{"id":{"repo_id":"rgu","oai_identifier":"oai:rgu-repository.worktribe.com:3020586"},"canonical_url":"https://search.dev.ndltd.org/etd/rgu/oai:rgu-repository.worktribe.com:3020586","repository":{"repo_id":"rgu","name":"Robert Gordon University","base_url":"https://rgu-repository.worktribe.com/oaiprovider"},"display":{"title":"Automating systematic literature reviews in healthcare: leveraging artificial intelligence for enhanced evidence-based decision making.","abstract":"Systematic literature reviews (SLRs) are considered the gold standard in synthesising evidence across various research disciplines due to their structured, transparent, and reproducible nature. Despite their critical role, the SLR process is often perceived as burdensome and time-intensive, largely due to the escalating volume of published research and the detailed methodological rigour required. This thesis addresses these challenges by identifying the specific stages of the SLR process that are most laborious and exploring the application of state-of-the-art (SOTA) artificial intelligence (AI) techniques to enhance their efficiency. The thesis presents an online survey conducted to gather insights from systematic reviewers, pinpointing key bottlenecks in the SLR process. Based on these findings, this research investigates the application of AI methodologies, including natural language processing (NLP), machine learning (ML), and deep learning (DL), to automate and expedite the identified stages. The study explores the integration of domain-specific knowledge into pre-trained large language models (LLMs) and evaluates their performance in automating abstract screening and data extraction/synthesis phase. Additionally, the thesis proposes a novel monolingual dual-stage information retrieval system, focusing on non-English SLRs to address the language diversity in research publications. The proposed AI frameworks are validated using both private and public datasets, demonstrating significant improvements in the accuracy, reliability, and speed of systematic reviews. These advancements aim to reduce the workload on researchers, improve the timeliness of evidence synthesis, and enhance the overall quality of SLRs.","abstract_html":"Systematic literature reviews (SLRs) are considered the gold standard in synthesising evidence across various research disciplines due to their structured, transparent, and reproducible nature. Despite their critical role, the SLR process is often perceived as burdensome and time-intensive, largely due to the escalating volume of published research and the detailed methodological rigour required. This thesis addresses these challenges by identifying the specific stages of the SLR process that are most laborious and exploring the application of state-of-the-art (SOTA) artificial intelligence (AI) techniques to enhance their efficiency. The thesis presents an online survey conducted to gather insights from systematic reviewers, pinpointing key bottlenecks in the SLR process. Based on these findings, this research investigates the application of AI methodologies, including natural language processing (NLP), machine learning (ML), and deep learning (DL), to automate and expedite the identified stages. The study explores the integration of domain-specific knowledge into pre-trained large language models (LLMs) and evaluates their performance in automating abstract screening and data extraction/synthesis phase. Additionally, the thesis proposes a novel monolingual dual-stage information retrieval system, focusing on non-English SLRs to address the language diversity in research publications. The proposed AI frameworks are validated using both private and public datasets, demonstrating significant improvements in the accuracy, reliability, and speed of systematic reviews. These advancements aim to reduce the workload on researchers, improve the timeliness of evidence synthesis, and enhance the overall quality of SLRs.","abstract_has_math":false,"creators":["Ofori-Boateng, Regina"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["C. Moreno-Garcia, N. Wiratunga and M. Aceves-Martins"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-24T04:10:12Z","subjects":["Systematic literature reviews","Evidence synthesis automation","Machine learning","Natural language processing","Data extraction and synthesis","Domain-specific knowledge integration"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:rgu-repository.worktribe.com:3020586","https://doi.org/10.48526/rgu-wt-3020586"],"render_values":[{"text":"oai:rgu-repository.worktribe.com:3020586","href":null,"code":true},{"text":"https://doi.org/10.48526/rgu-wt-3020586","href":"https://doi.org/10.48526/rgu-wt-3020586","code":true}]},{"key":"dc:creator.authoridentifier","label":"Author Identifier","values":["0000-0002-0319-773X"],"render_values":[{"text":"0000-0002-0319-773X","href":"https://orcid.org/0000-0002-0319-773X","code":true}]}]},"links":{"outbound_url":"https://rgu-repository.worktribe.com/3020586/1/OFORI-BOATENG%202025%20Automating%20systematic%20literature%20reviews","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["C. Moreno-Garcia, N. Wiratunga and M. Aceves-Martins"]},{"key":"dc:contributor.sponsor","label":"Sponsor","values":["RGU Funded Studentship"]},{"key":"dc:creator","label":"Author","values":["Ofori-Boateng, Regina"]},{"key":"dc:creator.authoridentifier","label":"Author Identifier","values":["0000-0002-0319-773X"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-03-31"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://rgu-repository.worktribe.com/output/3020586"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Systematic literature reviews","Evidence synthesis automation","Machine learning","Natural language processing","Data extraction and synthesis","Domain-specific knowledge integration"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:rgu-repository.worktribe.com:3020586","https://doi.org/10.48526/rgu-wt-3020586"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://rgu-repository.worktribe.com/3020586/1/OFORI-BOATENG%202025%20Automating%20systematic%20literature%20reviews"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Systematic literature reviews (SLRs) are considered the gold standard in synthesising evidence across various research disciplines due to their structured, transparent, and reproducible nature. Despite their critical role, the SLR process is often perceived as burdensome and time-intensive, largely due to the escalating volume of published research and the detailed methodological rigour required. This thesis addresses these challenges by identifying the specific stages of the SLR process that are most laborious and exploring the application of state-of-the-art (SOTA) artificial intelligence (AI) techniques to enhance their efficiency. The thesis presents an online survey conducted to gather insights from systematic reviewers, pinpointing key bottlenecks in the SLR process. Based on these findings, this research investigates the application of AI methodologies, including natural language processing (NLP), machine learning (ML), and deep learning (DL), to automate and expedite the identified stages. The study explores the integration of domain-specific knowledge into pre-trained large language models (LLMs) and evaluates their performance in automating abstract screening and data extraction/synthesis phase. Additionally, the thesis proposes a novel monolingual dual-stage information retrieval system, focusing on non-English SLRs to address the language diversity in research publications. The proposed AI frameworks are validated using both private and public datasets, demonstrating significant improvements in the accuracy, reliability, and speed of systematic reviews. These advancements aim to reduce the workload on researchers, improve the timeliness of evidence synthesis, and enhance the overall quality of SLRs."]},{"key":"dc:title","label":"Title","values":["Automating systematic literature reviews in healthcare: leveraging artificial intelligence for enhanced evidence-based decision making."]}]}],"canonical_facts":{"dc:contributor.advisor":["C. Moreno-Garcia, N. Wiratunga and M. Aceves-Martins"],"dc:contributor.sponsor":["RGU Funded Studentship"],"dc:creator":["Ofori-Boateng, Regina"],"dc:creator.authoridentifier":["0000-0002-0319-773X"],"dc:date":["2025-03-31"],"dc:date.issued":["2025"],"dc:description.abstract":["Systematic literature reviews (SLRs) are considered the gold standard in synthesising evidence across various research disciplines due to their structured, transparent, and reproducible nature. Despite their critical role, the SLR process is often perceived as burdensome and time-intensive, largely due to the escalating volume of published research and the detailed methodological rigour required. This thesis addresses these challenges by identifying the specific stages of the SLR process that are most laborious and exploring the application of state-of-the-art (SOTA) artificial intelligence (AI) techniques to enhance their efficiency. The thesis presents an online survey conducted to gather insights from systematic reviewers, pinpointing key bottlenecks in the SLR process. Based on these findings, this research investigates the application of AI methodologies, including natural language processing (NLP), machine learning (ML), and deep learning (DL), to automate and expedite the identified stages. The study explores the integration of domain-specific knowledge into pre-trained large language models (LLMs) and evaluates their performance in automating abstract screening and data extraction/synthesis phase. Additionally, the thesis proposes a novel monolingual dual-stage information retrieval system, focusing on non-English SLRs to address the language diversity in research publications. The proposed AI frameworks are validated using both private and public datasets, demonstrating significant improvements in the accuracy, reliability, and speed of systematic reviews. These advancements aim to reduce the workload on researchers, improve the timeliness of evidence synthesis, and enhance the overall quality of SLRs."],"dc:identifier":["oai:rgu-repository.worktribe.com:3020586","https://doi.org/10.48526/rgu-wt-3020586"],"dc:identifier.uri":["https://rgu-repository.worktribe.com/3020586/1/OFORI-BOATENG%202025%20Automating%20systematic%20literature%20reviews"],"dc:language":["en"],"dc:relation.isreferencedby":["https://rgu-repository.worktribe.com/output/3020586"],"dc:subject":["Systematic literature reviews","Evidence synthesis automation","Machine learning","Natural language processing","Data extraction and synthesis","Domain-specific knowledge integration"],"dc:title":["Automating systematic literature reviews in healthcare: leveraging artificial intelligence for enhanced evidence-based decision making."],"dc:type":["Thesis"]},"updated_at":"2026-07-24T04:10:12Z"}