Data Mining Framework for Discovering and Clustering Phenotypes of Atypical Diabetes

Parikh, Hemang; Remedios, Cassandra; Hampe, Christiane S.; Balasubramanyam, Ashok; Fisher‐Hoch, Susan P.; Choi, Ye Ji; Patel, Sanjeet G.; McCormick, Joseph B.; Redondo, María J.; Krischer, Jeffrey P.

doi:10.1210/clinem/dgac632

Cited by 7 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is now generally recognized that the binary categorization of diabetes into type 1 and type 2 is insufficient to capture the range of metabolic and clinical phenotypes, molecular mechanisms, and disease pathogenesis that lead to the final common end point of hyperglycemia. The frequency of non–type 1, non–type 2 diabetes—now referred to as “atypical diabetes”—is likely underestimated, and the proportion varies considerably (from 5% to 11%) depending on the ethnic and other characteristics of the population studied ( 1 ).…”

Section: Atypical Diabetesmentioning

confidence: 99%

“…In this review, we seek to provide an overview of some of the characteristic features of well-described forms of atypical diabetes, including examples of those for which the etiological basis is known and others for which the etiological basis is not yet fully understood. Atypical diabetes is suspected in individuals who do not fit clearly into currently accepted criteria that define type 1 diabetes (T1D), type 2 diabetes (T2D), or secondary diabetes ( 1 , 2 ). We introduce the concept of endotypes, in which patients with diabetes can be clustered based on similar clinical or molecular/genetic mechanisms.…”

Section: Atypical Diabetesmentioning

confidence: 99%

See 1 more Smart Citation

Atypical Diabetes: What Have We Learned and What Does the Future Hold?

Stone,

Balasubramanyam,

Posey

2024

Diabetes Care

Self Cite

View full text Add to dashboard Cite

As our understanding of the pathophysiology of diabetes evolves, we increasingly recognize that many patients may have a form of diabetes that does not neatly fit with a diagnosis of either type 1 or type 2 diabetes. The discovery and description of these forms of “atypical diabetes” have led to major contributions to our collective understanding of the basic biology that drives insulin secretion, insulin resistance, and islet autoimmunity. These discoveries now pave the way to a better classification of diabetes based on distinct endotypes. In this review, we highlight the key biological and clinical insights that can be gained from studying known forms of atypical diabetes. Additionally, we provide a framework for identification of patients with atypical diabetes based on their clinical, metabolic, and molecular features. Helpful clinical and genetic resources for evaluating patients suspected of having atypical diabetes are provided. Therefore, appreciating the various endotypes associated with atypical diabetes will enhance diagnostic accuracy and facilitate targeted treatment decisions.

show abstract

Section: Atypical Diabetesmentioning

confidence: 99%

Section: Atypical Diabetesmentioning

confidence: 99%

Atypical Diabetes: What Have We Learned and What Does the Future Hold?

Stone,

Balasubramanyam,

Posey

2024

Diabetes Care

Self Cite

View full text Add to dashboard Cite

show abstract

“…Applications of clustering approaches in medical data analysis include disease nosology [11], early diagnosis of diseases [12,13], predictions of diseases [14,15], etc. The clustering of diseases is mostly for chronic diseases and severe illnesses, for example, diabetes [13,16,17], heart failure [18,19], cancer [20,21], stroke [22,23], and COVID-19 cases [24,25]. Arora et al [16] used K-means clustering for the prediction of diabetes.…”

Section: Clustering Techniques and Applications For Medical Data Anal...mentioning

confidence: 99%

Using Medical Data and Clustering Techniques for a Smart Healthcare System

Yang,

Lai,

Liu

et al. 2023

Electronics

View full text Add to dashboard Cite

With the rapid advancement of information technology, both hardware and software, smart healthcare has become increasingly achievable. The integration of medical data and machine-learning technology is the key to realizing this potential. The quality of medical data influences the results of a smart healthcare system to a great extent. This study aimed to design a smart healthcare system based on clustering techniques and medical data (SHCM) to analyze potential risks and trends in patients in a given time frame. Evidence-based medicine was also employed to explore the results generated by the proposed SHCM system. Thus, similar and different discoveries examined by applying evidence-based medicine could be investigated and integrated into the SHCM to provide personalized smart medical services. In addition, the presented SHCM system analyzes the relationship between health conditions and patients in terms of the clustering results. The findings of this study show the similarities and differences in the clusters obtained between indigenous patients and non-indigenous patients in terms of diseases, time, and numbers. Therefore, the analyzed potential health risks could be further employed in hospital management, such as personalized health education control, personal healthcare, improvement in the utilization of medical resources, and the evaluation of medical expenses.

show abstract

“…Although there is heightened interest in the challenges surrounding diagnosis of diabetes type [5,[10][11][12][13][14][15][16][17][18], the prevalence of imprecise diagnosis of pediatric diabetes types and the factors associated with imprecise diagnosis are not fully understood. Therefore, we aimed to study imprecise diagnosis of diabetes type in racially and ethnically diverse youth.…”

Section: Introductionmentioning

confidence: 99%

Imprecise Diagnosis of Diabetes Type in Youth: Prevalence, Characteristics, and Implications

Tosur

Huang

Inglis

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Classifying diabetes at diagnosis is crucial for disease management but increasingly difficult due to overlaps in characteristics between the commonly encountered diabetes types. We evaluated the prevalence and characteristics of youth with diabetes type that was unknown at diagnosis or was revised over time. We studied 2073 youth with new-onset diabetes (median age [IQR]=11.4 [6.2] years; 50% male; 75% White, 21% Black, 4% other race; overall, 37% Hispanic) and compared youth with unknown versus known diabetes type, per pediatric endocrinologist diagnosis. In a longitudinal subcohort of patients with data for ≥3 years post-diabetes diagnosis (n=1019), we compared youth with unchanged versus changed diabetes classification. In the entire cohort, after adjustment for confounders, diabetes type was unknown in 62 youth (3%), associated with older age, negative IA-2 autoantibody, lower C-peptide, and no diabetic ketoacidosis (all, p<0.05). In the longitudinal subcohort, diabetes classification changed in 35 youth (3.4%); this was not statistically associated with any single characteristic. Having unknown or revised diabetes type was associated with less continuous glucose monitor use on follow-up (both, p<0.004). In sum, among racially/ethnically diverse youth with diabetes, 6.5% had imprecise diabetes classification at diagnosis. Further research is warranted to improve accurate diagnosis of pediatric diabetes type.

show abstract

Data Mining Framework for Discovering and Clustering Phenotypes of Atypical Diabetes

Cited by 7 publications

References 43 publications

Atypical Diabetes: What Have We Learned and What Does the Future Hold?

Atypical Diabetes: What Have We Learned and What Does the Future Hold?

Using Medical Data and Clustering Techniques for a Smart Healthcare System

Imprecise Diagnosis of Diabetes Type in Youth: Prevalence, Characteristics, and Implications

Contact Info

Product

Resources

About