Background: Artificial intelligence (AI) has the potential to personalize treatment strategies for patients with cancer. However, current methodological weaknesses could limit clinical impact. We identified common limitations and suggested potential solutions to facilitate translation of AI to breast cancer management.
Methods: A systematic review was conducted in MEDLINE, Embase, SCOPUS, Google Scholar and PubMed Central in July 2021. Studies investigating the performance of AI to predict outcomes among patients undergoing treatment for breast cancer were included. Algorithm design and adherence to reporting standards were assessed following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement. Risk of bias was assessed by using the Prediction model Risk Of Bias Assessment Tool (PROBAST), and correspondence with authors to assess data and code availability.
Results: Our search identified 1,124 studies, of which 64 were included: 58 had a retrospective study design, with 6 studies with a prospective design. Access to datasets and code was severely limited (unavailable in 77% and 88% of studies, respectively). On request, data and code were made available in 28% and 18% of cases, respectively. Ethnicity was often under-reported (not reported in 52 of 64, 81%), as was model calibration (63/64, 99%). The risk of bias was high in 72% (46/64) of the studies, especially because of analysis bias.
Conclusion: Development of AI algorithms should involve external and prospective validation, with improved code and data availability to enhance reliability and translation of this promising approach. Protocol registration number: PROSPERO - CRD42022292495.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ctrv.2022.102410 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Omega-3 fatty acids: molecular weapons against chemoresistance in breast cancer.
Cell Mol Biol Lett
January 2025
Department of Pharmacy, Health and Nutritional Sciences, University of Calabria, Arcavacata Di Rende, 87036, Cosenza, Italy.
Breast cancer is the most commonly diagnosed type of cancer and the leading cause of cancer-related death in women worldwide. Highly targeted therapies have been developed for different subtypes of breast cancer, including hormone receptor (HR)-positive and human epidermal growth factor receptor 2 (HER2)-positive breast cancer. However, triple-negative breast cancer (TNBC) and metastatic breast cancer disease are primarily treated with chemotherapy, which improves disease-free and overall survival, but does not offer a curative solution for these aggressive forms of breast cancer.
View Article and Find Full Text PDFProteomic profiling identifies upregulation of aurora kinases causing resistance to taxane-type chemotherapy in triple negative breast cancer.
Sci Rep
January 2025
Department of Genetics, The University of Alabama at Birmingham, Birmingham, AL, USA.
Nowadays, chemotherapy and immunotherapy remain the major treatment strategies for Triple-Negative Breast Cancer (TNBC). Identifying biomarkers to pre-select and subclassify TNBC patients with distinct chemotherapy responses is essential. In the current study, we performed an unbiased Reverse Phase Protein Array (RPPA) on TNBC cells treated with chemotherapy compounds and found a leading significant increase of phosphor-AURKA/B/C, AURKA, AURKB, and PLK1, which fall into the mitotic kinase group.
View Article and Find Full Text PDFPersonality traits of women with hereditary risk for breast/ovarian cancer versus obstetric history and cancer preventive behaviors.
Sci Rep
January 2025
Chair of Obstetrics Development, Faculty of Health Sciences, Medical University of Lublin, Lublin, Poland.
The aim of the study is to analyze the relationship between personality traits of women with hereditary predisposition to breast/ovarian cancer and their obstetric history and cancer-preventive behaviors. A total of 357 women, participants of 'The National Program for Families With Genetic/Familial High Risk for Cancer', were included in the study. The Neo Five-Factor Inventory (NEO-FFI) and a standardized original questionnaire designed for the purpose of the study were used.
View Article and Find Full Text PDFA quantum-optimized approach for breast cancer detection using SqueezeNet-SVM.
Sci Rep
January 2025
College of Information Science and Technology, Hainan Normal University, Haikou, 571158, China.
Breast cancer is one of the most aggressive types of cancer, and its early diagnosis is crucial for reducing mortality rates and ensuring timely treatment. Computer-aided diagnosis systems provide automated mammography image processing, interpretation, and grading. However, since the currently existing methods suffer from such issues as overfitting, lack of adaptability, and dependence on massive annotated datasets, the present work introduces a hybrid approach to enhance breast cancer classification accuracy.
View Article and Find Full Text PDFThe diagnostic value of cytology in the mammary intraductal lesions of patients with pathological nipple discharge.
Sci Rep
January 2025
Department of Thyroid and Breast Surgery, Liaoning Provincial People's Hospital, People's Hospital of China Medical University), Shenyang, China.
This study aimed to explore the diagnostic value of the two cytology techniques, including liquid-based cytology of mammary ductal lavage fluid and nipple discharge smear cytology, in the intraductal lesions in patients with pathological nipple discharge (PND). This retrospective analysis included 119 patients with PND who underwent surgical treatment. At the same time, they all underwent fiberoptic ductoscopy (FDS), nipple discharge smear cytology and liquid-based cytology of ductal lavage fluid before surgery.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!