Current Tools Research Articles

Curating models from BioModels: Developing a workflow for creating OMEX files.

The reproducibility of computational biology models can be greatly facilitated by widely adopted standards and public repositories. We examined 50 models from the BioModels Database and attempted to validate the original curation and correct some of them if necessary. For each model, we reproduced these published results using Tellurium. Once reproduced we manually created a new set of files, with the model information stored by the Systems Biology Markup Language (SBML), and simulation instructions stored by the Simulation Experiment Description Markup Language (SED-ML), and everything included in an Open Modeling EXchange (OMEX) file, which could be used with a variety of simulators to reproduce the same results. On the one hand, the reproducibility procedure of 50 models developed a manual workflow that we would use to build an automatic platform to help users more easily curate and verify models in the future. On the other hand, these exercises allowed us to find the limitations and possible enhancement of the current curation and tooling to verify and curate models.

Abstract 7669: Use of computational pathology to predict biochemical recurrence in prostate cancer (Pca) (Rp) patients following radical prostatectomy: Evaluation in low decipher risk category

Abstract Background: Current tools for predicting prostate cancer biochemical recurrence (BCR) after RP often depend on parameters determined by pathologists, such as tumor grade, which is known to vary between reviewers. Genomic risk classifiers provide useful information but require substantial tissue, are costly, and are not commonly accessible in many medical centers. The study presents an artificial intelligence (AI) model for automated risk assessment of biochemical recurrence (BCR) by analyzing nuclear morphologic patterns from Pca archival H&E slides. Nuclear morphometric features are essential for disease diagnosis and gaining insights into cellular functions. Specifically, we sought to evaluate whether the computational pathology approach could provide additional granular risk stratification within the low-risk group identified by Decipher. Methods: The study employed two cohorts from the University of Pennsylvania D1 and D2. D1 comprised 180 patients, while D2 comprised 175 patients, including 63 individuals from the Decipher low-risk group. None of the patients in either cohort had received any pre-operative treatments. Within the Decipher cohort, a tumor segmentation model was created using the U-net deep learning network. The HoVer-Net model was used to both segment and classify nuclei. The feature extracted included a combination of nuclear texture and quantitative measurements of the spatial arrangement of nuclei. The eleven most significant features, selected via the least absolute shrinkage and selection operator (LASSO), were utilized to build a Cox regression model for predicting the risk of BCR in D1. In D2, patients were classified as either low-risk or high-risk for BCR based on the median risk score derived from D1. Results: Patients from D1 identified as high risk by the AI model experienced shorter survival, with a median BCR time of 27 months, in contrast to 55 months for those classified as low risk. The AI model demonstrated significant prognostic value for BCR in both D1 (HR = 6.82, 95% confidence interval [CI]: 3.54-13.12, p < 0.0019), and D2 (HR = 2.72, 95% CI: 1.53-4.82, p < 0.0032). Furthermore, the model effectively stratified the Decipher low-risk group in D2 into distinct low and high-risk categories (HR = 4.52, 95% confidence interval [CI]: 1.70-12.05, p < 0.0085). The most prognostic features identified included five related to nuclei shape diversity (Minor Axis Length, Eccentricity, Equivalent Diameter, Solidity, and Circularity) in conjunction with nine nuclear texture features. Conclusions: The AI model's findings suggest that a digital image-based prognostic classifier for prostate cancer could serve as an alternative or complementary method to molecular-based companion risk tests. Additional, independent multi-site and prospective validation of these findings are warranted. Citation Format: Kamal Hammouda, Tilak Pathak, Tuomas Mirtti, Priti Lal, Shilpa Gupta, Anant Madabhushi. Use of computational pathology to predict biochemical recurrence in prostate cancer (Pca) (Rp) patients following radical prostatectomy: Evaluation in low decipher risk category [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7669.

CPhaMAS: An online platform for pharmacokinetic data analysis based on optimized parameter fitting algorithm

Background and objectiveClinical pharmacological modeling and statistical analysis software is an essential basic tool for drug development and personalized drug therapy. The learning curve of current basic tools is steep and unfriendly to beginners. The curve is even more challenging in cases of significant individual differences or measurement errors in data, resulting in difficulties in accurately estimating pharmacokinetic parameters by existing fitting algorithms. Hence, this study aims to explore a new optimized parameter fitting algorithm that reduces the sensitivity of the model to initial values and integrate it into the CPhaMAS platform, a user-friendly online application for pharmacokinetic data analysis. MethodsIn this study, we proposed an optimized Nelder-Mead method that reinitializes simplex vertices when trapped in local solutions and integrated it into the CPhaMAS platform. The CPhaMAS, an online platform for pharmacokinetic data analysis, includes three modules: compartment model analysis, non-compartment analysis (NCA) and bioequivalence/bioavailability (BE/BA) analysis. Our proposed CPhaMAS platform was evaluated and compared with existing WinNonlin. ResultsThe platform was easy to learn and did not require code programming. The accuracy investigation found that the optimized Nelder-Mead method of the CPhaMAS platform showed better accuracy (smaller mean relative error and higher R2) in two-compartment and extravascular administration models when the initial value was set to true and abnormal values (10 times larger or smaller than the true value) compared with the WinNonlin. The mean relative error of the NCA calculation parameters of CPhaMAS and WinNonlin was <0.0001 %. When calculating BE for conventional, high-variability and narrow-therapeutic drugs. The main statistical parameters of the parameters Cmax, AUCt, and AUCinf in CPhaMAS have a mean relative error of <0.01% compared to WinNonLin. ConclusionsIn summary, CPhaMAS is a user-friendly platform with relatively accurate algorithms. It is a powerful tool for analysing pharmacokinetic data for new drug development and precision medicine.

Suitability of risk assessment tools used during the portfolio recommendation process

Orientation: Investors are overwhelmed with Collective Investment Schemes (CIS) portfolio options.Research purpose: The study set out to assess the emerging themes considered essential and prevalent in establishing a risk profile, establishing a framework for risk assessment tools, and evaluating existing risk assessment tools used in the industry.Motivation for the study: In 2020, newly amended legislation confirmed the importance of a risk assessment. This legislation made it mandatory and compulsory for financial planners to conduct a risk profile analysis concerning investment products in South Africa. Consequently, CIS have implemented various risk assessment tools to establish the investor risk profile.Research approach/design and method: Documentary research methodology was employed, where secondary data were analysed qualitatively. Twelve risk assessment tools were collected, and the established framework was used to evaluate existing risk assessment tools.Main findings: A sound theoretical framework for risk assessment tools, which is comprehensive in nature and include demographic factors, risk categorisation, and regulatory factors, was established. The results indicate that current tools used in the industry are inconsistent and do not address all the factors required to establish an investor risk profile.Practical/managerial implications: The study is significant in that it guides the financial services industry into the elements of assessment in establishing an investor risk profile.Contribution/value-add: A risk profile analysis is compulsory for financial planning. Financial planners and policymakers can consider the established framework to implement a standardised, comprehensive, holistic, risk assessment tool.

Early machine learning prediction of hospitalized patients at low risk of respiratory deterioration or mortality in community-acquired pneumonia: Derivation and validation of a multivariable model.

Current prognostic tools for pneumonia predominantly focus on mortality, often neglecting other crucial outcomes such as the need for advanced respiratory support. The objective of this study was to develop and validate a tool that predicts the early risk of non-occurrence of respiratory deterioration or mortality. We conducted a single-center, retrospective cohort study involving hospitalized adult patients with community-acquired pneumonia (CAP) and acute hypoxic respiratory failure from January 2009 to December 2019 (n = 4379). We employed the gradient boosting machine (GBM) learning to create a model that estimates the likelihood of patients requiring advanced respiratory support (high flow nasal cannula [HFNC], non-invasive mechanical ventilation [NIMV], and invasive mechanical ventilation [IMV]) or facing mortality during hospitalization. This model utilized readily available data including demographic, physiologic, and laboratory data, sourced from electronic health records and obtained within the first six hours of admission. Out of the cohort, 890 patients (25.2%) either required advanced respiratory support or died during their hospital stay. Our predictive model displayed superior discrimination and higher sensitivity (cross-validation C-statistic = 0.71; specificity = 0.56; sensitivity = 0.72) compared to the pneumonia severity index (PSI) (C-statistic = 0.65; specificity = 0.91; sensitivity = 0.24; P value < 0.001), while maintaining a negative predictive value (NPV) of approximately 0.85. These data demonstrate that our machine learning model predicted the non-occurrence of respiratory deterioration or mortality among hospitalized CAP patients more accurately than the PSI. The enhanced sensitivity of this model holds potential for reliably excluding low-risk patients from pneumonia clinical trials.

DCas13-mediated translational repression for accurate gene silencing in mammalian cells

Current gene silencing tools based on RNA interference (RNAi) or, more recently, clustered regularly interspaced short palindromic repeats (CRISPR)‒Cas13 systems have critical drawbacks, such as off-target effects (RNAi) or collateral mRNA cleavage (CRISPR‒Cas13). Thus, a more specific method of gene knockdown is needed. Here, we develop CRISPRδ, an approach for translational silencing, harnessing catalytically inactive Cas13 proteins (dCas13). Owing to its tight association with mRNA, dCas13 serves as a physical roadblock for scanning ribosomes during translation initiation and does not affect mRNA stability. Guide RNAs covering the start codon lead to the highest efficacy regardless of the translation initiation mechanism: cap-dependent, internal ribosome entry site (IRES)-dependent, or repeat-associated non-AUG (RAN) translation. Strikingly, genome-wide ribosome profiling reveals the ultrahigh gene silencing specificity of CRISPRδ. Moreover, the fusion of a translational repressor to dCas13 further improves the performance. Our method provides a framework for translational repression-based gene silencing in eukaryotes.

Genetically encoded sensors for invivo detection of neurochemicals relevant to depression.

Depressive disorders are a common and debilitating form of mental illness with significant impacts on individuals and society. Despite the high prevalence, the underlying causes and mechanisms of depressive disorders are still poorly understood. Neurochemical systems, including serotonin, norepinephrine, and dopamine, have been implicated in the development and perpetuation of depressive symptoms. Current treatments for depression target these neuromodulator systems, but there is a need for a better understanding of their role in order to develop more effective treatments. Monitoring neurochemical dynamics during depressive symptoms is crucial for gaining a better a understanding of their involvement in depressive disorders. Genetically encoded sensors have emerged recently that offer high spatial-temporal resolution and the ability to monitor neurochemical dynamics in real time. This review explores the neurochemical systems involved in depression and discusses the applications and limitations of current monitoring tools for neurochemical dynamics. It also highlights the potential of genetically encoded sensors for better characterizing neurochemical dynamics in depression-related behaviors. Furthermore, potential improvements to current sensors are discussed in order to meet the requirements of depression research.

Protect the Children, Body and Soul

This paper critically examines American schooling systems, challenges their subtractive nature, and juxtaposes it with the culturally sustaining potential of education. We problematize the current tools for evaluating trauma and stress in young people of color and emphasize the need for a comprehensive understanding of indigenous medicines as a remedy. Drawing on interdisciplinary theories, we elucidate the pervasive and evolving nature of anti-blackness, reinforcing the sociohistorical structure of inequity within schools. As a response, this study presents a unique wellness survey (comprising two newly validated wellness scales) developed from a previous four-year longitudinal study investigating the relationship between culturally relevant teaching practices and improved health outcomes for children. We found a strong correlation between exposure to our culturally relevant intervention and several health indicators. Particularly, sustained telomere growth (protection of cells) was observed in over 90% of the participants in the intervention group, indicating a potential biological mechanism through which culturally informed interventions might contribute to improved health outcomes. We use these findings to argue that proactive measures centered on cultural and community contexts can serve as crucial protective factors, thereby potentially mitigating negative health outcomes related to racialized stress.

DeltaLCA

Reducing the environmental footprint of electronics and computing devices requires new tools that empower designers to make informed decisions about sustainability during the design process itself. This is not possible with current tools for life cycle assessment (LCA) which require substantial domain expertise and time to evaluate the numerous chips and other components that make up a device. We observe first that informed decision-making does not require absolute metrics and can instead be done by comparing designs. Second, we can use domain-specific heuristics to perform these comparisons. We combine these insights to develop DeltaLCA, an open-source interactive design tool that addresses the dual challenges of automating life cycle inventory generation and data availability by performing comparative analyses of electronics designs. Users can upload standard design files from Electronic Design Automation (EDA) software and the tool will guide them through determining which one has greater carbon footprints. DeltaLCA leverages electronics-specific LCA datasets and heuristics and tries to automatically rank the two designs, prompting users to provide additional information only when necessary. We show through case studies DeltaLCA achieves the same result as evaluating full LCAs, and that it accelerates LCA comparisons from eight expert-hours to a single click for devices with ~30 components, and 15 minutes for more complex devices with ~100 components.

Increased unpredictability in spruce budworm outbreaks following habitat loss and landscape fragmentation

The spruce budworm (SBW) is the insect defoliator responsible for the greatest tree mortality in North America. Fragmentation and loss of habitat are expected to affect the movement of SBW through forested landscapes during periods of dispersal thereby modifying outbreak severity and frequency.We developed a spatially explicit tri-trophic model by combining a forest landscape model and a system of difference equations to evaluate how the interactions between the SBW, its hosts and its parasitoids are disrupted by habitat loss and fragmentation. We designed landscapes with varying quantities of habitat and fragmentation levels to measure their influence on population dynamics and outbreak severity and frequency.Our model simulations show that landscapes with higher proportion of host tree habitat were also characterised by greater SBW average densities, average cumulative defoliation and outbreak severity, which agrees with earlier studies. However, the bottom-up control by tree hosts breaks down as their proportion in the landscape decreased or when they formed isolated patches. Indeed, we found that landscapes with a low proportion of habitat fragmented into relatively large distant patches produced greatest variability in average SBW abundance and cumulative defoliation between simulation runs. In landscapes with higher habitat proportion, increased isolation between patches produced asynchronous outbreaks. Moreover, in these landscapes, parasitoids occupy fewer habitat cells than the SBW, suggesting that they were not able to efficiently track their prey. Together, these results indicate that increased distance between habitat patches can disrupt trophic control of SBW leading to increased unpredictability and asynchrony in outbreak dynamics.For continued effective management of SBW using current deterministic decision-making tools, we recommend prioritising the maintenance of habitat connectivity in forested landscapes.

ORCA: A Tool for Radiological Consequences for Accidental Releases

Evaluating atmospheric dispersion and radiological doses in the vicinity of buildings is required for small modular reactors (SMRs) because of the reduced size of their exclusion area boundary. The current Canadian nuclear industry tool for these calculations implements the methodology defined in CSA Standard N288.2-M91, which was written to support large Canada Deuterium Uranium (CANDU) nuclear reactors as opposed to SMRs. The ORCA (On/offsite Radiological Consequences of Accidents) code has been developed to address this technical concern in addition to evaluating atmospheric dispersion and doses in the far field. The code calculates worker and public doses following an airborne release of radioactive material into the atmosphere under postulated accident conditions at a nuclear facility. The current paper presents the key assumptions and methods utilized in ORCA and discusses qualification of the software to the requirements of CSA Standard N286.7-16. The new model is applicable to SMRs and existing reactor designs and reduces conservatisms in the near field (i.e., <1 km from the source) relative to the methods in CSA N288.2-M91.

Microfluidic point-of-care testing for the detection of Bordetella pertussis: A mini-review

Bordetella pertussis is a bacterial pathogen responsible for pertussis, which is a highly contagious respiratory disease. Despite the relatively high vaccination coverage, pertussis is considered a reemerging disease that necessitates enhanced strategies for identification, prevention, and control. The diagnosis of pertussis typically involves a combination of clinical evaluation, laboratory tests, and a thorough medical history. The current technologies for pertussis diagnosis have their own limitations, prompting the exploration of alternative diagnostic approaches that offer enhanced sensitivity, specificity, and speed. Microfluidic technology is considered a very promising tool for the diagnosis of infectious diseases, as it offers more rapid and accurate outputs. It allows point-of-care testing (POCT) at or near the patient site, which can be critical, especially for an outbreak or pandemic. In this paper, current pertussis diagnostic tools with their limitations were discussed, and microfluidic approaches for the diagnosis of pertussis were highlighted.

Design of a Compact 3-D Vibration-Assisted Turning Device With Large Amplitude and High Frequency for Diversified Microstructure Sculpturing

The 3D vibration-assisted turning (VAT) has attracted increasing attention for its merits in microstructure sculpturing and ultra-precision machining. However, most current 3D VAT tools adopt complex structures and it is still difficult to implement high frequency and large amplitude simultaneously on a simple integrated tool. Here, a 3D VAT tool with high-frequency and large amplitude adjustment capability is proposed for the first time, which adopts a more stable and compact single sandwich piezoelectric transducer structure. High frequency and large amplitude adjustment capabilities improve the machining efficiency and the range of machinable microstructures. The structure of the tool is simplified by using the sandwich-type single transducer structure, which is convenient to reduce cost and improve machining stability. Surface microstructures with variable inclination angles and distribution ratios are firstly sculptured by the proposed 3D VAT tool, which provides a new idea for surface modification. In addition, surface microstructures with different depths and high-precision microgrooves are machined, and better machining results are obtained. The texture depth and machining efficiency of microstructure are increased with the increase of amplitude and frequency. Microgrooves with a surface roughness of Sa 29 nm, minimized burrs and defects, and a specific cutting force reduction of 54.8% are obtained.

Improving Diagnostic Procedures in Autism for Girls and Women: A Narrative Review.

Biases exist in the diagnostic process for autism spectrum disorder (henceforth "autism"), which result in some girls and women being diagnosed later or missed entirely. Current diagnostic tools may not capture the full range of behavioural presentations of autism, leading to under-identification. This review explores why these biases may occur, and how diagnostic procedures could be adapted to better identify autistic girls and women. We recommend that diagnostic assessments are adjusted to capture a broader range of behavioural exemplars of autism; that camouflaging of autistic traits is taken into account; and that care is taken to ensure co-occurring mental health conditions do not overshadow autism diagnosis. We offer recommendations, building on gold-standard diagnostic guidelines, for how diagnostic procedures can be improved for girls and women.

Probing Tissue Viscoelasticity With STL Ultrasound Shearwave Spectroscopy Using Cole-Cole Diagrams.

Viscoelasticity is mapped by dispersion in shearwave elastography. Incomplete spectral information of shearwaves is therefore used to estimate mechanical stiffness. We propose capturing the "full-waveform-information" of the shear wave spectra to better resolve complex shear modulus μ* (ω). Approach is validated on phantom models, animal tissues, and feasibility demonstrated on human post-delivery placenta. We captured robust estimates of μ* in ex-vivo livers subjected to water bath ablation, glutaraldehyde exposure and in the placenta. Complex modulus at 200 Hz is more reflective of tissue stiffness than cross-correlation estimate. Bias increased in phantoms with higher gelatin (G) (0.65: 6% G) and oil (O) (0.58: 6% G and 40% O) concentration, compared to elastic phantoms with low stiffness (0.33: 3% G). Actual tissues also reported higher bias in cross-correlation estimate (rabbit liver: 0.61, porcine liver: 2.20, and human placenta: 0.63). Stiffness is sensitive to ablation temperature, where the overall modulus changed from 3.02 KPa at 16 °C to 2.75 KPa at 56 °C in water bath. With exposure to Glutaraldehyde, the overall modulus increased from 2.37 to 9.03 KPa. Reconstruction errors in the loss modulus decreased by 68% with the power law compared to a Maxwell model in porcine livers with Cole-Cole inverse fitting. Omitting Shear wave attenuation leads to bias. Reconstruction of rheological response with a model is sensitive to its architecture and also the framework. We use "full spectral information" in ultrasound shear wave elastography to better map μ*(ω) changes in viscoelastic tissues.

Atrial fibrillation in the elderly - the geriatric perspective

Atrial fibrillation is the most common cardiac arrhythmia in older adults. As a result of the positive data on ablation, the focus has shifted to rhythm control. The method of choice is pulmonary vein isolation. Even older patients may benefit from ablation. Oral anticoagulation remains an essential component of pharmacological therapy for atrial fibrillation. Older adults require an individualised treatment approach, which should be based on current guidelines and complementary tools. The assessment of functionality should be taken into account in therapy and goal planning.

Tool Damage Detection Method Based on Improved Threshold Segmentation Algorithm

In order to solve the problem that the current tool wear defects are difficult to be collected by the visual inspection system, an Otsu threshold segmentation algorithm based on particle swarm optimization is proposed.to detect tool wear The algorithm improved update strategy for inertia coefficients which effectively expanding the search scope of the algorithm and shortens the running time of the algorithm. By adding a perturbation equation to the particle swarm, solved the problem of traditional particle swarm optimization algorithms easily falling into local optima. Finally, an experimental platform is built to verify the effectiveness of the algorithm. This inspection method can achieve the identification of tool damage areas and the measurement of tool damage amount, and has advantages such as high recognition accuracy and fast running speed compared to traditional Otsu algorithm, Canny algorithm ,local threshold segmentation and so on. The research results have certain reference value for the actual tool defect detection system.

Gene doping detection in the era of genomics.

Recent progress in gene editing has enabled development of gene therapies for many genetic diseases, but also made gene doping an emerging risk in sports and competitions. By delivery of exogenous transgenes into human body, gene doping not only challenges competition fairness but also places health risk on athletes. World Anti-Doping Agency (WADA) has clearly inhibited the use of gene and cell doping in sports, and many techniques have been developed for gene doping detection. In this review, we will summarize the main tools for gene doping detection at present, highlight the main challenges for current tools, and elaborate future utilizations of high-throughput sequencing for unbiased, sensitive, economic and large-scale gene doping detections. Quantitative real-time PCR assays are the widely used detection methods at present, which are useful for detection of known targets but are vulnerable to codon optimization at exon-exon junction sites of the transgenes. High-throughput sequencing has become a powerful tool for various applications in life and health research, and the era of genomics has made it possible for sensitive and large-scale gene doping detections. Non-biased genomic profiling could efficiently detect new doping targets, and low-input genomics amplification and long-read third-generation sequencing also have application potentials for more efficient and straightforward gene doping detection. By closely monitoring scientific advancements in gene editing and sport genetics, high-throughput sequencing could play a more and more important role in gene detection and hopefully contribute to doping-free sports in the future.

Analyzing GPU Performance in Virtualized Environments: A Case Study

The graphics processing unit (GPU) plays a crucial role in boosting application performance and enhancing computational tasks. Thanks to its parallel architecture and energy efficiency, the GPU has become essential in many computing scenarios. On the other hand, the advent of GPU virtualization has been a significant breakthrough, as it provides scalable and adaptable GPU resources for virtual machines. However, this technology faces challenges in debugging and analyzing the performance of GPU-accelerated applications. Most current performance tools do not support virtual GPUs (vGPUs), highlighting the need for more advanced tools. Thus, this article introduces a novel performance analysis tool that is designed for systems using vGPUs. Our tool is compatible with the Intel GVT-g virtualization solution, although its underlying principles can apply to many vGPU-based systems. Our tool uses software tracing techniques to gather detailed runtime data and generate relevant performance metrics. It also offers many synchronized graphical views, which gives practitioners deep insights into GVT-g operations and helps them identify potential performance bottlenecks in vGPU-enabled virtual machines.

Design and In Silico Evaluation of an Exercise Decision Support System Using Digital Twin Models.

Managing glucose levels during exercise is challenging for individuals with type 1 diabetes (T1D) since multiple factors including activity type, duration, intensity and other factors must be considered. Current decision support tools lack personalized recommendations and fail to distinguish between aerobic and resistance exercise. We propose an exercise-aware decision support system (exDSS) that uses digital twins to deliver personalized recommendations to help people with T1D maintain safe glucose levels (70-180 mg/dL) and avoid low glucose (<70 mg/dL) during and after exercise. We evaluated exDSS using various exercise and meal scenarios recorded from a large, free-living study of aerobic and resistance exercise. The model inputs were heart rate, insulin, and meal data. Glucose responses were simulated during and after 30-minute exercise sessions (676 aerobic, 631 resistance) from 247 participants. Glucose outcomes were compared when participants followed exDSS recommendations, clinical guidelines, or did not modify behavior (no intervention). exDSS significantly improved mean time in range for aerobic (80.2% to 92.3%, P < .0001) and resistance (72.3% to 87.3%, P < .0001) exercises compared with no intervention, and versus clinical guidelines (aerobic: 82.2%, P < .0001; resistance: 80.3%, P < .0001). exDSS reduced time spent in low glucose for both exercise types compared with no intervention (aerobic: 15.1% to 5.1%, P < .0001; resistance: 18.2% to 6.6%, P < .0001) and was comparable with following clinical guidelines (aerobic: 4.5%, resistance: 8.1%, P = N.S.). The exDSS tool significantly improved glucose outcomes during and after exercise versus following clinical guidelines and no intervention providing motivation for clinical evaluation of the exDSS system.