Obstructive sleep apnea (OSA) is a sleep disorder associated with elevated cardiovascular and metabolic risks. This study presents a multimodal late-fusion framework to identify OSA patients most at risk using data from the MIMIC-IV database. Structured electronic health record data were encoded with an autoencoder trained through a joint reconstruction and classification loss, while unstructured discharge notes were represented by topic distributions extracted with BERTopic using BioClinicalBERT embeddings. The fused data were combined, reduced with UMAP, and clustered using HDBSCAN. Results show that multimodal fusion outperformed single-modality approaches, achieving a Silhouette Score of 0.8186 and an Adjusted Rand Index of 0.2802, compared with 0.8025/0.2797 for structured data and 0.4878 / -0.0012 for unstructured data. These findings highlight the synergistic value of multimodal data and its potential to advance precision medicine.

Objective Phase II of MVP-CHAMPION, a federal collaboration between the Veterans Affairs Healthcare System (VA) and the Department of Energy (DoE), leveraged large-scale clinical, geo-spatial, and genetic data with state-of-the-art artificial intelligence (AI), and high-performance computing (HPC) to improve value in healthcare.Materials and Methods Eight clinical priority projects for which AI was a critical missing capability were initiated to address: lung cancer screening (MVP 061), suicide risk screening (MVP 062), cardiovascular risk in obstructive sleep apnea (MVP 063), checkpoint inhibitor toxicity (MVP 064), heart failure (MVP 065), renal complications in diabetes (MVP 066), post COVID-19 sequelae (MVP 067), and antipsychotic medication toxicity (MVP 068).Results Building on a strong regulatory and administrative foundation, we developed multimorbidity-aware analytic frameworks, reusable computational tools, and analytic pipelines. These greatly facilitated identification of novel risk factors including genetic variants and specification of more discriminating prediction models. Novel genetic risk factors are informing development and repurposing of medications and discriminating prediction models promise to improve healthcare value.Discussion The research foundation developed in Phase I and extended in Phase II of MVP CHAMPION has supported an unprecedented federal collaboration and yielded significant scientific advances. Our clinical findings are poised for near-term application, while advances in machine learning and high-performance computing may accelerate the broader adoption of artificial intelligence in healthcare.Conclusion This maturing VA-DoE federal collaboration is poised to transform the future of Veterans' healthcare and the broader national landscape of precision health.

Objective Predictive models of suicide risk have focused on features extracted from structured data found in electronic health records, with limited consideration of predisposing life events (LE) expressed in unstructured clinical text such as housing instability and marital troubles. This study aims to expand upon previous research, demonstrating how high-performance computing (HPC) and machine learning methodologies can be used to extract and annotate 8 LE across all Veterans Health Administration (VHA) unstructured clinical text data with enriched performance metrics. Integration of the 8 LE with the structured features using different statistical and machine learning (ML) methods is also discussed.Materials/Methods VHA-wide clinical text from January 2000 to January 2022 was pre-processed and analyzed using HPC. Data-driven lexicon curation enabled a rule-based annotator to extract LE, followed by machine learning for improved positive predictive value (PPV). NLP results were analyzed longitudinally and then integrated and compared to a baseline statistical model predicting risk for a combined outcome (suicide death, suicide attempt and overdose).Results First-time LE mentions showed a significant temporal correlation to suicide-related events (SRE) (suicide ideation, attempt and/or death) and are not associated with administrative bias. Predictive linear regression (LR) models integrating NLP-derived LE show an improved AUC of 0.81 and novel patient identification of up to 18%.Discussion Our analysis shows that these methodologies helped improve performance metrics significantly from previous work, while outperforming related works. These results demonstrated that NLP-derived LE served as acute predictors for SRE.Conclusion NLP integration into predictive models may help improve clinician decision support. Future work is necessary to better define and integrate these and other potential LE.

PURPOSE:Immune checkpoint inhibitor (ICI)-induced thyroiditis is a common immune-related adverse event (irAE) linked to improved survival. Polygenic risk scores (PRS) for autoimmune hypothyroidism predict thyroid irAEs in European-ancestry patients; performance in non-European populations is unclear. EXPERIMENTAL DESIGN:In the Veterans Affairs Million Veteran Program (MVP; 2011-2023), we identified ICI-treated patients with germline genotyping and a chemotherapy-treated control cohort, excluding those with thyroid disease or prior thyroid-directed treatments. Harmonized ancestry and race/ethnicity (HARE) defined non-Hispanic White (NHW) and non-Hispanic Black (NHB) groups. Thyroid irAEs within 1 year were defined using laboratory criteria capturing both hyperthyroid and hypothyroid phases. We compared two PRSs: a published European-derived PRS and an updated PRS selected across multiple genome-wide association study (GWAS) sources and methods (including the MVP multiancestry GWAS) to maximize discrimination in African-ancestry individuals in a held-out test set. HARE-stratified multivariable Cox models estimated time to thyroiditis; a 6-month landmark analysis assessed overall survival. RESULTS:The ICI cohort included 4,289 patients (3,473 NHW; 816 NHB). The baseline PRS was associated with thyroiditis in NHW [adjusted hazard ratio (aHR) per standard deviation, 1.33; 95% confidence interval (CI), 1.19-1.50) but not NHB patients or controls. The updated PRS improved risk stratification in NHW (aHR, 1.45; 95% CI, 1.28-1.63) and predicted thyroiditis in NHB patients (aHR, 1.48; 95% CI, 1.11-1.98) but not in controls. Thyroiditis within 6 months was associated with improved survival, but neither PRS was. CONCLUSIONS:Germline polygenic liability to hypothyroidism predicts ICI-induced thyroiditis in NHW and NHB patients when PRSs are selected via ancestry-stratified validation. Careful exploration of the dataset-method space is critical for equitable PRS development.

Obstructive sleep apnea (OSA) is linked to elevated cardiovascular and metabolic risks. We developed a multimodal framework integrating structured clinical data and unstructured discharge summaries using TabNet and ClinicalBERT with late fusion to generate unified patient embeddings. After UMAP dimensionality reduction, multimodal clustering outperformed single-modality approaches (Silhouette Score: 0.74 vs. 0.49) and revealed two OSA subgroups with marked differences in hypertension prevalence ($\mathbf{1 0 0 \%}$ vs. $\mathbf{0. 6 \%}$) and survival ($\boldsymbol{p}\lt \mathbf{0. 0 5}$). Multimodal classification achieved a higher AUROC for phenotype prediction with Random Forest (0.884 vs. 0.878 structured; 0.713 unstructured) and comparable performance with Logistic Regression (0.886 vs. 0.890 structured; 0.721 unstructured). These results demonstrate that integrating heterogeneous data improves OSA patient stratification and phenotype prediction.

Obstructive Sleep Apnea (OSA) is a common sleep disorder associated with serious health risks. This study leverages large language models (LLMs) to process and interpret clinical narratives in electronic health records. It develops clinically meaningful lexicons for predicting mortality and readmission risk, as well as for multiclass diagnostic classification in OSA patients. Using LLM-expanded lexicons, logistic regression models achieved ROC-AUC scores of 0.844 for 6-month all-cause post-discharge mortality, 0.817 for 1-year all-cause post-discharge mortality, and 0.729 for all-cause hospital readmissions following the first discharge. Diagnostic performance was highest with smaller n-gram representations, indicating that additional contextual length did not improve performance. Compared with frequency-based n-gram models, LLM-expanded lexicons yielded sparser feature sets with lower computational cost and comparable performance. Our findings highlight the potential of LLM-expanded lexicons to enhance OSA diagnosis and clinical risk stratification.

Supplemental Figure 1: Liver metastases promote cancer progression in patients.

Objective: By personalizing healthcare to an individual's specific requirements, precision health promises to maximize benefit and minimize harm, thereby maximizing value. We describe here, how in Phase 2 of the Million Veteran Program Computational Health Analytics for Medical Precision to Improve Outcomes Now (MVP CHAMPION), artificial intelligence (AI) and high performance computing (HPC) have been applied to Veteran's electronic health records (EHRs) and genetic data to advance real world precision health. Materials and Methods: Eight concept projects were selected on the basis of potential impact on high burden conditions among Veterans, including heart failure, suicide, lung cancer, diabetes, post COVID 19 sequelae, medication toxicity, and obstructive sleep apnea. Results: Achievements include new and more discriminating risk prediction models to inform medical decision making, multimorbidity aware analytic frameworks, and development and deployment of reusable computational tools. The identification of novel risk factors from genetic data and unstructured text in the EHR has both informed risk prediction and offered new insights for medication repurposing and development. Discussion: We not only confirmed the need for shared infrastructure, data management, and novel AI based workflows to inform precision health, but also found that such programmatic improvements result in valuable mechanistic insights. Conclusion: By building on these foundations through expanded deployment, adaptive modeling, and broader partnerships, the VA DOE collaboration is poised to transform not only the future of Veterans' healthcare, but the broader national landscape of precision health. ### Competing Interest Statement The authors have declared no competing interest. ### Clinical Protocols ### Funding Statement This study was funded by MVP000. This manuscript has been authored in part by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan). ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The study used ONLY openly available human data that were originally located at the Department of Veteran's Affairs Electronic Health Record system. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors

Supplemental Figure 5: Liver metastases enhance neutrophil migration and function.

ABSTRACTBackground/AimsPredictive models of suicide risk have focused on predictors extracted from structured data found in electronic health records (EHR), with limited consideration of predisposing life events (LE) expressed in unstructured clinical text such as housing instability and marital troubles. Additionally, there has been limited work in large-scale analysis of natural language processing (NLP) derived predictors for suicide risk and integration of extracted LE into longitudinal models of suicide risk. This study aims to expand upon previous research, demonstrating how high-performance computing (HPC) and machine learning technologies such as language models (LM) can be used to annotate and integrate 8 LE across all Veterans Health Administration (VHA) unstructured clinical text data with enriched performance metrics.Materials/MethodsVHA-wide clinical text from January 2000 to January 2022 were pre-processed and analyzed using HPC. Data-driven lexicon curation was performed for each LE by scaling a nearest-neighbor search over a precomputed index with LM embeddings. Data parallelism was applied to a rule-based annotator to extract LE, followed by random forest for improved positive predictive value (PPV). NLP results were analyzed and then integrated and compared to a baseline statistical model predicting risk for a combined outcome (suicide death, suicide attempt and overdose).ResultsFirst-time LE mentions, with a PPV of 0.8 or higher, showed a temporal correlation to suicide-related events (SRE) (suicide ideation, attempt and/or death). A significant increase of LE occurrences was observed starting 2.5 months prior to an SRE. Predictive models integrating NLP-derived LE show an improved AUC of 0.81 vs. a 0.79 obtained with the baseline and novel patient identification of up to 57%.DiscussionOur analysis shows that: 1) performance metrics, specifically PPV, improved significantly from previous work and outperform related works; 2) the mentions of LE in the unstructured data increase as time to a SRE approaches; 3) LE identified from the notes in the weeks prior to a SRE were not associated with administrative bias caused by outreach; and 4) LE improved the AUC of predictive models and identified novel patients at risk for suicide.ConclusionThe resulting person-period longitudinal data demonstrated that NLP-derived LE served as acute predictors for suicide-related events. NLP integration into predictive models may help improve clinician decision support. Future work is necessary to better define these LE.

Supplemental Figure 6: Liver metastases increase IL-1 signaling to promote neutrophil accumulation and cancer progression.

Forty percent of Veterans express concern about military toxic exposures (TEs) which may include airborne hazards. Veterans with overseas wartime service and TEs show increased rates of cardiometabolic disorders, including heart disease, stroke, and type 2 diabetes mellitus (T2DM). Additionally, 24% of Veterans have been diagnosed with Obstructive Sleep Apnea (OSA), which is epidemiologically linked to cardiometabolic disease. However, the extent to which OSA modifies the risk of developing cardiometabolic comorbidities after military TEs remains unknown Using data from the VA Corporate Data Warehouse (CDW), we identified Veterans receiving care in the past five years with a wartime record indicating service overseas in an area where TEs were reported. These Veterans were further stratified based on OSA diagnosis and cardiometabolic comorbidities. Of the 8.53 million Veterans receiving care within VA between 2019 and 2024 and who had an overseas wartime service record, 1.32 million (16%) had potential TEs. Among these, 452,140 (34%) had a diagnosis of OSA. In the group with both potential TEs plus OSA, 205,646 (45%) had one or more cardiometabolic comorbidities compared to only 210,468 (25%) in those with no OSA. Veterans with an overseas deployment and potential TEs had higher rates of OSA compared to the general VA population. Furthermore, they were more likely to have at least one or more comorbidities compared to those with an overseas wartime deployment but no OSA. This data suggests that the combination of OSA and military TEs is associated with a higher incidence of cardiometabolic comorbidities, warranting further investigation in this area. Million Veteran Program MVP063

Liver metastases are associated with poor cancer outcomes in many solid malignancies, but the factors influencing the trajectory of patients with liver metastases are poorly defined. It is known that liver metastases suppress systemic antitumor immunity; however, the underlying mechanisms remain incompletely described. We report that liver metastases promote disease progression in patients and preclinical models. Patients with liver metastases progress rapidly, regardless of primary tumor type. In multiple murine models, we find that liver metastases potentiate neutrophil migration and activity. Neutrophils licensed by liver metastasis augment metastatic colonization in an IL1-dependent manner. Thus, liver metastasis rewires systemic immunity to promote cancer progression. This work has implications for treatment strategies to address the poor clinical outcomes associated with liver metastasis.

Supplemental Figure 4: Liver metastases augment neutrophils to promote cancer progression.

Objectives:In 2016, the Department of Veterans Affairs (VA) and the Department of Energy (DOE) established an Interagency Agreement (IAA), the Million Veteran Program-Computational Health Analytics for Medical Precision to Improve Outcomes Now (MVP-CHAMPION) research collaboration. Materials and Methods:Oversight fell under the VA Office of Research Development (VA ORD) and DOE headquarters. An Executive Committee and 2 senior scientific liaisons work with VA and DOE leadership to optimize efforts in the service of shared scientific goals. The program supported centralized data management and genomic analysis including creation of a scalable approach to cataloging phenotypes. Cross-cutting methods including natural language processing, image processing, and reusable code were developed. Results:The 79.6 million dollar collaboration has supported centralized data management and genomic analysis including a scalable approach to cataloging phenotypes and launched over 10 collaborative scientific projects in health conditions highly prevalent in veterans. A ground-breaking analysis on the Summit and Andes supercomputers at the Oak Ridge National Laboratory (ORNL) of the genetic underpinnings of over 2000 health conditions across 44 million genetic variants which resulted in the identification of 38 270 independent genetic variants associating with one or more health traits. Of these, over 2000 identified associations were unique to non-European ancestry. Cross-cutting methods have advanced state-of-the-art artificial intelligence (AI) including large language natural language processing and a system biology study focused on opioid addiction awarded the 2018 Gordon Bell Prize for outstanding achievement in high-performance computing. The collaboration has completed work in prostate cancer, suicide prevention, and cardiovascular disease, and cross-cutting data science. Predictive models developed in these projects are being tested for application in clinical management. Discussion:Eight new projects were launched in 2023, taking advantage of the momentum generated by the previous collaboration. A major challenge has been limitations in the scope of appropriated funds at DOE which cannot currently be used for health research. Conclusion:Extensive multidisciplinary interactions take time to establish and are essential to continued progress. New funding models for maintaining high-performance computing infrastructure at the ORNL and for supporting continued collaboration by joint VA-DOE research teams are needed.

Obstructive Sleep Apnea (OSA) is a prevalent sleep disorder associated with serious health conditions. This project utilized large language models (LLMs) to develop lexicons for OSA sub-phenotypes. Our study found that LLMs can identify informative lexicons for OSA subphenotyping in simple patient cohorts, achieving wAUC scores of 0.9 or slightly higher. Among the six models studied, BioClinical BERT and BlueBERT outperformed the rest. Additionally, the developed lexicons exhibited some utility in predicting mortality risk (wAUC score of 0.86) and hospital readmission (wAUC score of 0.72). This work demonstrates the potential benefits of incorporating LLMs into healthcare. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement We thank The National Energy Research Scientific Computing Center, The U.S. Department of Energy, The Sustainable Research Pathways Program, and The Hood College Volpe Scholarship for supporting the project. We are grateful to the physicians from Veterans Affairs for providing medical guidance. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: This paper used the MIMIC-IV dataset, which is available on the PhysioNet repository (https://physionet.org/content/mimiciv/2.2/). I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors.

Abstract We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of $$\sim$$ ∼ 4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics.

Housing instability is considered a significant life stressor and preemptive screening should be applied to identify those at risk for homelessness as early as possible so that they can be targeted for specialized care. We developed models to classify patient outcomes for an established VA Homelessness Screening Clinical Reminder (HSCR), which identifies housing instability, in the two months prior to its administration. Logistic Regression and Random Forest models were fit to classify responses using the last 18 months of document activity. We measure concentration of risk across stratifications of predicted probability and observe an enriched likelihood of finding confirmed false negative responses from veterans with diagnosed housing instability. Positive responses were 34 times more likely to be detected within the top 1 % of patients predicted at risk than from those randomly selected. There is a 1 in 4 chance of detecting false negatives within the top 1 % of predicted risk. Machine learning methods can classify between episodes of housing instability using a data-driven approach that does not rely on variables curated from domain experts. This method has the potential to improve clinicians’ ability to identify veterans who are experiencing housing instability but are not captured by HSCR.

PURPOSE:Real world evidence is crucial to understanding the diffusion of new oncologic therapies, monitoring cancer outcomes, and detecting unexpected toxicities. In practice, real world evidence is challenging to collect rapidly and comprehensively, often requiring expensive and time-consuming manual case-finding and annotation of clinical text. In this Review, we summarise recent developments in the use of artificial intelligence to collect and analyze real world evidence in oncology. METHODS:We performed a narrative review of the major current trends and recent literature in artificial intelligence applications in oncology. RESULTS:Artificial intelligence (AI) approaches are increasingly used to efficiently phenotype patients and tumors at large scale. These tools also may provide novel biological insights and improve risk prediction through multimodal integration of radiographic, pathological, and genomic datasets. Custom language processing pipelines and large language models hold great promise for clinical prediction and phenotyping. CONCLUSIONS:Despite rapid advances, continued progress in computation, generalizability, interpretability, and reliability as well as prospective validation are needed to integrate AI approaches into routine clinical care and real-time monitoring of novel therapies.

Khurram, Ifrah1; Zamora-Resendiz, Rafael2; Morrow, Destinee2; Crivelli, Silvia2 Author Information