An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms.
<h4>Background and objective</h4>Systematic reviews and meta-analyses are critical in forensic medicine; however, these processes are labor-intensive and time-consuming. ASReview, an open-source machine learning framework, has demonstrated potential to improve the efficiency and transpar...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0329349 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849467042068955136 |
|---|---|
| author | Ya-Wen Liu Dong-Hua Zou He-Wen Dong Yuan-Yuan Liu En-Hao Fu Zhi-Ling Tian Ning-Guo Liu |
| author_facet | Ya-Wen Liu Dong-Hua Zou He-Wen Dong Yuan-Yuan Liu En-Hao Fu Zhi-Ling Tian Ning-Guo Liu |
| author_sort | Ya-Wen Liu |
| collection | DOAJ |
| description | <h4>Background and objective</h4>Systematic reviews and meta-analyses are critical in forensic medicine; however, these processes are labor-intensive and time-consuming. ASReview, an open-source machine learning framework, has demonstrated potential to improve the efficiency and transparency of systematic reviews in other disciplines. Nevertheless, its applicability to forensic medicine remains unexplored. This study evaluates the utility of ASReview for forensic medical literature review.<h4>Methods</h4>A three-stage experimental design was implemented. First, stratified five-fold cross-validation was conducted to assess ASReview's compatibility with forensic medical literature. Second, incremental learning and sampling methods were employed to analyze the model's performance on imbalanced datasets and the effect of training set size on predictive accuracy. Third, gold standard were translated into computational languages to evaluate ASReview's capacity to address real-world systematic review objectives.<h4>Results</h4>ASReview exhibited robust viability for screening forensic medical literature. The tool efficiently prioritized relevant studies while excluding irrelevant records, thereby improving review productivity. Model performance remained stable when labeled training data constituted less than 80% of the total sample size. Notably, when the training set proportion ranged from 10% to 55%, ASReview's predictions aligned closely with human reviewer decisions.<h4>Conclusion</h4>ASReview represents a promising tool for forensic medical literature review. Its ability to handle imbalanced datasets and gather goal-oriented information enhances the efficiency and transparency of systematic reviews and meta-analyses in forensic medicine. Further research is required to optimize implementation strategies and validate its utility across diverse forensic medical contexts. |
| format | Article |
| id | doaj-art-18b99bcffd174e52b599e2162c6e206a |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-18b99bcffd174e52b599e2162c6e206a2025-08-20T03:39:14ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01208e032934910.1371/journal.pone.0329349An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms.Ya-Wen LiuDong-Hua ZouHe-Wen DongYuan-Yuan LiuEn-Hao FuZhi-Ling TianNing-Guo Liu<h4>Background and objective</h4>Systematic reviews and meta-analyses are critical in forensic medicine; however, these processes are labor-intensive and time-consuming. ASReview, an open-source machine learning framework, has demonstrated potential to improve the efficiency and transparency of systematic reviews in other disciplines. Nevertheless, its applicability to forensic medicine remains unexplored. This study evaluates the utility of ASReview for forensic medical literature review.<h4>Methods</h4>A three-stage experimental design was implemented. First, stratified five-fold cross-validation was conducted to assess ASReview's compatibility with forensic medical literature. Second, incremental learning and sampling methods were employed to analyze the model's performance on imbalanced datasets and the effect of training set size on predictive accuracy. Third, gold standard were translated into computational languages to evaluate ASReview's capacity to address real-world systematic review objectives.<h4>Results</h4>ASReview exhibited robust viability for screening forensic medical literature. The tool efficiently prioritized relevant studies while excluding irrelevant records, thereby improving review productivity. Model performance remained stable when labeled training data constituted less than 80% of the total sample size. Notably, when the training set proportion ranged from 10% to 55%, ASReview's predictions aligned closely with human reviewer decisions.<h4>Conclusion</h4>ASReview represents a promising tool for forensic medical literature review. Its ability to handle imbalanced datasets and gather goal-oriented information enhances the efficiency and transparency of systematic reviews and meta-analyses in forensic medicine. Further research is required to optimize implementation strategies and validate its utility across diverse forensic medical contexts.https://doi.org/10.1371/journal.pone.0329349 |
| spellingShingle | Ya-Wen Liu Dong-Hua Zou He-Wen Dong Yuan-Yuan Liu En-Hao Fu Zhi-Ling Tian Ning-Guo Liu An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms. PLoS ONE |
| title | An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms. |
| title_full | An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms. |
| title_fullStr | An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms. |
| title_full_unstemmed | An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms. |
| title_short | An open-source interactive AI framework for assisting automatic literature review in forensic medicine: Focus on brain injury mechanisms. |
| title_sort | open source interactive ai framework for assisting automatic literature review in forensic medicine focus on brain injury mechanisms |
| url | https://doi.org/10.1371/journal.pone.0329349 |
| work_keys_str_mv | AT yawenliu anopensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT donghuazou anopensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT hewendong anopensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT yuanyuanliu anopensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT enhaofu anopensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT zhilingtian anopensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT ningguoliu anopensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT yawenliu opensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT donghuazou opensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT hewendong opensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT yuanyuanliu opensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT enhaofu opensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT zhilingtian opensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms AT ningguoliu opensourceinteractiveaiframeworkforassistingautomaticliteraturereviewinforensicmedicinefocusonbraininjurymechanisms |