A recurrent neural network approach to predicting hemoglobin trajectories in patients with End-Stage Renal Disease.

The most severe form of kidney disease, End-Stage Renal Disease (ESRD) is treated with various forms of dialysis - artificial blood cleansing. Dialysis patients suffer many health burdens including high mortality and hospitalization rates, and symptomatic anemia: a low red blood cell count as indicated by a low hemoglobin (Hgb) level. ESRD-induced anemia is treated, with variable patient response, by erythropoiesis stimulating agents (ESAs): expensive injectable medications typically administered during dialysis sessions. The dosing protocol is typically a population level protocol based on original clinical trials, the use of which often results in Hgb cycling. This cycling phenomenon occurs primarily due to the mismatch in the time between dosing decisions and the time it takes for the effects of a dosing change to be fully realized. In this paper we develop a recurrent neural network approach that uses historic data together with future ESA and iron dosing data to predict the 1, 2, and 3 month Hgb levels of patients with ESRD-induced anemia. The results of extensive experimentation indicate that this approach generates predictions that are clinically relevant: the mean absolute error of the predictions is comparable to estimates of the intra-individual variability of the laboratory test for Hgb.

Tumor necrosis factor-α elevates neurite outgrowth through an NF-κB-dependent pathway in cultured adult sensory neurons: Diminished expression in diabetes may contribute to sensory neuropathy.

The presence of a proinflammatory environment in the sensory neuron axis in diabetes was tested by measuring levels of proinflammatory cytokines in lumbar dorsal root ganglia (DRG) and peripheral nerve from age matched control and streptozotocin (STZ)-induced diabetic rats. The levels of tumor necrosis factor-α (TNFα) and other cytokines were diminished in lumbar DRG from diabetic animals. Consequently, we tested the hypothesis that TNFα modulated axonal plasticity in adult sensory neurons and posited that impairments in this signal transduction pathway may underlie degeneration in diabetic sensory neuropathy. Cultured adult rat sensory neurons were grown under defined conditions and TNFα caused a dose-dependent 2-fold (P<0.05) elevation in neurite outgrowth. Neurons derived from 3 to 5month STZ-induced diabetic rats exhibited significantly reduced levels of neurite outgrowth in response to TNFα. TNFα enhanced NF-κB activity as assessed using Western blotting and plasmid reporter technology. Blockade of TNFα-induction of NF-κB activation caused inhibition of neurite outgrowth in cultured neurons. Immunofluorescent staining for NF-κB subunit p50 within neuronal nuclei revealed that medium to large diameter neurons were most susceptible to NF-κB inhibition and was associated with decreased neurite outgrowth. The results demonstrating reduced cytokine expression in DRG confirm that diabetic sensory neuropathy does not involve a neuroinflammatory component at this stage of the disease in experimental animal models. In addition, it is hypothesized that reduced TNFα expression in the DRG and possibly associated deficits in anterograde transport may contribute to impaired collatoral sprouting and regeneration in target tissue in type 1 diabetes.