Ayanian, Shant

Importance Thirty-day hospital readmission is used to guide postdischarge care; however, a single binary 30-day estimate does not distinguish when risk occurs from when intervention is most actionable, with implications for allocation of postdischarge resources. Objective To evaluate time-structured hospital readmission risk within 30 days after discharge and implications for clinical utility. Design, Setting, and Participants Retrospective prognostic study of adults with hospital discharges from 2017 to 2024 (from 19 hospitals within a US health system for the development cohort) and 2008 to 2019 (from Medical Information Mart for Intensive Care IV for the external cohort) with 30-day follow-up. Analyses were conducted from November 2025 through June 2026. Exposure Postdischarge prediction window, including landmark intervals of 0 to 7, 8 to 14, 15 to 21, and 22 to 30 days and cumulative horizons through days 7, 14, 21, and 30 after discharge. Main Outcomes and Measures First all-cause hospital readmission before death during each landmark interval and by each cumulative horizon. Risk estimates were derived using clinical information available at hospital discharge. Performance was assessed using discrimination, calibration, decision curves, and capacity-constrained analyses. Results Among 617 841 discharges in the development cohort, the median (IQR) patient age was 65 (50-76) years, and 315 220 discharges (51.0%) occurred among female patients. The 30-day readmission rate was 16.3% (95% CI, 16.2%-16.5%), with 68 797 readmissions (68.2%) occurring within 14 days. Cumulative-horizon analyses characterized readmission risk through days 7, 14, 21, and 30, whereas landmark interval-specific analyses showed lower positive predictive values (PPVs) beyond day 7. At 5% intervention capacity, landmark PPVs were 58.3% (95% CI, 57.4%-59.1%) for days 0 to 7, 16.0% (95% CI, 15.5%-16.6%) for days 8 to 14, 14.5% (95% CI, 13.9%-15.0%) for days 15 to 21, and 12.9% (95% CI, 12.4% to 13.5%) for days 22 to 30; numbers needed to prevent 1 readmission were 8.6, 31.3, 34.6, and 38.6, respectively. Conclusions and Relevance In this prognostic study of adult hospital discharges, hospital readmission risk varied over time and was not captured by a single binary 30-day estimate. These findings suggest that time-structured readmission modeling can characterize when readmission risk occurs, but additional work is needed before such models can reliably guide interventions during specific postdischarge intervals.

Abstract Scientific foundation models learn high-dimensional representations from diverse data modalities, yet what they encode and how to extract that knowledge remain open questions. Here we show that probing the internal representations of Evo 2, a 7-billion-parameter genomic foundation model, enables accurate and interpretable genetic variant effect prediction. We introduce a covariance-based probe that captures second-order structure from Evo 2 sequence embeddings to predict variant pathogenicity across variant types and functional consequences, matching or exceeding specialized predictors within their domains. To ground these predictions in known biological mechanisms, we train a complementary panel of probes on existing annotations to detect which genomic properties are disrupted by a variant. This categorized evidence is then integrated with each variant’s genomic context through a language model to generate variant-specific mechanistic hypotheses. Our pathogenicity predictions correlate with experimental measures of variant function, clinical penetrance, and biobank disease associations while the mechanistic hypotheses are consistent with expert reviews, known mechanism classes, and downstream molecular readouts. We release pathogenicity scores, disruption profiles, and contextualized interpretations for 4.2 million variants from the ClinVar database as an open resource through the Evo Variant Effect Explorer (EVEE). More broadly, this structured probing approach offers a general framework for interrogating foundation models across scientific disciplines and grounding their outputs in existing domain concepts.

Abstract The advent of high-throughput sequencing has led to an exponential increase in genomic data, highlighting the need for efficient and accurate models to analyze and interpret this information. In this study, we introduce a novel, exomic foundational model that leverages a combination of the human reference genome and multispecies data to improve variant detection and interpretation. Our model utilizes a short-range transformer architecture and is trained on a large dataset of human exomic sequences derived from the Tapestry study. Through a series of ablation studies and scaling experiments, we demonstrate the effectiveness of our model in predicting next token accuracy and identifying clinically pathogenic variants. We also show that our model outperforms existing models in a range of downstream tasks, including variant effect prediction and disease state identification. In fact, our largest sequence transformer for range adaptive nucleotide decoding variant (1B parameters) surpassed previous benchmarks, demonstrating a mean accuracy of 0.880 [an 8.2% improvement over the original nucleotide transformer (NT) and a 7% improvement over NT-v2]. Furthermore, we construct a unique exomic ClinVar dataset to evaluate the model’s performance on pathogenicity and disease states. Our results highlight the potential of this model to improve our understanding of the human exome and its role in disease. The model and its applications have significant implications for genomics-based diagnosis and personalized medicine, including tailored therapeutic development.

Abstract Background Hospital discharge summaries are critical for ensuring continuity of care, but their quality often varies. Large language models (LLMs) have the potential to standardize and enhance the efficiency of this documentation process. Objectives To evaluate the quality of hospital discharge summaries created by an LLM‐based hospital course drafting tool created by Epic Systems compared with human‐written summaries. Methods Retrospective study at a single tertiary‐care institution in 2024. The cohort included 100 adult hospitalizations lasting >72 h across medical and surgical dismissing services. No interventions were performed. Summaries (LLM‐generated vs. human‐written) were independently reviewed using a standardized rubric covering nine domains (e.g., comprehensiveness, clarity, relevance). Scores were normalized and compared. Readability was assessed using Flesch Reading Ease. Results LLM‐generated summaries outperformed human‐written summaries across all criteria ( p < .05), with the greatest difference observed in comprehensiveness (LLM median 0.62 vs. human −0.23). Human‐written summaries from surgical services scored lower than those from medical services, but LLM performance was consistent across both. Human summaries had higher Flesch Reading Ease scores (33.11 vs. 26.2; p < .05), reflecting simpler language. Conclusions LLM‐generated summaries demonstrated superior quality, consistency, and clinical utility compared with human‐written summaries, highlighting their potential to improve documentation efficiency and standardization.

Abstract Background: Spatial Reasoning AI (SRAI) systems are emerging as a transformative class of clinical artificial intelligence, enabling real-time interpretation of complex anatomy in imaging, surgery, and chronic disease management. Unlike traditional AI approaches constrained to tabular or 2D inputs, SRAI models incorporate geometric priors, multimodal fusion, and 3D anatomical reasoning to support high-impact tasks such as volumetric segmentation, lesion localization, intraoperative guidance, and prognostic modeling. Objective: This scoping review aimed to (1) map the emerging landscape of SRAI in healthcare, (2) assess its clinical performance across diagnostic, prognostic, and workflow applications, and (3) identify opportunities and barriers for safe translation into practice. Methods: Following PRISMA 2020 guidelines, we systematically searched PubMed, Springer Nature, and IEEE Xplore (including CVPR, ICCV, ISBI, and EMBC) for original studies implementing spatially aware AI models with clinical validation or workflow relevance. Data extraction captured model architecture, input modality, anatomical scope, application domain, and performance outcomes. Results: We identified eligible studies spanning oncology, neurology, cardiology, surgery, and infectious diseases. SRAI systems consistently outperformed conventional methods in segmentation, lesion classification, and risk stratification. A paradigm shift is underway from task-specific CNNs to foundation-level models, including MedSAM and MedCLIP for zero-shot segmentation and retrieval, and NeRF-based pipelines for anatomically faithful 3D reconstruction. Randomized evidence shows that SRAI can improve workflow efficiency without compromising diagnostic accuracy. Conclusion: SRAI models demonstrate strong potential to advance diagnostic precision, prognostic accuracy, and workflow integration across multiple clinical domains. Their safe adoption will require standardized evaluation metrics, prospective multi-institutional validation, and interpretable outputs. As foundation models evolve to better encode spatial priors, SRAI is poised to become a cornerstone of workflow-integrated precision medicine.

Abstract Background: Spatial Reasoning AI (SRAI) systems are reshaping clinical practice by enabling real-time interpretation of complex anatomical structures in medical imaging, surgery, and chronic disease management (Lin et al., 2023, Qiao et al., 2021; Song et al., 2024) . Unlike traditional AI approaches that rely on tabular or 2D data, SRAI models incorporate geometric priors, multimodal fusion, and 3D anatomical reasoning to support high-impact tasks such as volumetric segmentation, disease localization, and intraoperative guidance (Milletari et al., 2016; Hatamizadeh et al., 2022; Zhang et al., 2022) . Objective: This scoping review aimed to (1) characterize the emerging landscape of spatial reasoning models in healthcare, (2) evaluate their clinical performance across diagnostic and prognostic applications, and (3) identify architectural trends that underpin successful translation into practice. Methods: Following PRISMA guidelines, we systematically screened PubMed to identify studies that implemented spatially aware AI models with real-time or clinically validated outcomes (Page et al., 2021) . Data extraction captured model architecture, modality, anatomical scope, clinical application, and performance metrics. Results: We identified 124 eligible studies across the clinical domains of oncology, neurology, cardiology, orthopedic surgery, and infectious diseases (Nie et al., 2019; Hao et al., 2020; Tasken et al., 2023) . SRAI systems consistently outperformed conventional methods in segmentation, lesion classification, and risk stratification. (Lin et al., 2023; Qiao et al., 2021; Mahootiha et al., 2024) . A paradigm shift from task-specific CNNs to foundation models that reason across spatial structures has emerged, beginning with adaptations of generalist models such as MedSAM and MedCLIP for zero-shot segmentation and cross-modal retrieval, and NeRF-based reconstruction for anatomically faithful 3D modeling (Ma et al., 2024; Mildenhall et al., 2020; Radford et al., 2021). Beyond technical performance, randomized evidence shows that SRAI systems can improve workflow efficiency without compromising outcomes (Lang et al., 2023) . Conclusion: SRAI models hold promise for enhancing diagnostic accuracy, prognostic precision, and clinical efficiency across diverse applications. Their successful integration will depend on standardized evaluation metrics, robust validation, and interpretable outputs. As foundation models evolve to better encode spatial priors, SRAI is poised to become a cornerstone of personalized and procedural medicine.

Abstract The advent of high-throughput sequencing has led to an exponential increase in genomic data, highlighting the need for efficient and accurate models to analyze and interpret this information. Here, we introduce a novel, exomic foundational model that leverages a combination of human reference genome and multispecies data to improve variant detection and interpretation. Our model utilizes a short- range transformer architecture and is trained on a large dataset of human exomic sequences derived from the Tapestry study. Through a series of ablation studies and scaling experiments, we demonstrate the effectiveness of our model in pre- dicting next token accuracy and identifying clinically pathogenic variants. We also show that our model outperforms existing models in a range of downstream tasks, including variant effect prediction and disease state identification. In fact, our largest STRAND variant (1B parameters) surpassed previous benchmarks, demonstrating a mean accuarcy of 0.880 (8.2% improvement over the original NT and 7% improvement over NT-v2). Furthermore, we construct a unique exomic ClinVar dataset to evaluate the model’s performance on pathogenicity and disease states. Our results highlight the potential of this model to improve our understanding of the human exome and its role in disease. The model and its applications have significant implications for genomic based diagnosis and personalized medicine including tailored therapeutic development.

Introduction Optimal hospital bed utilization requires innovative patient care models. We studied a novel hospitalist model utilizing telemedicine to facilitate collaboration with affiliated emergency departments (EDs) and support medical triage and care of ED patients with high likelihood of hospital admission. Methods Telehospitalists based at a tertiary care facility collaborated with four community EDs in the same healthcare network between January 1, 2022, and April 30, 2023. Telehospitalists supported ED clinicians in medical care decisions and facilitated patient disposition. Emergency department length of stay (LOS) and disposition were evaluated, as were hospital LOS, 30-day readmission, and in-hospital mortality. For patients discharged from the ED, 7-day ED readmission and subsequent hospitalization were evaluated. Results Telehospitalists discussed 550 “admit-likely” patients with ED clinicians: 105 patients (19.1%) discharged from the ED and avoided admission; 322 patients (58.5%) were admitted to local or nearby community hospitals; 123 patients (22.4%) transferred to the tertiary care facility. Emergency department LOS differed significantly among disposition groups, including patients discharged home (10.2 h), admitted to local hospitals (12.6 h), and transferred to tertiary care hospitalist services (14.9 h; p < 0.001). Hospital LOS and in-hospital mortality were not significantly different among disposition groups. Patients admitted locally had lower 30-day readmission compared to those transferred to tertiary care facility (odds ratio = 0.59 [0.36, 0.99], p = 0.048). Discussion Telehospitalists as triage clinicians is an innovative approach to support local ED clinicians and patients. Telehospitalists optimized hospital bed utilization and healthcare system resources by facilitating safe discharges to home and expediting tertiary care transfers when necessary.