arXiv subjects

Amelia Fiske

Publications and source records attributed to Amelia Fiske.

5 recordsLinked to original sources

arXiv2025

The Community Index: A More Comprehensive Approach to Assessing Scholarly Impact

The h index is a widely recognized metric for assessing the research impact of scholars, defined as the maximum value h such that the scholar has published h papers each cited at least h times. While it has proven useful measuring individual scholarly productivity and citation impact, the h index has limitations, such as an inability to account for interdisciplinary collaboration or demographic differences in citation patterns. Moreover, it is sometimes mistakenly treated as a measure of research quality, even though it only reflects how often work has been cited. While metric based evaluations of research have grown in importance in some areas of academia, such as medicine, these evaluations fail to consider other important aspects of intellectual work, such as representational and epistemic diversity in research. In this article, we propose a new metric called the c index, or the community index, which combines multiple dimensions of scholarly impact. This is important because a plurality of perspectives and lived experiences within author teams can promote epistemological reflection and humility as part of the creation and validation of scientific knowledge. The c index is a means of accounting for the often global, and increasingly interdisciplinary nature of contemporary research, in particular, the data that is collected, curated and analyzed in the process of scientific inquiry. While the c index provides a means of quantifying diversity within research teams, diversity is integral to the advancement of scientific excellence and should be actively fostered through formal recognition and valuation. We herein describe the mathematical foundation of the c index and demonstrate its potential to provide a more comprehensive representation and more multidimensional assessment of scientific contributions of research impact as compared to the h index.

cs.DL↗

arXiv2025

The Power of Data Communities

Datasets together with active scientific communities prepared to leverage them can contribute to scientific progress and facilitate making research more equitable. In this study we found that MIMIC, despite its limited amount of funding, managed to provide higher impact per dollar spent through accessible data communities. These findings support the notion that making clinical data available empowers innovation which directly addresses clinical concerns and can set new standards for inclusivity.

cs.DL↗

arXiv2025

M3: Conversational LLMs Simplify Secure Clinical Data Access, Understanding, and Analysis

Large-scale clinical databases offer opportunities for medical research, but their complexity creates barriers to effective use. The Medical Information Mart for Intensive Care (MIMIC-IV), one of the world's largest open-source electronic health record databases, traditionally requires both SQL proficiency and clinical domain expertise. We introduce M3, a system that enables natural language querying of MIMIC-IV data through the Model Context Protocol. With a single command, M3 retrieves MIMIC-IV from PhysioNet, launches a local SQLite instance or connects to hosted BigQuery, and allows researchers to pose clinical questions in plain English. We evaluated M3 using samples from the EHRSQL 2024 benchmark with two language models. On one hundred answerable questions, the proprietary Claude Sonnet 4 achieved 94% accuracy and the open-weights gpt-oss-20B (deployable locally on consumer hardware) achieved 93%; on a matched sample of one hundred unanswerable questions, where correct behavior is to abstain rather than produce SQL, gpt-oss-20B correctly abstained on 69%. Both models translate natural language into SQL, execute queries against MIMIC-IV, and return structured results alongside the underlying query for verification. Error analysis revealed that most failures stemmed from complex temporal reasoning or ambiguous question phrasing rather than fundamental architectural limitations. The comparable performance of a smaller open-weights model demonstrates that privacy-preserving local deployment is viable for sensitive clinical data analysis. M3 lowers technical barriers to critical care data analysis and is designed with security measures including OAuth2 authentication, query validation, and audit logging.

cs.IR↗

arXiv2025

An Algorithmic Approach for Causal Health Equity: A Look at Race Differentials in Intensive Care Unit (ICU) Outcomes

The new era of large-scale data collection and analysis presents an opportunity for diagnosing and understanding the causes of health inequities. In this study, we describe a framework for systematically analyzing health disparities using causal inference. The framework is illustrated by investigating racial and ethnic disparities in intensive care unit (ICU) outcome between majority and minority groups in Australia (Indigenous vs. Non-Indigenous) and the United States (African-American vs. White). We demonstrate that commonly used statistical measures for quantifying inequity are insufficient, and focus on attributing the observed disparity to the causal mechanisms that generate it. We find that minority patients are younger at admission, have worse chronic health, are more likely to be admitted for urgent and non-elective reasons, and have higher illness severity. At the same time, however, we find a protective direct effect of belonging to a minority group, with minority patients showing improved survival compared to their majority counterparts, with all other variables kept equal. We demonstrate that this protective effect is related to the increased probability of being admitted to ICU, with minority patients having an increased risk of ICU admission. We also find that minority patients, while showing improved survival, are more likely to be readmitted to ICU. Thus, due to worse access to primary health care, minority patients are more likely to end up in ICU for preventable conditions, causing a reduction in the mortality rates and creating an effect that appears to be protective. Since the baseline risk of ICU admission may serve as proxy for lack of access to primary care, we developed the Indigenous Intensive Care Equity (IICE) Radar, a monitoring system for tracking the over-utilization of ICU resources by the Indigenous population of Australia across geographical areas.

cs.LG↗

arXiv2024

Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias

Large language models (LLMs) are increasingly essential in processing natural languages, yet their application is frequently compromised by biases and inaccuracies originating in their training data. In this study, we introduce Cross-Care, the first benchmark framework dedicated to assessing biases and real world knowledge in LLMs, specifically focusing on the representation of disease prevalence across diverse demographic groups. We systematically evaluate how demographic biases embedded in pre-training corpora like $ThePile$ influence the outputs of LLMs. We expose and quantify discrepancies by juxtaposing these biases against actual disease prevalences in various U.S. demographic groups. Our results highlight substantial misalignment between LLM representation of disease prevalence and real disease prevalence rates across demographic subgroups, indicating a pronounced risk of bias propagation and a lack of real-world grounding for medical applications of LLMs. Furthermore, we observe that various alignment methods minimally resolve inconsistencies in the models' representation of disease prevalence across different languages. For further exploration and analysis, we make all data and a data visualization tool available at: www.crosscare.net.

cs.CL↗