Identification of novel population clusters with different susceptibilities to type 2 diabetes and their impact on the prediction of diabetes

Artificial intelligence in endocrinology: a comprehensive review

BACKGROUND AND AIM

Artificial intelligence (AI) has emerged as a promising technology in the field of endocrinology, offering significant potential to revolutionize the diagnosis, treatment, and management of endocrine disorders. This comprehensive review aims to provide a concise overview of the current landscape of AI applications in endocrinology and metabolism, focusing on the fundamental concepts of AI, including machine learning algorithms and deep learning models.

METHODS

The review explores various areas of endocrinology where AI has demonstrated its value, encompassing screening and diagnosis, risk prediction, translational research, and "pre-emptive medicine". Within each domain, relevant studies are discussed, offering insights into the methodology and main findings of AI in the treatment of different pathologies, such as diabetes mellitus and related disorders, thyroid disorders, adrenal tumors, and bone and mineral disorders.

RESULTS

Collectively, these studies show the valuable contributions of AI in optimizing healthcare outcomes and unveiling new understandings of the intricate mechanisms underlying endocrine disorders. Furthermore, AI-driven approaches facilitate the development of precision medicine strategies, enabling tailored interventions for patients based on their individual characteristics and needs.

CONCLUSIONS

By embracing AI in endocrinology, a future can be envisioned where medical professionals and AI systems synergistically collaborate, ultimately enhancing the lives of individuals affected by endocrine disorders.

How Socio-economic Inequalities Cluster People with Diabetes in Malaysia: Geographic Evaluation of Area Disparities Using a Non-parameterized Unsupervised Learning Method

Accurate assessments of epidemiological associations between health outcomes and routinely observed proximal and distal determinants of health are fundamental for the execution of effective public health interventions and policies. Methods to couple big public health data with modern statistical techniques offer greater granularity for describing and understanding data quality, disease distributions, and potential predictive connections between population-level indicators with areal-based health outcomes. This study applied clustering techniques to explore patterns of diabetes burden correlated with local socio-economic inequalities in Malaysia, with a goal of better understanding the factors influencing the collation of these clusters. Through multi-modal secondary data sources, district-wise diabetes crude rates from 271,553 individuals with diabetes sampled from 914 primary care clinics throughout Malaysia were computed. Unsupervised machine learning methods using hierarchical clustering to a set of 144 administrative districts was applied. Differences in characteristics of the areas were evaluated using multivariate non-parametric test statistics. Five statistically significant clusters were identified, each reflecting different levels of diabetes burden at the local level, each with contrasting patterns observed under the influence of population-level characteristics. The hierarchical clustering analysis that grouped local diabetes areas with varying socio-economic, demographic, and geographic characteristics offer opportunities to local public health to implement targeted interventions in an attempt to control the local diabetes burden.

A new turn-on fluorescent probe for fast detection of diabetic biomarker beta-hydroxybutyrate in vitro

Beta-hydroxybutyrate (β-HB) serve as a valuable diagnostic biomarker for Diabetic Ketoacidosis (DKA). Here, a new Schiff base fluorescent probe T was designed and synthesized to detect β-HB level in aqueous solution in vitro. The probe T can detect β-HB sensitively and selectively in DMF solution (5.0 × 10-5 M) among other interfering species (cations, anions, amino acids, biomarkers). The detection limit of probe T for β-HB was calculated to be 0.154 μM. These results demonstrate that the probe T may provide a convenient method for rapid detection of β-HB to diagnose diabetic ketoacidosis.

ExpertNet: A Deep Learning Approach to Combined Risk Modeling and Subtyping in Intensive Care Units

Risk models play a crucial role in disease prevention, particularly in intensive care units (ICUs). Diseases often have complex manifestations with heterogeneous subpopulations, or subtypes, that exhibit distinct clinical characteristics. Risk models that explicitly model subtypes have high predictive accuracy and facilitate subtype-specific personalization. Such models combine clustering and classification methods but do not effectively utilize the inferred subtypes in risk modeling. Their limitations include tendency to obtain degenerate clusters and cluster-specific data scarcity leading to insufficient training data for the corresponding classifier. In this article, we develop a new deep learning model for simultaneous clustering and classification, ExpertNet, with novel loss terms and network training strategies that address these limitations. The performance of ExpertNet is evaluated on the tasks of predicting risk of (i) sepsis and (ii) acute respiratory distress syndrome (ARDS), using two large electronic medical records datasets from ICUs. Our extensive experiments show that, in comparison to state-of-the-art baselines for combined clustering and classification, ExpertNet achieves superior accuracy in risk prediction for both ARDS and sepsis; and comparable clustering performance. Visual analysis of the clusters further demonstrates that the clusters obtained are clinically meaningful and a knowledge-distilled model shows significant differences in risk factors across the subtypes. By addressing technical challenges in training neural networks for simultaneous clustering and classification, ExpertNet lays the algorithmic foundation for the future development of subtype-aware risk models.

Characterization of data-driven clusters in diabetes-free adults and their utility for risk stratification of type 2 diabetes

BACKGROUND

The prevention of type 2 diabetes is challenging due to the variable effects of risk factors at an individual level. Data-driven methods could be useful to detect more homogeneous groups based on risk factor variability. The aim of this study was to derive characteristic phenotypes using cluster analysis of common risk factors and to assess their utility to stratify the risk of type 2 diabetes.

METHODS

Data on 7317 diabetes-free adults from Sweden were used in the main analysis and on 2332 diabetes-free adults from Mexico for external validation. Clusters were based on sex, family history of diabetes, educational attainment, fasting blood glucose and insulin levels, estimated insulin resistance and β-cell function, systolic and diastolic blood pressure, and BMI. The risk of type 2 diabetes was assessed using Cox proportional hazards models. The predictive accuracy and long-term stability of the clusters were then compared to different definitions of prediabetes.

RESULTS

Six risk phenotypes were identified independently in both cohorts: very low-risk (VLR), low-risk low β-cell function (LRLB), low-risk high β-cell function (LRHB), high-risk high blood pressure (HRHBP), high-risk β-cell failure (HRBF), and high-risk insulin-resistant (HRIR). Compared to the LRHB cluster, the VLR and LRLB clusters showed a lower risk, while the HRHBP, HRBF, and HRIR clusters showed a higher risk of developing type 2 diabetes. The high-risk clusters, as a group, had a better predictive accuracy than prediabetes and adequate stability after 20 years.

CONCLUSIONS

Phenotypes derived using cluster analysis were useful in stratifying the risk of type 2 diabetes among diabetes-free adults in two independent cohorts. These results could be used to develop more precise public health interventions.

Identification and epidemiological characterization of Type-2 diabetes sub-population using an unsupervised machine learning approach

Background

Studies on Type-2 Diabetes Mellitus (T2DM) have revealed heterogeneous sub-populations in terms of underlying pathologies. However, the identification of sub-populations in epidemiological datasets remains unexplored. We here focus on the detection of T2DM clusters in epidemiological data, specifically analysing the National Family Health Survey-4 (NFHS-4) dataset from India containing a wide spectrum of features, including medical history, dietary and addiction habits, socio-economic and lifestyle patterns of 10,125 T2DM patients.

Methods

Epidemiological data provide challenges for analysis due to the diverse types of features in it. In this case, applying the state-of-the-art dimension reduction tool UMAP conventionally was found to be ineffective for the NFHS-4 dataset, which contains diverse feature types. We implemented a distributed clustering workflow combining different similarity measure settings of UMAP, for clustering continuous, ordinal and nominal features separately. We integrated the reduced dimensions from each feature-type-distributed clustering to obtain interpretable and unbiased clustering of the data.

Results

Our analysis reveals four significant clusters, with two of them comprising mainly of non-obese T2DM patients. These non-obese clusters have lower mean age and majorly comprises of rural residents. Surprisingly, one of the obese clusters had 90% of the T2DM patients practising a non-vegetarian diet though they did not show an increased intake of plant-based protein-rich foods.

Conclusions

From a methodological perspective, we show that for diverse data types, frequent in epidemiological datasets, feature-type-distributed clustering using UMAP is effective as opposed to the conventional use of the UMAP algorithm. The application of UMAP-based clustering workflow for this type of dataset is novel in itself. Our findings demonstrate the presence of heterogeneity among Indian T2DM patients with regard to socio-demography and dietary patterns. From our analysis, we conclude that the existence of significant non-obese T2DM sub-populations characterized by younger age groups and economic disadvantage raises the need for different screening criteria for T2DM among rural Indian residents.

Toward an Improved Classification of Type 2 Diabetes: Lessons From Research into the Heterogeneity of a Complex Disease

CONTEXT

Accumulating evidence indicates that type 2 diabetes (T2D) is phenotypically heterogeneous. Defining and classifying variant forms of T2D are priorities to better understand its pathophysiology and usher clinical practice into an era of "precision diabetes."

EVIDENCE ACQUISITION AND METHODS

We reviewed literature related to heterogeneity of T2D over the past 5 decades and identified a range of phenotypic variants of T2D. Their descriptions expose inadequacies in current classification systems. We attempt to link phenotypically diverse forms to pathophysiology, explore investigative methods that have characterized "atypical" forms of T2D on an etiological basis, and review conceptual frameworks for an improved taxonomy. Finally, we propose future directions to achieve the goal of an etiological classification of T2D.

EVIDENCE SYNTHESIS

Differences among ethnic and racial groups were early observations of phenotypic heterogeneity. Investigations that uncover complex interactions of pathophysiologic pathways leading to T2D are supported by epidemiological and clinical differences between the sexes and between adult and youth-onset T2D. Approaches to an etiological classification are illustrated by investigations of atypical forms of T2D, such as monogenic diabetes and syndromes of ketosis-prone diabetes. Conceptual frameworks that accommodate heterogeneity in T2D include an overlap between known diabetes types, a "palette" model integrated with a "threshold hypothesis," and a spectrum model of atypical diabetes.

CONCLUSION

The heterogeneity of T2D demands an improved, etiological classification scheme. Excellent phenotypic descriptions of emerging syndromes in different populations, continued clinical and molecular investigations of atypical forms of diabetes, and useful conceptual models can be utilized to achieve this important goal.

Machine learning for subtype definition and risk prediction in heart failure, acute coronary syndromes and atrial fibrillation: systematic review of validity and clinical utility

BACKGROUND

Machine learning (ML) is increasingly used in research for subtype definition and risk prediction, particularly in cardiovascular diseases. No existing ML models are routinely used for cardiovascular disease management, and their phase of clinical utility is unknown, partly due to a lack of clear criteria. We evaluated ML for subtype definition and risk prediction in heart failure (HF), acute coronary syndromes (ACS) and atrial fibrillation (AF).

METHODS

For ML studies of subtype definition and risk prediction, we conducted a systematic review in HF, ACS and AF, using PubMed, MEDLINE and Web of Science from January 2000 until December 2019. By adapting published criteria for diagnostic and prognostic studies, we developed a seven-domain, ML-specific checklist.

RESULTS

Of 5918 studies identified, 97 were included. Across studies for subtype definition (n = 40) and risk prediction (n = 57), there was variation in data source, population size (median 606 and median 6769), clinical setting (outpatient, inpatient, different departments), number of covariates (median 19 and median 48) and ML methods. All studies were single disease, most were North American (n = 61/97) and only 14 studies combined definition and risk prediction. Subtype definition and risk prediction studies respectively had limitations in development (e.g. 15.0% and 78.9% of studies related to patient benefit; 15.0% and 15.8% had low patient selection bias), validation (12.5% and 5.3% externally validated) and impact (32.5% and 91.2% improved outcome prediction; no effectiveness or cost-effectiveness evaluations).

CONCLUSIONS

Studies of ML in HF, ACS and AF are limited by number and type of included covariates, ML methods, population size, country, clinical setting and focus on single diseases, not overlap or multimorbidity. Clinical utility and implementation rely on improvements in development, validation and impact, facilitated by simple checklists. We provide clear steps prior to safe implementation of machine learning in clinical practice for cardiovascular diseases and other disease areas.

Silencing of the tRNA Modification Enzyme Cdkal1 Effects Functional Insulin Synthesis in NIT-1 Cells: tRNALys3 Lacking ms2- (ms2t6A37) is Unable to Establish Sufficient Anticodon:Codon Interactions to Decode the Wobble Codon AAG

Human Genome Wide Association Studies found a significant risk of Type 2 Diabetes Mellitus (T2DM) in single nucleotide polymorphisms in the cdkal1 gene. The cdkal1 gene is remote from the insulin gene and with the surprising function of a specific tRNA modification. Population studies and case control studies acquired evidences of the connection between Cdkal1 protein and insulin production over the years. To obtain biochemical proofs directly linking potential SNPs to their roles in insulin production and availability is challenging, but the development of Cdkal1 knock out mice and knock out cell lines made it possible to extend our knowledge towards therapeutic field of diabetic research. Supporting the evidences, here we show that knock down of the cdkal1 gene using small interfering and short hairpin RNA in the NIT-1 cell line, a β-cell line inducible for insulin resulted in reduced levels of cdkal1 and mature insulin mRNAs, increased the level of precursor insulin mRNA, decreased Cdkal1 and insulin proteins, and diminished modification of tRNA^Lys3 from t⁶A₃₇ to ms²t⁶A₃₇, the specified function of Cdkal1. tRNA^Lys3 lacking ms²- is incapable of establishing sufficient hydrogen bonding energy and hydrophobic stabilization to decode the wobble codon AAG.

Machine Learning for Predicting the 3-Year Risk of Incident Diabetes in Chinese Adults

Purpose: We aimed to establish and validate a risk assessment system that combines demographic and clinical variables to predict the 3-year risk of incident diabetes in Chinese adults. Methods: A 3-year cohort study was performed on 15,928 Chinese adults without diabetes at baseline. All participants were randomly divided into a training set (n = 7,940) and a validation set (n = 7,988). XGBoost method is an effective machine learning technique used to select the most important variables from candidate variables. And we further established a stepwise model based on the predictors chosen by the XGBoost model. The area under the receiver operating characteristic curve (AUC), decision curve and calibration analysis were used to assess discrimination, clinical use and calibration of the model, respectively. The external validation was performed on a cohort of 11,113 Japanese participants. Result: In the training and validation sets, 148 and 145 incident diabetes cases occurred. XGBoost methods selected the 10 most important variables from 15 candidate variables. Fasting plasma glucose (FPG), body mass index (BMI) and age were the top 3 important variables. And we further established a stepwise model and a prediction nomogram. The AUCs of the stepwise model were 0.933 and 0.910 in the training and validation sets, respectively. The Hosmer-Lemeshow test showed a perfect fit between the predicted diabetes risk and the observed diabetes risk (p = 0.068 for the training set, p = 0.165 for the validation set). Decision curve analysis presented the clinical use of the stepwise model and there was a wide range of alternative threshold probability spectrum. And there were almost no the interactions between these predictors (most P-values for interaction >0.05). Furthermore, the AUC for the external validation set was 0.830, and the Hosmer-Lemeshow test for the external validation set showed no statistically significant difference between the predicted diabetes risk and observed diabetes risk (P = 0.824). Conclusion: We established and validated a risk assessment system for characterizing the 3-year risk of incident diabetes.

Current Pharmacological Treatment of Type 2 Diabetes Mellitus in Undocumented Migrants: Is It Appropriate for the Phenotype of the Disease?

Type 2 diabetes is increasingly recognized as a spectrum of metabolic disorders sharing chronic hyperglycaemia. In Europe, the continually growing number of migrants from developing countries could affect diabetes phenotypes. We evaluated a population of 426 Italians and 412 undocumented migrants. Using 17 variables (with the exclusion of ethnic origin) we performed a multiple component analysis to detect potential clusters, independently from ethnicity. We also compared the two groups to evaluate potential ethnicity associated differences. We found five clusters of patients with different disease phenotypes. Comparing Italians with undocumented migrants, we noted that the first had more often cardiovascular risk factors and neurologic involvement, while the latter had a higher frequency of diabetic ulcers and renal involvement. Metformin was used in a comparable percentage of patients in all clusters, but other antidiabetic treatments showed some differences. Italians were more often on insulin, due to a larger use of long acting insulin, and received a larger number of oral antidiabetics in combination. Pharmacological treatment of comorbidities showed some differences too. We suggest that type 2 diabetes should be considered as a spectrum of diseases with different phenotypes also in heterogeneous populations, and that this is not due only to ethnic differences.

Defining and Classifying New Subgroups of Diabetes

An etiologically based classification of diabetes is needed to account for the heterogeneity of type 1 and type 2 diabetes (T1D and T2D) and emerging forms of diabetes worldwide. It may be productive for both classification and clinical discovery to consider variant forms of diabetes as a spectrum. Maturity onset diabetes of youth and neonatal diabetes serve as models for etiologically defined, rare forms of diabetes in the spectrum. Ketosis-prone diabetes is a model for more complex forms, amenable to phenotypic dissection. Bioinformatic approaches such as clustering analyses of large datasets and multi-omics investigations of rare and atypical phenotypes are promising avenues to explore and define new subgroups of diabetes.

Protein-conformational diseases in childhood: Naturally-occurring hIAPP amyloid-oligomers and early β-cell damage in obesity and diabetes

BACKGROUND AND AIMS

This is the first time that obesity and diabetes mellitus (DM) as protein conformational diseases (PCD) are reported in children and they are typically diagnosed too late, when β-cell damage is evident. Here we wanted to investigate the level of naturally-ocurring or real (not synthetic) oligomeric aggregates of the human islet amyloid polypeptide (hIAPP) that we called RIAO in sera of pediatric patients with obesity and diabetes. We aimed to reduce the gap between basic biomedical research, clinical practice-health decision making and to explore whether RIAO work as a potential biomarker of early β-cell damage.

MATERIALS AND METHODS

We performed a multicentric collaborative, cross-sectional, analytical, ambispective and blinded study; the RIAO from pretreated samples (PTS) of sera of 146 pediatric patients with obesity or DM and 16 healthy children, were isolated, measured by sound indirect ELISA with novel anti-hIAPP cytotoxic oligomers polyclonal antibody (MEX1). We carried out morphological and functional studied and cluster-clinical data driven analysis.

RESULTS

We demonstrated by western blot, Transmission Electron Microscopy and cell viability experiments that RIAO circulate in the blood and can be measured by ELISA; are elevated in serum of childhood obesity and diabetes; are neurotoxics and works as biomarkers of early β-cell failure. We explored the range of evidence-based medicine clusters that included the RIAO level, which allowed us to classify and stratify the obesity patients with high cardiometabolic risk.

CONCLUSIONS

RIAO level increases as the number of complications rises; RIAOs > 3.35 μg/ml is a predictor of changes in the current indicators of β-cell damage. We proposed a novel physio-pathological pathway and shows that PCD affect not only elderly patients but also children. Here we reduced the gap between basic biomedical research, clinical practice and health decision making.