
Young Patients ◽  
Nonproliferative Diabetic Retinopathy

scholarly journals Prediction of COVID-19 severity using laboratory findings on admission: informative values, thresholds, ML model performance

BMJ Open ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. e044500
Author(s):  
Yauhen Statsenko ◽  
Fatmah Al Zahmi ◽  
Tetiana Habuza ◽  
Klaus Neidl-Van Gorkom ◽  
Nazar Zaki
Keyword(s):  
Lymphocyte Count ◽  
Prediction Models ◽  
Model Performance ◽  
Area Under The Curve ◽  
Predictive Biomarkers ◽  
Supervised Machine Learning ◽  
Study Cohort ◽  
Threshold Values ◽  
Laboratory Findings ◽  
Study Results

BackgroundDespite the necessity, there is no reliable biomarker to predict disease severity and prognosis of patients with COVID-19. The currently published prediction models are not fully applicable to clinical use.ObjectivesTo identify predictive biomarkers of COVID-19 severity and to justify their threshold values for the stratification of the risk of deterioration that would require transferring to the intensive care unit (ICU).MethodsThe study cohort (560 subjects) included all consecutive patients admitted to Dubai Mediclinic Parkview Hospital from February to May 2020 with COVID-19 confirmed by the PCR. The challenge of finding the cut-off thresholds was the unbalanced dataset (eg, the disproportion in the number of 72 patients admitted to ICU vs 488 non-severe cases). Therefore, we customised supervised machine learning (ML) algorithm in terms of threshold value used to predict worsening.ResultsWith the default thresholds returned by the ML estimator, the performance of the models was low. It was improved by setting the cut-off level to the 25th percentile for lymphocyte count and the 75th percentile for other features. The study justified the following threshold values of the laboratory tests done on admission: lymphocyte count <2.59×109/L, and the upper levels for total bilirubin 11.9 μmol/L, alanine aminotransferase 43 U/L, aspartate aminotransferase 32 U/L, D-dimer 0.7 mg/L, activated partial thromboplastin time (aPTT) 39.9 s, creatine kinase 247 U/L, C reactive protein (CRP) 14.3 mg/L, lactate dehydrogenase 246 U/L, troponin 0.037 ng/mL, ferritin 498 ng/mL and fibrinogen 446 mg/dL.ConclusionThe performance of the neural network trained with top valuable tests (aPTT, CRP and fibrinogen) is admissible (area under the curve (AUC) 0.86; 95% CI 0.486 to 0.884; p<0.001) and comparable with the model trained with all the tests (AUC 0.90; 95% CI 0.812 to 0.902; p<0.001). Free online tool at https://med-predict.com illustrates the study results.

scholarly journals The Effect of HbA1c Variability as a Risk Measure for Microangiopathy in Type 1 Diabetes Mellitus

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1151
Author(s):  
Pedro Romero-Aroca ◽  
Raul Navarro-Gil ◽  
Albert Feliu ◽  
Aida Valls ◽  
Antonio Moreno ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 1 Diabetes ◽  
Diabetic Retinopathy ◽  
Type 1 Diabetes Mellitus ◽  
Risk Measure ◽  
Case Series ◽  
Multivariate Statistical ◽  
Case Series Study ◽  
Prospective Case Series

Background: To measure the relationship between variability in HbA1c and microalbuminuria (MA) and diabetic retinopathy (DR) in the long term. Methods: A prospective case-series study, was conducted on 366 Type 1 Diabetes Mellitus patients with normoalbuminuria and without diabetic retinopathy at inclusion. The cohort was followed for a period of 12 years. The Cox survival analysis was used for the multivariate statistical study. The effect of variability in microangiopathy (retinopathy and nephropathy) was evaluated by calculating the standard deviation of HbA1c (SD-HbA1c), the coefficient of variation of HbA1c (CV-HbA1c), average real variability (ARV-HbA1c) and variability irrespective of the mean (VIM-HbA1c) adjusted for the other known variables. Results: A total of 106 patients developed diabetic retinopathy (29%) and 73 microalbuminuria (19.9%). Overt diabetic nephropathy, by our definition, affected only five patients (1.36%). Statistical results show that the current age, mean HbA1c, SD-HbA1c and ARV-HbA1c are significant in the development of diabetic retinopathy. Microalbuminuria was significant for current age, mean HbA1c, CV-HbA1c and ARV-HbA1c. Conclusions: By measuring the variability in HbA1c, we can use SD-HbA1c and ARV-HbA1c as possible targets for judging which patients are at risk of developing DR and MA, and CV-HbA1c as the target for severe DR.

Sign in / Sign up

Export Citation Format

Share Document