Prediction models of diabetes complications: a scoping review

Ndjaboué, Ruth; Ngueta, Gérard; Rochefort-Brihay, Charlotte; Delorme, Sasha; Guay, Daniel; Ivers, Noah; Shah, Baiju R.; Straus, Sharon E.; Yu, Catherine; Comeau, Sandrine; Farhat, Imen; Racine, Charles; Drescher, Olivia; Witteman, Holly O.

doi:10.1136/jech-2021-217793

Cited by 5 publications

(2 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these studies suffer from (1) a small and nonrepresentative population (eg, individuals in a single hospital) or (2) a limited number of complications, or (3) they lack important patient information (eg, biomarkers or disease codes). Furthermore, according to a review of prediction models for diabetes complications [19], there exist no prediction models for micro-or macrovascular complications in individuals with prediabetes. However, such prediction models are important because they allow for an earlier intervention (ie, treatment via medications or lifestyle changes) to prevent the onset of microor macrovascular complications.…”

Section: Objectivesmentioning

confidence: 99%

Machine Learning for Predicting Micro- and Macrovascular Complications in Individuals With Prediabetes or Diabetes: Retrospective Cohort Study

Schallmoser¹,

Zueger

Kraus³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Micro- and macrovascular complications are a major burden for individuals with diabetes and can already arise in a prediabetic state. To allocate effective treatments and to possibly prevent these complications, identification of those at risk is essential. Objective This study aimed to build machine learning (ML) models that predict the risk of developing a micro- or macrovascular complication in individuals with prediabetes or diabetes. Methods In this study, we used electronic health records from Israel that contain information about demographics, biomarkers, medications, and disease codes; span from 2003 to 2013; and were queried to identify individuals with prediabetes or diabetes in 2008. Subsequently, we aimed to predict which of these individuals developed a micro- or macrovascular complication within the next 5 years. We included 3 microvascular complications: retinopathy, nephropathy, and neuropathy. In addition, we considered 3 macrovascular complications: peripheral vascular disease (PVD), cerebrovascular disease (CeVD), and cardiovascular disease (CVD). Complications were identified via disease codes, and, for nephropathy, the estimated glomerular filtration rate and albuminuria were considered additionally. Inclusion criteria were complete information on age and sex and on disease codes (or measurements of estimated glomerular filtration rate and albuminuria for nephropathy) until 2013 to account for patient dropout. Exclusion criteria for predicting a complication were diagnosis of this specific complication before or in 2008. In total, 105 predictors from demographics, biomarkers, medications, and disease codes were used to build the ML models. We compared 2 ML models: logistic regression and gradient-boosted decision trees (GBDTs). To explain the predictions of the GBDTs, we calculated Shapley additive explanations values. Results Overall, 13,904 and 4259 individuals with prediabetes and diabetes, respectively, were identified in our underlying data set. For individuals with prediabetes, the areas under the receiver operating characteristic curve for logistic regression and GBDTs were, respectively, 0.657 and 0.681 (retinopathy), 0.807 and 0.815 (nephropathy), 0.727 and 0.706 (neuropathy), 0.730 and 0.727 (PVD), 0.687 and 0.693 (CeVD), and 0.707 and 0.705 (CVD); for individuals with diabetes, the areas under the receiver operating characteristic curve were, respectively, 0.673 and 0.726 (retinopathy), 0.763 and 0.775 (nephropathy), 0.745 and 0.771 (neuropathy), 0.698 and 0.715 (PVD), 0.651 and 0.646 (CeVD), and 0.686 and 0.680 (CVD). Overall, the prediction performance is comparable for logistic regression and GBDTs. The Shapley additive explanations values showed that increased levels of blood glucose, glycated hemoglobin, and serum creatinine are risk factors for microvascular complications. Age and hypertension were associated with an elevated risk for macrovascular complications. Conclusions Our ML models allow for an identification of individuals with prediabetes or diabetes who are at increased risk of developing micro- or macrovascular complications. The prediction performance varied across complications and target populations but was in an acceptable range for most prediction tasks.

show abstract

Section: Objectivesmentioning

confidence: 99%

Machine Learning for Predicting Micro- and Macrovascular Complications in Individuals With Prediabetes or Diabetes: Retrospective Cohort Study

Schallmoser¹,

Zueger

Kraus³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…The etiopathogenesis of T2D relies on insulin resistance and/or reduced secretion from beta-cells ( 13 ). The result is a persistent increase of blood glucose levels (hyperglycemia) leading to micro- and macro-vascular generalized damages (nephropathy, neuropathy, maculopathy, central and peripheral vasculopathy) ( 14 ). The etiopathogenesis of primary HT include alterations in the activity of sympathetic nervous system, the renin-angiotensin system, the pathways involved in calcium and sodium homeostasis, the structure and reactivity of the vascular smooth muscle network ( 15 – 17 ).…”

Section: Introductionmentioning

confidence: 99%

Hypertension, type 2 diabetes, obesity, and p53 mutations negatively correlate with metastatic colorectal cancer patients’ survival

Ottaiano

Santorsola

Circelli³

et al. 2023

Front. Med.

View full text Add to dashboard Cite

IntroductionWe studied the predictive and prognostic influences of hypertension (HT), type 2 diabetes (T2D), weight, and p53 mutations in metastatic colorectal cancer (CRC) patients.Patients and methodsT2D was diagnosed according to the ADA criteria. HT was classified according to the ACC/AHA guidelines. BMI (body-mass index) was calculated and classified according to the WHO criteria. TruSigt™Oncology 500 kit was applied to construct the genomic libraries for Next Generation Sequencing (NGS) analysis. The Illumina NovaSeq 6000 technological platform and the Illumina TruSight Oncology 500 bioinformatics pipeline were applied to analyze results. Overall survival (OS) was calculated through Kaplan-Meier curves. Univariate and multivariate analyses were performed to assess the relationships between clinical and/or molecular covariates. Associations between HT, T2D, BMI, p53, and clinical variables were evaluated by the χ2 test. P < 0.05 were considered statistically significant.ResultsTwo-hundred-forty-four patients were enrolled. One-hundred-twenty (49.2%), 110 (45.1%), and 50 (20.5%) patients were affected by overweight, HT, and T2D, respectively. DC (disease control) was achieved more frequently in patients without T2D (83.1%) compared to the diabetic ones (16.9%) (P = 0.0246). DC, KRAS mutational status, T2D, BMI, and concomitant presence of T2D, BMI, and HT associated with survival (P < 0.05). At multivariate analysis, age (≥65 vs. <65 years), response to first-line chemotherapy (DC vs. no DC), and concomitant presence of T2D, BMI, and HT (HR: 4.56; 95% CI: 2.40–8.67; P = 0.0217) emerged as independent prognostic variables. P53 was mutated in 31/53 analyzed cases (60.4%). The most frequent gene variants were p.Arg175His and p.Cys135Tyr. High BMI (>25 kg/m2) associated with occurrence of p53 mutations (P < 0.0001). P53 mutated patients presented a worse prognosis compared to the wild-type ones (HR: 3.21; 95% CI: 1.43–7.23; P = 0.0047).ConclusionDiabetic, hypertensive and overweight metastatic CRC patients are a negative prognostic subgroup deserving specific therapeutic strategies. P53 mutations associate with prognosis and BMI unrevealing complex and unexplored connections between metabolism and cancer occurrence.

show abstract

Changes in prediction modelling in biomedicine – do systematic reviews indicate whether there is any trend towards larger data sets and machine learning methods?

Lusa,

Kappenberg,

Collins

et al. 2024

Preprint

View full text Add to dashboard Cite

The number of prediction models proposed in the biomedical literature has been growing year on year. In the last few years there has been an increasing attention to the changes occurring in the prediction modeling landscape. It is suggested that machine learning techniques are becoming more popular to develop prediction models to exploit complex data structures, higher-dimensional predictor spaces, very large number of participants, heterogeneous subgroups, with the ability to capture higher-order interactions.We examine these changes in modelling practices by investigating a selection of systematic reviews on prediction models published in the biomedical literature. We selected systematic reviews published since 2020 which included at least 50 prediction models. Information was extracted guided by the CHARMS checklist. Time trends were explored using the models published since 2005.We identified 8 reviews, which included 1448 prediction models published in 887 papers. The average number of study participants and outcome events increased considerably between 2015 and 2019, but remained stable afterwards. The number of candidate and final predictors did not noticeably increase over the study period, with a few recent studies using very large numbers of predictors. Internal validation and reporting of discrimination measures became more common, but assessing calibration and carrying out external validation were less common. Information about missing values was not reported in about half of the papers, however the use of imputation methods increased. There was no sign of an increase in using of machine learning methods. Overall, most of the findings were heterogeneous across reviews.Our findings indicate that changes in the prediction modeling landscape in biomedicine are less dramatic than expected and that poor reporting is still common; adherence to well established best practice recommendations from the traditional biostatistics literature is still needed. For machine learning best practice recommendations are still missing, whereas such recommendations are available in the traditional biostatistics literature, but adherence is still inadequate.

show abstract

Prediction models of diabetes complications: a scoping review

Cited by 5 publications

References 124 publications

Machine Learning for Predicting Micro- and Macrovascular Complications in Individuals With Prediabetes or Diabetes: Retrospective Cohort Study

Machine Learning for Predicting Micro- and Macrovascular Complications in Individuals With Prediabetes or Diabetes: Retrospective Cohort Study

Hypertension, type 2 diabetes, obesity, and p53 mutations negatively correlate with metastatic colorectal cancer patients’ survival

Changes in prediction modelling in biomedicine – do systematic reviews indicate whether there is any trend towards larger data sets and machine learning methods?

Contact Info

Product

Resources

About