-
The Oncologist Feb 2024Rare cancers and other rare nonmalignant tumors comprise 25% of all cancer diagnoses and account for 25% of all cancer deaths. They are difficult to study due to many...
Rare cancers and other rare nonmalignant tumors comprise 25% of all cancer diagnoses and account for 25% of all cancer deaths. They are difficult to study due to many factors, including infrequent occurrence, lack of a universal infrastructure for data and/or tissue collection, and a paucity of disease models to test potential treatments. For each individual rare cancer, the limited number of diagnosed cases makes it difficult to recruit sufficient patients for clinical studies, and rare cancer research studies are often siloed. As a result, progress has been slow for many of these cancers. While rare cancer research efforts have increased over time, the breadth of the research landscape is not known. A recent literature search revealed a sharp increase in rare tumor, and rare cancer publications began in the early 2000s. To identify rare cancer research efforts being conducted in the US and globally, we conducted an online search of rare tumor/rare cancer research programs and identified 76 programs. To gain a deeper understanding of these programs, we composed and conducted a survey to ask programs for details about their research efforts. Of the 42 programs contacted to complete the survey, 23 programs responded. Survey results show most programs are collecting clinical data, molecular data, and biospecimens, and many are conducting molecular analyses. This landscape analysis demonstrates that multiple rare cancer research efforts are ongoing, and the rare cancer community may benefit from collaboration among stakeholders to accelerate research and improve patient outcomes.
Topics: Humans; Neoplasms; Tissue Banks; Rare Diseases; Biomedical Research
PubMed: 37878787
DOI: 10.1093/oncolo/oyad285 -
Clinical & Translational Oncology :... May 2024This study aimed to develop a set of criteria and indicators to evaluate the quality of care of patients with head and neck cancer (HNC).
PURPOSE
This study aimed to develop a set of criteria and indicators to evaluate the quality of care of patients with head and neck cancer (HNC).
METHODS
A systematic literature review was conducted to identify valuable criteria/indicators for the assessment of the quality of care in HNC. With the aid of a technical group, a scientific committee of oncologists specialised in HNC used selected criteria to propose indicators that were evaluated with a two-round Delphi method. Indicators on which consensus was achieved were then prioritised by the scientific committee to develop a final set of indicators.
RESULTS
We proposed a list of 50 indicators used in the literature or developed by us to be evaluated with a Delphi method. There was consensus on the appropriateness of 47 indicators in the first round; the remaining 3 achieved consensus in the second round. The 50 indicators were scored to prioritise them, leading to a final selection of 29 indicators related to structure (3), process (22), or outcome (4) and covering diagnosis, treatment, follow-up, and health outcomes in patients with HNC. Easy-to-use index cards were developed for each indicator, with their criterion, definition, formula for use in real-world clinical practice, rationale, and acceptable level of attainment.
CONCLUSIONS
We have developed a set of 29 evidence-based and expert-supported indicators for evaluating the quality of care in HNC, covering diagnosis, treatment, follow-up, and health outcomes.
Topics: Humans; Spain; Quality Indicators, Health Care; Head and Neck Neoplasms; Consensus; Delphi Technique
PubMed: 37848694
DOI: 10.1007/s12094-023-03298-z -
The Oncologist Jan 2024Breast surgery in cases of de novo metastatic breast cancer (MBC) is associated with improved outcomes in retrospective studies, although the results of randomized... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Breast surgery in cases of de novo metastatic breast cancer (MBC) is associated with improved outcomes in retrospective studies, although the results of randomized controlled trials (RCTs) are conflicting. We aimed to investigate whether surgery in this context prolongs patient survival.
METHODS
We performed a systematic review of the literature to identify RCTs comparing surgery of primary breast cancer to no surgery in patients with de novo MBC. Cochrane Library, Embase, Medline (OVID), and Web of Science were searched with latest update in July 2023, while conference proceedings were manually searched. Data concerning patient and tumor characteristics, as well as outcomes, were extracted. A meta-analysis with random effects models was performed considering heterogeneity between trials.
RESULTS
Overall, 3255 entries were identified and 5 RCTs fulfilled all inclusion criteria, which had enrolled 1381 patients. The overall estimation in the intention-to-treat population showed no benefit for patients who had surgical excision of the primary breast tumor (HR = 0.93; 95% CI, 0.76-1.14). No subgroups in terms of receptor status or patterns of metastasis seemed to benefit from surgery, except for younger/premenopausal patients (HR = 0.74, 95% CI, 0.58-0.94). Breast surgery was associated with improved local progression-free survival (HR = 0.37, 95% CI, 0.19-0.74).
CONCLUSION
Surgery of the primary tumor in patients with de novo MBC does not prolong survival, except possibly in younger/premenopausal patients. Breast surgery should be offered within the context of well-designed clinical trials examining the issue.
Topics: Humans; Female; Breast Neoplasms; Mastectomy; Breast; Retrospective Studies
PubMed: 37700450
DOI: 10.1093/oncolo/oyad266 -
European Journal of Obstetrics,... Oct 2023Following compelling evidence that open techniques may be related to better survival and disease free survival rates, many gynecologic oncologists in the US have turned... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
Following compelling evidence that open techniques may be related to better survival and disease free survival rates, many gynecologic oncologists in the US have turned away from performing laparoscopic radical hysterectomy (LRH) and robotic radical hysterectomy (RRH) for the treatment of early-stage cervical cancer. While this may be warranted as a safety concern, there is little high-quality data on the head-to-head comparison of LRH and RRH and therefore little evidence to answer the question of where this decrease in patient survival is originating from. In our systematic review, we aimed to compare the complications and outcomes of LRH against those of RRH.
DATA SOURCES
We searched PubMed, Cochrane CENTRAL, Medline, ClinicalTrials.Gov, SCOPUS, and Web of Science from database inception until February 1st, 2022.
METHODS OF STUDY SELECTION
A total of 676 studies were identified and screened through a manual three-step process. Ultimately 33 studies were included in our final analysis. We included all studies that compared LRH and RRH and included at least one of our selected outcomes. We included retrospective cohorts, prospective cohorts, case-control, and randomized clinical trials.
TABULATION, INTEGRATION, AND RESULTS
Data was independently extracted manually by multiple observers and the analysis was performed using Review Manager Software. PRISMA guidelines were followed. We analyzed homogenous data using a fixed-effects model, while a random-effects model was used for heterogeneous outcomes. We found that following RRH, women had a decreased hospital stay (MD = 0.80[0.38,1.21],(P < 0.002). We found no differences in estimated blood loss (MD = 35.24[-0.40,70.89],(P = 0.05), blood transfusion rate ((OR = 1.32[0.86,2.02],(P = 0.20), rate of post-operative complications (OR = 0.84[0.60,1.17],(P = 0.30), the operative time (MD = 6.01[-4.64,16.66],(P = 0.27), number of resected lymph node (MD = -1.22[-3.28,0.84],(P = 0.25) intraoperative complications (OR = 0.78[0.51,1.19],(P = 0.25), five-year overall survival (OR = 1.37[0.51,3.69],(P = 0.53), lifetime disease free survival (OR = 0.89[0.59,1.32],(P = 0.55), intraoperative and postoperative mortality (within 30 days) (OR = 1.30[0.66,2.54],(P = 0.44), and recurrence (OR = 1.14[0.79,1.64],(P = 0.50).
CONCLUSIONS
RRH seems to result in the patient leaving the hospital sooner after surgery. We were unable to find any differences in our ten other outcomes related to complications or efficacy. These findings suggest that the decreased survival seen in minimally invasive RH in previous studies could be due to factors inherent to both LRH and RRH.
PROSPERO PROSPECTIVE REGISTRATION NUMBER
CRD42022273727.
Topics: Female; Humans; Robotic Surgical Procedures; Prospective Studies; Retrospective Studies; Uterine Cervical Neoplasms; Hysterectomy; Laparoscopy
PubMed: 37690282
DOI: 10.1016/j.ejogrb.2023.09.002 -
Cancer Medicine Sep 2023With the rapid increase in the prevalence of cancer worldwide, the utilization of complementary and alternative medicine (CAM) has increased among cancer patients. This... (Review)
Review
BACKGROUND
With the rapid increase in the prevalence of cancer worldwide, the utilization of complementary and alternative medicine (CAM) has increased among cancer patients. This review aimed to understand the perception, attitudes, and knowledge of healthcare professionals toward using CAM for cancer patients.
METHODS
A mixed-methods systematic review was undertaken in four databases. Inclusion criteria were primary studies reporting perception, attitudes, and knowledge of healthcare professionals for using CAM for cancer patients were eligible. A mixed-methods convergent synthesis was carried out, and the findings were subjected to a GRADE-CERQual assessment of confidence.
RESULTS
Forty-two studies were chosen. The majority of the studies were quantitative and had less than 100 participants. Most publications were from European countries, and oncology was the highest among the specialties. The review found the following themes: feasibility of having negative adverse effects, low expectations of using CAM among HCPs, potential positive effects of using CAM, specific CAM training may be helpful, no concrete regulations to promote CAM practice, and poor physician-patient communication.
CONCLUSIONS
Nurses had more positive views than other professions; oncologists were concerned regarding herb-drug interactions; integration of CAM into the healthcare system was favorable; HCPs felt the need to participate in specific CAM training; and HCPs agreed that CAM education should be provided more regularly. Future studies should explore the studies views of cancer patients and details of in-depth evidence of CAM in oncology settings.
PubMed: 37676102
DOI: 10.1002/cam4.6499 -
Frontiers in Medicine 2023Gastric cancer (GC) is an aggressive and clinically heterogeneous tumor, and better risk stratification of lymph node metastasis (LNM) could lead to personalized...
INTRODUCTION
Gastric cancer (GC) is an aggressive and clinically heterogeneous tumor, and better risk stratification of lymph node metastasis (LNM) could lead to personalized treatments. The role of radiomics in the prediction of nodal involvement in GC has not yet been systematically assessed. This study aims to assess the role of radiomics in the prediction of LNM in GC.
METHODS
A PubMed/MEDLINE systematic review was conducted to assess the role of radiomics in LNM. The inclusion criteria were as follows: i. original articles, ii. articles on radiomics, and iii. articles on LNM prediction in GC. All articles were selected and analyzed by a multidisciplinary board of two radiation oncologists and one surgeon, under the supervision of one radiation oncologist, one surgeon, and one medical oncologist.
RESULTS
A total of 171 studies were obtained using the search strategy mentioned on PubMed. After the complete selection process, a total of 20 papers were considered eligible for the analysis of the results. Radiomics methods were applied in GC to assess the LNM risk. The number of patients, imaging modalities, type of predictive models, number of radiomics features, TRIPOD classification, and performances of the models were reported.
CONCLUSIONS
Radiomics seems to be a promising approach for evaluating the risk of LNM in GC. Further and larger studies are required to evaluate the clinical impact of the inclusion of radiomics in a comprehensive decision support system (DSS) for GC.
PubMed: 37663653
DOI: 10.3389/fmed.2023.1189740 -
Ontario Health Technology Assessment... 2023Ovarian cancer affects the cells of the ovaries, and epithelial cancer is the most common type of malignant ovarian cancer. The homologous recombination repair pathway...
Homologous Recombination Deficiency Testing to Inform Patient Decisions About Niraparib Maintenance Therapy for High-Grade Serous or Endometrioid Epithelial Ovarian Cancer: A Health Technology Assessment.
BACKGROUND
Ovarian cancer affects the cells of the ovaries, and epithelial cancer is the most common type of malignant ovarian cancer. The homologous recombination repair pathway enables error-free repair of DNA double-strand breaks. Damage of key genes associated with this pathway leads to homologous recombination deficiency (HRD), which results in unrepaired DNA and can lead to cancer. Tumours with HRD are believed to be sensitive to treatment with poly-adenosine diphosphate (ADP)-ribose polymerase (PARP) inhibitors, such as niraparib. We conducted a health technology assessment to evaluate the clinical utility and cost-effectiveness of HRD testing to inform patient decisions about the use of niraparib maintenance therapy for patients with high-grade serous or endometrioid epithelial ovarian cancer. We also evaluated the efficacy and safety of niraparib maintenance therapy in patients with HRD or homologous recombination proficiency (HRP), the cost-effectiveness of HRD testing, the budget impact of publicly funding HRD testing, and patient preferences and values.
METHODS
We performed a systematic literature search of the clinical evidence. We assessed the risk of bias of each included study using the Cochrane risk-of-bias tool for randomized trials version 2, and the quality of the body of evidence according to the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) Working Group criteria. We performed a systematic economic literature search and conducted a cost-utility analysis with a 5-year time horizon from a public payer perspective. We also analyzed the budget impact of publicly funding HRD testing in people with ovarian cancer in Ontario. We performed a literature search for quantitative evidence of patient and provider preferences with respect to HRD testing and maintenance therapy with PARP inhibitors. To contextualize the potential value of HRD testing, we spoke with people with ovarian cancer.
RESULTS
The clinical evidence review included two studies in high-grade epithelial ovarian cancer (one in patients with newly diagnosed advanced cases and one in patients with recurrent cancer). The studies evaluated niraparib maintenance therapy compared with no maintenance therapy and used HRD testing to group patients according to HRD status. Compared to placebo, niraparib maintenance therapy improved progression-free survival in patients with newly diagnosed and recurrent ovarian cancer, and in tumours with HRD or HRP (GRADE: High), but the studies did not compare the results between the HRD and HRP groups. The frequency of adverse events was higher in the niraparib group. We identified no studies that evaluated the clinical utility of HRD testing.We conducted a primary economic evaluation to evaluate the cost-effectiveness of HRD testing for people with newly diagnosed ovarian cancer in an Ontario setting. Our analysis used a 5-year time horizon. HRD testing (for all eligible people or only for people with wild type) resulted in a lower proportion of patients receiving niraparib maintenance therapy, leading to lower costs and fewer quality-adjusted life-years (QALYs). The average total cost per patient was $131,375 for no HRD testing, $126,867 for HRD testing only in people with wild type, and $127,746 for HRD testing in all eligible people. The average total QALYs per patient were 2.087 for no HRD testing, 1.971 for HRD testing only in people with wild type, and 1.971 for HRD testing in all eligible people. Our budget impact analysis suggested that assuming a high uptake rate, publicly funding HRD testing for people with newly diagnosed ovarian cancer would lead to a total saving of $9.00 million (if HRD testing were funded for all) to $12.67 million (if HRD testing were funded for people with wild type) over the next 5 years. Publicly funding HRD testing for people with recurrent cancer would lead to a total saving of $16.31 million (if HRD testing were funded for all) to $21.67 million (if HRD testing were funded for people with wild type) over the next 5 years.We identified no studies that evaluated quantitative preferences for HRD testing. Based on two studies that evaluated patients and oncologists' preferences for maintenance therapy with a PARP inhibitor in the recurrent setting, a decrease in moderate to severe adverse events was more important for patients than an improvement in progression-free survival; however, improvement in progression-free survival was more important for oncologists. Both patients and oncologists accepted some trade-offs between efficacy and safety. The people with ovarian cancer we spoke with demonstrated a shared value for access to information, prevention of cancer recurrence, and overall survival with minimal adverse effects. This was consistent with findings from another survey in patients with ovarian cancer and at least one episode of recurrence, which suggest that patients prioritize treatment benefit over some treatment adverse events in the context of niraparib maintenance therapy. Interviewees also emphasized the importance of the patient-doctor partnership, access to local health care services, and patient education.
CONCLUSIONS
In patients with newly diagnosed (advanced) or recurrent high-grade serous or endometrioid ovarian cancer, niraparib maintenance therapy improved progression-free survival compared with no maintenance therapy in tumours with HRD or HRP (GRADE: High). Because we identified no studies on the clinical utility of HRD testing, we cannot comment on how it would affect patient decisions and clinical outcomes.Over a 5-year time horizon, HRD testing for people with wild type could save $4,509 per person and lead to a loss of 0.116 QALY. The findings of our economic analyses are dependent on assumptions about the use of niraparib following HRD testing. We estimate that publicly funding HRD testing would lead to a total saving of $9 million to $12.67 million for newly diagnosed cancer, and a total saving of $16.31 million to $21.67 million for recurrent cancer over 5 years, assuming the use of niraparib maintenance therapy would be reduced following HRD testing.Patients prioritized decreasing the risk of moderate to severe adverse events of maintenance therapy with PARP inhibitors over improving progression-free survival, and oncologists prioritized improving progression-free survival over decreasing the risk of moderate to severe adverse events. However, both patients and oncologists were open to accepting certain trade-offs between treatment efficacy and toxicity. The people we interviewed, who had lived experience with ovarian cancer and genetic testing, valued the potential clinical benefits of HRD testing for themselves and their family members. They emphasized patient education as an important consideration for public funding in Ontario.
Topics: Humans; Female; Carcinoma, Ovarian Epithelial; Technology Assessment, Biomedical; Poly(ADP-ribose) Polymerase Inhibitors; Carcinoma, Endometrioid; Ovarian Neoplasms
PubMed: 37637244
DOI: No ID Found -
The Oncologist Nov 2023Due to increased use of imaging, advanced stages of cancer are increasingly being diagnosed in an early, asymptomatic phase. Traditionally, chemotherapy is started... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Due to increased use of imaging, advanced stages of cancer are increasingly being diagnosed in an early, asymptomatic phase. Traditionally, chemotherapy is started immediately in these patients. However, a strategy wherein chemotherapy is withheld until symptoms occur may be beneficial for patients in terms of quality of life (QOL). A systematic review regarding optimal timing of chemotherapy including survival and QOL is lacking.
METHODS
We systematically searched PubMed, EMBASE, and Cochrane for studies investigating the timing of start of chemotherapy in asymptomatic patients with advanced cancer. Overall survival (OS) was abstracted as primary, QOL, and toxicity as secondary outcomes. A meta-analysis was performed on OS. QOL was described using the global health status derived from the EORTC-QLQ-C30 questionnaire and toxicity as grade 3-4 adverse events.
RESULTS
Overall, 919 patients from 4 randomized controlled trials and 1 retrospective study were included. The included studies investigated colorectal cancer (n = 3), ovarian cancer (n = 1), and gastric cancer (n = 1). Pooled analysis demonstrated no significant differences in OS between delayed and immediate start of chemotherapy (pooled HR: 1.05, 95% CI, 0.90-1.22, P = .52). QOL, evaluated in 3 studies, suggested a better QOL in the delayed treatment group. Toxicity, evaluated in 2 studies, did not differ significantly between groups.
CONCLUSION
This meta-analysis confirms the need for prospective studies on timing of start of chemotherapy in asymptomatic patients with advanced cancer. The limited evidence available suggests that delayed start of chemotherapy, once symptoms occur, as compared to immediate start in asymptomatic patients does not worsen OS while it may preserve QOL.
Topics: Female; Humans; Quality of Life; Prospective Studies; Retrospective Studies; Stomach Neoplasms; Ovarian Neoplasms
PubMed: 37589234
DOI: 10.1093/oncolo/oyad235 -
The Cochrane Database of Systematic... Aug 2023This is the third update of the original Cochrane Review published in July 2005 and updated previously in 2012 and 2016. Cancer is a significant global health issue.... (Review)
Review
BACKGROUND
This is the third update of the original Cochrane Review published in July 2005 and updated previously in 2012 and 2016. Cancer is a significant global health issue. Radiotherapy is a treatment modality for many malignancies, and about 50% of people having radiotherapy will be long-term survivors. Some will experience late radiation tissue injury (LRTI), developing months or years following radiotherapy. Hyperbaric oxygen therapy (HBOT) has been suggested as a treatment for LRTI based on the ability to improve the blood supply to these tissues. It is postulated that HBOT may result in both healing of tissues and the prevention of complications following surgery and radiotherapy.
OBJECTIVES
To evaluate the benefits and harms of hyperbaric oxygen therapy (HBOT) for treating or preventing late radiation tissue injury (LRTI) compared to regimens that excluded HBOT.
SEARCH METHODS
We used standard, extensive Cochrane search methods. The latest search date was 24 January 2022.
SELECTION CRITERIA
We included randomised controlled trials (RCTs) comparing the effect of HBOT versus no HBOT on LRTI prevention or healing.
DATA COLLECTION AND ANALYSIS
We used standard Cochrane methods. Our primary outcomes were 1. survival from time of randomisation to death from any cause; 2. complete or substantial resolution of clinical problem; 3. site-specific outcomes; and 4.
ADVERSE EVENTS
Our secondary outcomes were 5. resolution of pain; 6. improvement in quality of life, function, or both; and 7. site-specific outcomes. We used GRADE to assess certainty of evidence.
MAIN RESULTS
Eighteen studies contributed to this review (1071 participants) with publications ranging from 1985 to 2022. We added four new studies to this updated review and evidence for the treatment of radiation proctitis, radiation cystitis, and the prevention and treatment of osteoradionecrosis (ORN). HBOT may not prevent death at one year (risk ratio (RR) 0.93, 95% confidence interval (CI) 0.47 to 1.83; I = 0%; 3 RCTs, 166 participants; low-certainty evidence). There is some evidence that HBOT may result in complete resolution or provide significant improvement of LRTI (RR 1.39, 95% CI 1.02 to 1.89; I = 64%; 5 RCTs, 468 participants; low-certainty evidence) and HBOT may result in a large reduction in wound dehiscence following head and neck soft tissue surgery (RR 0.24, 95% CI 0.06 to 0.94; I = 70%; 2 RCTs, 264 participants; low-certainty evidence). In addition, pain scores in ORN improve slightly after HBOT at 12 months (mean difference (MD) -10.72, 95% CI -18.97 to -2.47; I = 40%; 2 RCTs, 157 participants; moderate-certainty evidence). Regarding adverse events, HBOT results in a higher risk of a reduction in visual acuity (RR 4.03, 95% CI 1.65 to 9.84; 5 RCTs, 438 participants; high-certainty evidence). There was a risk of ear barotrauma in people receiving HBOT when no sham pressurisation was used for the control group (RR 9.08, 95% CI 2.21 to 37.26; I = 0%; 4 RCTs, 357 participants; high-certainty evidence), but no such increase when a sham pressurisation was employed (RR 1.07, 95% CI 0.52 to 2.21; I = 74%; 2 RCTs, 158 participants; high-certainty evidence).
AUTHORS' CONCLUSIONS
These small studies suggest that for people with LRTI affecting tissues of the head, neck, bladder and rectum, HBOT may be associated with improved outcomes (low- to moderate-certainty evidence). HBOT may also result in a reduced risk of wound dehiscence and a modest reduction in pain following head and neck irradiation. However, HBOT is unlikely to influence the risk of death in the short term. HBOT also carries a risk of adverse events, including an increased risk of a reduction in visual acuity (usually temporary) and of ear barotrauma on compression. Hence, the application of HBOT to selected participants may be justified. The small number of studies and participants, and the methodological and reporting inadequacies of some of the primary studies included in this review demand a cautious interpretation. More information is required on the subset of disease severity and tissue type affected that is most likely to benefit from this therapy, the time for which we can expect any benefits to persist and the most appropriate oxygen dose. Further research is required to establish the optimum participant selection and timing of any therapy. An economic evaluation should also be undertaken.
Topics: Humans; Hyperbaric Oxygenation; Radiation Injuries; Neoplasms; Osteoradionecrosis; Disease Progression; Pain; Barotrauma
PubMed: 37585677
DOI: 10.1002/14651858.CD005005.pub5 -
JCO Clinical Cancer Informatics Aug 2023Selection of appropriate adjuvant therapy to ultimately reduce the risk of breast cancer (BC) recurrence is a challenge for medical oncologists. Several automated risk... (Review)
Review
PURPOSE
Selection of appropriate adjuvant therapy to ultimately reduce the risk of breast cancer (BC) recurrence is a challenge for medical oncologists. Several automated risk prediction models have been developed using retrospective clinical data and have evolved significantly over the years in terms of predictors of recurrence, data usage, and predictive techniques (statistical/machine learning [ML]).
METHODS
Following PRISMA guidelines, we performed a systematic literature review of the aforementioned statistical and ML models published between January 2008 and December 2022 through searching five digital databases-PubMed, ScienceDirect, Scopus, Cochrane, and Web of Science. The comprehensive search yielded a total of 163 papers and after a screening process focusing on papers that dealt exclusively with statistical/ML methods, only 23 papers were deemed appropriate for further analysis. We benchmarked the studies on the basis of development, evaluation metrics, and validation strategy with an added emphasis on racial diversity of patients included in the studies.
RESULTS
In total, 30.4% of the included studies use statistical techniques, while 69.6% are ML-based. Among these, traditional ML models (support vector machines, decision tree, logistic regression, and naïve Bayes) are the most frequently used (26.1%) along with deep learning (26.1%). Deep learning and ensemble learning provide the most accurate predictions (AUC = 0.94 each).
CONCLUSION
ML-based prediction models exhibit outstanding performance, yet their practical applicability might be hindered by limited interpretability and reduced generalization. Moreover, predictive models for BC recurrence often focus on limited variables related to tumor, treatment, molecular, and clinical features. Imbalanced classes and the lack of open-source data sets impede model development and validation. Furthermore, existing models predominantly overlook African and Middle Eastern populations, as they are trained and validated mainly on Caucasian and Asian patients.
Topics: Humans; Female; Breast Neoplasms; Retrospective Studies; Bayes Theorem; Neoplasm Recurrence, Local; Machine Learning
PubMed: 37566789
DOI: 10.1200/CCI.23.00049