Artificial Intelligence-Assisted Systematic Literature Reviews in Metabolic Phenotyping: A Methodological Framework and Validation Study

Maartje Cox; Javier Osorio Mosquera; Shaimaa Khandaker; Samuele Sala; Julien Wist; Jeremy K. Nicholson; Elaine Holmes; Timothy Fairchild; Nathan G. Lawler

doi:10.1007/s43657-026-00336-y

Back

Artificial Intelligence-Assisted Systematic Literature Reviews in Metabolic Phenotyping: A Methodological Framework and Validation Study

Journal article

Open access

Artificial Intelligence-Assisted Systematic Literature Reviews in Metabolic Phenotyping: A Methodological Framework and Validation Study

Maartje Cox, Javier Osorio Mosquera, Shaimaa Khandaker, Samuele Sala, Julien Wist, Jeremy K. Nicholson, Elaine Holmes, Timothy Fairchild and Nathan G. Lawler

Phenomics (Cham, Switzerland)

2026

DOI: https://doi.org/10.1007/s43657-026-00336-y

Files and links (1)

pdf

Published2.66 MBDownload View

Open Access CC BY V4.0

Abstract

Genetics & Heredity

Life Sciences & Biomedicine

Science & Technology

Systematic literature reviews are widely acknowledged to be at the top of most evidence hierarchies but are very time-consuming and labour-intensive. The advent of artificial intelligence (AI) offers possibilities to accelerate the review process. We propose a systematic literature review protocol that incorporates AI and evaluate the accuracy of AI against a human-constructed gold standard. Human researchers performed a systematic literature review on the PubMed metabolomic literature investigating Long COVID. OpenAI model o3-mini was then used via the application programming interface to carry out the three key stages of a systematic literature review: 1) screening articles for inclusion criteria, 2) evaluating articles' risk of bias (RoB) using a customised metabolomics tool based on well-established quality criteria, and 3) extracting data from articles. The performance of AI was evaluated against a manually created reference by the assessment of accuracy, negative predictive value, precision, sensitivity, specificity, F1 score, and Cohen's kappa. Out of the 320 identified articles, 33 met all inclusion criteria. AI performed screening, RoB assessment, and data extraction with mean accuracies of 92.7% +/- 4.9%, 91.9% +/- 5.9%, and 92.0% +/- 9.2%, respectively, in similar to 10 h and at a cost of similar to 15.35 USD, while human reviewers took similar to 116 h, equivalent to similar to 2000 USD at minimum wages, to complete these steps in duplicate. OpenAI model o3-mini can independently complete the three main stages of systematic literature reviews in the metabolomics domain, thus considerably reducing the time to complete such reviews, at minimal cost. Nonetheless, human reviewers should always verify the AI-generated output to ensure robustness.

Details

Title: Artificial Intelligence-Assisted Systematic Literature Reviews in Metabolic Phenotyping: A Methodological Framework and Validation Study
Authors/Creators: Maartje Cox - Murdoch University
Javier Osorio Mosquera - Murdoch University
Shaimaa Khandaker - Murdoch University
Samuele Sala - Murdoch University
Julien Wist - Murdoch University
Jeremy K. Nicholson - Imperial College London
Elaine Holmes - Murdoch University, Centre for Computational and Systems Medicine
Timothy Fairchild - Murdoch University
Nathan G. Lawler - Murdoch University
Publication Details: Phenomics (Cham, Switzerland)
Publisher: Springer Nature
Number of pages: 19
Grant note: Murdoch University
Identifiers: 991005912901607891
Murdoch Affiliation: Personalised Medicine Centre; School of Allied Health; Centre for Computational and Systems Medicine
Language: English
Resource Type: Journal article

Metrics

3 File views/ downloads

1 Record Views