DSDavid Seong

David Seong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


David Seong has a total of 197 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PregMedNet: Multifaceted maternal medication impacts on neonatal complications

    by Yeasul Kim, Ivana Marić, Chloe M. Kashiwagi, Lichy Han, Philip Chung, Jonathan D. Reiss, Lindsay D. Butcher, Kaitlin J. Caoili, Eloïse Berson, Lei Xue, et al.

    While medication use is common among pregnant women, medication safety remains insufficiently characterized because studies in pregnant women are challenging due to safety concerns. The recent digitization of healthcare databases and advances in computational methods have created new opportunities for large-scale, retrospective drug safety evaluations. Here, we present PregMedNet, a platform that characterizes multifaceted maternal medication associations on neonatal outcomes during pregnancy, covering more than 27,000 drug-disease pairs across 1,152 medications and 24 outcomes. These results encompass known and additional odds ratios (ORs), adjusted ORs, and drug-drug interactions, systematically analyzed using nationwide claims data and an advanced machine learning pipeline. Notably, one of the associations identified in this study is supported by in vivo experiments, increasing confidence in PregMedNet’s findings and highlighting the utility of claims data and machine learning for perinatal medication safety studies. Additionally, potential biological mechanisms underlying the associations are explored using a graph learning method, providing candidate pathways for future mechanistic investigations. We expect that PregMedNet will contribute to advancing maternal medication safety and improving neonatal outcomes by providing extensive, multifaceted drug safety information on this previously underrepresented population.

  • Open Access

    Blood-brain barrier dysfunction predicts cognitive trajectory after ischemic stroke

    by Lei Xue, Olivia A Jones, Lauren Drag, Kristy A. Zera, Li Zhu, Michael Mlynash, Natasha S. Carmichael, Chi-Hung Shu, Zuzanna Biesiada, David Seong, et al.

    Ischemic stroke doubles the risk of dementia. 1–4 Stroke severity and location affect cognition early, 5,6 but late dementia risk is not related to infarct characteristics, nor is it reduced by preventing additional strokes, 3,6,7 and its mechanism is unknown. We identified a plasma proteomic signature of chronic stroke that was consistent with blood-brain barrier (BBB) dysfunction, including a 58% decrease in plasma levels of platelet-derived growth factor B and downregulation of its pathway compared to healthy controls. During 2 years of follow-up, the stroke-specific proteome was accentuated in stroke survivors who subsequently declined in the processing speed/executive function cognitive domain. To test BBB function, we performed dynamic contrast-enhanced MRI 6-9 months after stroke in an additional cohort and found 1.7-fold higher whole brain BBB leakage compared to controls. Finally, we compared autopsy tissue from people with infarcts and dementia at death to those with infarcts and no dementia. Those who died with dementia had dramatic loss of vascular mural cell coverage compared to those without dementia (median 0.7% vs. 27%). Thus, our proteomic, functional, and structural data implicate chronic BBB dysfunction in cognitive decline late after stroke, revealing potential proteomic and imaging biomarkers and, importantly, a novel target for intervention.


  • Top Cited Papers

    Verifying Facts in Patient Care Documents Generated by Large Language Models Using Electronic Health Records

    by Philip Chung, Akshay Swaminathan, Alex J. Goodell, Yeasul Kim, S. Momsen Reincke, Lichy Han, Ben Deverett, Mohammad Amin Sadeghi, Abdel-Badih Ariss, Marc Ghanem, et al.


  • Epigenomic profile of GBA1 in Parkinson's disease

    by Eloise Berson, Raphael Zaghroun, Matteo Santoro, Syed Bukhari, David Seong, Chi-Hung Shu, Amalia Perna, Tomin James, Kathleen S. Montine, Geidy E. Serrano, et al.


  • Open Access

    Benchmarking of pre-training strategies for electronic health record foundation models

    by Samson Mataraso, Shreya D’sOuza, David Seong, Eloïse Berson, Camilo Espinosa, Nima Aghaeepour

    Objective: Our objective is to compare different pre-training strategies for electronic health record (EHR) foundation models. Materials and Methods: We evaluated three approaches using a transformer-based architecture: baseline (no pre-training), self-supervised pre-training with masked language modeling, and supervised pre-training. The models were assessed on their ability to predict both major adverse cardiac events and mortality occurring within 12 months. The pre-training cohort was 405 679 patients prescribed antihypertensives and the fine tuning cohort was 5525 patients who received doxorubicin. Results: Task-specific supervised pre-training achieved superior performance (AUROC 0.70, AUPRC 0.23), outperforming both self-supervised pre-training and the baseline. However, when the model was evaluated on the task of 12-month mortality prediction, the self-supervised model performed best. Discussion: While supervised pre-training excels when aligned with downstream tasks, self-supervised approaches offer more generalized utility. Conclusion: Pre-training strategy selection should consider intended applications, data availability, and transferability requirements.


  • Open Access

    Author Correction: AI-guided precision parenteral nutrition for neonatal intensive care units

    by Thanaphong Phongpreecha, Marc Ghanem, Jonathan D. Reiss, Tomiko T. Oskotsky, Samson J. Mataraso, Davide De Francesco, S. Momsen Reincke, Camilo Espinosa, Philip Chung, Taryn Ng, et al.


  • Open Access

    CD301b+ monocyte-derived dendritic cells mediate resistance to radiotherapy

    by Sirimuvva Tadepalli, Derek R. Clements, Hayley M. Raquer-McKay, Anja Lüdtke, Sanjana Saravanan, David Seong, Lorraine Vitek, Christopher M. Richards, Jan E. Carette, Matthias Mack, et al.

    Monocytes infiltrating tumors acquire various states that distinctly impact cancer treatment. Here, we show that resistance of tumors to radiotherapy (RT) is controlled by the accumulation of monocyte-derived dendritic cells (moDCs). These moDCs are characterized by the expression of CD301b and have a superior capacity to generate regulatory T cells (Tregs). Accordingly, moDC depletion limits Treg generation and improves the therapeutic outcome of RT. Mechanistically, we demonstrate that granulocyte–macrophage colony-stimulating factor (GM-CSF) derived from radioresistant tumor cells following RT is necessary for the accumulation of moDCs. Our results unravel the immunosuppressive function of moDCs and identify GM-CSF as an immunotherapeutic target during RT.


  • Top Cited Papers
    Open Access

    AI-guided precision parenteral nutrition for neonatal intensive care units

    by Thanaphong Phongpreecha, Marc Ghanem, Jonathan D. Reiss, Tomiko T. Oskotsky, Samson J. Mataraso, Davide De Francesco, S. Momsen Reincke, Camilo Espinosa, Philip Chung, Taryn Ng, et al.

    One in ten neonates are admitted to neonatal intensive care units, highlighting the need for precise interventions. However, the application of artificial intelligence (AI) in guiding neonatal care remains underexplored. Total parenteral nutrition (TPN) is a life-saving treatment for preterm neonates; however, implementation of the therapy in its current form is subjective, error-prone and resource-consuming. Here, we developed TPN2.0—a data-driven approach that optimizes and standardizes TPN using information collected routinely in electronic health records. We assembled a decade of TPN compositions (79,790 orders; 5,913 patients) at Stanford to train TPN2.0. In addition to internal validation, we also validated our model in an external cohort (63,273 orders; 3,417 patients) from a second hospital. Our algorithm identified 15 TPN formulas that can enable a precision-medicine approach (Pearson’s R = 0.94 compared to experts), increasing safety and potentially reducing cost. A blinded study (n = 192) revealed that physicians rated TPN2.0 higher than current best practice. In patients with high disagreement between the actual prescriptions and TPN2.0, standard prescriptions were associated with increased morbidities (for example, odds ratio = 3.33; P value = 0.0007 for necrotizing enterocolitis), while TPN2.0 recommendations were linked to reduced risk. Finally, we demonstrated that TPN2.0 employing a transformer architecture enabled guideline-adhering, physician-in-the-loop recommendations that allow collaboration between the care team and AI.


  • Open Access

    Generating pregnant patient biological profiles by deconvoluting clinical records with electronic health record foundation models

    by David Seong, Samson Mataraso, Camilo Espinosa, Eloise Berson, S Momsen Reincke, Lei Xue, Chloe Kashiwagi, Yeasul Kim, Chi-Hung Shu, Philip Chung, et al.

    Translational biology posits a strong bi-directional link between clinical phenotypes and a patient’s biological profile. By leveraging this bi-directional link, we can efficiently deconvolute pre-existing clinical information into biological profiles. However, traditional computational tools are limited in their ability to resolve this link because of the relatively small sizes of paired clinical–biological datasets for training and the high dimensionality/sparsity of tabular clinical data. Here, we use state-of-the-art foundation models (FMs) for electronic health record (EHR) data to generate proteomics profiles of pregnant patients, thereby deconvoluting pre-existing clinical information into biological profiles without the cost and effort of running large-scale traditional omics studies. We show that FM-derived representations of a patient’s EHR data coupled with a fully connected neural network prediction head can generate 206 blood protein expression levels. Interestingly, these proteins were enriched for developmental pathways, while proteins not able to be generated from EHR data were enriched for metabolic pathways. Finally, we show a proteomic signature of gestational diabetes that includes proteins with established and novel links to gestational diabetes. These results showcase the power of FM-derived EHR representations in efficiently generating biological states of pregnant patients. This capability can revolutionize disease understanding and therapeutic development, offering a cost-effective, time-efficient, and less invasive alternative to traditional methods of generating proteomics.


  • Open Access

    Comprehensive overview of the anesthesiology research landscape: A machine Learning Analysis of 737 NIH-funded anesthesiology primary Investigator's publication trends

    by Marc Ghanem, Camilo Espinosa, Philip Chung, Momsen Reincke, Natasha Harrison, Thanaphong Phongpreecha, Sayane Shome, Geetha Saarunya, Eloise Berson, Tomin James, et al.