Determination of Imaging Biomarkers to Decipher Disease Trajectories and Differential Diagnosis of Neurodegenerative Diseases (DIsease TreND).

BACKGROUND: Understanding disease progression of neurodegenerative diseases (NDs) is important for better prognosis and decisions on the appropriate course of treatment to slow down the disease progression. NEW METHOD: We present here an innovative machine learning framework capable of (1) indicating the trajectory of disease progression by identifying relevant imaging biomarkers and (2) automated disease diagnosis. Self-Organizing Maps (SOM) have been used for data dimensionality reduction and to reveal potentially useful disease-specific biomarkers, regions of interest (ROIs). These ROIs have been used for automated disease diagnosis using Least Square Support Vector Machines (LS-SVM) and to delineate disease progression. RESULTS: A multi-site, multi-scanner dataset containing 1316 MRIs was obtained from ADNI3 and PPMI. Identified biomarkers have been used to decipher (1) trajectory of disease progression and (2) identify clinically relevant ROIs. Furthermore, we have obtained a classification accuracy of 94.29 ±â€¯0.08% and 95.37 ±â€¯0.02% for distinguishing AD and PD from HC subjects respectively. COMPARISON WITH OTHER EXISTING METHODS: The goal of this study was fundamentally different from other machine learning based studies for automated disease diagnosis. We aimed to develop a method that has two-fold benefits (1) It can be used to understand pathology of neurodegenerative diseases and (2) It also achieves automated disease diagnosis. CONCLUSIONS: In the absence of established disease biomarkers, clinical diagnosis is heavily prone to misdiagnosis. Being clinically relevant and readily adaptable in the current clinical settings, the developed framework could be a stepping stone to make machine learning based Clinical Decision Support System (CDSS) for neurodegenerative disease diagnosis a reality.

RhizoFlowCell system reveals early effects of micropollutants on aquatic plant rhizosphere.

In aquatic systems, one of the non-destructive ways to quantify toxicity of contaminants to plants is to monitor changes in root exudation patterns. In aquatic conditions, monitoring and quantifying such changes are currently challenging because of dilution of root exudates in water phase and lack of suitable instrumentation to measure them. Exposure to pollutants would not only change the plant exudation, but also affect the microbial communities that surround the root zone, thereby changing the metabolic profiles of the rhizosphere. This study aims at developing a device, the RhizoFlowCell, which can quantify metabolic response of plants, as well as changes in the microbial communities, to give an estimate of the stress to which the rhizosphere is exposed. The usefulness of RhizoFlowCell is demonstrated using naphthalene as a test pollutant. Results show that RhizoFlowCell system is useful in quantifying the dynamic metabolic response of aquatic rhizosphere to determine ecosystem health.

Unsupervised learning based feature extraction for differential diagnosis of neurodegenerative diseases: A case study on early-stage diagnosis of Parkinson disease.

BACKGROUND: The development of MRI based methods could prove extremely valuable for identification of reliable biomarkers to aid diagnosis of neurodegenerative diseases (NDs). A great deal of current research has been aimed at identification biomarkers for both diagnosis at early stage and evaluation of the progression of NDs. NEW METHOD: We present here a novel synergetic paradigm integrating Kohonen self organizing map (KSOM) and least squares support vector machine (LS-SVM) for individual-level clinical diagnosis of NDs. Feature are extracted in an unsupervised manner using KSOM on preprocessed brain MRIs. Thereafter, these features are fed as input to LSSVM for subject classification. RESULTS: The applicability of the proposed methodology has been demonstrated using 831 T1-weighted MRIs obtained from Parkinson's Progression Markers Initiative (PPMI) database. We have achieved classification accuracy of up to 99% for differential diagnosis of Parkinson disease with confidence interval of 99.9%. COMPARISON WITH OTHER EXISTING METHODS: The potential for translation of similar research findings to clinical application is greatly dependent upon two factors (1) accuracy of subject classification achieved and (2) size of the dataset used. Here, we report very high accuracy achieved on one of the largest MRI datasets using multivariate analysis tools. CONCLUSIONS: In this paper, we describe a methodology that has the potential to be translated into first-line diagnostic tool for NDs. We also demonstrate the applicability of this methodology for diagnosing PD subjects in early stages of the disease, i.e., subjects in age of 31-60 years.

Effect of cool vs. warm dialysate on toxin removal: rationale and study design.

BACKGROUND: Cool dialysate is often recommended for prevention of intra-dialytic hypotensive episodes in maintenance hemodialysis (HD) patients. However, its effect on toxin removal is not studied. It is known that inter-compartmental resistance is the main barrier for toxin removal. Cool dialysate can potentially increase this resistance by vasoconstriction and thus impair the toxin removal. The aim of this trial is to compare the toxin removal outcome associated with cool vs. warm dialysate. METHOD/DESIGN: This study is based on the hypothesis that dialysate temperature, a potential maneuver to maintain hemodynamic stability during HD, may influence inter-compartmental resistance and hence, toxin removal. Only stable HD patients will be recruited for this study. The quantum of removed toxins will be assessed by the total spent dialysate, which is a gold standard to quantify the efficacy of a single dialysis session. Collected samples will be analyzed for urea, creatinine, phosphate, ß2-microglobulin, and uric acid. The study is a single center, self-controlled, randomized prospective clinical research where 20 study subjects will undergo 2 dialysis sessions: (a) cool dialysis with dialysate at 35.5°C, and (b) warm dialysis with dialysate at 37°C. Pre- and post-dialysis blood samples will be collected to quantify the dialysis adequacy and toxin reduction ratio. DISCUSSION: This is the first clinical research to investigate the effect of dialysate temperature on removal of both small and large-sized toxins. Successful completion of this research will provide important knowledge pertaining to dialysate temperature prescription. Results can also lead to the hypothesis that cool dialysate may help in by preventing intra-dialytic hypotensive episodes, but prolonged prescription of cool dialysate may lead to comorbidities associated with excess toxin accumulation. The new knowledge will encourage for personalized dialysate temperature profiling. TRIAL REGISTRATION: Clinicaltrials.gov Identifier--NCT02064153.

Personalized mechanistic models for exercise, meal and insulin interventions in children and adolescents with type 1 diabetes.

Personalized mechanistic models involving exercise, meal and insulin interventions for type 1 diabetic children and adolescents are not commonly seen in the literature. Patient specific variations in blood glucose homeostasis and adverse effects of exercise-induced hypoglycemia emphasize the need for personalized models. Hence, a modified mechanistic model for exercise, meal and insulin interventions is proposed and tailored as personalized models for 34 type 1 diabetic children and adolescents. This is achieved via a 3-stage methodology comprising of modification, a priori identifiability analysis, and personalized parameter estimation and validation using the clinical data. Rate of perceived exertion is introduced as a marker quantifying exercise intensity. Six out of 16 parameters in the modified model are identified to be estimable and are estimated for each subject as personalized parameters. The R(2) values for both fitness and validation vary between 0.7 and 0.96 in 97% of the patients, indicating the goodness of the proposed model in explaining the glucose dynamics. For most of the estimated parameters, values of personalized point estimates and their confidence intervals are found to be within physiological ranges reported in the modeling literature. Personalized values of appearance rate of exercise effect on glucose uptake in 34 subjects are 54-250% higher than the nominal values of adults. This is expected for children and adolescents as the literature shows that they exhibit higher fat and exogenous carbohydrate oxidation rates during exercise when compared to adults.

Genetic programming-based approach to elucidate biochemical interaction networks from data.

Biochemical systems are characterised by cyclic/reversible reciprocal actions, non-linear interactions and a mixed relationship structures (linear and non-linear; static and dynamic). Deciphering the architecture of such systems using measured data to provide quantitative information regarding the nature of relationships that exist between the measured variables is a challenging proposition. Causality detection is one of the methodologies that are applied to elucidate biochemical networks from such data. Autoregressive-based modelling approach such as granger causality, partial directed coherence, directed transfer function and canonical variate analysis have been applied on different systems for deciphering such interactions, but with limited success. In this study, the authors propose a genetic programming-based causality detection (GPCD) methodology which blends evolutionary computation-based procedures along with parameter estimation methods to derive a mathematical model of the system. Application of the GPCD methodology on five data sets that contained the different challenges mentioned above indicated that GPCD performs better than the other methods in uncovering the exact structure with less false positives. On a glycolysis data set, GPCD was able to fill the 'interaction gaps' which were missed by other methods.

Comparison of toxin removal outcomes in online hemodiafiltration and intra-dialytic exercise in high-flux hemodialysis: a prospective randomized open-label clinical study protocol.

BACKGROUND: Maintenance hemodialysis (HD) patients universally suffer from excess toxin load. Hemodiafiltration (HDF) has shown its potential in better removal of small as well as large sized toxins, but its efficacy is restricted by inter-compartmental clearance. Intra-dialytic exercise on the other hand is also found to be effective for removal of toxins; the augmented removal is apparently obtained by better perfusion of skeletal muscles and decreased inter-compartmental resistance. The aim of this trial is to compare the toxin removal outcome associated with intra-dialytic exercise in HD and with post-dilution HDF. METHODS/DESIGN: The main hypothesis of this study is that intra-dialytic exercise enhances toxin removal by decreasing the inter-compartmental resistance, a major impediment for toxin removal. To compare the HDF and HD with exercise, the toxin rebound for urea, creatinine, phosphate, and ß2-microglobulin will be calculated after 2 hours of dialysis. Spent dialysate will also be collected to calculate the removed toxin mass. To quantify the decrease in inter-compartmental resistance, the recently developed regional blood flow model will be employed. The study will be single center, randomized, self-control, open-label prospective clinical research where 15 study subjects will undergo three dialysis protocols (a) high flux HD, (b) post-dilution HDF, (c) high flux HD with exercise. Multiple blood samples during each study session will be collected to estimate the unknown model parameters. DISCUSSION: This will be the first study to investigate the exercise induced physiological change(s) responsible for enhanced toxin removal, and compare the toxin removal outcome both for small and middle sized toxins in HD with exercise and HDF. Successful completion of this clinical research will give important insights into exercise effect on factors responsible for enhanced toxin removal. The knowledge will give confidence for implementing, sustaining, and optimizing the exercise in routine dialysis care. We anticipate that toxin removal outcomes from intra-dialytic exercise session will be comparable to that obtained by standalone HDF. These results will encourage clinicians to combine HDF with intra-dialytic exercise for significantly enhanced toxin removal. TRIAL REGISTRATION: ClinicalTrials.gov number, NCT01674153.

Personalized blood glucose models for exercise, meal and insulin interventions in type 1 diabetic children.

Modern healthcare is rapidly evolving towards a personalized, predictive, preventive and participatory approach of treatment to achieve better quality of life (QoL) in patients. Identification of personalized blood glucose (BG) prediction models incorporating the lifestyle interventions can help in devising optimal patient specific exercise, food, and insulin prescriptions, which in turn can prevent the risk of frequent hypoglycemic episodes and other diabetes complications. Hence, we propose a modeling methodology based on multi-input single-output time series models, to develop personalized BG models for 12 type 1 diabetic (T1D) children, using the clinical data from Diabetes Research in Children's Network. The multiple inputs needed to develop the proposed models were rate of perceived exertion (RPE) values (which quantify the exercise intensity), carbohydrate absorption dynamics, basal insulin infusion and bolus insulin absorption kinetics. Linear model classes like Box-Jenkins (1 patient), state space (1 patient) and process transfer function models (7 patients) of different orders were found to be the most suitable as the personalized models for 9 patients, whereas nonlinear Hammerstein-Wiener models of different orders were found to be the personalized models for 3 patients. Hence, inter-patient variability was captured by these models as each patient follows a different personalized model.

A regional blood flow model for ß2-microglobulin kinetics and for simulating intra-dialytic exercise effect.

A kinetic model based on first principles, for ß(2)-microglobulin, is presented to obtain precise parameter estimates for individual patient. To reduce the model complexity, the number of model parameters was reduced using a priori identifiability analysis. The model validity was confirmed with the clinical data of ten renal patients on post-dilution hemodiafiltration. The model fit resulted in toxin distribution volume (V(d)) of 14.22 ± 0.75 L, plasma fraction in extracellular compartment (f(P)) of 0.39 ± 0.03, and inter-compartmental clearance of 44 ± 4.1 mL min(-1). Parameter estimates suggest that V(d) and f(P) are much higher in hemodialysis patients than in normal subjects. The developed model predicts larger removed toxin mass than that predicted by the two-pool model. On the application front, the developed model was employed to explain the effect of intra-dialytic exercise on toxin removal. The presented simulations suggest that intra-dialytic exercise not only increases the blood flow to low flow region, but also decreases the inter-compartmental resistance. Combined, they lead to increased toxin removal during dialysis and reduced post-dialysis rebound. The developed model can assist in suggesting the improved dialysis dose based on ß(2)-microglobulin, and also lead to quantitative inclusion of intra-dialytic exercise in the future.

Rich can get poor: conversion of hub to non-hub proteins.

Hubs are ubiquitous network elements with high connectivity. One of the common observations about hub proteins is their preferential attachment leading to scale-free network topology. Here we examine the question: does rich protein always get richer, or can it get poor too? To answer this question, we compared similar and well-annotated hub proteins in six organisms, from prokaryotes to eukaryotes. Our findings indicate that hub proteins retain, gain or lose connectivity based on the context. Furthermore, the loss or gain of connectivity appears to correlate with the functional role of the protein in a given system.