Nicholas W Barendregt, Joshua I Gold, Krešimir Josić, Zachary P Kilpatrick
{"title":"Information-Seeking Decision Strategies Mitigate Risk in Dynamic, Uncertain Environments.","authors":"Nicholas W Barendregt, Joshua I Gold, Krešimir Josić, Zachary P Kilpatrick","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>To survive in dynamic and uncertain environments, individuals must develop effective decision strategies that balance information gathering and decision commitment. Models of such strategies often prioritize either optimizing tangible payoffs, like reward rate, or gathering information to support a diversity of (possibly unknown) objectives. However, our understanding of the relative merits of these two approaches remains incomplete, in part because direct comparisons have been limited to idealized, static environments that lack the dynamic complexity of the real world. Here we compared the performance of normative reward- and information-seeking strategies in a dynamic foraging task. Both strategies show similar transitions between exploratory and exploitative behaviors as environmental uncertainty changes. However, we find subtle disparities in the actions they take, resulting in meaningful performance differences: whereas reward-seeking strategies generate slightly more reward on average, information-seeking strategies provide more consistent and predictable outcomes. Our findings support the adaptive value of information-seeking behaviors that can mitigate risk with minimal reward loss.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11975046/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Distributional bias compromises leave-one-out cross-validation.","authors":"George I Austin, Itsik Pe'er, Tal Korem","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Cross-validation is a common method for estimating the predictive performance of machine learning models. In a data-scarce regime, where one typically wishes to maximize the number of instances used for training the model, an approach called \"leave-one-out cross-validation\" is often used. In this design, a separate model is built for predicting each data instance after training on all other instances. Since this results in a single test instance available per model trained, predictions are aggregated across the entire dataset to calculate common performance metrics such as the area under the receiver operating characteristic or R2 scores. In this work, we demonstrate that this approach creates a negative correlation between the average label of each training fold and the label of its corresponding test instance, a phenomenon that we term distributional bias. As machine learning models tend to regress to the mean of their training data, this distributional bias tends to negatively impact performance evaluation and hyperparameter optimization. We show that this effect generalizes to leave-P-out cross-validation and persists across a wide range of modeling and evaluation approaches, and that it can lead to a bias against stronger regularization. To address this, we propose a generalizable rebalanced cross-validation approach that corrects for distributional bias for both classification and regression. We demonstrate that our approach improves cross-validation performance evaluation in synthetic simulations, across machine learning benchmarks, and in several published leave-one-out analyses.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11177965/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141332659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nicholas Wan, Qiao Jin, Joey Chan, Guangzhi Xiong, Serina Applebaum, Aidan Gilson, Reid McMurry, R Andrew Taylor, Aidong Zhang, Qingyu Chen, Zhiyong Lu
{"title":"Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators.","authors":"Nicholas Wan, Qiao Jin, Joey Chan, Guangzhi Xiong, Serina Applebaum, Aidan Gilson, Reid McMurry, R Andrew Taylor, Aidong Zhang, Qingyu Chen, Zhiyong Lu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Although large language models (LLMs) have been assessed for general medical knowledge using licensing exams, their ability to support clinical decision-making, such as selecting medical calculators, remains uncertain. We assessed nine LLMs, including open-source, proprietary, and domain-specific models, with 1,009 multiple-choice question-answer pairs across 35 clinical calculators and compared LLMs to humans on a subset of questions. While the highest-performing LLM, OpenAI o1, provided an answer accuracy of 66.0% (CI: 56.7-75.3%) on the subset of 100 questions, two human annotators nominally outperformed LLMs with an average answer accuracy of 79.5% (CI: 73.5-85.0%). Ultimately, we evaluated medical trainees and LLMs in recommending medical calculators across clinical scenarios like risk stratification and diagnosis. With error analysis showing that the highest-performing LLMs continue to make mistakes in comprehension (49.3% of errors) and calculator knowledge (7.1% of errors), our findings highlight that LLMs are not superior to humans in calculator recommendation.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11722524/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142973560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sophia Tang, Yinuo Zhang, Alexander Tong, Pranam Chatterjee
{"title":"Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation.","authors":"Sophia Tang, Yinuo Zhang, Alexander Tong, Pranam Chatterjee","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Flow matching in the continuous simplex has emerged as a promising strategy for DNA sequence design, but struggles to scale to higher simplex dimensions required for peptide and protein generation. We introduce <b>Gumbel-Softmax Flow and Score Matching</b>, a generative framework on the simplex based on a novel Gumbel-Softmax interpolant with a time-dependent temperature. Using this interpolant, we introduce Gumbel-Softmax Flow Matching by deriving a parameterized velocity field that transports from smooth categorical distributions to distributions concentrated at a single vertex of the simplex. We alternatively present Gumbel-Softmax Score Matching which learns to regress the gradient of the probability density. Our framework enables high-quality, diverse generation and scales efficiently to higher-dimensional simplices. To enable training-free guidance, we propose <b>Straight-Through Guided Flows (STGFlow)</b>, a classifier-based guidance method that leverages straight-through estimators to steer the unconditional velocity field toward optimal vertices of the simplex. STGFlow enables efficient inference-time guidance using classifiers pre-trained on clean sequences, and can be used with any discrete flow method. Together, these components form a robust framework for controllable <i>de novo</i> sequence generation. We demonstrate state-of-the-art performance in conditional DNA promoter design, sequence-only protein generation, and target-binding peptide design for rare disease treatment.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957225/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design of 3D Non-Cartesian Trajectories for Fast Volumetric MRI via Analytic Coordinate Discretization.","authors":"Kwang Eun Jang, Dwight G Nishimura","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>3D non-Cartesian trajectories offer several advantages over rectilinear trajectories for rapid volumetric imaging, including improved sampling efficiency and greater robustness to motion, flow, and aliasing artifacts. In this paper, we present a unified framework for designing three widely used non-Cartesian trajectories: 3D Radial, 3D Cones, and Stack-of-Spirals. Our approach is based on the idea that a non-Cartesian trajectory can be interpreted as a discretized version of an analytic coordinate defined by a set of template trajectories. Equivalently, the analytic coordinate is conceptualized as a non-Cartesian trajectory composed of an infinite number of copies of a set of template trajectories. The discretization is accomplished by constructing a continuous spiral path on a surface and sampling points along this path at unit intervals, leaving only the essential spokes/interleaves, thereby yielding the practical non-Cartesian trajectory from the analytic coordinate. One of the advantages of our approach is that the analytic density compensation factor can be readily derived using Jacobian determinants, which quantify changes in unit areas due to the transformation from the analytic coordinate to the Cartesian grid. Additionally, the proposed approach derives analytic formulae to compute the number of readouts based on prescribed parameters, allowing us to specify the trajectory's acceleration factor for a given total scan time. Furthermore, variable-density sampling can be easily incorporated, and spokes/interleaves are smoothly distributed in k-space along the derived spiral path, even for a small number of readouts. In a preliminary phantom study, the proposed method demonstrated improved sampling efficiency and image quality compared to the conventional approach.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957235/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ezekiel Williams, Alexandre Payeur, Avery Hee-Woon Ryoo, Thomas Jiralerspong, Matthew G Perich, Luca Mazzucato, Guillaume Lajoie
{"title":"Expressivity of Neural Networks with Random Weights and Learned Biases.","authors":"Ezekiel Williams, Alexandre Payeur, Avery Hee-Woon Ryoo, Thomas Jiralerspong, Matthew G Perich, Luca Mazzucato, Guillaume Lajoie","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Landmark universal function approximation results for neural networks with trained weights and biases provided the impetus for the ubiquitous use of neural networks as learning models in neuroscience and Artificial Intelligence (AI). Recent work has extended these results to networks in which a smaller subset of weights (e.g., output weights) are tuned, leaving other parameters random. However, it remains an open question whether universal approximation holds when only biases are learned, despite evidence from neuroscience and AI that biases significantly shape neural responses. The current paper answers this question. We provide theoretical and numerical evidence demonstrating that feedforward neural networks with fixed random weights can approximate any continuous function on compact sets. We further show an analogous result for the approximation of dynamical systems with recurrent neural networks. Our findings are relevant to neuroscience, where they demonstrate the potential for behaviourally relevant changes in dynamics without modifying synaptic weights, as well as for AI, where they shed light on recent fine-tuning methods for large language models, like bias and prefix-based approaches.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11247913/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141621926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zitong Yu, Nu Ri Choi, Zezhang Yang, Nancy A Obuchowski, Barry A Siegel, Abhinav K Jha
{"title":"ISIT-GEN: An in silico imaging trial to assess the inter-scanner generalizability of CTLESS for myocardial perfusion SPECT on defect-detection task.","authors":"Zitong Yu, Nu Ri Choi, Zezhang Yang, Nancy A Obuchowski, Barry A Siegel, Abhinav K Jha","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>A recently proposed scatter-window and deep learning-based attenuation compensation (AC) method for myocardial perfusion imaging (MPI) by single-photon emission computed tomography (SPECT), namely CTLESS, demonstrated promising performance on the clinical task of myocardial perfusion defect detection with retrospective data acquired on SPECT scanners from a single vendor. For clinical translation of CTLESS, it is important to assess the generalizability of CTLESS across different SPECT scanners. For this purpose, we conducted a virtual imaging trial, titled in silico imaging trial to assess generalizability (ISIT-GEN). ISIT-GEN assessed the generalizability of CTLESS on the cardiac perfusion defect detection task across SPECT scanners from three different vendors. The performance of CTLESS was compared with a standard-of-care CT-based AC (CTAC) method and a no-attenuation compensation (NAC) method using an anthropomorphic model observer. We observed that CTLESS had receiver operating characteristic (ROC) curves and area under the ROC curves similar to those of CTAC. Further, CTLESS was observed to significantly outperform the NAC method across three scanners. These results are suggestive of the inter-scanner generalizability of CTLESS and motivate further clinical evaluations. The study also highlights the value of using in silico imaging trials to assess the generalizability of deep learning-based AC methods feasibly and rigorously.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957238/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vivek Gopalakrishnan, Neel Dey, David-Dimitris Chlorogiannis, Andrew Abumoussa, Anna M Larson, Darren B Orbach, Sarah Frisken, Polina Golland
{"title":"Rapid patient-specific neural networks for intraoperative X-ray to volume registration.","authors":"Vivek Gopalakrishnan, Neel Dey, David-Dimitris Chlorogiannis, Andrew Abumoussa, Anna M Larson, Darren B Orbach, Sarah Frisken, Polina Golland","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The integration of artificial intelligence in image-guided interventions holds transformative potential, promising to extract 3D geometric and quantitative information from conventional 2D imaging modalities during complex procedures. Achieving this requires the rapid and precise alignment of 2D intraoperative images (<i>e.g</i>., X-ray) with 3D preoperative volumes (<i>e.g</i>., CT, MRI). However, current 2D/3D registration methods fail across the broad spectrum of procedures dependent on X-ray guidance: traditional optimization techniques require custom parameter tuning for each subject, whereas neural networks trained on small datasets do not generalize to new patients or require labor-intensive manual annotations, increasing clinical burden and precluding application to new anatomical targets. To address these challenges, we present xvr, a fully automated framework for training <i>patient-specific</i> neural networks for 2D/3D registration. xvr uses physics-based simulation to generate abundant high-quality training data from a patient's own preoperative volumetric imaging, thereby overcoming the inherently limited ability of supervised models to generalize to new patients and procedures. Furthermore, xvr requires only 5 min of training per patient, making it suitable for emergency interventions as well as planned procedures. We perform the largest evaluation of a 2D/3D registration algorithm on real X-ray data to date and find that xvr robustly generalizes across a diverse dataset comprising multiple anatomical structures, imaging modalities, and hospitals. Across surgical tasks, xvr achieves submillimeter-accurate registration at intraoperative speeds, improving upon existing methods by an order of magnitude. xvr is released as open-source software freely available at https://github.com/eigenvivek/xvr.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957231/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Genome evolution in an endangered freshwater mussel.","authors":"Rebekah L Rogers, John P Wares, Jeffrey T Garner","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Nearly neutral theory predicts that evolutionary processes will differ in small populations compared to large populations, a key point of concern for endangered species. The nearly-neutral threshold, the span of neutral variation, and the adaptive potential from new mutations all differ depending on N_e. To determine how genomes respond in small populations, we have created a reference genome for a US federally endangered IUCN Red List freshwater mussel, Elliptio spinosa, and compare it to genetic variation for a common and successful relative, Elliptio crassidens. We find higher rates of background duplication rates in E. spinosa consistent with proposed theories of duplicate gene accumulation according to nearly-neutral processes. Along with these changes we observe fewer cases of adaptive gene family amplification in this endangered species. However, TE content is not consistent with nearly-neutral theory. We observe substantially less recent TE proliferation in the endangered species with over 500 Mb of newly copied TEs in Elliptio crassidens. These results suggest a more complex interplay between TEs and duplicate genes than previously proposed for small populations. They further suggest that TEs and duplications require greater attention in surveys of genomic health for endangered species.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11952574/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jian Jiang, Long Chen, Lu Ke, Bozheng Dou, Yueying Zhu, Yazhou Shi, Huahai Qiu, Bengong Zhang, Tianshou Zhou, Guo-Wei Wei
{"title":"Machine learning predictions from unpredictable chaos.","authors":"Jian Jiang, Long Chen, Lu Ke, Bozheng Dou, Yueying Zhu, Yazhou Shi, Huahai Qiu, Bengong Zhang, Tianshou Zhou, Guo-Wei Wei","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Chaos is omnipresent in nature, and its understanding provides enormous social and economic benefits. However, the unpredictability of chaotic systems is a textbook concept due to their sensitivity to initial conditions, aperiodic behavior, fractal dimensions, nonlinearity, and strange attractors. In this work, we introduce, for the first time, chaotic learning, a novel multiscale topological paradigm that enables accurate predictions from chaotic systems. We show that seemingly random and unpredictable chaotic dynamics counterintuitively offer unprecedented quantitative predictions. Specifically, we devise multiscale topological Laplacians to embed real-world data into a family of interactive chaotic dynamical systems, modulate their dynamical behaviors, and enable the accurate prediction of the input data. As a proof of concept, we consider 28 datasets from four categories of realistic problems: 10 brain waves, four benchmark protein datasets, 13 single-cell RNA sequencing datasets, and an image dataset, as well as two distinct chaotic dynamical systems, namely the Lorenz and Rossler attractors. We demonstrate chaotic learning predictions of the physical properties from chaos. Our new chaotic learning paradigm profoundly changes the textbook perception of chaos and bridges topology, chaos, and learning for the first time.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957220/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}