Association of Machine Assisted Screening with Review Efficiency in Biomedical Evidence Syntheses
Keywords:
Machine Assisted Screening, Systematic Reviews, Review Efficiency, Difference Analysis, Biomedical Evidence SynthesesAbstract
The exponential growth of biomedical literature has created a critical bottleneck for researchers conducting systematic reviews and evidence syntheses. Manual screening of thousands of citations to identify a few relevant studies is both labor-intensive and prone to human error. To mitigate this burden, machine assisted screening tools leveraging active learning and natural language processing have been increasingly proposed. However, empirical evidence regarding the precise efficiency gains and the factors influencing these gains remains fragmented. This study conducts a rigorous difference analysis across diverse biomedical evidence syntheses to link the deployment of machine assisted screening to actual review efficiency. Utilizing a simulation-based approach on multiple benchmark datasets, we compare the efficiency outcomes of traditional manual screening against various machine-assisted active learning configurations. Our findings demonstrate that active learning algorithms can reduce the screening workload by up to sixty percent while maintaining a high recall rate of over ninety-five percent. Furthermore, the difference analysis reveals that the efficiency gains are highly sensitive to the initial training set composition, the underlying text representation model, and the inherent heterogeneity of the study topic. This paper provides concrete empirical evidence and actionable guidelines for optimizing screening workflows in biomedical evidence syntheses.References
1. Wohlin, C.; Mendes, E.; Felizardo, K.R.; Kalinowski, M. Guidelines for the search strategy to update systematic literature reviews in software engineering. Inf. Softw. Technol. 2020, 127, 106366.
2. Cook, D.J.; Mulrow, C.; Haynes, R.B. Systematic Reviews: Synthesis of Best Evidence for Clinical Decisions. Ann. Intern. Med. 1997, 126, 376–380.
3. Mickan, S.; Tilson, J.K.; Atherton, H.; Roberts, N.W.; Heneghan, C. Evidence of effectiveness of health care professionals using handheld computers: A scoping review of systematic reviews. J. Med. Internet Res. 2013, 15, e212.
4. García-Pineda, V.; Valencia-Arias, A.; Patiño-Vanegas, J.C.; Flores Cueto, J.J.; Arango-Botero, D.; Rojas Coronel, A.M.; Rodríguez-Correa, P.A. Research Trends in the Use of Machine Learning Applied in Mobile Networks: A Bibliometric Approach and Research Agenda. Informatics 2023, 10, 73.
5. Papoudakis, G.; Christianos, F.; Schäfer, L.; Albrecht, S.V. Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS 2021), Virtual Event, 6–14 December 2021; Neural Information Processing Systems Foundation, Inc.: La Jolla, CA, USA, 2021.
6. Chen, A.C.H.; Jia, W.-K.; Hwang, F.-J.; Liu, G.; Song, F.; Pu, L. Machine Learning and Deep Learning Methods for Wireless Network Applications. EURASIP J. Wirel. Commun. Netw. 2022, 2022, 115.
7. Ayyappan, V.; Bruno, M.A. Applying Machine Learning to Optimize Resource Allocation & Maritime Wireless Mobile Network. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. 2025, 16, 406–416.
8. Sheikh, A.; Chong, E.K.P. Multi-Agent Reinforcement Learning Framework for Optimizing Smart Cities as System of Systems. Syst. Eng. 2026, 29, 3–19.
9. Gou, J.; Liu, L.; Zhang, K.; Yin, C. Current situation and optimization strategies of childcare service demand of parents of children aged 0–3 years—Analysis based on the Kano model. Stud. Early Child. Educ. 2024, 54–72.
10. Zhang, H.; Han, X.; Xing, C.; Chen, H.; Zhao, J. Analysis of Uplink Transmission Scheduling Strategies for LoRa-Based Direct-to-Satellite IoT Networks Using Deep Reinforcement Learning. IEEE Trans. Green Commun. Netw. 2026, 10, 1279–1292.
11. Jestl, S.; Maucorps, A.; Römisch, R. The Effects of the EU Cohesion Policy on Regional Economic Growth: Using Structural Equation Modelling for Impact Assessment; The Vienna Institute for International Economic Studies, Wiiw: Wien, Austria, 2020.
12. Kumar, R.; Gupta, S.K.; Wang, H.-C.; Kumari, C.S.; Korlam, S.S.V.P. From Efficiency to Sustainability: Exploring the Potential of 6G for a Greener Future. Sustainability 2023, 15, 16387.
13. Bereketeab, L.; Zekeria, A.; Aloqaily, M.; Guizani, M.; Debbah, M. Energy Optimization in Sustainable Smart Environments with Machine Learning and Advanced Communications. IEEE Sens. J. 2024, 24, 5704–5712.
14. Hagen, T.; Mohl, P. Econometric evaluation of EU Cohesion Policy: A survey. In International Handbook on the Economics of Integration, Volume Iii: Factor Mobility, Agriculture, Environment and Quantitative Studies; Springer: Berlin/Heidelberg, Germany, 2011; pp. 343–370.
15. Mohl, P.; Hagen, T. Do EU structural funds promote regional growth? New evidence from various panel data approaches. Reg. Sci. Urban Econ. 2010, 40, 353–365.
16. Iqbal, A.; Al-Habashna, A.; Wainer, G.; Boudreau, G.; Bouali, F. PPO-Based Energy Efficiency Maximization For RIS-Assisted Multi-User Miso Systems. In Proceedings of the 2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall), Washington, DC, USA, 7–10 October 2024; pp. 1–6.
17. Piętak, Ł. Did Structural Funds Affect Economic Growth and Convergence Across Regions? Spanish Case in the Years 1989–2016; INE PAN Working Paper Series; INE PAN: Warsaw, Poland, 2018; Available online: https://inepan.pl/wp-content/uploads/2016/07/working-papers-44-Hiszpania-Pietak.pdf (accessed on 22 December 2025).
18. Zhao, D.; Wang, Y.; Song, B.; Zhou, Y.; Qin, P. Learning When and Where to Handover: A Hierarchical Reinforcement Learning Framework for Dense LEO Satellite Constellations. IEEE Trans. Wirel. Commun. 2026, 25, 12787–12801.
19. Chen, L. (2024). An extended TF-IDF method for improving keyword extraction in traditional corpus-based research: An example of a climate change corpus. Data & Knowledge Engineering, 153, 102322.
20. Blanchard, P.; El Mhamdi, E.M.; Guerraoui, R.; Stainer, J. Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. In Advances in Neural Information Processing Systems; Curran Associates, Inc.: Red Hook, NY, USA, 2017; Volume 30.
21. Mata, L.; Sousa, M.; Vieira, P.; Queluz, M.P.; Rodrigues, A. Optimizing Energy and Spectral Efficiency in Mobile Networks: A Comprehensive Energy Sustainability Framework for Network Operators. IEEE Access 2025, 13, 22342–22364.
22. Scotti, F.; Flori, A.; Pammolli, F. The economic impact of structural and Cohesion Funds across sectors: Immediate, medium-to-long term effects and spillovers. Econ. Model. 2022, 111, 105833.
23. Ferrag, M.A.; Friha, O.; Kantarci, B.; Tihanyi, N.; Cordeiro, L.; Debbah, M.; Hamouda, D.; Al-Hawawreh, M.; Choo, K.-K.R. Edge Learning for 6G-Enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses. IEEE Commun. Surv. Tutor. 2023, 25, 2654–2713.
24. Jiao, L.; Shao, Y.; Sun, L.; Liu, F.; Yang, S.; Ma, W.; Li, L.; Liu, X.; Hou, B.; Zhang, X.; et al. Advanced Deep Learning Models for 6G: Overview, Opportunities, and Challenges. IEEE Access 2024, 12, 133245–133314.
25. Fu, S.; Wei, W.; Feng, X.; Yin, L. Average Sum Rate Optimization in RIS-Assisted NOMA Satellite Network: A Deep Reinforcement Learning Approach. IEEE Wirel. Commun. Lett. 2025, 14, 1772–1776.
26. Cui, H. Evaluating the Performance Metrics of PPO, DQN, and DDPG in Continuous Control Tasks. ITM Web Conf. 2025, 78, 01009.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are distributed under the Creative Commons Attribution 4.0 International License (CC BY 4.0), unless otherwise stated.
