Artificial Intelligence-Assisted Systematic Literature Reviews in Metabolic Phenotyping: A Methodological Framework and Validation Study.
6 affiliations
- 1Australian National Phenome Centre, Health Futures Institute, Harry Perkins Institute of Medical Research, Murdoch University, 5 Robin Warren Drive, Murdoch, Perth, WA 6150 Australia.
- 2Chemistry Department, Universidad del Valle, Melendez, 76001 Cali, Colombia.
- 3Centre for Computational and Systems Medicine, Health Futures Institute, Harry Perkins Institute, Murdoch University, Perth, WA 6150 Australia.
- 4Department of Metabolism, Digestion and Reproduction, Faculty of Medicine, Imperial College, London, SW7 2AZ UK.
- 5School of Allied Health, College of Health and Education, Murdoch University, Perth, WA 6150 Australia.
- 6Centre for Healthy Ageing, Health Futures Institute, Murdoch University, Perth, WA 6150 Australia.
Abstract
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 ~ 10 h and at a cost of ~ 15.35 USD, while human reviewers took ~ 116 h, equivalent 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. The online version contains supplementary material available at https://doi.org/10.1007/s43657-026-00336-y.
Related
- Patient-Specific Implant Design: Current Evidence for Artificial Intelligence, Imaging and Computational Planning—A Systematic Review of the Biomedical-Indexed Literature
- From chronic kidney disease classification to genuine early prediction: a systematic review of artificial intelligence, methodological quality, and translational evidence
- Comprehensive application of artificial intelligence in preserved ratio impaired spirometry: A systematic literature review
- Artificial Intelligence and Machine Learning in the Transformation of Forensic Accounting: A Systematic Literature Review
- Advances in artificial intelligence for brain imaging and computer-aided diagnosis of neurological diseases: a systematic literature review.
BibTeX
@article{cox2026artificial,
title = {{Artificial Intelligence-Assisted Systematic Literature Reviews in Metabolic Phenotyping: A Methodological Framework and Validation Study.}},
author = {Maartje Cox and Javier Osorio Mosquera and Shaimaa Khandaker and Samuele Sala and Julien Wist and Jeremy K Nicholson and Elaine Holmes and Timothy Fairchild and Nathan G Lawler},
journal = {Phenomics (Cham, Switzerland)},
year = {2026},
month = aug,
doi = {10.1007/s43657-026-00336-y},
url = {https://europepmc.org/article/MED/42953262},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial Intelligence-Assisted Systematic Literature Reviews in Metabolic Phenotyping: A Methodological Framework and Validation Study.
AU - Maartje Cox
AU - Javier Osorio Mosquera
AU - Shaimaa Khandaker
AU - Samuele Sala
AU - Julien Wist
AU - Jeremy K Nicholson
AU - Elaine Holmes
AU - Timothy Fairchild
AU - Nathan G Lawler
PY - 2026
DA - 2026/08/17
JO - Phenomics (Cham, Switzerland)
DO - 10.1007/s43657-026-00336-y
UR - https://europepmc.org/article/MED/42953262
AB - 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 ~ 10 h and at a cost of ~ 15.35 USD, while human reviewers took ~ 116 h, equivalent 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. The online version contains supplementary material available at https://doi.org/10.1007/s43657-026-00336-y.
SN - 2730-583X
SN - 2730-5848
ER -