OBJECTIVEAn association between insulin resistance and microalbuminuria in type 2 diabetes has often been found in cross-sectional studies. We aimed to reassess this relationship in a prospective Taiwanese cohort of type 2 diabetic subjects.RESEARCH DESIGN AND METHODSWe enrolled 738 normoalbuminuric type 2 diabetic subjects, aged 56.6 ± 9.0 years, between 2003 and 2005 and followed them through the end of 2009. Average follow-up time was 5.2 ± 0.8 years. We used urine albumin-to-creatinine ratio to define microalbuminuria and the homeostasis model assessment of insulin resistance (HOMA-IR) to assess insulin resistance. The incidence rate ratio and Cox proportional hazards model were used to evaluate the association between HOMA-IR and development of microalbuminuria.RESULTSWe found incidences of microalbuminuria of 64.8, 83.5, 93.3, and 99.0 per 1,000 person-years for the lowest to highest quartiles of HOMA-IR. Compared with those in the lowest quartile of HOMA-IR, the incidence rate ratios for those in the 2nd, 3rd, and highest quartiles were 1.28 (95% CI 0.88–1.87), 1.44 (0.99–2.08), and 1.52 (1.06–2.20), respectively (trend test: P < 0.001). By comparison with those in the lowest quartile, the adjusted hazard ratios were 1.37 (0.93–2.02), 1.66 (1.12–2.47), and 1.76 (1.20–2.59) for those in the 2nd, 3rd, and highest HOMA-IR quartiles, respectively.CONCLUSIONSAccording to the dose-response effects of HOMA-IR shown in this prospective study, we conclude that insulin resistance could significantly predict development of microalbuminuria in type 2 diabetic patients.

Clinical intelligence about a patient's risk of future adverse health events can support clinical decision making in personalized and preventive care. Healthcare predictive analytics using electronic health records offers a promising direction to address the challenging tasks of risk profiling. Patients with chronic diseases often face risks of not just one, but an array of adverse health events. However, existing risk models typically focus on one specific event and do not predict multiple outcomes. To attain enhanced risk profiling, we adopt the design science paradigm and propose a principled approach called Bayesian multitask learning (BMTL). Considering the model development for an event as a single task, our BMTL approach is to coordinate a set of baseline models-one for each event-and communicate training information across the models. The BMTL approach allows healthcare providers to achieve multifaceted risk profiling and model an arbitrary number of events simultaneously. Our experimental evaluations demonstrate that the BMTL approach attains an improved predictive performance when compared with the alternatives that model multiple events separately. We also find that, in most cases, the BMTL approach significantly outperforms existing multitask learning techniques. More importantly, our analysis shows that the BMTL approach can create significant potential impacts on clinical practice in reducing the failures and delays in preventive interventions. We discuss several implications of this study for health IT, big data and predictive analytics, and design science research.

Presented in this study is an online Nominal Group Technique (NGT) platform for implementing knowledge transfer. A platform was developed to record the experimental experiences of thirteen Information Technology (IT) experts from academia and industry. We found that an online NGT platform could provide formal activities for promoting knowledge transfer in pursuit of consensus at a distance. Internalization of knowledge resulted from the review and rethinking process when applied to solution priorities. The results of this study have implications for users to initiate knowledge transfer at a distance for students conducting a capstone project with industry, for industry/academia research projects, and on industry projects between faculty and industry personnel. The processes of providing knowledge creation, interaction, and internalization were shown to lead to knowledge transfer for consensus building. The implementation efficiency was mainly contributed to by platform recognition, an important outcome when constructing information platforms for transferring knowledge among industry engineers, engineering students, and engineering educators.