Dataset Information

Histological validation of a type 1 diabetes clinical diagnostic model for classification of diabetes.

ABSTRACT:

Aims

Misclassification of diabetes is common due to an overlap in the clinical features of type 1 and type 2 diabetes. Combined diagnostic models incorporating clinical and biomarker information have recently been developed that can aid classification, but they have not been validated using pancreatic pathology. We evaluated a clinical diagnostic model against histologically defined type 1 diabetes.

Methods

We classified cases from the Network for Pancreatic Organ donors with Diabetes (nPOD) biobank as type 1 (n = 111) or non-type 1 (n = 42) diabetes using histopathology. Type 1 diabetes was defined by lobular loss of insulin-containing islets along with multiple insulin-deficient islets. We assessed the discriminative performance of previously described type 1 diabetes diagnostic models, based on clinical features (age at diagnosis, BMI) and biomarker data [autoantibodies, type 1 diabetes genetic risk score (T1D-GRS)], and singular features for identifying type 1 diabetes by the area under the curve of the receiver operator characteristic (AUC-ROC).

Results

Diagnostic models validated well against histologically defined type 1 diabetes. The model combining clinical features, islet autoantibodies and T1D-GRS was strongly discriminative of type 1 diabetes, and performed better than clinical features alone (AUC-ROC 0.97 vs. 0.95; P = 0.03). Histological classification of type 1 diabetes was concordant with serum C-peptide [median < 17 pmol/l (limit of detection) vs. 1037 pmol/l in non-type 1 diabetes; P < 0.0001].

Conclusions

Our study provides robust histological evidence that a clinical diagnostic model, combining clinical features and biomarkers, could improve diabetes classification. Our study also provides reassurance that a C-peptide-based definition of type 1 diabetes is an appropriate surrogate outcome that can be used in large clinical studies where histological definition is impossible. Parts of this study were presented in abstract form at the Network for Pancreatic Organ Donors Conference, Florida, USA, 19-22 February 2019 and Diabetes UK Professional Conference, Liverpool, UK, 6-8 March 2019.

SUBMITTER: Carr ALJ

PROVIDER: S-EPMC8086995 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAccurate classification of type 1 diabetes (T1DM) and type 2 diabetes (T2DM) in the early phase is crucial for individual precision treatment. This study aimed to develop a classification model having fewer and easier to access clinical variables to distinguish T1DM in newly diagnosed diabetes in adults.MethodsClinical and laboratory data were collected from 15,206 adults with newly diagnosed diabetes in this cross-sectional study. This cohort represented 20 provinces and 4 municipalities in China. Types of diabetes were determined based on postprandial C-peptide (PCP) level and glutamic acid decarboxylase autoantibody (GADA) titer. We developed multivariable clinical diagnostic models using the eXtreme Gradient Boosting (XGBoost) algorithm. Classification variables included in the final model were based on their scores of importance. Model performance was evaluated by area under the receiver operating characteristic curve (ROC AUC), sensitivity, and specificity. The performance of models with different variable combinations was compared. Calibration intercept and slope were evaluated for the final model.ResultsAmong the newly diagnosed diabetes cohort, 1,465 (9.63%) persons had T1DM and 13,741 (90.37%) had T2DM. Body mass index (BMI) contributed the most to the model, followed by age of onset and hemoglobin A1c (HbA1c). Compared with models with other clinical variable combinations, a final model that integrated age of onset, BMI and HbA1c had relatively higher performance. The ROC AUC, sensitivity, and specificity for this model were 0.83 (95% CI, 0.80 to 0.85), 0.77, and 0.76, respectively. The calibration intercept and slope were 0.02 (95% CI, -0.03 to 0.06) and 0.90 (95% CI, 0.79 to 1.02), respectively, which suggested a good calibration performance.ConclusionsOur classification model that integrated age of onset, BMI, and HbA1c could distinguish T1DM from T2DM, which provides a useful tool in assisting physicians in subtyping and precising treatment in diabetes.

Project description:A multivariate longitudinal DCM is developed that is the composite of two components, the log-linear cognitive diagnostic model (LCDM) as the measurement model component that evaluates the mastery status of attributes at each measurement occasion, and a generalized multivariate growth curve model that describes the growth of each attribute over time. The proposed model represents an improvement in the current longitudinal DCMs given its ability to incorporate both balanced and unbalanced data and to measure the growth of a single attribute directly without assuming that attributes grow in the same pattern. One simulation study was conducted to evaluate the proposed model in terms of the convergence rates, the accuracy of classification, and parameter recoveries under different combinations of four design factors: the sample size, the growth patterns, the G matrix design, and the number of measurement occasions. The results revealed the following: (1) In general, the proposed model provided good convergence rates under different conditions. (2) Regarding the classification accuracy, the proposed model achieved good recoveries on the probabilities of attribute mastery. However, the correct classification rates depended on the cut point that was used to classify individuals. For individuals who truly mastered the attributes, the correct classification rates increased as the measurement occasions increased; however, for individuals who truly did not master the attributes, the correct classification rates decreased slightly as the numbers of measurement occasions increased. Cohen's kappa increased as the number of measurement occasions increased. (3) Both the intercept and main effect parameters in the LCDM were recovered well. The interaction effect parameters had a relatively large bias under the condition with a small sample size and fewer measurement occasions; however, the recoveries were improved as the sample size and the number of measurement occasions increased. (4) Overall, the proposed model achieved acceptable recoveries on both the fixed and random effects in the generalized growth curve model.

Project description:OBJECTIVE:To develop and validate multivariable clinical diagnostic models to assist distinguishing between type 1 and type 2 diabetes in adults aged 18-50. DESIGN:Multivariable logistic regression analysis was used to develop classification models integrating five pre-specified predictor variables, including clinical features (age of diagnosis, body mass index) and clinical biomarkers (GADA and Islet Antigen 2 islet autoantibodies, Type 1 Diabetes Genetic Risk Score), to identify type 1 diabetes with rapid insulin requirement using data from existing cohorts. SETTING:UK cohorts recruited from primary and secondary care. PARTICIPANTS:1352 (model development) and 582 (external validation) participants diagnosed with diabetes between the age of 18 and 50 years of white European origin. MAIN OUTCOME MEASURES:Type 1 diabetes was defined by rapid insulin requirement (within 3 years of diagnosis) and severe endogenous insulin deficiency (C-peptide <200?pmol/L). Type 2 diabetes was defined by either a lack of rapid insulin requirement or, where insulin treated within 3 years, retained endogenous insulin secretion (C-peptide >600?pmol/L at ?5 years diabetes duration). Model performance was assessed using area under the receiver operating characteristic curve (ROC AUC), and internal and external validation. RESULTS:Type 1 diabetes was present in 13% of participants in the development cohort. All five predictor variables were discriminative and independent predictors of type 1 diabetes (p<0.001 for all) with individual ROC AUC ranging from 0.82 to 0.85. Model performance was high: ROC AUC range 0.90 (95% CI 0.88 to 0.93) (clinical features only) to 0.97 (95% CI 0.96 to 0.98) (all predictors) with low prediction error. Results were consistent in external validation (clinical features and GADA ROC AUC 0.93 (0.90 to 0.96)). CONCLUSIONS:Clinical diagnostic models integrating clinical features with biomarkers have high accuracy for identifying type 1 diabetes with rapid insulin requirement, and could assist clinicians and researchers in accurately identifying patients with type 1 diabetes.

Project description:BackgroundNumerous studies have utilized machine-learning techniques to predict the early onset of type 2 diabetes mellitus. However, fewer studies have been conducted to predict an appropriate diagnosis code for the type 2 diabetes mellitus condition. Further, ensemble techniques such as bagging and boosting have likewise been utilized to an even lesser extent. The present study aims to identify appropriate diagnosis codes for type 2 diabetes mellitus patients by means of building a multi-class prediction model which is both parsimonious and possessing minimum features. In addition, the importance of features for predicting diagnose code is provided.MethodsThis study included 149 patients who have contracted type 2 diabetes mellitus. The sample was collected from a large hospital in Taiwan from November, 2017 to May, 2018. Machine learning algorithms including instance-based, decision trees, deep neural network, and ensemble algorithms were all used to build the predictive models utilized in this study. Average accuracy, area under receiver operating characteristic curve, Matthew correlation coefficient, macro-precision, recall, weighted average of precision and recall, and model process time were subsequently used to assess the performance of the built models. Information gain and gain ratio were used in order to demonstrate feature importance.ResultsThe results showed that most algorithms, except for deep neural network, performed well in terms of all performance indices regardless of either the training or testing dataset that were used. Ten features and their importance to determine the diagnosis code of type 2 diabetes mellitus were identified. Our proposed predictive model can be further developed into a clinical diagnosis support system or integrated into existing healthcare information systems. Both methods of application can effectively support physicians whenever they are diagnosing type 2 diabetes mellitus patients in order to foster better patient-care planning.

Project description:Aims/hypothesisWe aimed to report current rates of CVD in type 1 diabetes and to develop a CVD risk prediction tool for type 1 diabetes.MethodsA cohort of 27,527 people with type 1 diabetes without prior CVD was derived from the national register in Scotland. Incident CVD events during 199,552 person-years of follow-up were ascertained using hospital admissions and death registers. A Poisson regression model of CVD was developed and then validated in the Swedish National Diabetes Register (n = 33,183). We compared the percentage with a high 10 year CVD risk (i.e., ≥10%) using the model with the percentage eligible for statins using current guidelines by age.ResultsThe age-standardised rate of CVD per 100,000 person-years was 4070 and 3429 in men and women, respectively, with type 1 diabetes in Scotland, and 4014 and 3956 in men and women in Sweden. The final model was well calibrated (Hosmer-Lemeshow test p > 0.05) and included a further 22 terms over a base model of age, sex and diabetes duration (C statistic 0.82; 95% CI 0.81, 0.83). The model increased the base model C statistic from 0.66 to 0.80, from 0.60 to 0.75 and from 0.62 to 0.68 in those aged <40, 40-59 and ≥ 60 years, respectively (all p values <0.005). The model required minimal calibration in Sweden and had a C statistic of 0.85. Under current guidelines, >90% of those aged 20-39 years and 100% of those ≥40 years with type 1 diabetes were eligible for statins, but it was not until age 65 upwards that 100% had a modelled risk of CVD ≥10% in 10 years.Conclusions/interpretationA prediction tool such as that developed here can provide individualised risk predictions. This 10 year CVD risk prediction tool could facilitate patient discussions regarding appropriate statin prescribing. Apart from 10 year risk, such discussions may also consider longer-term CVD risk, the potential for greater benefits from early vs later statin intervention, the potential impact on quality of life of an early CVD event and evidence on safety, all of which could influence treatment decisions, particularly in younger people with type 1 diabetes.