Using Artificial Intelligence to Support Informed Decision-Making on BRAF Mutation Testing DOI
Jennifer Webster, Jennifer Ghith, Orion Penner

et al.

JCO Precision Oncology, Journal Year: 2024, Volume and Issue: 8

Published: Oct. 1, 2024

PURPOSE Precision oncology relies on accurate and interpretable reporting of testing mutation rates. Focusing the BRAFV600 mutations in advanced colorectal carcinoma, non–small-cell lung cutaneous melanoma, we developed a platform displaying rates reported literature, which annotated using an artificial intelligence (AI) natural language processing (NLP) pipeline. METHODS Using AI, identified publications that likely or rate, filtered for cancer type, sentences Rates covariates were subsequently manually curated by three experts. The AI performance was evaluated precision recall metrics. We used interactive to explore present certain study characteristics. RESULTS dashboard, accessible at BRAF dimensions website, enables users filter with relevant options (eg, country study, type) visualize pipeline demonstrated excellent filtering (>90% all target types) moderate sentence classification (53%-99% precision; ≥75% recall). manual annotation revealed inter-rater disagreement (testing 19%; 70%), indicating unclear nonstandard some publications. CONCLUSION Our AI-driven NLP potential annotating biomarker difficulties encountered highlight need more AI-powered literature searching data extraction, consistent These improvements would reduce risk misinterpretation misunderstanding AI-based technologies health care community, beneficial impacts clinical decision-making, research, trial design.

Language: Английский

The Use of Artificial Intelligence for Cancer Therapeutic Decision-Making DOI
Olivier Elemento, Sean Khozin, Cora N. Sternberg

et al.

NEJM AI, Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Language: Английский

Citations

0
Exploring the World of Coding in Artificial Intelligence DOI
Purushothman Munusamy, Mageswaran Sanmugam, Bosede Iyiade Edwards

et al.

Advances in educational technologies and instructional design book series, Journal Year: 2024, Volume and Issue: unknown, P. 165 - 182

Published: Oct. 24, 2024

This paper introduces artificial intelligence and coding basics to young learners. AI is a scientific field enabling machines do tasks needing human intelligence. It's widely used in modern life, from virtual assistants smart devices. Coding key how works. The also explains help understanding. Students can create basic applications using platforms like Scratch Blockly. Real-world examples show AI's potential inspire students. Early education crucial for the new generation navigate technology-driven world encourage lifelong learning.

Language: Английский

Citations

0
Using Artificial Intelligence to Support Informed Decision-Making on BRAF Mutation Testing DOI
Jennifer Webster, Jennifer Ghith, Orion Penner

et al.

JCO Precision Oncology, Journal Year: 2024, Volume and Issue: 8

Published: Oct. 1, 2024

PURPOSE Precision oncology relies on accurate and interpretable reporting of testing mutation rates. Focusing the BRAFV600 mutations in advanced colorectal carcinoma, non–small-cell lung cutaneous melanoma, we developed a platform displaying rates reported literature, which annotated using an artificial intelligence (AI) natural language processing (NLP) pipeline. METHODS Using AI, identified publications that likely or rate, filtered for cancer type, sentences Rates covariates were subsequently manually curated by three experts. The AI performance was evaluated precision recall metrics. We used interactive to explore present certain study characteristics. RESULTS dashboard, accessible at BRAF dimensions website, enables users filter with relevant options (eg, country study, type) visualize pipeline demonstrated excellent filtering (>90% all target types) moderate sentence classification (53%-99% precision; ≥75% recall). manual annotation revealed inter-rater disagreement (testing 19%; 70%), indicating unclear nonstandard some publications. CONCLUSION Our AI-driven NLP potential annotating biomarker difficulties encountered highlight need more AI-powered literature searching data extraction, consistent These improvements would reduce risk misinterpretation misunderstanding AI-based technologies health care community, beneficial impacts clinical decision-making, research, trial design.

Language: Английский

Citations

0