Modification and Validation of the System Causability Scale Using AI-Based Therapeutic Recommendations for Urological Cancer Patients: A Basis for the Development of a Prospective Comparative Study DOI Creative Commons

E Rinderknecht,

Dominik von Winning,

Anton Kravchuk

et al.

Current Oncology, Journal Year: 2024, Volume and Issue: 31(11), P. 7061 - 7073

Published: Nov. 11, 2024

The integration of artificial intelligence, particularly Large Language Models (LLMs), has the potential to significantly enhance therapeutic decision-making in clinical oncology. Initial studies across various disciplines have demonstrated that LLM-based treatment recommendations can rival those multidisciplinary tumor boards (MTBs); however, such data are currently lacking for urological cancers. This preparatory study establishes a robust methodological foundation forthcoming CONCORDIA trial, including validation System Causability Scale (SCS) and its modified version (mSCS), as well selection LLMs cancer based on from ChatGPT-4 an MTB 40 scenarios. Both scales strong validity, reliability (all aggregated Cohen’s K > 0.74), internal consistency Cronbach’s Alpha 0.9), with mSCS showing superior reliability, consistency, applicability (p < 0.01). Two Delphi processes were used define be tested (ChatGPT-4 Claude 3.5 Sonnet) establish acceptable non-inferiority margin LLM compared recommendations. ethics-approved registered trial will require 110 scenarios, difference threshold 0.15, Bonferroni corrected alpha 0.025, beta 0.1. Blinded assessments then LLMs. In summary, this work necessary prerequisites prior initiating validates score high future trials.

Language: Английский

Artificial intelligence in rheumatology research: what is it good for? DOI Creative Commons
José Miguel Sequí-Sabater, Diego Benavent

RMD Open, Journal Year: 2025, Volume and Issue: 11(1), P. e004309 - e004309

Published: Jan. 1, 2025

Artificial intelligence (AI) is transforming rheumatology research, with a myriad of studies aiming to improve diagnosis, prognosis and treatment prediction, while also showing potential capability optimise the research workflow, drug discovery clinical trials. Machine learning, key element discriminative AI, has demonstrated ability accurately classifying rheumatic diseases predicting therapeutic outcomes by using diverse data types, including structured databases, imaging text. In parallel, generative driven large language models, becoming powerful tool for optimising workflow supporting content generation, literature review automation decision support. This explores current applications future both AI in rheumatology. It highlights challenges posed these technologies, such as ethical concerns need rigorous validation regulatory oversight. The integration promises substantial advancements but requires balanced approach benefits minimise possible downsides.

Language: Английский

Citations

1
Modification and Validation of the System Causability Scale Using AI-Based Therapeutic Recommendations for Urological Cancer Patients: A Basis for the Development of a Prospective Comparative Study DOI Creative Commons

E Rinderknecht,

Dominik von Winning,

Anton Kravchuk

et al.

Current Oncology, Journal Year: 2024, Volume and Issue: 31(11), P. 7061 - 7073

Published: Nov. 11, 2024

The integration of artificial intelligence, particularly Large Language Models (LLMs), has the potential to significantly enhance therapeutic decision-making in clinical oncology. Initial studies across various disciplines have demonstrated that LLM-based treatment recommendations can rival those multidisciplinary tumor boards (MTBs); however, such data are currently lacking for urological cancers. This preparatory study establishes a robust methodological foundation forthcoming CONCORDIA trial, including validation System Causability Scale (SCS) and its modified version (mSCS), as well selection LLMs cancer based on from ChatGPT-4 an MTB 40 scenarios. Both scales strong validity, reliability (all aggregated Cohen’s K > 0.74), internal consistency Cronbach’s Alpha 0.9), with mSCS showing superior reliability, consistency, applicability (p < 0.01). Two Delphi processes were used define be tested (ChatGPT-4 Claude 3.5 Sonnet) establish acceptable non-inferiority margin LLM compared recommendations. ethics-approved registered trial will require 110 scenarios, difference threshold 0.15, Bonferroni corrected alpha 0.025, beta 0.1. Blinded assessments then LLMs. In summary, this work necessary prerequisites prior initiating validates score high future trials.

Language: Английский

Citations

1