Artificial Creative Societies: Adaption, Intention, and Evaluation

Peeperkorn, Max

doi:10.1145/3527927.3533728

Cited by 3 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LLMs are inherently non-deterministic due to the probabilistic nature of their architecture 12 . Despite this, we found that DxGPT demonstrated minimal response inconsistencies among replicates, highlighting its robustness.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of the Clinical Utility of DxGPT, a GPT-4 Based Large Language Model, through an Analysis of Diagnostic Accuracy and User Experience

Alvarez-Estape,

Cano,

Pino

et al. 2024

Preprint

View full text Add to dashboard Cite

ImportanceThe time to accurately diagnose rare pediatric diseases often spans years. Assessing the diagnostic accuracy of an LLM-based tool on real pediatric cases can help reduce this time, providing quicker diagnoses for patients and their families.ObjectiveTo evaluate the clinical utility of DxGPT as a support tool for differential diagnosis of both common and rare diseases.DesignUnicentric descriptive cross-sectional exploratory study. Anonymized data from 50 pediatric patients' medical histories, covering common and rare pathologies, were used to generate clinical case notes. Each clinical case included essential data, with some expanded by complementary tests.SettingThis study was conducted at a reference pediatric hospital, Sant Joan de Déu Barcelona Children′s Hospital.ParticipantsA total of 50 clinical cases were diagnosed by 78 volunteer doctors (medical diagnostic team) with varying experience, each reviewing 3 clinical cases.InterventionsEach clinician listed up to five diagnoses per clinical case note. The same was done on the DxGPT web platform, obtaining the Top-5 diagnostic proposals. To evaluate DxGPT's variability, each note was queried three times.Main Outcome(s) and Measure(s)The study mainly focused on comparing diagnostic accuracy, defined as the percentage of cases with the correct diagnosis, between the medical diagnostic team and DxGPT. Other evaluation criteria included qualitative assessments. The medical diagnostic team also completed a survey on their user experience with DxGPT.ResultsTop-5 diagnostic accuracy was 65% for clinicians and 60% for DxGPT, with no significant differences. Accuracies for common diseases were higher (Clinicians: 79%, DxGPT: 71%) than for rare diseases (Clinicians: 50%, DxGPT: 49%). Accuracy increased similarly in both groups with expanded information, but this increase was only stastically significant in clinicians (simple 52% vs. expanded 69%; p=0.03). DxGPT′s response variability affected less than 5% of clinical case notes. A survey of 48 clinicians rated the DxGPT platform 3.9/5 overall, 4.1/5 for usefulness, and 4.5/5 for usability.Conclusions and RelevanceDxGPT showed diagnostic accuracies similar to medical staff from a pediatric hospital, indicating its potential for supporting differential diagnosis in other settings. Clinicians praised its usability and simplicity. These tools could provide new insights for challenging diagnostic cases.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of the Clinical Utility of DxGPT, a GPT-4 Based Large Language Model, through an Analysis of Diagnostic Accuracy and User Experience

Alvarez-Estape,

Cano,

Pino

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The solution proposed by ACM in the form of abatement costs is, in his opinion, "not consistent with the way benefits are assessed and quantified under Article 101(3) TFEU". 167 Still, we believe that the Guidelines are not hugely innovative. Two of the changes that ACM introduces (i.e.…”

Section: Transposition Of the Guidelines To The Eu Levelmentioning

confidence: 98%

The sustainability guidelines of the Netherlands Authority for Consumers and Markets: an impetus for a modern EU approach to sustainability and competition policy reflecting the principle that the polluter pays?

Jansen

Beeston²,

Acker

2021

European Competition Journal

View full text Add to dashboard Cite

In October 2020, the European Commission (EC) published a call for contributions on how competition rules could support the Green Deal. With this initiative, the EC followed in the footsteps of several national competition authorities which had already issued guidance on competition policy and sustainability initiatives. The Netherlands Authority for Consumers and Markets (ACM) is, to date, the only authority to publish draft Sustainability Guidelines with progressive, practical guidance. In this paper, we explore the extent to which ACM's Sustainability Guidelines could serve as a source of inspiration for a modern EU approach to sustainability and competition policy. We will conclude that while these Guidelines constitute a clear compromise, ACM has created an intelligent modus operandi to allow for more cooperative sustainability initiatives under the third paragraph of Articles 6 Dutch Competition Act and 101 TFEU without itself having to take decisions about public policy. Sustainability -Green Deal -fair sharepolluter pays -ACM -Netherlands -Article 101 TFEU.

show abstract

“…It also offers insights for areas of competition law that typically receive less attention in the sustainability debate (particularly the area of abuse of dominance). While it gives voices to those that are more cautious 11 (if not sceptical 12 ) about making competition law 'greener', those voices are certainly less represented in this book. The book focuses predominately on those voices that urge a 'greener' interpretation of competition law.…”

mentioning

confidence: 99%

Book Review

Gassler¹

2021

Carbon & Climate Law Review

View full text Add to dashboard Cite

Climate change and sustainability have become 'hot topics' in competition law. Competition law is often perceived as a hindrance to achieving climaterelated or sustainability-related goals. Margrethe Vestager, Executive Vice-President and Commissioner for Competition of the European Commission, stated in October 2019 that 'sustainability is at the centre of our politics' 1 , but later clarified that 'competition policy is by no means the main tool to reach our green goals' 2 and, thus, disappointed those hoping for a radical and fundamental 'green' change in EU competition law lead by the European Commission. Still, it is expected that the interpretation of EU competition law will become 'greener', the extent to which is subject to a lively debate.This book fits well in this current debate. It offers an extensive discussion of the opportunities, challenges and policy considerations when implementing sustainability aims in competition law, with a focus on climate-related or environmental sustainabil-

show abstract

Artificial Creative Societies: Adaption, Intention, and Evaluation

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 3 publications

References 14 publications

Evaluation of the Clinical Utility of DxGPT, a GPT-4 Based Large Language Model, through an Analysis of Diagnostic Accuracy and User Experience

Evaluation of the Clinical Utility of DxGPT, a GPT-4 Based Large Language Model, through an Analysis of Diagnostic Accuracy and User Experience

The sustainability guidelines of the Netherlands Authority for Consumers and Markets: an impetus for a modern EU approach to sustainability and competition policy reflecting the principle that the polluter pays?

Book Review

Contact Info

Product

Resources

About