'Personalized medicine' to identify genetic risks for type 2 diabetes and focus prevention: can it fulfill its promise?

A Review of Feature Selection Methods for Machine Learning-Based Disease Risk Prediction

Machine learning has shown utility in detecting patterns within large, unstructured, and complex datasets. One of the promising applications of machine learning is in precision medicine, where disease risk is predicted using patient genetic data. However, creating an accurate prediction model based on genotype data remains challenging due to the so-called “curse of dimensionality” (i.e., extensively larger number of features compared to the number of samples). Therefore, the generalizability of machine learning models benefits from feature selection, which aims to extract only the most “informative” features and remove noisy “non-informative,” irrelevant and redundant features. In this article, we provide a general overview of the different feature selection methods, their advantages, disadvantages, and use cases, focusing on the detection of relevant features (i.e., SNPs) for disease risk prediction.

Precision health care strategies for older adults with diabetes in Indonesia: a Delphi consensus study

BACKGROUND Studies on precision health care for older adults with diabetes in Indonesia are still limited. This study was aimed to reach the experts consensus on the suitable precision health care strategies for older adults with diabetes. METHODS A total of 10 experts (4 physicians, 4 nurses, and 2 dietitians) agreed to participate in the 3-round interview using Delphi technique. The experts should have at least 5 years of experience in teaching or working as health professionals in a hospital. RESULTS Consensus was reached that precision health care consisted of eight elements: self-management, interdisciplinary collaborative practice, personalized genetic or lifestyle factors, glycemic target, patient preferences, glycemic control, patient priority-directed care, and biodata- or evidence-based practice. The strategies of precision health care for diabetes were divided into seven steps: conducting brief deducting teaching; assessing self-management level and risk of cardiovascular disease; organizing a brainstorming session among patients to exchange experiences on glycemic target and specific target behavior; making a list of patients’ needs and ranking the priorities; setting a goal and writing action; doing follow-up; and reporting the goal attempts. CONCLUSIONS The eight elements of precision health care provided the basis of precision health care strategies for diabetic older adults, which are the real and measurable strategies for precision health care implementation in clinical settings.

Precision Health Care Elements, Definitions, and Strategies for Patients with Diabetes: A Literature Review

Diabetes is a prevalent disease with a high risk of complications. The number of people with diabetes worldwide was reported to increase every year. However, new integrated individualized health care related to diabetes is insufficiently developed. Purpose: The objective of this study was to conduct a literature review and discover precision health care elements, definitions, and strategies. Methods: This study involved a 2-stage process. The first stage comprised a systematic literature search, evidence evaluation, and article extraction. The second stage involved discovering precision health care elements and defining and developing strategies for the management of patients with diabetes. Results: Of 1337 articles, we selected 35 relevant articles for identifying elements and definitions of precision health care for diabetes, including personalized genetic or lifestyle factors, biodata- or evidence-based practice, glycemic target, patient preferences, glycemic control, interdisciplinary collaboration practice, self-management, and patient priority direct care. Moreover, strategies were developed to apply precision health care for diabetes treatment based on eight elements. Conclusions: We discovered precision health care elements and defined and developed strategies of precision health care for patients with diabetes. precision health care is based on team foundation, personalized glycemic target, and control as well as patient preferences and priority, thus providing references for future research and clinical practice.

Zebrafish models of diabetes-related CNS pathogenesis

Diabetes mellitus (DM) is a common metabolic disorder that affects multiple organ systems. DM also affects brain processes, contributing to various CNS disorders, including depression, anxiety and Alzheimer's disease. Despite active research in humans, rodent models and in-vitro systems, the pathogenetic link between DM and brain disorders remains poorly understood. Novel translational models and new model organisms are therefore essential to more fully study the impact of DM on CNS. The zebrafish (Danio rerio) is a powerful novel model species to study metabolic and CNS disorders. Here, we discuss how DM alters brain functions and behavior in zebrafish, and summarize their translational relevance to studying DM-related CNS pathogenesis in humans. We recognize the growing utility of zebrafish models in translational DM research, as they continue to improve our understanding of different brain pathologies associated with DM, and may foster the discovery of drugs that prevent or treat these diseases.

Machine Learning SNP Based Prediction for Precision Medicine

In the past decade, precision genomics based medicine has emerged to provide tailored and effective healthcare for patients depending upon their genetic features. Genome Wide Association Studies have also identified population based risk genetic variants for common and complex diseases. In order to meet the full promise of precision medicine, research is attempting to leverage our increasing genomic understanding and further develop personalized medical healthcare through ever more accurate disease risk prediction models. Polygenic risk scoring and machine learning are two primary approaches for disease risk prediction. Despite recent improvements, the results of polygenic risk scoring remain limited due to the approaches that are currently used. By contrast, machine learning algorithms have increased predictive abilities for complex disease risk. This increase in predictive abilities results from the ability of machine learning algorithms to handle multi-dimensional data. Here, we provide an overview of polygenic risk scoring and machine learning in complex disease risk prediction. We highlight recent machine learning application developments and describe how machine learning approaches can lead to improved complex disease prediction, which will help to incorporate genetic features into future personalized healthcare. Finally, we discuss how the future application of machine learning prediction models might help manage complex disease by providing tissue-specific targets for customized, preventive interventions.

Improving Prognostic Web Calculators: Violation of Preferential Risk Independence

BACKGROUND

Web-based applications are available for prognostication of individual patients. These prognostic models were developed for groups of patients. No one is the average patient, and using these calculators to inform individual patients could provide misleading results.

OBJECTIVE

This article gives an example of paradoxical results that may emerge when indices used for prognosis of the average person are used for care of an individual patient.

METHODS

We calculated the expected mortality risks of stomach cancer and its associated comorbidities. Mortality risks were calculated using data from 140,699 Veterans Administration nursing home residents.

RESULTS

On average, a patient with hypertension has a higher risk of mortality than one without hypertension. Surprisingly, among patients with lung cancer, hypertension is protective and reduces risk of mortality. This paradoxical result is explained by how group-level, average prognosis could mislead individual patients. In particular, average prognosis of lung cancer patients reflects the impact of various comorbidities that co-occur in lung cancer patients. The presence of hypertension, a relatively mild comorbidity of lung cancer, indicates that more serious comorbidities have not occurred. It is not that hypertension is protective; it is the absence of more serious comorbidities that is protective. The article shows how the presence of these anomalies can be checked through the mathematical concept of preferential risk independence.

CONCLUSION

Instead of reporting average risk scores, web-based calculators may improve accuracy of predictions by reporting the unconfounded risks.

The impact of personalized medicine of Type 2 diabetes mellitus in the global health context

Advances in the fields of genomic sciences have given rise to personalized medicine. This new paradigm draws upon a patient's genetic and metabolic makeup in order to tailor diagnostics and treatment. Personalized medicine holds remarkable promises to improve prevention and management of chronic diseases of global relevance, such as Type 2 diabetes mellitus (T2DM). This review article aims at summarizing the evidence from genome-based sciences on T2DM risk and management in different populations and in the Global Health context. Opinions from leading experts in the field were also included. Based on these findings, strengths and weaknesses of personalized approach to T2DM in a global context are delineated. Implications for future research and implementation on that subject are discussed.

Preventing type 2 diabetes mellitus: a call for personalized intervention

In parallel with the rising prevalence of obesity worldwide, especially in younger people, there has been a dramatic increase in recent decades in the incidence and prevalence of metabolic consequences of obesity, in particular prediabetes and type 2 diabetes mellitus (DM2). Although approximately one-third of US adults now meet one or more diagnostic criteria for prediabetes, only a minority of those so identified as being at risk for DM2 actually progress to diabetes, and some may regress to normal status. Given the uncertain prognosis of prediabetes, it is not clear who is most likely to benefit from lifestyle change or medication interventions that are known to reduce DM2 risk. We review the many factors known to influence risk of developing DM2 and summarize treatment trials demonstrating the possibility of preventing DM2. Applying the concepts of personalized medicine and the potential of "big data" approaches to analysis of massive amounts of routinely gathered clinical and laboratory data from large populations, we call for the development of tools to more precisely estimate individual risk of DM2.

Insulin sensitizing and anti-inflammatory effects of thiazolidinediones are heightened in obese patients

OBJECTIVE

The American Diabetes Association has called for further research on how patients' demographics should determine drug choices for individuals with type 2 diabetes mellitus (T2DM). Here, using in-depth physiology studies, we investigate whether obese patients with T2DM are likely to benefit from thiazolidinediones, medications with a known adverse effect of weight gain.

MATERIALS AND METHODS

Eleven obese and 7 nonobese individuals with T2DM participated in this randomized, placebo-controlled, double-blind, crossover study. Each subject underwent a pair of "stepped" pancreatic clamp studies with subcutaneous adipose tissue biopsies after 21 days of pioglitazone (45 mg) or placebo.

RESULTS

Obese subjects demonstrated significant decreases in insulin resistance and many adipose inflammatory parameters with pioglitazone relative to placebo. Specifically, significant improvements in glucose infusion rates, suppression of hepatic glucose production, and whole fat expression of certain inflammatory markers (IL-6, IL-1B, and inducible nitric oxide synthase) were observed in the obese subjects but not in the nonobese subjects. Additionally, adipose tissue from the obese subjects demonstrated reduced infiltration of macrophages, dendritic cells, and neutrophils as well as increased expression of factors associated with fat "browning" (peroxisome proliferator-activated receptor gamma coactivator-1α and uncoupling protein-1).

CONCLUSIONS

These findings support the efficacy of pioglitazone to improve insulin resistance and reduce adipose tissue inflammation in obese patients with T2DM.

Introduction to personalized medicine in diabetes mellitus

The world is facing an epidemic rise in diabetes mellitus (DM) incidence, which is challenging health funders, health systems, clinicians, and patients to understand and respond to a flood of research and knowledge. Evidence-based guidelines provide uniform management recommendations for "average" patients that rarely take into account individual variation in susceptibility to DM, to its complications, and responses to pharmacological and lifestyle interventions. Personalized medicine combines bioinformatics with genomic, proteomic, metabolomic, pharmacogenomic ("omics") and other new technologies to explore pathophysiology and to characterize more precisely an individual's risk for disease, as well as response to interventions. In this review we will introduce readers to personalized medicine as applied to DM, in particular the use of clinical, genetic, metabolic, and other markers of risk for DM and its chronic microvascular and macrovascular complications, as well as insights into variations in response to and tolerance of commonly used medications, dietary changes, and exercise. These advances in "omic" information and techniques also provide clues to potential pathophysiological mechanisms underlying DM and its complications.