Alexander David VanHelene
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Alexander David VanHelene has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jeremy Lyle Warner
Legorreta Cancer Center, Brown University, Providence, RI
3 shared publications - Cameron Beau Hilton
Affiliation Department of Internal Medicine, Vanderbilt University, Nashville, Tennessee, United States of America
2 shared publications Ece D. Gamsiz Uzun
Affiliations Center for Clinical Cancer Informatics and Data Science, Legorreta Cancer Center, Brown University, Providence, Rhode Island, Warren Alpert Medical School, Brown University, Providence, Rhode Island, United States of America, Center for Computational Molecular Biology, Brown University, Providence, Rhode Island, United States of America, Department of Pathology and Laboratory Medicine, Brown University, Providence, Rhode Island, United States of America
2 shared publicationsIshaani Khatri
Affiliation Warren Alpert Medical School, Brown University, Providence, Rhode Island, United States of America
2 shared publications- Sanjay Mishra
Brown University 11 Center for Clinical Cancer Informatics and Data Science, Legorreta Cancer Center Providence, Rhode Island
2 shared publications - Amelie G. Ramirez
Department of Population Health Sciences, Institute for Health Promotion Research, Long School of Medicine, Mays Cancer Center, University of Texas Health Science Center at San Antonio , San Antonio, TX
1 shared publication
Latest Publications
- Open Access
- 24 December 2024
- Published by Taylor & Francis in Preventive Oncology & Epidemiology
- Vol. 3 (1)
CancerClarity app: Enhancing cancer data visualization with AI-generated narratives
Community cancer centers face challenges in accessing cancer data and communicating health information to patients and community members due to limited tools and resources. The CancerClarity app, recognized at the 2023 Catchment Area Data Conference Hackathon, addresses this need by integrating data visualization with Artificial intelligence (AI)-driven narrative generation. Converting quantitative cancer statistics to narrative descriptions using large language models (LLMs) may help cancer centers communicate complex cancer data more effectively to diverse stakeholders. The CancerClarity app employs LLM prompting within the R Shiny web framework, sourcing data from Cancer InFocus. It offers users an interactive exploration of cancer incidence, mortality, and health determinants across U.S. counties. The CancerClarity app integrates LLM via its application programming interface (API) for real-time, linguistically tailored narratives, making cancer data accessible to a broad audience. The app offers cancer centers a cost-effective solution to swiftly identify their catchment areas and assess the cancer burden within the populations they serve. By enhancing public health decision-making through AI-driven narratives, the app underscores the critical role of effective communication in public health. Future enhancements include the integration of Retrieval Augmented Generation (RAG) for improved AI responses and evidence-based public health guidance.
- 24 December 2024
- Published by Taylor & Francis in Preventive Oncology & Epidemiology
- Vol. 3 (1)
Open AccessCancerClarity app: Enhancing cancer data visualization with AI-generated narratives
Community cancer centers face challenges in accessing cancer data and communicating health information to patients and community members due to limited tools and resources. The CancerClarity app, recognized at the 2023 Catchment Area Data Conference Hackathon, addresses this need by integrating data visualization with Artificial intelligence (AI)-driven narrative generation. Converting quantitative cancer statistics to narrative descriptions using large language models (LLMs) may help cancer centers communicate complex cancer data more effectively to diverse stakeholders. The CancerClarity app employs LLM prompting within the R Shiny web framework, sourcing data from Cancer InFocus. It offers users an interactive exploration of cancer incidence, mortality, and health determinants across U.S. counties. The CancerClarity app integrates LLM via its application programming interface (API) for real-time, linguistically tailored narratives, making cancer data accessible to a broad audience. The app offers cancer centers a cost-effective solution to swiftly identify their catchment areas and assess the cancer burden within the populations they serve. By enhancing public health decision-making through AI-driven narratives, the app underscores the critical role of effective communication in public health. Future enhancements include the integration of Retrieval Augmented Generation (RAG) for improved AI responses and evidence-based public health guidance.
- Top Cited PapersOpen Access
- 29 October 2024
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 3 (10) , e0000456
Inferring gender from first names: Comparing the accuracy of Genderize, Gender API, and the gender R package on authors of diverse nationality
Meta-researchers commonly leverage tools that infer gender from first names, especially when studying gender disparities. However, tools vary in their accuracy, ease of use, and cost. The objective of this study was to compare the accuracy and cost of the commercial software Genderize and Gender API, and the open-source gender R package. Differences in binary gender prediction accuracy between the three services were evaluated. Gender prediction accuracy was tested on a multi-national dataset of 32,968 gender-labeled clinical trial authors. Additionally, two datasets from previous studies with 5779 and 6131 names, respectively, were re-evaluated with modern implementations of Genderize and Gender API. The gender inference accuracy of Genderize and Gender API were compared, both with and without supplying trialists’ country of origin in the API call. The accuracy of the gender R package was only evaluated without supplying countries of origin. The accuracy of Genderize, Gender API, and the gender R package were defined as the percentage of correct gender predictions. Accuracy differences between methods were evaluated using McNemar’s test. Genderize and Gender API demonstrated 96.6% and 96.1% accuracy, respectively, when countries of origin were not supplied in the API calls. Genderize and Gender API achieved the highest accuracy when predicting the gender of German authors with accuracies greater than 98%. Genderize and Gender API were least accurate with South Korean, Chinese, Singaporean, and Taiwanese authors, demonstrating below 82% accuracy. Genderize can provide similar accuracy to Gender API while being 4.85x less expensive. The gender R package achieved below 86% accuracy on the full dataset. In the replication studies, Genderize and gender API demonstrated better performance than in the original publications. Our results indicate that Genderize and Gender API achieve similar accuracy on a multinational dataset. The gender R package is uniformly less accurate than Genderize and Gender API.
- 29 October 2024
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 3 (10) , e0000456
Top Cited PapersOpen AccessInferring gender from first names: Comparing the accuracy of Genderize, Gender API, and the gender R package on authors of diverse nationality
Meta-researchers commonly leverage tools that infer gender from first names, especially when studying gender disparities. However, tools vary in their accuracy, ease of use, and cost. The objective of this study was to compare the accuracy and cost of the commercial software Genderize and Gender API, and the open-source gender R package. Differences in binary gender prediction accuracy between the three services were evaluated. Gender prediction accuracy was tested on a multi-national dataset of 32,968 gender-labeled clinical trial authors. Additionally, two datasets from previous studies with 5779 and 6131 names, respectively, were re-evaluated with modern implementations of Genderize and Gender API. The gender inference accuracy of Genderize and Gender API were compared, both with and without supplying trialists’ country of origin in the API call. The accuracy of the gender R package was only evaluated without supplying countries of origin. The accuracy of Genderize, Gender API, and the gender R package were defined as the percentage of correct gender predictions. Accuracy differences between methods were evaluated using McNemar’s test. Genderize and Gender API demonstrated 96.6% and 96.1% accuracy, respectively, when countries of origin were not supplied in the API calls. Genderize and Gender API achieved the highest accuracy when predicting the gender of German authors with accuracies greater than 98%. Genderize and Gender API were least accurate with South Korean, Chinese, Singaporean, and Taiwanese authors, demonstrating below 82% accuracy. Genderize can provide similar accuracy to Gender API while being 4.85x less expensive. The gender R package achieved below 86% accuracy on the full dataset. In the replication studies, Genderize and gender API demonstrated better performance than in the original publications. Our results indicate that Genderize and Gender API achieve similar accuracy on a multinational dataset. The gender R package is uniformly less accurate than Genderize and Gender API.
- Open Access
- 14 August 2024
- Published by BMJ in BMJ Oncology
- Vol. 3 (1) , e000410
As bleak as it sounds? Analysing trends in oncology clinical trial initiation in the UK from 2010 to 2022
Objectives: The UK’s withdrawal from the European Union (a political movement known as ‘Brexit’) incited concern both in the public and private sector about the future of drug development and the clinical trial landscape in the UK. This study evaluates trends in the initiation of phase III clinical trials that evaluated systemic anticancer treatments from 2010 to 2022 both in the UK and worldwide. Methods and analysis: Relevant clinical trials were identified through ClinicalTrials.gov. Initiation date in each country was defined as the date that a study’s record was updated to include a recruiting site in the country of interest. Concurrent clinical site counts were defined as the number of facilities that contemporaneously hosted trials. Temporal trends in trial initiation and site counts were evaluated. Results: Our analysis uncovered a worldwide increase in clinical trial initiation from 2013 to 2019. The UK experienced a decrease in clinical trial initiation immediately post-Brexit in 2020 but rebounded in 2021. The UK’s resurgence in clinical trials in 2021 was driven predominately by industry-funded trials. Other countries saw a similar increase in clinical trial initiation from 2020 to 2021. Conclusions: The UK’s trends in phase III oncology clinical trial initiation from 2010 to 2022 largely reflects global trends, suggesting that other factors (eg, COVID-19 pandemic) beyond Brexit, may have had a stronger influence on clinical trial initiation within the UK.
- 14 August 2024
- Published by BMJ in BMJ Oncology
- Vol. 3 (1) , e000410
Open AccessAs bleak as it sounds? Analysing trends in oncology clinical trial initiation in the UK from 2010 to 2022
Objectives: The UK’s withdrawal from the European Union (a political movement known as ‘Brexit’) incited concern both in the public and private sector about the future of drug development and the clinical trial landscape in the UK. This study evaluates trends in the initiation of phase III clinical trials that evaluated systemic anticancer treatments from 2010 to 2022 both in the UK and worldwide. Methods and analysis: Relevant clinical trials were identified through ClinicalTrials.gov. Initiation date in each country was defined as the date that a study’s record was updated to include a recruiting site in the country of interest. Concurrent clinical site counts were defined as the number of facilities that contemporaneously hosted trials. Temporal trends in trial initiation and site counts were evaluated. Results: Our analysis uncovered a worldwide increase in clinical trial initiation from 2013 to 2019. The UK experienced a decrease in clinical trial initiation immediately post-Brexit in 2020 but rebounded in 2021. The UK’s resurgence in clinical trials in 2021 was driven predominately by industry-funded trials. Other countries saw a similar increase in clinical trial initiation from 2020 to 2021. Conclusions: The UK’s trends in phase III oncology clinical trial initiation from 2010 to 2022 largely reflects global trends, suggesting that other factors (eg, COVID-19 pandemic) beyond Brexit, may have had a stronger influence on clinical trial initiation within the UK.
- Open Access
Inferring Gender from First Names: Comparing the Accuracy of Genderize, Gender API, and the gender R Package on Authors of Diverse Nationality
Meta-researchers commonly leverage tools that infer gender from first names, especially when studying gender disparities. However, tools vary in their accuracy, ease of use, and cost. The objective of this study was to compare the accuracy and cost of the commercial software Genderize and Gender API, and the open-source gender R package. Differences in binary gender prediction accuracy between the three services were evaluated. Gender prediction accuracy was tested on a multi-national dataset of 32,968 gender-labeled clinical trial authors. Additionally, two datasets from previous studies with 5779 and 6131 names, respectively, were re-evaluated with modern implementations of Genderize and Gender API. The gender inference accuracy of Genderize and Gender API were compared, both with and without supplying trialists’ country of origin in the API call. The accuracy of the gender R package was only evaluated without supplying countries of origin since. The accuracy of Genderize, Gender API, and the gender R package were defined as the percentage of correct gender predictions. Accuracy differences between methods were evaluated using McNemar’s test. Genderize and Gender API demonstrated overall 96.6% and 96.1% accuracy, respectively, when countries of origin were not supplied in the API calls. Genderize and Gender API achieved the highest accuracy when predicting the gender of German authors with accuracies greater than 98%. Genderize and Gender API were least accurate with South Korean, Chinese, Singaporean, and Taiwanese authors, demonstrating below 82% accuracy. The gender R package achieved below 86% accuracy on the full dataset. In the replication studies, Genderize and gender API demonstrated better performance than in the original publications. Our results indicate that Genderize and Gender API are highly accurate, except when evaluating South Korean, Chinese, Singaporean, and Taiwanese names. We also demonstrated that Genderize can provide similar accuracy to Gender API while being 4.85x less expensive. Author Summary Gender disparities in academia have prompted researchers to investigate gender gaps in professorship roles and publication authorship. Of particular concern are the gender gaps in cancer clinical trial authorship. Methodologies that evaluate gender disparities in academia often rely on tools that infer gender from first names. Tools that predict gender from first names are often used in methodologies that determine the gender ratios of academic departments or publishing authors in a discipline. However, researchers must choose between different gender predicting tools that vary in their accuracy, ease of use, and cost. We evaluated the binary gender prediction accuracy of Genderize, Gender API, and the gender R package on a gold-standard dataset of 32,968 clinical trialists from around the world. Genderize and Gender API cost money to use, while the gender R package is free and open source. We found that Genderize and Gender API were more accurate than the gender R package. In addition, Genderize is cheaper than Gender API, but is more sensitive to inconsistencies in name formatting and the presence of diacritical marks. Both Genderize and Gender API were most accurate with western names.
Open AccessInferring Gender from First Names: Comparing the Accuracy of Genderize, Gender API, and the gender R Package on Authors of Diverse Nationality
Meta-researchers commonly leverage tools that infer gender from first names, especially when studying gender disparities. However, tools vary in their accuracy, ease of use, and cost. The objective of this study was to compare the accuracy and cost of the commercial software Genderize and Gender API, and the open-source gender R package. Differences in binary gender prediction accuracy between the three services were evaluated. Gender prediction accuracy was tested on a multi-national dataset of 32,968 gender-labeled clinical trial authors. Additionally, two datasets from previous studies with 5779 and 6131 names, respectively, were re-evaluated with modern implementations of Genderize and Gender API. The gender inference accuracy of Genderize and Gender API were compared, both with and without supplying trialists’ country of origin in the API call. The accuracy of the gender R package was only evaluated without supplying countries of origin since. The accuracy of Genderize, Gender API, and the gender R package were defined as the percentage of correct gender predictions. Accuracy differences between methods were evaluated using McNemar’s test. Genderize and Gender API demonstrated overall 96.6% and 96.1% accuracy, respectively, when countries of origin were not supplied in the API calls. Genderize and Gender API achieved the highest accuracy when predicting the gender of German authors with accuracies greater than 98%. Genderize and Gender API were least accurate with South Korean, Chinese, Singaporean, and Taiwanese authors, demonstrating below 82% accuracy. The gender R package achieved below 86% accuracy on the full dataset. In the replication studies, Genderize and gender API demonstrated better performance than in the original publications. Our results indicate that Genderize and Gender API are highly accurate, except when evaluating South Korean, Chinese, Singaporean, and Taiwanese names. We also demonstrated that Genderize can provide similar accuracy to Gender API while being 4.85x less expensive. Author Summary Gender disparities in academia have prompted researchers to investigate gender gaps in professorship roles and publication authorship. Of particular concern are the gender gaps in cancer clinical trial authorship. Methodologies that evaluate gender disparities in academia often rely on tools that infer gender from first names. Tools that predict gender from first names are often used in methodologies that determine the gender ratios of academic departments or publishing authors in a discipline. However, researchers must choose between different gender predicting tools that vary in their accuracy, ease of use, and cost. We evaluated the binary gender prediction accuracy of Genderize, Gender API, and the gender R package on a gold-standard dataset of 32,968 clinical trialists from around the world. Genderize and Gender API cost money to use, while the gender R package is free and open source. We found that Genderize and Gender API were more accurate than the gender R package. In addition, Genderize is cheaper than Gender API, but is more sensitive to inconsistencies in name formatting and the presence of diacritical marks. Both Genderize and Gender API were most accurate with western names.