Prediction model has been the focus of studies since the last century in the diagnosis and prognosis of various diseases. With the advancement in computational technology, machine learning (ML) has become the widely used tool to develop a prediction model. This review is to investigate the current development of prediction model for the risk of cardiovascular disease (CVD) among type 2 diabetes (T2DM) patients using machine learning. A systematic search on Scopus and Web of Science (WoS) was conducted to look for relevant articles based on the research question. The risk of bias (ROB) for all articles were assessed based on the Prediction model Risk of Bias Assessment Tool (PROBAST) statement. Neural network with 76.6% precision, 88.06% sensitivity, and area under the curve (AUC) of 0.91 was found to be the most reliable algorithm in developing prediction model for cardiovascular disease among type 2 diabetes patients. The overall concern of applicability of all included studies is low. While two out of 10 studies were shown to have high ROB, another studies ROB are unknown due to the lack of information. The adherence to reporting standards was conducted based on the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) standard where the overall score is 53.75%. It is highly recommended that future model development should adhere to the PROBAST and TRIPOD assessment to reduce the risk of bias and ensure its applicability in clinical settings. Potential lipid peroxidation marker is also recommended in future cardiovascular disease prediction model to improve overall model applicability.

The Malaysian Cohort study was initiated in 2005 by the Malaysian government. The top-down approach to this population-based cohort study ensured the allocation of sufficient funding for the project which aimed to recruit 100 000 individuals aged 35–70 years. Participants were recruited from rural and urban areas as well as from various socioeconomic groups. The main objectives of the study were to identify risk factors, to study gene-environment interaction and to discover biomarkers for the early detection of cancers and other diseases. At recruitment, a questionnaire-based interview was conducted, biophysical measurements were performed and biospecimens were collected, processed and stored. Baseline investigations included fasting blood sugar, fasting lipid profile, renal profile and full blood count. From April 2006 to the end of September 2012 we recruited a total of 106 527participants. The baseline prevalence data showed 16.6% participants with diabetes, 46.5% with hypertension, 44.9% with hypercholesterolaemia and 17.7% with obesity. The follow-up phase commenced in June 2013. This is the most comprehensive and biggest cohort study in Malaysia, and has become a valuable resource for epidemiological and biological research. For information on collaboration and also data access, investigators can contact the project leader at (rahmanj@ppukm.ukm.edu.my).

Diabetic Nephropathy (DN) is the most common cause of End-stage renal disease (ESRD). Although various treatments and diagnosis applications are available, DN remains a clinical and economic burden. Recent findings showed that noncoding RNAs (ncRNAs) play an important role in DN progression, potentially can be used as biomarkers and therapeutic targets. NcRNAs refers to the RNA species that do not encode for any protein, and the most known ncRNAs are the microRNAs (miRNAs), long noncoding RNAs (lncRNAs), and circular RNAs (circRNAs). Dysregulation of these ncRNAs was reported before in DN patients and animal models of DN. Importantly, there are some interactions between these ncRNAs to regulate the crucial steps in DN progression. Here, we aimed to discuss the reported ncRNAs in DN and their interactions with critical genes in DN progression. Elucidating these ncRNAs regulatory network will allow for a better understanding of the molecular mechanisms in DN and how they can act as new biomarkers for DN and also as the potential targets for treatment.

The prevalence of Type 2 diabetes is rising rapidly in both developed and developing countries. Asia is developing as the epicentre of the escalating pandemic, reflecting rapid transitions in demography, migration, diet, and lifestyle patterns. The effective management of Type 2 diabetes in Asia may be complicated by differences in prevalence, risk factor profiles, genetic risk allele frequencies, and gene-environment interactions between different Asian countries, and between Asian and other continental populations. To reduce the worldwide burden of T2D, it will be important to understand the architecture of T2D susceptibility both within and between populations. This review will provide an overview of known genetic and nongenetic risk factors for T2D, placing the results from Asian studies in the context of broader global research. Given recent evidence from large-scale genetic studies of T2D, we place special emphasis on emerging knowledge about the genetic architecture of T2D and the potential contribution of genetic effects to population differences in risk.

Asians are more susceptible to type 2 diabetes mellitus (T2D) and its coronary heart disease (CHD) complications than the Western populations, possibly due to genetic factors, higher degrees of obesity, insulin resistance, and endothelial dysfunction that could occur even in healthy individuals. The genetic factors and their mechanisms, along with gene-gene and gene-environment interactions associated with CHD in T2D Asians, are yet to be explored. Therefore, the objectives of this paper were to review the current evidence of genetic factors for CHD, summarize the proposed mechanisms of these genes and how they may associate with CHD risk, and review the gene-gene and gene-environment interactions in T2D Asians with CHD. The genetic factors can be grouped according to their involvement in the energy and lipoprotein metabolism, vascular and endothelial pathology, antioxidation, cell cycle regulation, DNA damage repair, hormonal regulation of glucose metabolism, as well as cytoskeletal function and intracellular transport. Meanwhile, interactions between single nucleotide polymorphisms (SNPs) from different genes, SNPs within a single gene, and genetic interaction with environmental factors including obesity, smoking habit, and hyperlipidemia could modify the gene’s effect on the disease risk. Collectively, these factors illustrate the complexities of CHD in T2D, specifically among Asians.

The purpose of this meta-analysis was to compare the ability of the qSOFA in predicting short- (≤30 days or in-hospital mortality) and long-term (>30 days) mortality among patients outside the intensive care unit setting. Studies reporting on the qSOFA and mortality were searched using MEDLINE and SCOPUS. Studies were included if they involved patients presenting to the ED with suspected infection and usage of qSOFA score for mortality prognostication. Data on qSOFA scores and mortality rates were extracted from 36 studies. The overall pooled sensitivity and specificity for the qSOFA were 48% and 86% for short-term mortality and 32% and 92% for long-term mortality, respectively. Studies reporting on short-term mortality were heterogeneous (Odd ratio, OR = 5.6; 95% CI = 4.6–6.8; Higgins’s I² = 94%), while long-term mortality studies were homogenous (OR = 4.7; 95% CI = 3.5–6.1; Higgins’s I² = 0%). There was no publication bias for short-term mortality analysis. The qSOFA score showed poor sensitivity but moderate specificity for both short and long-term mortality, with similar performance in predicting both short- and long- term mortality. Geographical region was shown to have nominal significant (p = 0.05) influence on qSOFA short-term mortality prediction.