Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2406.18490

Parameter selection and optimization of a computational network model of blood flow in single-ventricle patients

Alyssa M. Taylor-LaPole·L. Mihaela Paun·Dan Lior·Justin D Weigand·Charles Puelz·Mette S. Olufsen
View original source ↗Read source document ↗Export metadata ↓

Abstract

Hypoplastic left heart syndrome (HLHS) is a congenital heart disease responsible for 23% of infant cardiac deaths each year. HLHS patients are born with an underdeveloped left heart, requiring several surgeries to reconstruct the aorta and create a single ventricle circuit known as the Fontan circulation. While survival into early adulthood is becoming more common, Fontan patients suffer from reduced cardiac output, putting them at risk for a multitude of complications. These patients are monitored using chest and neck MRI imaging, but these scans do not capture energy loss, pressure, wave intensity, or hemodynamics beyond the imaged region. This study develops a framework for predicting these missing features by combining imaging data and computational fluid dynamics (CFD) models. Predicted features from models of HLHS patients are compared to those from control patients with a double outlet right ventricle (DORV). We use parameter inference to render the model patient-specific. In the calibrated model, we predict pressure, flow, wave-intensity (WI), and wall shear stress (WSS). Results reveal that HLHS patients have higher vascular stiffness and lower compliance than DORV patients, resulting in lower WSS and higher WI in the ascending aorta and increased WSS and decreased WI in the descending aorta.

Explore related subjects

q-bio.QM

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Alyssa M. Taylor-LaPole, L. Mihaela Paun, Dan Lior, Justin D Weigand, Charles Puelz, Mette S. Olufsen. 2024-06-26. Parameter selection and optimization of a computational network model of blood flow in single-ventricle patients. https://arxiv.org/abs/2406.18490

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens

Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate perturbations must instead be prioritized over multiple experimental rounds. Despite the importance of this problem, existing benchmarks for adaptive hit discovery remain limited in scale and diversity. Here, we introduce AssayBench-Loop, a large-scale benchmark for adaptive hit discovery comprising 1,389 CRISPR screens across five phenotype categories. Beyond enabling systematic evaluation, its scale makes it possible to learn acquisition strategies across historical experiments. Building on this resource, we introduce AssayLoop, a sequential experimental design framework combining AssayFormer, a transformer-based amortized acquisition policy trained across historical screens to adapt from experimental feedback, with LLM-derived biological priors through an adaptive handoff. In this view, completed experiments become training data for learning how accumulated evidence should guide what to test next, while LLMs provide prior biological knowledge to seed the search. We further introduce AssayLLM, showing that the same principle can be extended directly to an LLM through task-specific post-training. On temporally held-out screens, AssayLoop achieves a 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying approximately 5% of the candidate library, outperforming existing adaptive-design methods and standalone LLMs, and AssayFormer alone. Performance improves with increasing historical training data and transfers to phenotype categories excluded from training. These results demonstrate the value of learning acquisition policies across historical experiments and combining them with broad biological priors for efficient adaptive hit discovery.

q-bio.QM↗
arXiv2026

Multi-Task Bacterial Colony Detection and Classification Using YOLOv8 with Edge Optimization for Resource-Constrained Deployment

Manual counting and classification of bacterial colonies are critical yet labor-intensive tasks in microbiology, prone to human error particularly on densely populated plates. This work proposes a multi-task deep learning framework trained on the Annotated Germs for Automated Recognition (AGAR) dataset (18,000 images; 9,202 training / 3,067 testing) to automate Colony Forming Unit (CFU) enumeration and species classification. A custom multi-task CNN employing global regression served as the baseline, but demonstrated limited performance in clustered colony environments due to the absence of spatial localization. To address this, a YOLOv8 object detection architecture was adopted with high-resolution 1024x1024 inputs, enabling instance-level colony detection and label assignment. The model achieved a classification accuracy of 98.13% and a counting accuracy of 98.27% (within a 10-colony margin), demonstrating strong predictive capability. To bridge the gap between model performance and practical deployability, the trained model was optimized through unstructured and structured pruning, ONNX conversion, and reduced-precision inference (FP32, FP16, INT8). On a Raspberry Pi 4B, ONNX FP32 and FP16 variants offered the best balance between inference speed (~6.4s) and accuracy (MAE ~2.20). Unstructured pruning preserved predictive accuracy (MAE ~2.01) without runtime gains, while structured pruning resulted in significant accuracy degradation (MAE ~6.3), revealing the sensitivity of instance-level colony detection to architectural compression. These findings provide practical guidance for selecting optimization strategies in resource-constrained laboratory deployments.

q-bio.QM↗
arXiv2026

ADMET-EvO: a self-evolving scientific agent for sustained research across heterogeneous tasks

Scientific agents can move beyond automated model building by using accumulated evidence to revise both their questions and experimental strategies. The challenge is sustaining this adaptation across heterogeneous tasks without overfitting decisions to internal validation. Absorption, distribution, metabolism, excretion and toxicity (ADMET) prediction provides a demanding setting across diverse assays, datasets and chemical domains. We therefore developed ADMET-EvO, an evidence-gated agent that formalizes endpoints, generates falsifiable hypotheses and tests interventions across data, feature and model axes. It carries supported, rejected and inconclusive outcomes forward to guide each new cycle. Across the 22-task Therapeutics Data Commons (TDC) ADMET benchmark, ADMET-EvO achieved the highest task-normalized score of 96.77. Evidence-guided selection reduced cumulative fitting time by 72.2% within a predefined non-inferiority margin. It also formalized 43 toxicity-related tasks and constructed endpoint-specific predictors. Together, these results show how ADMET-EvO can accumulate evidence, revise its strategy and expand its research scope over time.

q-bio.QM↗