scholarly journals Optimizing Literature Search: TEMAS, A New Text-Mining Algorithm-Assisted Search Tool

2020 ◽  
Author(s):  
Emmanuel Bonnet ◽  
Daurès Jean-Pierre ◽  
Landais Paul
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
Text Mining ◽  
Literature Search ◽  
Hierarchical Classification ◽  
Recall Rate ◽  
Average Precision ◽  
Mining Algorithm ◽  
Search Tool ◽  
Meta Analyses

Abstract Background: Literature search is challenging when thousands of articles are potentially involved. To facilitate literature search we created TEMAS a Text Mining Algorithm-assisted Search tool that we compared to a PubMed reference search (RS) in the context of etiological epidemiology.Methods: The 4 steps of TEMAS are: 1) a classic PubMed global search 2) a first sort removing articles without abstracts or containing off-topic terms 3) a clustering step with a descending hierarchical classification regrouping articles in independent classes 4) a final sort extracting from the targeted class the abstracts containing the terms of interest, with a link to the corresponding PubMed articles. Validation was performed for risk factors of breast cancer. We estimated the precision and recall rate compared to RS. Average precision and discounted cumulative gain (DCG) were also computed to perform a ranking-based evaluation. We also compared TEMAS results with articles selected in two meta-analyses.Results: For risk factors of breast cancer, breastfeeding, mammographic density, oral contraceptive, and menarche were explored. TEMAS consistently increased precision vs RS (from 23% to 32%), with a recall rate from 95% to 97%, and divided the number of selected articles to read from 2.3 to 4.8 times. Mean average precision for 100 articles was 47.4% for TEMAS vs 20.9% for PubMed ranked by best match, and DCG showed a consistent improvement for TEMAS compared to PubMed best match.Discussion: TEMAS divided the results of a literature search by 3.2, and improved the precision rate, the average precision, and the DCG compared to RS for epidemiological studies. Reducing the number of selected articles inevitably impacted the recall rate. However, it remained satisfactory and did not bias the corpus of information. Moreover, the recall rate was 100% for the two meta-analyses we analyzed, which suggests that the loss of recall rate observed above concerned articles not relevant enough to be included in the meta-analyses.Conclusion: TEMAS provides a user-friendly interface for non-specialists of literature search confronted with thousands of articles and appeared useful for meta-analyses.

scholarly journals Optimizing Literature Search: TEMAS, A New Text-mining Algorithm-assisted Search Tool

2020 ◽  
Author(s):  
Emmanuel Bonnet ◽  
Daurès Jean-Pierre ◽  
Landais Paul
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
Text Mining ◽  
Literature Search ◽  
Hierarchical Classification ◽  
Recall Rate ◽  
Average Precision ◽  
Mining Algorithm ◽  
Search Tool ◽  
Meta Analyses

Abstract Background: Literature search is challenging when thousands of articles are potentially involved. To facilitate literature search we created TEMAS a Text Mining Algorithm-assisted Search tool that we compared to a PubMed reference search (RS) in the context of etiological epidemiology.Methods: The 4 steps of TEMAS are: 1) a classic PubMed global search 2) a first sort removing articles without abstracts or containing off-topic terms 3) a clustering step with a descending hierarchical classification regrouping articles in independent classes 4) a final sort extracting from the targeted class the abstracts containing the terms of interest, with a link to the corresponding PubMed articles. Validation was performed for risk factors of breast cancer. We estimated the precision and recall rate compared to RS. Average precision and discounted cumulative gain (DCG) were also computed to perform a ranking-based evaluation. We also compared TEMAS results with articles selected in two meta-analyses.Results: For risk factors of breast cancer, breastfeeding, mammographic density, oral contraceptive, and menarche were explored. TEMAS consistently increased precision vs RS (from 23% to 32%), with a recall rate from 95% to 97%, and divided the number of selected articles to read from 2.3 to 4.8 times. Mean average precision for 100 articles was 47.4% for TEMAS vs 20.9% for PubMed ranked by best match, and DCG showed a consistent improvement for TEMAS compared to PubMed best match.Discussion: TEMAS divided the results of a literature search by 3.2, and improved the precision rate, the average precision, and the DCG compared to RS for epidemiological studies. Reducing the number of selected articles inevitably impacted the recall rate. However, it remained satisfactory and did not bias the corpus of information. Moreover, the recall rate was 100% for the two meta-analyses we analyzed, which suggests that the loss of recall rate observed above concerned articles not relevant enough to be included in the meta-analyses.Conclusion: TEMAS provides a user-friendly interface for non-specialists of literature search confronted with thousands of articles and appeared useful for meta-analyses.

scholarly journals Google Scholar Could Be Used as a Stand-Alone Resource for Systematic Reviews

2015 ◽  
Vol 10 (2) ◽  
pp. 147
Author(s):  
Saori Wendy Herman
Keyword(s):  
Systematic Reviews ◽  
Recall Rate ◽  
Biomedical Literature ◽  
Google Scholar ◽  
Cochrane Library ◽  
Bibliographic Database ◽  
Predictive Values ◽  
Advanced Search ◽  
Search Tool ◽  
Meta Analyses

A Review of: Gehanno, J. F., Rollin, L., & Darmoni, S. (2013). Is the coverage of Google Scholar enough to be used alone for systematic reviews. BMC Medical Informatics and Decision Making, 13(1): 7. doi: 10.1186/1472-6947-13-7 Abstract Objective – To determine if Google Scholar (GS) is sensitive enough to be used as the sole search tool for systematic reviews. Design – Citation analysis. Setting – Biomedical literature. Subjects – Original studies included in 29 systematic reviews published in the Cochrane Library or JAMA. Methods – The authors searched MEDLINE for any systematic reviews published in the 2008 and 2009 issues of JAMA or in the July 8, 2009 issue of the Cochrane Database of Systematic Reviews. They chose 29 systematic reviews for the study and included these reviews in a gold standard database created specifically for this project. The authors searched GS for the title of each of the original references for the 29 reviews. They computed and noted the recall of GS for each reference. Main Results – The authors searched GS for 738 original studies with a 100% recall rate. They also made a side discovery of a number of major errors in the bibliographic references. Conclusion – Researchers could use GS as a stand-alone database for systematic reviews or meta-analyses. With a couple improvements to the rate of positive predictive values and advanced search features, GS could become the leading medical bibliographic database. Conclusion – Researchers could use GS as a stand-alone database for systematic reviews or meta-analyses. With a couple improvements to the rate of positive predictive values and advanced search features, GS could become the leading medical bibliographic database.

Discovering bank risk factors from financial statements based on a new semi‐supervised text mining algorithm

2019 ◽  
Vol 59 (3) ◽  
pp. 1519-1552 ◽  
Author(s):  
Lu Wei ◽  
Guowen Li ◽  
Xiaoqian Zhu ◽  
Jianping Li
Keyword(s):  
Risk Factors ◽  
Text Mining ◽  
Financial Statements ◽  
Bank Risk ◽  
Mining Algorithm

scholarly journals Performance of ultrasonography screening for breast cancer: a systematic review and meta-analysis

2020 ◽  
Author(s):  
Lei Yang ◽  
Shengfeng Wang ◽  
Liwen Zhang ◽  
Chao Sheng ◽  
Fengju Song ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Meta Analysis ◽  
Recall Rate ◽  
Current Evidence ◽  
Screening Methods ◽  
Breast Cancers ◽  
Detection Rates ◽  
Meta Analyses ◽  
Sensitivity Specificity ◽  
Biopsy Rate

Abstract Background To investigate the performance of primary ultrasound (US) screening for breast cancer, and that of supplemental US screening for breast cancer after negative mammography (MAM). Methods Electronic databases (PubMed, Scopus, Wed of Science, and Embase) were systematically searched to identify relevant studies published between January 2003 and May 2018. Only high-quality or fair-quality studies reporting any of the following performance values for supplemental or primary US screening were included: sensitivity, specificity, cancer detected rate (CDR), recall rate (RR), biopsy rate (BR), and proportions of invasive cancers (ProIC) or node-negative invasive cancers (ProNNIC) among screening-detected cancers. Results Twenty-three studies were included, including 12 studies in which supplemental US screening was used after negative MAM and 11 joint screening studies in which both MAM and US were used as primary screening methods. Meta-analyses revealed that supplemental US screening could detect 96% [95% confidential intervals (CIs): 82% to 99%] of occult breast cancers missed by MAM and identify 94% (95% CIs: 88% to 97%) of healthy women, with a CDR of 2.9/1000 (95%CIs: 1.8/1000 to 3.9/1000), RR of 8.6% (95%CIs: 4.8% to 13.5%), BR of 3.9% (95%CIs: 2.5% to 5.5%), ProIC of 73.9% (95%CIs: 49.0% to 93.7%), and ProNNIC of 72.6% (95%CIs: 51.9% to 90.0%). Compared with primary MAM screening, primary US screening led to the recall of significantly more women with positive screening results [1.2% (95%CIs:0.4% to 1.9%), P =0.003] and detected significantly more invasive cancers [20.8% (95%CIs: 14.6% to 27.0%), P < 0.001]. However, there were no significant differences for other performance measures between the two screening methods, including sensitivity, specificity, CDR, BR, and ProNNIC. Conclusions Current evidence suggests that supplemental US screening could detect occult breast cancers missed by MAM. Primary US screening has shown to be comparable to primary MAM screening in women with dense breasts in terms of sensitivity, specificity, cancer detection rate, and biopsy rate, but with higher recall rates and higher detection rates for invasive cancers.

TP53 codon 72 polymorphisms and breast carcinoma susceptibility: A meta-analysis

2009 ◽  
Vol 27 (15_suppl) ◽  
pp. e22171-e22171
Author(s):  
B. Zhu ◽  
W. Zhuo ◽  
Z. Chen
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
Breast Carcinoma ◽  
Meta Analysis ◽  
Inclusion Criteria ◽  
Codon 72 ◽  
Knowledge Infrastructure ◽  
Increased Risk ◽  
Meta Analyses ◽  
Chinese National Knowledge Infrastructure

e22171 Background: Previously, TP53 codon 72 polymorphisms have been implicated as risk factors for various cancers. Several studies have conducted on the association of TP53 codon 72 polymorphisms with susceptibility to breast carcinoma and have yielded inconclusive results. The aim of the present study was to assess possible associations of breast cancer risk with TP53 codon 72 polymorphisms. Methods: We conducted a search in the Medline, EMBASE, OVID, Sciencedirect, and Chinese National Knowledge Infrastructure (CNKI) without a language limitation, covering all papers published up to Dec 2008. The associated literature was acquired through deliberate searching and selected based on the established inclusion criteria for publications. Results: Consequently, fifteen studies, including 3436 cases and 4394 controls, met the included criteria and thus were selected. Ultimately, the relevant data were extracted and further analyzed using systematic meta- analyses. The results showed that individuals carrying homozygote Arg/Arg genotype have a significant increased risk of breast cancer compared with those carrying Pro/Pro genotype (OR: 1.58, 95%CI:1.10–2.28). For Arg allele, no evidence indicated that individuals with Arg/Arg genotype have an increased risk of breast cancer compared with those with a combined Pro genotype (Arg/Pro+Pro/Pro) (OR: 1.68, 95%CI:1.24–2.29). For Pro allele, individuals with homozygote Pro/Pro genotype have a marked decreased susceptibility to breast cancer relative to those with a combined Arg genotype (Arg/Pro+Arg/Arg) (OR: 0.84, 95%CI:0.73–0.98). Conclusions: The results of the present study suggest that TP53 codon 72 polymorphisms might be a risk factor for breast cancer. Homozygote Arg allele genotype could significantly increase susceptibility to breast cancer, while Pro/Pro allele markedly decreases breast risk. No significant financial relationships to disclose.

scholarly journals Performance of ultrasonography screening for breast cancer: a systematic review and meta-analysis

2019 ◽  
Author(s):  
Lei Yang ◽  
Shengfeng Wang ◽  
Liwen Zhang ◽  
Chao Sheng ◽  
Fengju Song ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Performance Measures ◽  
Detection Rate ◽  
Meta Analysis ◽  
Recall Rate ◽  
Screening Methods ◽  
Breast Cancers ◽  
Primary Screening ◽  
Meta Analyses ◽  
Sensitivity Specificity

Abstract Background To investigate the performance of primary ultrasound (US) screening for breast cancer, and that of supplemental US screening for breast cancer after negative mammography (MAM).Methods Electronic databases (PubMed, Scopus, Wed of Science, and Embase) were systematically searched to identify relevant studies published between January 2003 and May 2018. Only high-quality or fair-quality studies reporting any of the following performance values for supplemental or primary US screening were included: sensitivity, specificity, cancer detected rate (CDR), recall rate (RR), biopsy rate (BR), and proportions of invasive cancers (ProIC) or node-positive cancers (ProNPC) among screening-detected cancers.Results Twenty-three studies were included, including 12 studies in which supplemental US screening was used after negative MAM and 11 joint screening studies in which both MAM and US were used as primary screening methods. Meta-analyses revealed that supplemental US screening could detect 96% [95% confidential intervals (CIs): 82% to 99%] of occult breast cancers missed by MAM and identify 94% (95% CIs: 88% to 97%) of healthy women, with a CDR of 2.9/1000 (95%CIs: 1.8/1000 to 3.9/1000), RR of 8.6% (95%CIs: 4.8% to 13.5%), BR of 3.9% (95%CIs: 2.5% to 5.5%), ProICof 73.9% (95%CIs: 49.0% to 93.7%), and ProNPC of 72.6% (95%CIs: 51.9% to 90.0%). Compared with primary MAM screening, primary US screening led to the recall of significantly more women with positive screening results [1.2% (95%CIs:0.4% to 1.9%), P =0.004] and detected significantly more invasive cancers [20.2% (95%CIs: 7.2% to 33.1%), P = 0.002]. However, there were no significant differences for other performance measures between the two screening methods, including sensitivity, specificity, CDR, BR, and ProNPC.Conclusions Supplemental US screening could detect occult breast cancers missed by MAM, while primary US screening would be considered as comparable to primary MAM screening in certain subgroup of women, but with a higher recall rate and a higher detection rate for invasive cancers.

scholarly journals Oral contraceptives and intrauterine devices as risk factors for breast and cervical cancers: a systematic review

2020 ◽  
Vol 8 (6) ◽  
pp. 2350
Author(s):  
Mary K. Murithi ◽  
Teresa K. Ogeto ◽  
Michael N. Walekhwa ◽  
Richard K. Njunge ◽  
Micah K. Lagat ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
Cervical Cancer ◽  
Oral Contraceptives ◽  
Cochrane Library ◽  
Intrauterine Devices ◽  
Case Control Studies ◽  
Cross Sectional ◽  
Cervical Cancers ◽  
Meta Analyses

Breast and cervical cancers have commandingly become major public health threats across the world. While studies have reported on the nexus between the use of oral contraceptives (OCs) and intrauterine devices (IUDs) as risk factors for breast and cervical cancers, there exists a paucity of explicit data on the nature of the association. Authors report the effect of oral contraceptives and the use of IUDs on the development of breast and cervical cancers. Several databases (Cochrane Library, Google Scholar and PubMed) were searched using well-specified criteria and a total of 15 papers selected. Meta-analyses, systematic reviews and studies that used cross-sectional designs were excluded from the review. Three and twelve cohort and case-control studies were reviewed respectively. Four of these studies reported an increased association between oral contraceptives and the risk of cervical cancer while nine showed positive correlation between oral contraceptives and risk of breast cancer. One study showed association between levonogestrel IUDs and risk of breast cancer while the other study did not show association between both levonogestrel and copper IUDs with risk of breast cancer. Use of copper IUDs was associated with diminishing risk of cervical cancer. Overall, use of oral contraceptives upsurges risk of breast and cervical cancers especially when used for longer periods of time. Further studies should therefore be done to understand the mechanisms of action of oral contraceptives and IUDs on the development of both cancers.

scholarly journals Performance of ultrasonography screening for breast cancer: a systematic review and meta-analysis

2020 ◽  
Author(s):  
Lei Yang ◽  
Shengfeng Wang ◽  
Liwen Zhang ◽  
Chao Sheng ◽  
Fengju Song ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Meta Analysis ◽  
Recall Rate ◽  
Current Evidence ◽  
Screening Methods ◽  
Breast Cancers ◽  
Detection Rates ◽  
Meta Analyses ◽  
Sensitivity Specificity ◽  
Biopsy Rate

Abstract Background To investigate the performance of primary ultrasound (P-US) screening for breast cancer, and that of supplemental ultrasound (S-US) screening for breast cancer after negative mammography (MAM). Methods Electronic databases (PubMed, Scopus, Web of Science, and Embase) were systematically searched to identify relevant studies published between January 2003 and May 2018. Only high-quality or fair-quality studies reporting any of the following performance values for P-US or S-US screening were included: sensitivity, specificity, cancer detected rate (CDR), recall rate (RR), biopsy rate (BR), proportion of invasive cancers among screening-detected cancers (ProIC), and proportion of node-negative cancers among screening-detected invasive cancers (ProNNIC). Results Twenty-three studies were included, including 12 studies in which S-US screening was used after negative MAM and 11 joint screening studies in which both primary MAM (P-MAM) and P-US were used. Meta-analyses revealed that S-US screening could detect 96% [95% confidential intervals (CIs): 82% to 99%] of occult breast cancers missed by MAM and identify 93% (95% CIs: 89% to 96%) of healthy women, with a CDR of 3.0/1000 (95%CIs: 1.8/1000 to 4.6/1000), RR of 8.8% (95%CIs: 5.0% to 13.4%), BR of 3.9% (95%CIs: 2.7% to 5.4%), ProIC of 73.9% (95%CIs: 49.0% to 93.7%), and ProNNIC of 70.9% (95%CIs: 46.0% to 91.6%). Compared with P-MAM screening, P-US screening led to the recall of significantly more women with positive screening results [1.5% (95%CIs:0.6% to 2.3%), P =0.001] and detected significantly more invasive cancers [16.3% (95%CIs: 10.6% to 22.1%), P < 0.001]. However, there were no significant differences for other performance measures between the two screening methods, including sensitivity, specificity, CDR, BR, and ProNNIC. Conclusions Current evidence suggests that S-US screening could detect occult breast cancers missed by MAM. P-US screening has shown to be comparable to P-MAM screening in women with dense breasts in terms of sensitivity, specificity, cancer detection rate, and biopsy rate, but with higher recall rates and higher detection rates for invasive cancers.

Associations of coronary and peripheral artery disease with presence, expansion, and rupture of abdominal aortic aneurysm – a grin without a cat!

VASA ◽  
2017 ◽  
Vol 46 (3) ◽  
pp. 151-158 ◽  
Author(s):  
Hisato Takagi ◽  
Takuya Umemoto
Keyword(s):  
Abdominal Aortic Aneurysm ◽  
Aortic Aneurysm ◽  
Peripheral Artery Disease ◽  
Literature Search ◽  
Systematic Literature Search ◽  
Peripheral Artery ◽  
Epidemiological Evidence ◽  
Abdominal Aortic ◽  
Artery Disease ◽  
Meta Analyses

Abstract. Both coronary and peripheral artery disease are representative atherosclerotic diseases, which are also known to be positively associated with presence of abdominal aortic aneurysm. It is still controversial, however, whether coronary and peripheral artery disease are positively associated with expansion and rupture as well as presence of abdominal aortic aneurysm. In the present article, we overviewed epidemiological evidence, i. e. meta-analyses, regarding the associations of coronary and peripheral artery disease with presence, expansion, and rupture of abdominal aortic aneurysm through a systematic literature search. Our exhaustive search identified seven meta-analyses, which suggest that both coronary and peripheral artery disease are positively associated with presence of abdominal aortic aneurysm, may be negatively associated with expansion of abdominal aortic aneurysm, and might be unassociated with rupture of abdominal aortic aneurysm.

Sign in / Sign up

Export Citation Format

Share Document