Experience (see LinkedIn)

Passionate about using new technology to help patients access care at Assort Health.

Honors and Awards

Delta Fellow

$50,000 equity-free grant to build accessible mental health services

Gates-Cambridge Scholar Elect, Gates-Cambridge Trust [Press]

One of 90 students (1% of applicants) internationally elected for Gates-Cambridge scholarship to pursue a PhD in Computer Science. Additionally offered NIH Oxford Cambridge MD-PhD scholarship to cover medical school

J.E. Wallace Sterling Award for Scholastic Achievement, Dean of H&S

Awarded to top 25 students of each year’s graduating class

Phi Beta Kappa

1 of 32 juniors elected for the Phi Beta Kappa nomination at Stanford

President’s Award for Excellence in the Freshman Year, Stanford University Office of the President

Honors the top 3% of undergraduates at Stanford University

2nd Place Individual, Minnesota Mathematics League Championship

2nd Place National Tournament, Science Olympiad

AIME Qualifier, Mathematics Association of America

Publications [Google Scholar]

Effect of Mailed Fecal Immunochemical Test Outreach for Patients Newly Eligible for Colorectal Cancer Screening
Shohei Burns, Jon Wang, & Ma Somsouk
Digestive Diseases and Sciences. Mar 2023.

Nurturing diversity and inclusion in AI in Biomedicine through a virtual summer program for high school students
Oskotsky T, Bajaj R, Burchard J, Cavazos T, Chen I, Connell W, Eaneff S, Grant T, Kanungo I, Lindquist K, Myers-Turnbull D, Naing ZZC, Tang A, Vora B, Wang J, Karim I, Swadling C, Yang J, AI4ALL Student Cohort 2020, Lindstaedt B, Sirota M, Connell WT
PLoS Comput Biol. Jan 2022.

Health Equity in Artificial Intelligence and Primary Care Research: Protocol for a Scoping Review
Jonathan Xin Wang’, Sulaiman Somani’, Jonathan H Chen, Sara Murray, Urmimala Sarkar
JMIR Res Protoc. Sep 2021.

Utilizing a Novel Unified Healthcare Model to Compare Practice Patterns Between Telemedicine and In-Person Visits
Justin Gregory Norden’, Jonathan X Wang’, Sumbul A. Desai, Lauren Cheung
Digital Health. August 2020.

ClinicNet: machine learning for personalized clinical order set recommendations
Jonathan X Wang’, Delaney K Sullivan’, Alex C Wells, Jonathan H Chen
JAMIA Open

Neural Networks for Clinical Order Decision Support
JX Wang, DK Sullivan, AJ Wells, AC Wells, JH Chen (equal contributors)
AMIA Summits on Translational Science Proceedings 2019, 315

Healthcare Service Utilization under a New Virtual Primary Care Delivery Model
Lauren Cheung, Tiffany I. Leung, Victoria Y. Ding, Jonathan X. Wang, Justin Norden, Manisha Desai, Robert A. Harrington, and Sumbul Desai
Telemedicine and e-Health, 2018

Non Peer-Reviewed:

The Role of Macrophages in Tumor Cell Recurrence Following Radiation Therapy
Wang, Jonathan X and Graves, Edward and Feldman, Marcus.
Stanford Digital Repository, 2019. (Stanford Undergraduate Honors Thesis)

DeepSign: Efficient Siamese Convolutional Neural Networks for Signature Verification
Jonathan X Wang’, Kevin Ko

DeepDoc: Natural Language Processing with Deep Neural Networks for the American Board of Internal Medicine Certification Exam
Jonathan X Wang’, Britni Chau’, Kinbert Chou’, Jonathan H Chen’

Deep Vein Thrombosis Screening with Three-Dimensional Deep Learning on Lower Extremity Computed Tomography Studies
Jonathan X Wang’, Brianna Kozemzak’, Anoop Manjunath’, Trevor Tsue’, Andre Souffrant, and Lawrence Hoffman

Machine Learning for Automated Classification of Patient Cases
Jonathan X Wang’, Cole Deisseroth’, James Bai’, Jonathan H Chen’


‘ = equal contributors

Projects

DeepSign: Efficient Siamese Convolutional Neural Networks for Signature Verification [Demo] [Paper] [Poster]

Jonathan X Wang, Kevin Ko (equal contributors)
We develop a deep learning algorithm that performs handwritten signature verification. We created our own SqueezeNet-inspired efficient siamese convolutional neural network architecture, DeepSign, that uses 65% fewer parameters than Google’s MobileNetv2 and 97% fewer parameters than the current state of the art, SigNet, while acheiving similar if not better performance. We test our models on both the CEDAR and BHSig260 datasets and demonstrate that our model outperforms both models in all evaluation metrics (accuracy: 0.85, precision: 0.76, recall: 0.84, AUROC: 0.93). This lightweight model is readily applicable to mobile devices for both online or offline signature verification.

DeepSign is integrated into a React web app so that viewers can demo and test their own signatures against the model.

DeepDoc: Natural Language Processing with Deep Neural Networks for the American Board of Internal Medicine Certification Exam [Paper] [Poster]

Jonathan X Wang, Britni Chau, Kinbert Chou, Jonathan H Chen (equal contributors)
We train a model to answer review questions for the American Board of Internal Medicine Certification Exam. We adapt approaches traditionally used for question answer tasks to our multiple choice exam, as well as experiment with the following enhancements: PubMed Embeddings, BiDAF, DrQA, SAR, GA, and RACE. Ultimately we find that GA models perform best (Accuracy: 0.38, AUROC: 0.64). Our work is an initial study towards the development of a intelligent medical QA system, demonstrating the capability of modern day machine learning to answer questions clinicians typically take many years to study for.

UVify: A simple, non-disruptive far UV-c light stethoscope sterilization device [Hong Kong Economic Journal] [SingTao Daily] [Money Talk HK Podcast (32:28-43:20)]

Jonathan X Wang, Mashiat Lamisa, Jasmine Poon, Xuelai Wei, Sik Kwan Chan (equal contributors)
As part of the Dreamcatchers MedTech Hackathon, we shadow physicians in the Hong Kong hospitals and use the BioDesign curriculum to search for problems in patient care. We discover a central issue where physicians were not consistently sterilizing their own stethoscopes, leading to hospital acquired infections. We develop a sterilization device using far UV-c light to automatically sterilize stethoscopes for physicians during their daily routine checkups.

  • 2019 Dreamcatchers MedTech Hackathon Champion

Deep Vein Thrombosis Screening with Three-Dimensional Deep Learning on Lower Extremity Computed Tomography Studies [Paper]

Jonathan X Wang*, Brianna Kozemzak*, Anoop Manjunath*, Trevor Tsue*, Andre Souffrant, and Lawrence Hoffman (*equal contributors)
Recent advances in deep neural networks (DNNs) allow us to leverage spatial dependencies between slices in imaging studies to identify false positives and ultimately deploy DNN systems that lighten physicians’ workloads while not exacerbating alarm fatigue. To train our DNN, we have acquired 119 lower-body CT imaging studies labeled by radiologists for DVT at the pixel level. Using these studies, we have developed a DNN-based CAD system that will (1) segment targeted deep veins in a CT slice, (2) classify whether a DVT is present within multiple slices given segmentations of deep veins, and (3) evaluate different deep learning approaches for handling 3D datasets for DVT detection. For segmentation, we use a 2D U-Net, 2D VGG encoder-decoder, and 3D U-Net and find that VGG performs best (Dice: 0.07, IoU: 0.48, AUROC: 0.78). For classification, we use a 2D ResNet, CNN-RNN, and 3D Inception model with and without segmentation masks. We find that our CNN-RNN without masks performs best in AUROC (Average Precision: 0.31, AUROC 0.64) and 3D Inception with masks performs best in average precision (Average Precision: 0.33, AUROC: 0.62). By developing more effective detection algorithms, we hope to ensure more frequent and accurate diagnosis of DVT, thereby reducing its high mortality rate.

Automated Electronic Calculator for Management of DKA/HHS [Poster]

Sara Choi, Madeline Grade, Jonathan X Wang, Lawrence Cai, Julie Chen
Surveyed 73 staff members to develop DKA software estimated to save $78,000 a year and reduce readmissions by 45%. Currently implemented in Stanford Hospital and integrated into the hospital’s health record system along with educational video.

  • Awarded best poster at Resident & Fellow Quality Improvement & Patient Safety Symposium

Machine Learning for Automated Classification of Patient Cases [Paper][Poster]

Jonathan X Wang, Cole Deisseroth, James Bai, Jonathan H Chen (equal contributors)
This is an initial study toward the development of an intelligent patient-allocation system to save medical personnel valuable time, and help patients find the care they need more efficiently by automatically categorizing cases into specific departments. We develop an algorithm which predicts the categories of patient cases from the American Board of Internal Medicine Examinations—a certification that all physicians must go through to practice general medicine. Our ontology breaks questions into their components (Case, AnswerChoice, Explanation). We then run an automatic concept extractor (ClinPhen) on the passage (description of the case) to compile a list of concepts (words, phenotypes, and phenotype closures). We then use a Naïve Bayes classifier to take the concepts and predict the category of the case. We have developed a classifier that predicts the category of a patient case correctly 80.5% of the time, and has over 80% precision and recall. Future work will include developing more-sophisticated techniques of leveraging up-to-date knowledge graphs, and building our own graphs to categorize these cases. Ultimately, this classifier should become applicable in clinical settings (and not just for medical board cases), and be able to accurately suggest a department to send a patient to.

Writing

Subscribe for updates here: https://jonwang.substack.com/

“Leaving Shimmer & how I figured out what was next”, Aug 25, 2022

“Reflections and learnings from a medical school student turned founder”, Jan 25, 2022

“Why I Left UCSF Medical School (for now)”, Feb 2, 2021

“Fighting Global Health Disparities with AI w/ Jon Wang”, Nov 9, 2020
TWIML AI Podcast

“Choosing your life’s work”, July 1, 2019

“What End-of-Life Care Taught Me About Medicine Beyond Medication”, May 17, 2019

Talks

Panel Speaker. Startup Grind Student Entrepreneurship Conference. 3/22.

My Startup Journey. UCSF Launchpad Startup Weekend Keynote. 8/21.

Wang J, Lamisa M, Poon J, Wei X. UVify: A simple, non-disruptive far UV-c light stethoscope sterilization device. 2019 Dreamcatchers MedTech Hackathon. 7/19. [Hong Kong Economic Journal] [SingTao Daily] [Money Talk HK Podcast (32:28-43:20)]

Delaney S, Wang J…Chen J. Neural Networks for Clinical Order Decision Support. 2019 AMIA Informatics Summit.3/19.

Wang J, Kaufman G, Ramos A. Deep Neural Networks and Cluster Analysis for Patient Phenotyping. Apple. 8/18

Wang J, et al. AI-enabled Mobile Optometry. Bay area global health innovation challenge. 5/18.

Sole J, Wang J…Girod S. OR Teams and Communication. Anesthesia Grand Rounds. 8/16.

Wang J, Yonghun K, Periyakoil VJ. Empathy and Patient Care Improvement for Asian Americans. Palliative Medicine, Hospice, and End of Life Care. 12/16.

Poster Sessions

Clark D. Wang ; William Zhang ; Jonathan Wang ; Julian C. Hong. Network analysis to characterize chronological relationships in comorbidity trajectories: breast cancer as a case model. 2019 AMIA Informatics Summit. [Poster]

Wang J, Ko K. DeepSign: Efficient Siamese Convolutional Neural Networks for Signature Verification. Convolutional Neural Networks for Visual Recognition. 6/19. [Demo] [Paper] [Poster]

Wang J, Chau O, Chou K. DeepDoc: Natural Language Processing with Deep Neural Networks for the American Board of Internal Medicine Certification Exam. Stanford Natural Language Processing with Deep Learning Poster Session. 3/19.[Paper] [Poster]

Wang J, Deisseroth C, Bai J, Chen J. Machine Learning for Automated Classification of Patient Cases. 3/19 [Paper][Poster]

Wang J…Chen J. Automated Clinical Decision Support and Patient Progression Prediction through Deep Neural Networks. Stanford Deep Learning Poster Session. 3/18.

Wang J…Graves E. Effects of Tumor Irradiation on Circulating Macrophage Localization. Stanford Bio-X Symposium. 8/17.

Choi S, Grade M, Wang J, Chen J. Automated Electronic Calculator for Management of DKA/HHS. Stanford Resident & Fellow Quality Improvement & Patient Safety Symposium. 5/17.