Philip Chung

All Publications

• Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication. JAMA surgery Chung, P., Fong, C. T., Walters, A. M., Aghaeepour, N., Yetisgen, M., O'Reilly-Shah, V. N. 2024

  Abstract

  General-domain large language models may be able to perform risk stratification and predict postoperative outcome measures using a description of the procedure and a patient's electronic health record notes.To examine predictive performance on 8 different tasks: prediction of American Society of Anesthesiologists Physical Status (ASA-PS), hospital admission, intensive care unit (ICU) admission, unplanned admission, hospital mortality, postanesthesia care unit (PACU) phase 1 duration, hospital duration, and ICU duration.This prognostic study included task-specific datasets constructed from 2 years of retrospective electronic health records data collected during routine clinical care. Case and note data were formatted into prompts and given to the large language model GPT-4 Turbo (OpenAI) to generate a prediction and explanation. The setting included a quaternary care center comprising 3 academic hospitals and affiliated clinics in a single metropolitan area. Patients who had a surgery or procedure with anesthesia and at least 1 clinician-written note filed in the electronic health record before surgery were included in the study. Data were analyzed from November to December 2023.Compared original notes, note summaries, few-shot prompting, and chain-of-thought prompting strategies.F1 score for binary and categorical outcomes. Mean absolute error for numerical duration outcomes.Study results were measured on task-specific datasets, each with 1000 cases with the exception of unplanned admission, which had 949 cases, and hospital mortality, which had 576 cases. The best results for each task included an F1 score of 0.50 (95% CI, 0.47-0.53) for ASA-PS, 0.64 (95% CI, 0.61-0.67) for hospital admission, 0.81 (95% CI, 0.78-0.83) for ICU admission, 0.61 (95% CI, 0.58-0.64) for unplanned admission, and 0.86 (95% CI, 0.83-0.89) for hospital mortality prediction. Performance on duration prediction tasks was universally poor across all prompt strategies for which the large language model achieved a mean absolute error of 49 minutes (95% CI, 46-51 minutes) for PACU phase 1 duration, 4.5 days (95% CI, 4.2-5.0 days) for hospital duration, and 1.1 days (95% CI, 0.9-1.3 days) for ICU duration prediction.Current general-domain large language models may assist clinicians in perioperative risk stratification on classification tasks but are inadequate for numerical duration predictions. Their ability to produce high-quality natural language explanations for the predictions may make them useful tools in clinical workflows and may be complementary to traditional risk prediction models.

  View details for DOI 10.1001/jamasurg.2024.1621

  View details for PubMedID 38837145

• Prediction of American Society of Anesthesiologists Physical Status Classification from preoperative clinical text narratives using natural language processing. BMC anesthesiology Chung, P., Fong, C. T., Walters, A. M., Yetisgen, M., O'Reilly-Shah, V. N. 2023; 23 (1): 296

  Abstract

  Electronic health records (EHR) contain large volumes of unstructured free-form text notes that richly describe a patient's health and medical comorbidities. It is unclear if perioperative risk stratification can be performed directly from these notes without manual data extraction. We conduct a feasibility study using natural language processing (NLP) to predict the American Society of Anesthesiologists Physical Status Classification (ASA-PS) as a surrogate measure for perioperative risk. We explore prediction performance using four different model types and compare the use of different note sections versus the whole note. We use Shapley values to explain model predictions and analyze disagreement between model and human anesthesiologist predictions.Single-center retrospective cohort analysis of EHR notes from patients undergoing procedures with anesthesia care spanning all procedural specialties during a 5 year period who were not assigned ASA VI and also had a preoperative evaluation note filed within 90 days prior to the procedure. NLP models were trained for each combination of 4 models and 8 text snippets from notes. Model performance was compared using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC). Shapley values were used to explain model predictions. Error analysis and model explanation using Shapley values was conducted for the best performing model.Final dataset includes 38,566 patients undergoing 61,503 procedures with anesthesia care. Prevalence of ASA-PS was 8.81% for ASA I, 31.4% for ASA II, 43.25% for ASA III, and 16.54% for ASA IV-V. The best performing models were the BioClinicalBERT model on the truncated note task (macro-average AUROC 0.845) and the fastText model on the full note task (macro-average AUROC 0.865). Shapley values reveal human-interpretable model predictions. Error analysis reveals that some original ASA-PS assignments may be incorrect and the model is making a reasonable prediction in these cases.Text classification models can accurately predict a patient's illness severity using only free-form text descriptions of patients without any manual data extraction. They can be an additional patient safety tool in the perioperative setting and reduce manual chart review for medical billing. Shapley feature attributions produce explanations that logically support model predictions and are understandable to clinicians.

  View details for DOI 10.1186/s12871-023-02248-0

  View details for PubMedID 37667258

  View details for PubMedCentralID PMC10476287

• Author Correction: AI-guided precision parenteral nutrition for neonatal intensive care units. Nature medicine Phongpreecha, T., Ghanem, M., Reiss, J. D., Oskotsky, T. T., Mataraso, S. J., De Francesco, D., Reincke, S. M., Espinosa, C., Chung, P., Ng, T., Costello, J. M., Sequoia, J. A., Razdan, S., Xie, F., Berson, E., Kim, Y., Seong, D., Szeto, M. Y., Myers, F., Gu, H., Feister, J., Verscaj, C. P., Rose, L. A., Sin, L. W., Oskotsky, B., Roger, J., Shu, C. H., Shome, S., Yang, L. K., Tan, Y., Levitte, S., Wong, R. J., Gaudillière, B., Angst, M. S., Montine, T. J., Kerner, J. A., Keller, R. L., Shaw, G. M., Sylvester, K. G., Fuerch, J., Chock, V., Gaskari, S., Stevenson, D. K., Sirota, M., Prince, L. S., Aghaeepour, N. 2025

  View details for DOI 10.1038/s41591-025-03691-x

  View details for PubMedID 40205201

• AI-guided precision parenteral nutrition for neonatal intensive care units. Nature medicine Phongpreecha, T., Ghanem, M., Reiss, J. D., Oskotsky, T., Mataraso, S. J., De Francesco, D., Reincke, S. M., Espinosa, C., Chung, P., Ng, T., Costello, J. M., Sequoia, J. A., Razdan, S., Xie, F., Berson, E., Kim, Y., Seong, D., Szeto, M. Y., Myers, F., Gu, H., Feister, J., Verscaj, C. P., Rose, L. A., Sin, L. W., Oskotsky, B., Roger, J., Shu, C. H., Shome, S., Yang, L. K., Tan, Y., Levitte, S., Wong, R. J., Gaudillière, B., Angst, M. S., Montine, T. J., Kerner, J. A., Keller, R. L., Shaw, G. M., Sylvester, K. G., Fuerch, J., Chock, V., Gaskari, S., Stevenson, D. K., Sirota, M., Prince, L. S., Aghaeepour, N. 2025

  Abstract

  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.

  View details for DOI 10.1038/s41591-025-03601-1

  View details for PubMedID 40133525

  View details for PubMedCentralID 10593864

• Mitigation of outcome conflation in predicting patient outcomes using electronic health records. Journal of the American Medical Informatics Association : JAMIA Reincke, S. M., Espinosa, C., Chung, P., James, T., Berson, E., Aghaeepour, N. 2025

  Abstract

  OBJECTIVES: Artificial intelligence (AI) models utilizing electronic health record data for disease prediction can enhance risk stratification but may lack specificity, which is crucial for reducing the economic and psychological burdens associated with false positives. This study aims to evaluate the impact of confounders on the specificity of single-outcome prediction models and assess the effectiveness of a multi-class architecture in mitigating outcome conflation.MATERIALS AND METHODS: We evaluated a state-of-the-art model predicting pancreatic cancer from disease code sequences in an independent cohort of 2.3 million patients and compared this single-outcome model with a multi-class model designed to predict multiple cancer types simultaneously. Additionally, we conducted a clinical simulation experiment to investigate the impact of confounders on the specificity of single-outcome prediction models.RESULTS: While we were able to independently validate the pancreatic cancer prediction model, we found that its prediction scores were also correlated with ovarian cancer, suggesting conflation of outcomes due to underlying confounders. Building on this observation, we demonstrate that the specificity of single-outcome prediction models is impaired by confounders using a clinical simulation experiment. Introducing a multi-class architecture improves specificity in predicting cancer types compared to the single-outcome model while preserving performance, mitigating the conflation of outcomes in both the real-world and simulated contexts.DISCUSSION: Our results highlight the risk of outcome conflation in single-outcome AI prediction models and demonstrate the effectiveness of a multi-class approach in mitigating this issue.CONCLUSION: The number of predicted outcomes needs to be carefully considered when employing AI disease risk prediction models.

  View details for DOI 10.1093/jamia/ocaf033

  View details for PubMedID 40056434

• AnesthesiaChat: An Anesthesia-Specific Large Language Model Built from WikiAnesthesia Goodell, A., Chung, P., Chu, L., Larson, B., Chu, S. N., Rishel, C. LIPPINCOTT WILLIAMS & WILKINS. 2025

  View details for Web of Science ID 001460830000032

• PregMedNet: Multifaceted Maternal Medication Impacts on Neonatal Complications. medRxiv : the preprint server for health sciences Kim, Y., Marić, I., Kashiwagi, C. M., Han, L., Chung, P., Reiss, J. D., Butcher, L. D., Caoili, K. J., Berson, E., Xue, L., Espinosa, C., James, T., Shome, S., Xie, F., Ghanem, M., Seong, D., Chang, A. L., Reincke, S. M., Mataraso, S., Shu, C. H., Francesco, D. D., Becker, M., Kumar, W. M., Wong, R., Gaudilliere, B., Angst, M. S., Shaw, G. M., Bateman, B. T., Stevenson, D. K., Prince, L. S., Aghaeepour, N. 2025

  Abstract

  While medication intake is common among pregnant women, medication safety remains underexplored, leading to unclear guidance for patients and healthcare professionals. PregMedNet addresses this gap by providing a multifaceted maternal medication safety framework based on systematic analysis of 1.19 million mother-baby dyads from U.S. claims databases. A novel confounding adjustment pipeline was applied to systematically control confounders for multiple medication-disease pairs, robustly identifying both known and novel maternal medication effects. Notably, one of the newly discovered associations was experimentally validated, demonstrating the reliability of claims data and machine learning for perinatal medication safety studies. Additionally, potential biological mechanisms of newly identified associations were generated using a graph learning method. These findings highlight PregMedNet's value in promoting safer medication use during pregnancy and maternal-neonatal outcomes.

  View details for DOI 10.1101/2025.02.13.25322242

  View details for PubMedID 39990567

  View details for PubMedCentralID PMC11844599

• Information Extraction from Clinical Texts with Generative Pre-trained Transformer Models. International journal of medical sciences Kim, M. S., Chung, P., Aghaeepour, N., Kim, N. 2025; 22 (5): 1015-1028

  Abstract

  Purpose: Processing and analyzing clinical texts are challenging due to its unstructured nature. This study compared the performance of GPT (Generative Pre-trained Transformer)-3.5 and GPT-4 for extracting information from clinical text. Materials and Methods: Three types of clinical texts, containing patient characteristics, medical history, and clinical test results extracted from case reports in open-access journals were utilized as input. Simple prompts containing queries for information extraction were then applied to both models using the Greedy Approach as the decoding strategy. When GPT models underperformed in certain tasks, we applied alternative decoding strategies or incorporated prompts with task-specific definitions. The outputs generated by GPT models were evaluated as True or False to determine the accuracy of information extraction. Results: Clinical texts containing patient characteristics (60 texts), medical history (50 texts), and clinical test results (25 texts) were extracted from 60 case reports. GPT models could extract information accurately with simple prompts to extract straightforward information from clinical texts. Regarding sex, GPT-4 demonstrated a significantly higher accuracy rate (95%) compared to GPT-3.5 (70%). GPT-3.5 (78%) outperformed GPT-4 (57%) in extracting body mass index (BMI). Utilizing alternative decoding strategies to sex and BMI did not practically improve the performance of the two models. In GPT-4, the revised prompts, including definitions of each sex category or the BMI formula, rectified all incorrect responses regarding sex and BMI generated during the main workflow. Conclusion: GPT models could perform adequately with simple prompts for extracting straightforward information. For complex tasks, incorporating task-specific definitions into the prompts is a suitable strategy than relying solely on simple prompts. Therefore, researchers and clinicians should use their expertise to create effective prompts and monitor LLM outcomes when extracting complex information from clinical texts.

  View details for DOI 10.7150/ijms.103332

  View details for PubMedID 40027192

  View details for PubMedCentralID PMC11866537

• Generating pregnant patient biological profiles by deconvoluting clinical records with electronic health record foundation models. Briefings in bioinformatics Seong, D., Mataraso, S., Espinosa, C., Berson, E., Reincke, S. M., Xue, L., Kashiwagi, C., Kim, Y., Shu, C. H., Chung, P., Ghanem, M., Xie, F., Wong, R. J., Angst, M. S., Gaudilliere, B., Shaw, G. M., Stevenson, D. K., Aghaeepour, N. 2024; 25 (6)

  Abstract

  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.

  View details for DOI 10.1093/bib/bbae574

  View details for PubMedID 39545787

  View details for PubMedCentralID PMC11565587

• Single-cell peripheral immunoprofiling of lewy body and Parkinson's disease in a multi-site cohort. Molecular neurodegeneration Phongpreecha, T., Mathi, K., Cholerton, B., Fox, E. J., Sigal, N., Espinosa, C., Reincke, M., Chung, P., Hwang, L. J., Gajera, C. R., Berson, E., Perna, A., Xie, F., Shu, C. H., Hazra, D., Channappa, D., Dunn, J. E., Kipp, L. B., Poston, K. L., Montine, K. S., Maecker, H. T., Aghaeepour, N., Montine, T. J. 2024; 19 (1): 59

  Abstract

  Multiple lines of evidence support peripheral organs in the initiation or progression of Lewy body disease (LBD), a spectrum of neurodegenerative diagnoses that include Parkinson's Disease (PD) without or with dementia (PDD) and dementia with Lewy bodies (DLB). However, the potential contribution of the peripheral immune response to LBD remains unclear. This study aims to characterize peripheral immune responses unique to participants with LBD at single-cell resolution to highlight potential biomarkers and increase mechanistic understanding of LBD pathogenesis in humans.In a case-control study, peripheral mononuclear cell (PBMC) samples from research participants were randomly sampled from multiple sites across the United States. The diagnosis groups comprise healthy controls (HC, n = 159), LBD (n = 110), Alzheimer's disease dementia (ADD, n = 97), other neurodegenerative disease controls (NDC, n = 19), and immune disease controls (IDC, n = 14). PBMCs were activated with three stimulants (LPS, IL-6, and IFNa) or remained at basal state, stained by 13 surface markers and 7 intracellular signal markers, and analyzed by flow cytometry, which generated 1,184 immune features after gating.The model classified LBD from HC with an AUROC of 0.87 ± 0.06 and AUPRC of 0.80 ± 0.06. Without retraining, the same model was able to distinguish LBD from ADD, NDC, and IDC. Model predictions were driven by pPLCγ2, p38, and pSTAT5 signals from specific cell populations under specific activation. The immune responses characteristic for LBD were not associated with other common medical conditions related to the risk of LBD or dementia, such as sleep disorders, hypertension, or diabetes.Quantification of PBMC immune response from multisite research participants yielded a unique pattern for LBD compared to HC, multiple related neurodegenerative diseases, and autoimmune diseases thereby highlighting potential biomarkers and mechanisms of disease.

  View details for DOI 10.1186/s13024-024-00748-2

  View details for PubMedID 39090623

  View details for PubMedCentralID 9739123

• Unlocking human immune system complexity through AI. Nature methods Berson, E., Chung, P., Espinosa, C., Montine, T. J., Aghaeepour, N. 2024; 21 (8): 1400-1402

  View details for DOI 10.1038/s41592-024-02351-1

  View details for PubMedID 39122943

  View details for PubMedCentralID 9586871

• Comprehensive overview of the anesthesiology research landscape: A machine Learning Analysis of 737 NIH-funded anesthesiology primary Investigator's publication trends. Heliyon Ghanem, M., Espinosa, C., Chung, P., Reincke, M., Harrison, N., Phongpreecha, T., Shome, S., Saarunya, G., Berson, E., James, T., Xie, F., Shu, C. H., Hazra, D., Mataraso, S., Kim, Y., Seong, D., Chakraborty, D., Studer, M., Xue, L., Marić, I., Chang, A. L., Tjoa, E., Gaudillière, B., Tawfik, V. L., Mackey, S., Aghaeepour, N. 2024; 10 (7): e29050

  Abstract

  Anesthesiology plays a crucial role in perioperative care, critical care, and pain management, impacting patient experiences and clinical outcomes. However, our understanding of the anesthesiology research landscape is limited. Accordingly, we initiated a data-driven analysis through topic modeling to uncover research trends, enabling informed decision-making and fostering progress within the field.The easyPubMed R package was used to collect 32,300 PubMed abstracts spanning from 2000 to 2022. These abstracts were authored by 737 Anesthesiology Principal Investigators (PIs) who were recipients of National Institute of Health (NIH) funding from 2010 to 2022. Abstracts were preprocessed, vectorized, and analyzed with the state-of-the-art BERTopic algorithm to identify pillar topics and trending subtopics within anesthesiology research. Temporal trends were assessed using the Mann-Kendall test.The publishing journals with most abstracts in this dataset were Anesthesia & Analgesia 1133, Anesthesiology 992, and Pain 671. Eight pillar topics were identified and categorized as basic or clinical sciences based on a hierarchical clustering analysis. Amongst the pillar topics, "Cells & Proteomics" had both the highest annual and total number of abstracts. Interestingly, there was an overall upward trend for all topics spanning the years 2000-2022. However, when focusing on the period from 2015 to 2022, topics "Cells & Proteomics" and "Pulmonology" exhibit a downward trajectory. Additionally, various subtopics were identified, with notable increasing trends in "Aneurysms", "Covid 19 Pandemic", and "Artificial intelligence & Machine Learning".Our work offers a comprehensive analysis of the anesthesiology research landscape by providing insights into pillar topics, and trending subtopics. These findings contribute to a better understanding of anesthesiology research and can guide future directions.

  View details for DOI 10.1016/j.heliyon.2024.e29050

  View details for PubMedID 38623206

  View details for PubMedCentralID PMC11016610

• AnesthesiaChat: An Anesthesia-Specific Large Language Model Built from WikiAnesthesia Goodell, A., Chung, P., Chu, L., Larson, B., Chu, S. N., Rishel, C. LIPPINCOTT WILLIAMS & WILKINS. 2024

  View details for Web of Science ID 001290723300048

• Transcriptional profiling of mouse projection neurons with VECTORseq. STAR protocols Cheung, V., Chung, P., Feinberg, E. H. 2022; 3 (3): 101625

  Abstract

  Existing techniques for transcriptional profiling of projection neurons could be applied to only one neuronal population per experiment. To increase throughput, we developed VECTORseq, which repurposes retrogradely infecting viruses to deliver multiplexable RNA barcodes, enabling projection anatomy to be read out in single-cell datasets. In this protocol, we describe the delivery of viral barcodes to mouse brain to label different projection neurons. We then detail single-cell or nuclei isolation for sequencing, followed by the analysis of single-cell sequencing data. For complete details on the use and execution of this protocol, please refer to Cheung et al. (2021).

  View details for DOI 10.1016/j.xpro.2022.101625

  View details for PubMedID 36035788

  View details for PubMedCentralID PMC9405111

• Virally encoded connectivity transgenic overlay RNA sequencing (VECTORseq) defines projection neurons involved in sensorimotor integration. Cell reports Cheung, V., Chung, P., Bjorni, M., Shvareva, V. A., Lopez, Y. C., Feinberg, E. H. 2021; 37 (12): 110131

  Abstract

  Behavior arises from concerted activity throughout the brain. Consequently, a major focus of modern neuroscience is defining the physiology and behavioral roles of projection neurons linking different brain areas. Single-cell RNA sequencing has facilitated these efforts by revealing molecular determinants of cellular physiology and markers that enable genetically targeted perturbations such as optogenetics, but existing methods for sequencing defined projection populations are low throughput, painstaking, and costly. We developed a straightforward, multiplexed approach, virally encoded connectivity transgenic overlay RNA sequencing (VECTORseq). VECTORseq repurposes commercial retrogradely infecting viruses typically used to express functional transgenes (e.g., recombinases and fluorescent proteins) by treating viral transgene mRNA as barcodes within single-cell datasets. VECTORseq is compatible with different viral families, resolves multiple populations with different projection targets in one sequencing run, and identifies cortical and subcortical excitatory and inhibitory projection populations. Our study provides a roadmap for high-throughput identification of neuronal subtypes based on connectivity.

  View details for DOI 10.1016/j.celrep.2021.110131

  View details for PubMedID 34936877

  View details for PubMedCentralID PMC8719358

• Case Report: Radiographic Identification of Intrapleural Misplacement of Epidural Catheter in an Intubated Post-Lung Transplant Patient. International medical case reports journal Wu, J., Chung, P., Wu, E. H., Zhang, K., Komatsu, R. 2021; 14: 823-828

  Abstract

  Intrapleural misplacement of epidural catheter is a rare complication of thoracic epidural placement, which can be difficult to detect in intubated patients with unreliable pain reports and hemodynamic response to the test dose. We describe a case of intrapleural misplacement of thoracic epidural in a 50-year-old man status-post bilateral lung transplant and highlight the use of radiographic techniques to identify the misplacement.

  View details for DOI 10.2147/IMCRJ.S338755

  View details for PubMedID 34887686

  View details for PubMedCentralID PMC8651211

• Natural Language Processing Predicts ASA Physical Status Classification from Pre-operative Note Text Chung, P., Fong, C. T., O'Reilly-Shah, V. LIPPINCOTT WILLIAMS & WILKINS. 2021: 870-873

  View details for Web of Science ID 000752526600373

• Compliance monitoring via a Bluetooth-enabled retainer: A prospective clinical pilot study. Orthodontics & craniofacial research Castle, E., Chung, P., Behfar, M. H., Chen, M., Gao, J., Chiu, N., Nelson, G., Roy, S., Oberoi, S. 2019; 22 Suppl 1: 149-153

  Abstract

  To conduct a prospective pilot trial to test the clinical efficacy and accuracy of a newly developed Bluetooth-enabled retainer, which was synchronized with an iOS mobile application, cloud database and provider webpage.Five orthodontic residents in a university setting.At the delivery of the retainers (T0), each participant was given an Bluetooth-enabled retainer, logbook and iPod Touch installed with the mobile application. Participants were instructed to wear the retainer for 12 hours per day and record in the logbook each time the retainer was inserted or removed and trained to synchronize the device daily to the mobile application. After the 5-day study period (T1), statistical analysis was performed comparing the device-reported data to the logbook data using two calculation methods.From T0 - T1, the participants wore their retainers for a median of 11.55 hours per day and the median difference between the self-reported (logbook) data and the device data was 35 minutes or 5.1% over the 5-day study period. Using an adjusted method to calculate the device-reported wear time, the median error was 13 minutes or 1.9%.Subjects were able to successfully wear the retainer and upload the data to the mobile application and cloud database. Patient compliance and technical issues could be monitored daily via the provider webpage, and early intervention was possible with reminder messaging. The Bluetooth-enabled retainer showed a clinically acceptable level of accuracy and usability that validates it for future clinical testing.

  View details for DOI 10.1111/ocr.12263

  View details for PubMedID 31074131

• Smart Diaphragm Study: Multi-omics profiling and cervical device measurements during pregnancy Liang, L., Dunn, J. P., Chen, S., Tsai, M., Hornburg, D., Newmann, S., Chung, P., Avina, M., Leng, Y., Holman, R., Lee, T. H., Berrios, S., Qureshi, S. A., Baer, R., Etemadi, M., Montelongo, E., Paynter, R., Zhao, B., Roy, S., Jelliffe, L., Snyder, M., Rand, L. MOSBY-ELSEVIER. 2019: S649

  View details for DOI 10.1016/j.ajog.2018.11.1033

  View details for Web of Science ID 000454249403169

• Galloping Heart. The New England journal of medicine Phan, B. A., Chung, P. 2017; 376 (21): e44

  View details for DOI 10.1056/NEJMicm1614250

  View details for PubMedID 28538123

• MyPectus: First-in-human pilot study of remote compliance monitoring of teens using dynamic compression bracing to correct pectus carinatum. Journal of pediatric surgery Harrison, B., Stern, L., Chung, P., Etemadi, M., Kwiat, D., Roy, S., Harrison, M. R., Martinez-Ferro, M. 2016; 51 (4): 608-11

  Abstract

  Patient compliance is a crucial determinant of outcomes in treatments involving medical braces, such as dynamic compression therapy for pectus carinatum (PC). We performed a pilot study to assess a novel, wireless, real-time monitoring system (MyPectus) to address noncompliance.Eight patients (10-16years old) with moderately severe PC deformities underwent bracing. Each patient received a data logger device inserted in the compression brace to sense temperature and pressure. The data were transmitted via Bluetooth 4.0 to an iOS smartphone app, then synced to cloud-based storage, and presented to the clinician on a web-based dashboard. Patients received points for brace usage on the app throughout the 4-week study, and completed a survey to capture patient-reported usage patterns.In all 8 patients, the data logger sensed and recorded data, which connected through all MyPectus system components. There were occasional lapses in data collection because of technical difficulties, such as limited storage capacity. Patients reported positive feedback regarding points.The components of the MyPectus system recorded, stored, and provided data to patients and clinicians. The MyPectus system will inform clinicians about issues related to noncompliance: discrepancy between patient-reported and sensor-reported data regarding brace usage; real-time, actionable information; and patient motivation.

  View details for DOI 10.1016/j.jpedsurg.2015.11.007

  View details for PubMedID 26700692

• Rapid and low-cost prototyping of medical devices using 3D printed molds for liquid injection molding. Journal of visualized experiments : JoVE Chung, P., Heller, J. A., Etemadi, M., Ottoson, P. E., Liu, J. A., Rand, L., Roy, S. 2014: e51745

  Abstract

  Biologically inert elastomers such as silicone are favorable materials for medical device fabrication, but forming and curing these elastomers using traditional liquid injection molding processes can be an expensive process due to tooling and equipment costs. As a result, it has traditionally been impractical to use liquid injection molding for low-cost, rapid prototyping applications. We have devised a method for rapid and low-cost production of liquid elastomer injection molded devices that utilizes fused deposition modeling 3D printers for mold design and a modified desiccator as an injection system. Low costs and rapid turnaround time in this technique lower the barrier to iteratively designing and prototyping complex elastomer devices. Furthermore, CAD models developed in this process can be later adapted for metal mold tooling design, enabling an easy transition to a traditional injection molding process. We have used this technique to manufacture intravaginal probes involving complex geometries, as well as overmolding over metal parts, using tools commonly available within an academic research laboratory. However, this technique can be easily adapted to create liquid injection molded devices for many other applications.

  View details for DOI 10.3791/51745

  View details for PubMedID 24998993

  View details for PubMedCentralID PMC4208739

• Towards BirthAlert--A Clinical Device Intended for Early Preterm Birth Detection. IEEE transactions on bio-medical engineering Etemadi, M., Chung, P., Heller, J. A., Liu, J. A., Rand, L., Roy, S. 2013; 60 (12): 3484-93

  Abstract

  Preterm birth causes 1 million infant deaths worldwide every year, making it the leading cause of infant mortality. Existing diagnostic tests such as transvaginal ultrasound or fetal fibronectin either cannot determine if preterm birth will occur in the future or can only predict the occurrence once cervical shortening has begun, at which point it is too late to reverse the accelerated parturition process. Using iterative and rapid prototyping techniques, we have developed an intravaginal proof-of-concept device that measures both cervical bioimpedance and cervical fluorescence to characterize microstructural changes in a pregnant woman's cervix in hopes of detecting preterm birth before macroscopic changes manifest in the tissue. If successful, such an early alert during this "silent phase" of the preterm birth syndrome may open a new window of opportunity for interventions that may reverse and avoid preterm birth altogether.

  View details for DOI 10.1109/TBME.2013.2272601

  View details for PubMedID 23893706

  View details for PubMedCentralID PMC4605421

• Novel device to trend impedance and fluorescence of the cervix for preterm birth detection. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Etemadi, M., Chung, P., Heller, J. A., Liu, J., Grossman-Kahn, R., Rand, L., Roy, S. 2013; 2013: 176-9

  Abstract

  Preterm birth is the leading cause of worldwide neonatal mortality. It follows a pathologically accelerated form of the normal processes that govern cervical softening and dilation. Softening and dilation occur due to changes in cervical collagen crosslinking, which can be measured non-invasively by changes in tissue fluorescence and impedance. We present a novel device designed specifically to take fluorescence and impedance measurements throughout pregnancy, with the end goal of fusing and trending these measurements to form an early diagnosis of preterm labor.

  View details for DOI 10.1109/EMBC.2013.6609466

  View details for PubMedID 24109653

  View details for PubMedCentralID PMC4606960

• Fabric-based pressure sensor array for decubitus ulcer monitoring. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Chung, P., Rowe, A., Etemadi, M., Lee, H., Roy, S. 2013; 2013: 6506-9

  Abstract

  Decubitus ulcers occur in an estimated 2.5 million Americans each year at an annual cost of $11 billion to the U.S. health system. Current screening and prevention techniques for assessing risk for decubitus ulcer formation and repositioning patients every 1-2 hours are labor-intensive and can be subjective. We propose use of a Bluetooth-enabled fabric-based pressure sensor array as a simple tool to objectively assess and continuously monitor decubitus ulcer risk.

  View details for DOI 10.1109/EMBC.2013.6611045

  View details for PubMedID 24111232

  View details for PubMedCentralID PMC4606918