William Speier

William Speier

Auto-generated profile, based on publicly available information

William Speier

University of California, Los Angeles

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 February 2021 in Journal of the American Medical Informatics Association
Verified
Journal Article
Open access
PDF file
KSKarthik V Sarma
Karthik V Sarma
SHStephanie Harmon
Stephanie Harmon
TSThomas Sanford
Thomas Sanford
HRHolger R Roth
Holger R Roth
ZXZiyue Xu
Ziyue Xu
CACorey W Arnold
Corey W Arnold
Objective: To demonstrate enabling multi-institutional training without centralizing or sharing the underlying physical data via federated learning (FL). Materials and Methods: Deep learning models were trained at each participating institution using local clinical data, and an additional model was trained using FL across all of the institutions. Results: We found that the FL model exhibited superior performance and generalizability to the models trained at single institutions, with an overall performance level that was significantly better than that of any of the institutional models alone when evaluated on held-out test sets from each institution and an outside challenge dataset. Discussion: The power of FL was successfully demonstrated across 3 academic institutions while avoiding the privacy risk associated with the transfer and pooling of patient data. Conclusion: Federated learning is an effective methodology that merits further study to enable accelerated development of models across institutions, enabling greater generalizability in clinical use.

5 August 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
YMYiwen Meng
Yiwen Meng
WSWilliam Speier
William Speier
MOMichael K. Ong
Michael K. Ong
CACorey W. Arnold
Corey W. Arnold
Advancements in machine learning algorithms have had a beneficial impact on representation learning, classification, and prediction models built using electronic health record (EHR) data. Effort has been put both on increasing models' overall performance as well as improving their interpretability, particularly regarding the decision-making process. In this study, we present a temporal deep learning model to perform bidirectional representation learning on EHR sequences with a transformer architecture to predict future diagnosis of depression. This model is able to aggregate five heterogenous and high-dimensional data sources from the EHR and process them in a temporal manner for chronic disease prediction at various prediction windows. We applied the current trend of pretraining and fine-tuning on EHR data to outperform the current state-of-the-art in chronic disease prediction, and to demonstrate the underlying relation between EHR codes in the sequence. The model generated the highest increases of precision-recall area under the curve (PRAUC) from 0.70 to 0.76 in depression prediction compared to the best baseline model. Furthermore, the self-attention weights in each sequence quantitatively demonstrated the inner relationship between various codes, which improved the model's interpretability. These results demonstrate the model's ability to utilize heterogeneous EHR data to predict depression while achieving high accuracy and interpretability, which may facilitate constructing clinical decision support systems in the future for chronic disease screening and early detection.

1 April 2021 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
JLJiayun Li
Jiayun Li
WLWenyuan Li
Wenyuan Li
ASAnthony Sisk
Anthony Sisk
HYHuihui Ye
Huihui Ye
WWW. Dean Wallace
W. Dean Wallace
CACorey W. Arnold
Corey W. Arnold

20 August 2007 in Journal of Clinical Oncology
Verified
Journal Article
Closed access
AKAndre Konski
Andre Konski
WSWilliam Speier
William Speier
AHAlexandra Hanlon
Alexandra Hanlon
JBJ. Robert Beck
J. Robert Beck
APAlan Pollack
Alan Pollack
Purpose: New treatments are introduced routinely into clinical practice without rigorous economic analysis. The specific aim of this study was to examine the cost effectiveness of proton beam radiation compared with current state-of-the art therapy in the treatment of patients with prostate cancer.Materials and Methods: A Markov model was informed with cost, freedom from biochemical failure (FFBF), and utility data obtained from the literature and from patient interviews to compare the cost effectiveness of 91.8 cobalt gray equivalent (CGE) delivered with proton beam versus 81 CGE delivered with intensity-modulated radiation therapy (IMRT). The length of how many years the model was run, patient's age, probability of FFBF after treatment with proton beam therapy and IMRT, utility of patients treated with salvage hormone therapy, and treatment cost were tested in sensitivity analyses.Results: Analysis at 15 years resulted in an expected mean cost of proton beam therapy and IMRT of $63,511 and $36,808, and $64,989 and $39,355 for a 70-year-old and 60-year-old man respectively, with quality-adjusted survival of 8.54 and 8.12 and 9.91 and 9.45 quality-adjusted life-years (QALY), respectively. The incremental cost effectiveness ratio was calculated to be $63,578/QALY for a 70-year-old man and $55,726/QALY for a 60-year-old man.Conclusion: Even when based on the unproven assumption that protons will permit a 10-Gy escalation of prostate dose compared with IMRT photons, proton beam therapy is not cost effective for most patients with prostate cancer using the commonly accepted standard of $50,000/QALY. Consideration should be given to limiting the number of proton facilities to allow comprehensive evaluation of this modality.

1 July 2019 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
KHKing Chung Ho
King Chung Ho
WSWilliam Speier
William Speier
HZHaoyue Zhang
Haoyue Zhang
FSFabien Scalzo
Fabien Scalzo
SESuzie El-Saden
Suzie El-Saden
CACorey W. Arnold
Corey W. Arnold
Current clinical practice relies on clinical history to determine the time since stroke (TSS) onset. Imaging-based determination of acute stroke onset time could provide critical information to clinicians in deciding stroke treatment options, such as thrombolysis. The patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within the therapeutic window. In this paper, we demonstrate a machine learning approach for TSS classification using routinely acquired imaging sequences. We develop imaging features from the magnetic resonance (MR) images and train machine learning models to classify the TSS. We also propose a deep-learning model to extract hidden representations for the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional deep features. The cross-validation results show that our best classifier achieved an area under the curve of 0.765, with a sensitivity of 0.788 and a negative predictive value of 0.609, outperforming existing methods. We show that the features generated by our deep-learning algorithm correlate with the MR imaging features, and validate the robustness of the model on imaging parameter variations (e.g., year of imaging). This paper advances magnetic resonance imaging analysis one-step-closer to an operational decision support tool for stroke treatment guidance.

19 July 2022 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
CCChao Chen
Chao Chen
CRCatalina Raymond
Catalina Raymond
WSWilliam Speier
William Speier
XJXinyu Jin
Xinyu Jin
TCTimothy F. Cloughesy
Timothy F. Cloughesy
CACorey W. Arnold
Corey W. Arnold
Objective: Gadolinium-based contrast agents (GBCAs) have been widely used to better visualize disease in brain magnetic resonance imaging (MRI). However, gadolinium deposition within the brain and body has raised safety concerns about the use of GBCAs. Therefore, the development of novel approaches that can decrease or even eliminate GBCA exposure while providing similar contrast information would be of significant use clinically. Methods: In this work, we present a deep learning based approach for contrast-enhanced T1 synthesis on brain tumor patients. A 3D high-resolution fully convolutional network (FCN), which maintains high resolution information through processing and aggregates multi-scale information in parallel, is designed to map pre-contrast MRI sequences to contrast-enhanced MRI sequences. Specifically, three pre-contrast MRI sequences, T1, T2 and apparent diffusion coefficient map (ADC), are utilized as inputs and the post-contrast T1 sequences are utilized as target output. To alleviate the data imbalance problem between normal tissues and the tumor regions, we introduce a local loss to improve the contribution of the tumor regions, which leads to better enhancement results on tumors. Results: Extensive quantitative and visual assessments are performed, with our proposed model achieving a PSNR of 28.24 dB in the brain and 21.2 dB in tumor regions. Conclusion and Significance: Our results suggest the potential of substituting GBCAs with synthetic contrast images generated via deep learning.