Explore the vast range of titles available.

Personalized decision-making can be implemented in a Federated learning (FL) framework that can collaboratively train a decision model by extracting knowledge across intelligent clients, e.g. smartphones or enterprises. FL can mitigate the data privacy risk of collaborative training since it merely collects local gradients from users without access to their data. However, FL is fragile in the presence of statistical heterogeneity that is commonly encountered in personalized decision making, e.g., non-IID data over different clients. Existing FL approaches usually update a single global model to capture the shared knowledge of all users by aggregating their gradients, regardless of the discrepancy between their data distributions. By comparison, a mixture of multiple global models could capture the heterogeneity across various clients if assigning the client to different global models (i.e., centers) in FL. To this end, we propose a novel multi-center aggregation mechanism to cluster clients using their models’ parameters. It learns multiple global models from data as the cluster centers, and simultaneously derives the optimal matching between users and centers. We then formulate it as an optimization problem that can be efficiently solved by a stochastic expectation maximization (EM) algorithm. Experiments on multiple benchmark datasets of FL show that our method outperforms several popular baseline methods. The experimental source codes are publicly available on the Github repository (GitHub repository: https://github.com/mingxuts/multi-center-fed-learning).

Background The human gut microbiome performs important functions in human health and disease. A classic example for host-gut microbial co-metabolism is host biosynthesis of primary bile acids and their subsequent deconjugation and transformation by the gut microbiome. To understand these system-level host-microbe interactions, a mechanistic, multi-scale computational systems biology approach that integrates the different types of omic data is needed. Here, we use a systematic workflow to computationally model bile acid metabolism in gut microbes and microbial communities. Results Therefore, we first performed a comparative genomic analysis of bile acid deconjugation and biotransformation pathways in 693 human gut microbial genomes and expanded 232 curated genome-scale microbial metabolic reconstructions with the corresponding reactions (available at https://vmh.life ). We then predicted the bile acid biotransformation potential of each microbe and in combination with other microbes. We found that each microbe could produce maximally six of the 13 secondary bile acids in silico , while microbial pairs could produce up to 12 bile acids, suggesting bile acid biotransformation being a microbial community task. To investigate the metabolic potential of a given microbiome, publicly available metagenomics data from healthy Western individuals, as well as inflammatory bowel disease patients and healthy controls, were mapped onto the genomes of the reconstructed strains. We constructed for each individual a large-scale personalized microbial community model that takes into account strain-level abundances. Using flux balance analysis, we found considerable variation in the potential to deconjugate and transform primary bile acids between the gut microbiomes of healthy individuals. Moreover, the microbiomes of pediatric inflammatory bowel disease patients were significantly depleted in their bile acid production potential compared with that of controls. The contributions of each strain to overall bile acid production potential across individuals were found to be distinct between inflammatory bowel disease patients and controls. Finally, bottlenecks limiting secondary bile acid production potential were identified in each microbiome model. Conclusions This large-scale modeling approach provides a novel way of analyzing metagenomics data to accelerate our understanding of the metabolic interactions between the host and gut microbiomes in health and diseases states. Our models and tools are freely available to the scientific community.

[Display omitted] •Model muscle strength personalized using maximum voluntary isometric contractions.•Model segmental mass personalized using dual-energy x-ray absorptiometry.•Personalization of biomechanical models affects simulation joint contact forces.•Changes in internal forces due to load carriage varied across the cohort. Military overuse injuries are associated with greater internal loads during load carriage and cause decreased readiness and increased costs. Low physical fitness, including low muscle strength, is a modifiable injury risk factor, making it an important focus for injury prevention. Evaluating potential injury mechanisms from biomechanical modeling and simulation may be useful, particularly for individuals who have unique muscle strengths and body segment mass distributions. However, modeled muscle strength from average adults is likely underestimated for trained, active-duty military personnel, which may influence internal load calculations. Thus, we evaluated the effects of muscle strength and segment mass distribution personalization on joint contact impulses and peak forces, and muscle force impulses from musculoskeletal simulations. Full-body kinematics, ground reaction forces, and electromyography were collected from 16 active-duty participants under two walking conditions: 1) no-pack and 2) pack (posteriorly added load, total 46 kg). These data drove and validated simulations of models with different types of personalization. Modeled segment masses were scaled using measured regional masses from dual-energy x-ray absorptiometry. Modeled muscle strengths were scaled from eight maximum voluntary isometric contractions measured using an instrumented dynamometer including the lumbar, hip, knee, and ankle. Personalized mass-distribution scaling had 6% greater lumbar joint contact impulses in walking compared to not personalized (p = .006). Personalized muscle strength scaling had greater joint contact impulses at the lumbar (42%), hip (25%), and knee (8%) (p < .001), and smaller impulses at the ankle (−4%) (p = .048) compared to not personalized. Results were similar for peak joint contact forces. Model personalization is beneficial to quantify internal loading and evaluate training interventions.

To elucidate the molecular mechanisms underlying non‐alcoholic fatty liver disease (NAFLD), we recruited 86 subjects with varying degrees of hepatic steatosis (HS). We obtained experimental data on lipoprotein fluxes and used these individual measurements as personalized constraints of a hepatocyte genome‐scale metabolic model to investigate metabolic differences in liver, taking into account its interactions with other tissues. Our systems level analysis predicted an altered demand for NAD + and glutathione (GSH) in subjects with high HS. Our analysis and metabolomic measurements showed that plasma levels of glycine, serine, and associated metabolites are negatively correlated with HS, suggesting that these GSH metabolism precursors might be limiting. Quantification of the hepatic expression levels of the associated enzymes further pointed to altered de novo GSH synthesis. To assess the effect of GSH and NAD + repletion on the development of NAFLD, we added precursors for GSH and NAD + biosynthesis to the Western diet and demonstrated that supplementation prevents HS in mice. In a proof‐of‐concept human study, we found improved liver function and decreased HS after supplementation with serine (a precursor to glycine) and hereby propose a strategy for NAFLD treatment. Synopsis Personalized modeling and metabolic measurements identified altered GSH and NAD + metabolism as a prevailing feature in NAFLD. These findings suggested a potential treatment strategy for NAFLD patients based on increased oxidation of fat and increased synthesis of GSH. We developed personalized genome‐scale metabolic models for NAFLD patients. We found that altered GSH and NAD + metabolism is a prevailing feature in NAFLD. Plasma and liver levels of glycine and serine were lower in NAFLD patients. Supplementation of precursors for glutathione and NAD + decreased HS in mice. Serine supplementation decreased liver fat and improved markers of liver function in humans. Graphical Abstract Personalized modeling and metabolic measurements identified altered GSH and NAD + metabolism as a prevailing feature in NAFLD. These findings suggested a potential treatment strategy for NAFLD patients based on increased oxidation of fat and increased synthesis of GSH.

Despite the large impact chronic obstructive pulmonary disease (COPD) that has on the population, the implementation of new technologies for diagnosis and treatment remains limited. Current practices in ambulatory oxygen therapy used in COPD rely on fixed doses overlooking the diverse activities which patients engage in. To address this challenge, we propose a software architecture aimed at delivering patient-personalized edge-based artificial intelligence (AI)-assisted models that are built upon data collected from patients’ previous experiences along with an evaluation function. The main objectives reside in proactively administering precise oxygen dosages in real time to the patient (the edge), leveraging individual patient data, previous experiences, and actual activity levels, thereby representing a substantial advancement over conventional oxygen dosing. Through a pilot test using vital sign data from a cohort of five patients, the limitations of a one-size-fits-all approach are demonstrated, thus highlighting the need for personalized treatment strategies. This study underscores the importance of adopting advanced technological approaches for ambulatory oxygen therapy.

Many patients with diabetes struggle with post-meal high blood glucose due to missed or untimely meal-related insulin doses. To address this challenge, our research aims to: (1) study mealtime patterns in patients with type 1 diabetes using wearable insulin pump data, and (2) develop personalized models for predicting future mealtimes to support timely insulin dose administration. Using two independent datasets with over 45,000 meal logs from 82 patients with diabetes, we find that the majority of people ( ∼ 60%) have irregular and inconsistent mealtime patterns that change notably through the course of each day and across months in their own historical data. We also show the feasibility of predicting future mealtimes with personalized LSTM-based models that achieve an average F1 score of > 95% with less than 0.25 false positives per day. Our research lays the groundwork for developing a meal prediction system that can nudge patients with diabetes to administer bolus insulin doses before meal consumption to reduce the occurrence of post-meal high blood glucose.

The success of lumbar interbody fusion, the key surgical procedure for treating different pathologies of the lumbar spine, is highly dependent on determining the patient-specific lumbar lordosis (LL) and restoring sagittal balance. This study aimed to (1) develop a personalized finite element (FE) model that automatically updates spinal geometry for different patients; and (2) apply this technique to study the influence of LL on post-fusion spinal biomechanics. Using an X-Ray image-based algorithm, the geometry of the lumbar spine (L1-S1) was updated using independent parameters. Ten subject-specific nonlinear osteoligamentous FE models were developed based on pre-operative images of fusion surgery candidate patients. Post-operative FE models of the same patients were consequently created. Comparison of the obtained results from FE models with pre- and post-operation functional images demonstrated the potential value of this technique in clinical applications. A parametric study of the effect of LL was conducted for cases with zero LL angle, positive LL angles (+6° and +12°) and negative LL angles (−3° and −6°) on fused level (L4-L5), resulting in a total of 50 fusion simulation models. The average range of motion, intradiscal pressure, and fiber strain at adjacent levels were significantly higher with decreased LL during different directions except axial rotation. This study demonstrates that the LL alters both the intersegmental motion and load-sharing in fusion, which may influence the initiation and rate of adjacent level degeneration. This personalized FE platform provides a practical, clinically applicable approach for the analyses of the biomechanical changes associated with lumbar spine fusion.

To improve abdominal aortic aneurysm (AAA) rupture risk assessment, a large, longitudinal study on AAA hemodynamics and biomechanics is necessary, using personalized fluid-structure interaction (FSI) modeling. 3-dimensional, time-resolved ultrasound (3D+t US) is the preferred image modality to obtain the patient-specific AAA geometry for such a study, since it is safe, affordable and provides temporal information. However, the 3D+t US field-of-view (FOV) is limited and therefore often fails to capture the inlet and aorto-iliac bifurcation geometry. In this study, a framework was developed to add parametric inlet and bifurcation geometries to the abdominal aortic aneurysm geometry by employing dataset statistics and parameters of the AAA geometry. The impact of replacing the patient-specific inlet and bifurcation geometries, acquired using computed tomography (CT) scans, by parametric geometries was evaluated by examining the differences in hemodynamics (systolic and time-averaged wall shear stress and oscillatory shear index) in the aneurysm region. The results show that the inlet geometry has a larger effect on the AAA hemodynamics (median differences of 7.5 to 18.8%) than the bifurcation geometry (median differences all below 1%). Therefore, it is not feasible to replace the patient-specific inlet geometry by a generic one. Future studies should investigate the possibilities of extending the proximal FOV of 3D+t US. However, this study did show the feasibility of adding a parametric bifurcation geometry to the aneurysm geometry. After extending the proximal FOV, the obtained framework can be used to extract AAA geometries from 3D+t US for FSI simulations, despite the absence of the bifurcation geometry.

Background Personalized modeling is a promising tool to improve abdominal aortic aneurysm (AAA) rupture risk assessment. Computed tomography (CT) and quantitative flow (Q-flow) magnetic resonance imaging (MRI) are widely regarded as the gold standard for acquiring patient-specific geometry and velocity profiles, respectively. However, their frequent utilization is hindered by various drawbacks. Ultrasound is used extensively in current clinical practice and offers a safe, rapid and cost-effective method to acquire patient-specific geometries and velocity profiles. This study aims to extract and validate patient-specific velocity profiles from Doppler ultrasound and to examine the impact of the velocity profiles on computed hemodynamics. Methods Pulsed-wave Doppler (PWD) and color Doppler (CD) data were successfully obtained for six volunteers and seven patients and employed to extract the flow pulse and velocity profile over the cross-section, respectively. The US flow pulses and velocity profiles as well as generic Womersley profiles were compared to the MRI velocities and flows. Additionally, CFD simulations were performed to examine the combined impact of the velocity profile and flow pulse. Results Large discrepancies were found between the US and MRI velocity profiles over the cross-sections, with differences for US in the same range as for the Womersley profile. Differences in flow pulses revealed that US generally performs best in terms of maximum flow, forward flow and ratios between forward and backward flow, whereas it often overestimates the backward flow. Both spatial patterns and magnitude of the computed hemodynamics were considerably affected by the prescribed velocity boundary conditions. Larger errors and smaller differences between the US and generic CFD cases were observed for patients compared to volunteers. Conclusion These results show that it is feasible to acquire the patient-specific flow pulse from PWD data, provided that the PWD acquisition could be performed proximal to the aneurysm region, and resulted in a triphasic flow pattern. However, obtaining the patient-specific velocity profile over the cross-section using CD data is not reliable. For the volunteers, utilizing the US flow profile instead of the generic flow profile generally resulted in improved performance, whereas this was the case in more than half of the cases for the patients.

The high incidence of stroke occurrence necessitates the understanding of its causes and possible ways for early prediction and prevention. In this respect, statistical methods offer the “big picture,” but they have a weak predictive ability at an individual level. This research proposes a new personalized modeling method based on computational spiking neural networks (SNN) for the identification of causal associations between clinical and environmental time series data that can be used to predict individual stroke events. The method is tested on 804 stroke patients. Given a clinical data set of patients who experienced a stroke in the past and the corresponding environmental time-series data for a selected time-window before the stroke event, the method identifies the clusters of individuals with a high risk for stroke under similar conditions. The methodology involves a pipeline of processes when creating a personalized model for an individual x : (1) selecting a group of individuals Gx with similar personal records to x ; (2) training a personalized SNN x model of several days of environmental data related to the Gx group to predict the risk of stroke for x at least one day earlier; (3) model interpretability through 3D visualization; (4) discovery of personalized predictive markers. The results are twofold, first proposing a new computational methodology and second presenting new findings. It is found that certain environmental factors, such as SO 2 , PM 10 , CO, and PM 2.5 , increase the risk of stroke if an individual x belongs to a certain cluster of people, characterized by a combination of family history of stroke and diabetes, overweight, vascular/heart disease, age, and other. For the used population data, the proposed method can predict accurately individual risk of stroke before the day of the stroke. The paper presents a new methodology for personalized machine learning methods to define subgroups of the population with a high risk of stroke and to predict early individual risk of the stroke event. This makes the proposed cognitive computation method useful to reduce morbidity and mortality in society. The method is broadly applicable for predicting individual risk of other diseases and mental health conditions.