Daniel Goldberg
· Associate Professor, Director of Undergraduate Programs, Director, TAMU GeoInnovation Service CenterVerifiedTexas A&M University · Geography
Active 1966–2025
About
Daniel Goldberg is an Associate Professor at Texas A&M University in the College of Arts and Sciences, where he also serves as the Director of Undergraduate Programs and the Director of the TAMU GeoInnovation Service Center. His research interests encompass GIS, Geocoding, GeoComputation, CyberGIS, 3D GIS, Routing, Spatial Databases, Spatial Uncertainty, Spatio-Temporal GIS, Environmental Exposure Assessment, and HealthGIS. Goldberg holds a Ph.D. in Computer Science from the University of Southern California, obtained in 2010, along with a Master's degree in Computer Science from the same institution and a Bachelor's degree from Rutgers University. He has received multiple awards including the Texas A&M University - Division of Finance and Operations Team Award for TAMU ADA GIS Routing in 2018, the Montague Scholar Award from the Center for Teaching Excellence in 2015, and the Partners in Learning Award of Excellence in 2015. Additionally, he was a CyberGIS Fellow at the National Center for Supercomputing Applications in 2014. Goldberg has contributed extensively to the field through numerous publications and book chapters, focusing on geocoding, spatial data analysis, and geographic information systems, emphasizing best practices and innovative applications in health, environment, and urban systems.
Research topics
- Computer Science
- Data Mining
- Geography
- Remote sensing
- Machine Learning
- Cartography
- Engineering
- Data science
- Biology
- Transport engineering
- Mathematics
- Statistics
- Ecology
- Telecommunications
Selected publications
Journal of Vascular and Interventional Radiology · 2025-02-19
articleOpen accessImproving Employee Turnover Intention: Outsourced Human Resources vs. In-house Human Resources
Engaged Management ReView · 2025-05-01
articleOpen accessSenior authorSmall business research has neglected comparing employees’ perceptions on variables related to in-house human resources (HRI) vs. outsourced human resources (HRO) in small businesses. We used a mixed methods research design to study this issue. The first study consisted of 11 in-depth interviews. The qualitative insights we gained helped to guide survey construction for the second quantitative survey-based study. For the survey, 101 HRI U.S. employees and 97 HRO U.S. employees filled out a survey. Results from the HRI and HRO samples were equivalent in terms of participants’ years of work experience, work schedule, gender, company size, company age, perceived timely HR response to a concern/issue, average HR response time, and turnover intention. However, the HRO sample had higher perceived employee engagement and organizational culture (OC). Subsequent hierarchical regression analyses comparing the two samples showed that although OC was a common correlate for explaining the outcome of turnover intention in both samples, employee engagement, timely HR response, and average HR response time were significant correlates of turnover intention only for the HRI sample.
Journal of Vascular and Interventional Radiology · 2025-02-19
articleOpen accessJournal of Vascular and Interventional Radiology · 2025-02-19
articleJournal of Vascular and Interventional Radiology · 2025-02-19
reviewAbstract No. 124 Sequelae of Splenic Embolization by Age: A Retrospective Analysis
Journal of Vascular and Interventional Radiology · 2024-02-21
articleOpen accessJournal of Vascular and Interventional Radiology · 2024-10-30 · 3 citations
articleJournal of Vascular and Interventional Radiology · 2024-02-21
articleOpen access47: ENDOCRINE EMERGENCIES IN IMMUNE CHECKPOINT INHIBITOR THERAPY FOR LUNG CANCER
Critical Care Medicine · 2023-12-14
articleIntroduction: Since the introduction of nivolumab in 2015 for the treatment of non-small cell lung cancer (NSCLC), four other immune checkpoint inhibitors (ICI) have gained FDA approval in advanced stage lung cancer. While efficacious, ICIs can lead to several immune related adverse events (irAEs) attributed to T cell dysfunction. Endocrinopathies account for up to 10% of irAEs. We aimed to characterize endocrine irAEs related to ICI use in patients with NSCLC using a national, multicenter cohort. Methods: Querying the TriNetX database, an aggregator of approximately 98 million patient records drawn from electronic chart and claim-derived data from across the U.S., we assessed patients with ICD-10-CM diagnostic codes for lung cancer between 03/2015 and 06/2022 who received approved ICI therapies. Establishing a propensity-matched control group (accounting for 19 demographic and comorbidity variables) with lung cancer patients who did not receive ICIs, we then examined the 1-year incidence of endocrine irAE diagnoses, including thyrotoxicosis (TT), hypothyroidism (HT), diabetic ketoacidosis (DKA), adrenal insufficiency (AI), and hypophysitis. Patients with antecedent diagnoses of the relevant outcomes were excluded from analysis. Results: Of the 97,891,305 patients in the database, 322,246 (0.3%) were diagnosed with lung cancer in the specified time period, of whom 32,087 received ICI therapy. Following propensity matching, the ICI-receiving lung cancer group had a significantly higher 1-year risk of TT (2.4% vs 0.6%, OR 3.8, CI 3.3 – 4.5), as well as HT (12.7% vs 2.8%, OR 4.9, CI 4.5 – 5.3), DKA (0.4% vs 0.2%, OR 1.5, CI 1.2 – 2.1), AI (2.8% vs 0.5%, OR 5.5, CI 4.7 – 6.5), and hypophysitis (1.1% vs 0.1%, OR 7.4, CI 5.4 – 10.0). For all associations, p-value < 0.01. Conclusions: Lung cancer patients who received ICI therapy since 2015 had markedly increased rates of endocrine irAEs than non-ICI treated patients, especially hypophysitis and adrenal insufficiency. Clinicians caring for patients with lung cancer receiving ICIs should be cognizant of the broad spectrum of endocrine irAEs to facilitate prompt work-up and timely management.
Is ChatGPT a game changer for geocoding - a benchmark for geocoding address parsing techniques
2023-11-13 · 12 citations
articleOpen accessSenior authorThe remarkable success of GPT models across various tasks, including toponymy recognition motivates us to assess the performance of the GPT-3 model in the geocoding address parsing task. To ensure that the evaluation more accurately mirrors performance in real-world scenarios with diverse user input qualities and resolve the pressing need for a `gold standard' evaluation dataset for geocoding systems, we introduce a benchmark dataset of low-quality address descriptions synthesized based on human input patterns mining from actual input logs of a geocoding system in production. This dataset has 21 different input errors and variations; contains over 239,000 address records that are uniquely selected from streets across all U.S. 50 states and D.C.; and consists of three subsets to be used as training, validation, and testing sets. Building on this, we train and gauge the performance of the GPT-3 model in extracting address components, contrasting its performance with transformer-based and LSTM-based models. The evaluation results indicate that Bidirectional LSTM-CRF model has achieved the best performance over these transformer-based models and GPT-3 model. Transformer-based models demonstrate very comparable results compared to the Bidirectional LSTM-CRF model. The GPT-3 model, though trailing in performance, showcases potential in the address parsing task with few-shot examples, exhibiting room for improvement with additional fine-tuning. We open source the code and data of this presented benchmark1 so that researchers can utilize it for future model development or extend it to evaluate similar tasks, such as document geocoding.
Recent grants
REU Site: Cyber-HealthGIS - Multidisciplinary Research Experiences in Spatial Dynamics of Health
NSF · $368k · 2016–2020
NIH · $16k · 2012
Frequent coauthors
- 24 shared
Tracy Hammond
Mitchell Institute
- 18 shared
Andrew Curtis
Case Western Reserve University
- 17 shared
James Muisyo
University Health System
- 17 shared
Jayakrishnan Ajayakumar
Case Western Reserve University
- 17 shared
Andrew Curtis
Case Western Reserve University
- 17 shared
Sarah Mihalik
University Health System
- 17 shared
Zachary Scott
University Health System
- 17 shared
Justin Yax
Mitchell Institute
Awards & honors
- Texas A&M University - Division of Finance and Operations Te…
- Texas A&M University - Center for Teaching Excellence, Monta…
- Texas A&M University - Partners in Learning Award of Excelle…
- National Center for Supercomputing Applications - CyberGIS F…
- Resume-aware match score
- Save to shortlist
- AI-drafted outreach
See your match with Daniel Goldberg
PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.
- Free to start
- No credit card
- 30-second signup