Materiały źródłowe

• #1 Physicians’ clinical prediction of survival in head and neck cancer patients in the palliative phase | BMC Palliative Care | Full Text

  https://bmcpalliatcare.biomedcentral.com/articles/10.1186/s12904-020-00682-2

  The prognosis of patients with incurable head and neck cancer (HNC) is a relevant topic. The mean survival of these patients is 5 months but may vary from weeks to more than 3 years. […] Physicians tend to overestimate the survival of palliative HNC patients. This optimism can result in suboptimal use of palliative and end-of-life care. […] HNC patients in general have a poor prognosis. The five-year survival rate varies between 30 and 70%, depending on the stage and location of the tumor. […] In 59% of cases survival was overestimated. These patients lived shorter than predicted by their physician (median AS 6 weeks, median CPS 20 weeks). In 18% of the cases survival was correctly predicted. The remaining 23% was underestimated (median AS 35 weeks, median CPS 20 weeks). […] This study set out to examine the accuracy of physicians clinical prediction of survival in palliative HNC. Survival predictions were accurate in less than one out of five palliative HNC patients (18%), while 59% of the predictions were overoptimistic, meaning that patients lived shorter than predicted by their physician.

• #2 Prognosis Prediction in Head and Neck Squamous Cell Carcinoma by Radiomics and Clinical Information

  https://www.mdpi.com/2227-9059/12/8/1646

  Prognosis Prediction in Head and Neck Squamous Cell Carcinoma by Radiomics and Clinical Information […] (1) Background: head and neck squamous cell carcinoma (HNSCC) is a common cancer whose prognosis is affected by its heterogeneous nature. We aim to predict 5-year overall survival in HNSCC radiotherapy (RT) patients by integrating radiomic and clinical information in machine-learning models; […] Despite the advancement of multi-modality treatment, the 5-year survival rate in patients with HNSCC is still less than 50% due to late diagnosis and the high risk of disease recurrence. […] To date, only programmed death-ligand 1 (PD-L1) and human papillomavirus (HPV) expressions are considered as useful biomarkers in HNSCC. […] Radiomics can potentially identify previously unknown tumor markers to improve prognosis prediction in large datasets. […] The ensemble technique may be combined with radiomic and clinical information for further enhancing the predictive outcome. […] Therefore, the addition of HPV status information could be important for a prognosis prediction of HNSCC. […] Heterogeneity remains a major concern affecting HNSCC prognosis and HPV information has been emerging as an important biomarker in HNSCC. […] In this study, we aimed to predict 5-year overall survival in HNSCC radiotherapy patients by integrating radiomic and clinical information in machine-learning models. […] The PWEM achieved an AUC of 0.86 with the accuracy significantly greater than the VCF model. This highlights the complementary nature of radiomic and clinical factors, resulting in a more reliable and precise prognosis prediction. […] Our radiomic–clinical combined model revealed superior performance (AUC = 0.86) when compared to radiomic and clinical factor models (AUC = 0.77 and 0.78, respectively) alone. It is evident that the ensemble model can improve prognosis prediction. Nevertheless, further prospective research with larger sample sizes is required to implement the model for clinical use. Furthermore, we revealed that T stage, age, and disease site were the most important prognostic factors in the clinical factor model.

• #3 Prognostic and Predictive Factors in Advanced Head and Neck Squamous Cell Carcinoma

  https://www.mdpi.com/1422-0067/22/9/4981

  Head and neck squamous cell carcinoma (HNSCC) is a heterogeneous disease arising from the mucosa of the upper aerodigestive tract. Despite multimodality treatments approximately half of all patients with locally advanced disease relapse and the prognosis of patients with recurrent or metastatic HNSCC is dismal. […] The overall outcome of patients with locally advanced HNSCC is poor and even after modern, multimodality treatments between 40–50% of the patients experience disease recurrence. […] Overall, these studies show that there is an urgent need to improve the treatment strategies for patients with advanced HNSCC. […] HPV positive OPSCC is nowadays seen as a distinct entity when compared to HPV negative disease due to the differences in the molecular profiles, clinical presentation, and prognosis.

• #4

  https://pmc.ncbi.nlm.nih.gov/articles/PMC5782422/

  The prognosis for HNC overall has improved slightly since the 1990s, and is influenced by site, stage, molecular markers and HPV status. […] Age and tumour staging are considered the most important prognostic factors for overall survival. Recurrence and second primary tumours are influenced negatively by high alcohol consumption and cigarette smoking.

• #5

  https://pmc.ncbi.nlm.nih.gov/articles/PMC5782422/

  This study was undertaken to evaluate the association between demographics, lifestyle habits, and clinical data and overall survival (OS), recurrence and second primary cancer (SPC) in patients with first primary head and neck cancer (HNC). […] Five-year OS was 60.6% for all HNC cases, 49.0% for oral cavity, 54.8% for oropharynx, 50.0% for hypopharynx and 63.4% for larynx. Predictors of OS were older age (HR = 1.04; 95% CI: 1.02-1.05) and advanced tumour stage (HR = 2.00; 95% CI: 1.41-2.84). […] OS differed among HNC sites. Increasing age was an unfavourable predictor of HNC OS. Tumour stage was a prognostic factor both for OS and for risk of developing SPC. Alcohol and tobacco consumption were prognostic factors for recurrence and SPC, respectively. […] We report a significant association between advanced tumour stage (S III-IV) and poor overall and disease-specific survival.

• #6 Prognostic and Predictive Factors in Advanced Head and Neck Squamous Cell Carcinoma

  https://www.mdpi.com/1422-0067/22/9/4981

  Several other trials have also shown that p16 positivity is associated with a significantly better prognosis in patients with OPSCC compared to patients with p16 negative disease. […] The exact prognostic role of HPV infection and p16 positivity in non-oropharyngeal HNSCC is still unclear and at present, routine testing is not recommended. […] The higher rate of CD4+ cells, the larger infiltration of activated CD8+ T cells, and the lower count of regulatory T cells in the microenvironment of HPV positive OPSCC shows that these tumors are less immunosuppressive when compared to HPV negative disease. […] Overall, these studies show that TILs and circulating immune cells have the potential to serve as prognostic and predictive biomarkers in HNSCC but confirmation in prospective trials is needed. […] Until today the only validated and routinely used biomarkers are p16 IHC in patients with OPSCC and the CPS for treatment selection in patients with recurrent or metastatic disease.

• #7 Prognosis and survival prediction by tumor markers in head and neck cancer patients

  https://www.oatext.com/prognosis-and-survival-prediction-by-tumor-markers-in-head-and-neck-cancer-patients.php

  Prognosis of HNC patients depends on stage of the disease, lymph nodes involvement and response to therapy. […] CEA, SCC, TPS, CYFRA 21-1 and sIL-2R are all useful Tumor Markers in the management of HNC patients. They assessed response to therapy, were prognostic for recurrence earlier than CT and predicted survival. […] The Tumor Markers sIL-2R and Cyfra 21-1 levels, were best correlated to prediction of patients survival. Patients having low levels had the best clinical outcome and a longer survival according to ROC analysis. […] Our findings of the present study including a large number of patients and comparison to other studies- should refer to Multi-Centric or Meta-analysis studies including also large numbers of patients and long follow up- to establish the significance for routine clinical practice. […] In summary, the most important, out of our panel of Tumor Markers studied, are: Cyfra 21-1 and sIL-2R, providing good prognosis and therapy response assessment.

• #8 Tumor volumes predict prognosis in head and neck cancer: a meta-analysis – Xie – Translational Cancer Research

  https://tcr.amegroups.org/article/view/15151/html

  Head and neck cancers (HNCs) are the 6th most common cancer worldwide and account for 4% of malignancies. Recent studies implied that tumor volumes play a useful prognostic role in HNC. This meta-analysis based on published studies was performed with the aim of obtaining an accurate evaluation of the relationship between tumor volume and prognosis of HNC. […] We found that HNC with a primary gross tumor volume (GTVp) larger than the cut-off value were associated with an increased risk of local control failure (pooled HR =1.34; 95% CI =1.221.47). For the longtime survival, a larger GTVp was significantly associated with disease free survival (DFS) (pooled HR =1.34; 95% CI =1.231.46) and overall survival (OS) (pooled HR =1.27; 95% CI =1.171.37). […] The GTVp and MTVp were highly significant in evaluating local control, OS and DFS of patients with HNC and might be a useful adjuvant and complementary index for a new T staging system in HNC.

• #9 Tumor volumes predict prognosis in head and neck cancer: a meta-analysis – Xie – Translational Cancer Research

  https://tcr.amegroups.org/article/view/15151/html

  From the literature, it appears that tumor volume (GTVp and MTVp) is a significant factor associated with outcomes in HNC. […] The pooled analysis implied that a larger MTVp also indicted a worse prognosis. […] Results from this analysis demonstrated that tumor volume (GTVp or MTVp) was a useful prognostic marker, and HNC patients with larger tumor volumes are associated with unfavorable local control and long-term survival.

• #10 Deep learning in head & neck cancer outcome prediction | Scientific Reports

  https://www.nature.com/articles/s41598-019-39206-1

  Traditional radiomics involves the extraction of quantitative texture features from medical images in an attempt to determine correlations with clinical endpoints. […] We test this hypothesis by training a CNN to predict treatment outcomes of patients with head and neck squamous cell carcinoma, based solely on their pre-treatment computed tomography image. […] Our framework yields models that are shown to explicitly recognize traditional radiomic features, be directly visualized and perform accurate outcome prediction. […] Thus, the development of a model capable of identifying potential high-risk patients prior to treatment is critical. […] A high-risk patient could be assigned a more aggressive treatment regimen, potentially improving their outcome. […] The primary focus of this work is to build a model that is capable of discerning high-risk HN cancer patients prior to their treatment using solely their computed tomography (CT) image.

• #11 Development and validation of survival prognostic models for head and neck cancer patients using machine learning and dosiomics and CT radiomics features: a multicentric study | Radiation Oncology | Full Text

  https://ro-journal.biomedcentral.com/articles/10.1186/s13014-024-02409-6

  This study aimed to investigate the value of clinical, radiomic features extracted from gross tumor volumes (GTVs) delineated on CT images, dose distributions (Dosiomics), and fusion of CT and dose distributions to predict outcomes in head and neck cancer (HNC) patients. […] Our results demonstrated that clinical features, Dosiomics and fusion of dose and CT images by specific ML-FS models could predict the overall survival of HNC patients with acceptable accuracy. […] The use of radiomics analysis as a noninvasive, fast, and cost-efficient approach to extract various image-based quantitative features has proven to be valuable for patient prognosis and outcome prediction modeling. […] Several studies have shown that using multi-modality fusion-based radiomic features from different medical imaging modalities, such as CT, MRI, and PET can significantly improve the predictive power of radiomics for other cancer types.

• #12 Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures

  https://www.repository.cam.ac.uk/items/af325140-7966-474a-8a3f-f1005da705af

  Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. […] The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. […] In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). […] By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only (p 0.001).

• #13

  https://link.springer.com/article/10.1007/s00330-020-06962-y

  Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. […] In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only (p 0.001).

• #14 Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures

  https://www.repository.cam.ac.uk/items/af325140-7966-474a-8a3f-f1005da705af

  MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.

• #15

  https://link.springer.com/article/10.1007/s00330-020-06962-y

  MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models. […] This study was set out to develop prognostic models based on MRI radiomics in oral cavity and oropharyngeal cancer patients. […] In validation setting, the prognostic performance of these models was accurate, and the combined models outperformed clinical characteristics alone in predicting both OS and RFS. These results are very promising and indicate that MRI radiomic analysis may have additional value to current prognostic variables.

• #16 Deep learning in head & neck cancer outcome prediction | Scientific Reports

  https://www.nature.com/articles/s41598-019-39206-1

  The novel contributions of this work are three-fold. Firstly, we develop a deep CNN-based framework capable of accurately predicting HN cancer treatment outcomes based solely on a patients pre-treatment CT image. […] The ability of our network to directly recognize radiomic features without being told their definition is powerful for a number of reasons, one of which being it may remove the need to specifically engineer new features. […] This indicates that although our network does recognize the features to some extent, it does not directly represent them. […] This report showed the power and potential of using a deep convolutional neural network built de novo to perform outcome predictions on the pre-treatment CT image of head and neck cancer patients. […] Our framework shows that a training set of 200 medical gray-scale images may be sufficient to train a network de novo, with proper data augmentation. […] The model was shown to have the ability to explicitly recognize radiomic features and further improve on the performance of a traditional radiomics framework.

• #17 Development and validation of survival prognostic models for head and neck cancer patients using machine learning and dosiomics and CT radiomics features: a multicentric study | Radiation Oncology | Full Text

  https://ro-journal.biomedcentral.com/articles/10.1186/s13014-024-02409-6

  However, to the best of our knowledge, previous studies barely integrated the dose distribution with one of the imaging modalities to predict prognosis or treatment outcome for HNCs using fusion-based features. […] Our results demonstrated that the 3D dose distribution included valuable information highly correlated with overall survival prediction in HNC patients. […] The fusion-based models showed a comparable result to dosimics tending to improve the results of overall survival prediction probably by training models with large-scale datasets.

• #18 Prognosis Prediction in Head and Neck Squamous Cell Carcinoma by Radiomics and Clinical Information

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11352052/

  (1) Background: head and neck squamous cell carcinoma (HNSCC) is a common cancer whose prognosis is affected by its heterogeneous nature. We aim to predict 5-year overall survival in HNSCC radiotherapy (RT) patients by integrating radiomic and clinical information in machine-learning models; […] (3) Results: a total of 299 cases were included in the analysis. By receiver operating characteristic (ROC) curve analysis, PWEM achieved an area under the curve (AUC) of 0.86, which outperformed both radiomic and clinical factor models. Mean decrease accuracy, mean decrease Gini, and a chi-square test identified T stage, age, and disease site as the most important clinical factors in prognosis prediction; […] (4) Conclusions: our radiomicclinical combined model revealed superior performance when compared to radiomic and clinical factor models alone. Further prospective research with a larger sample size is warranted to implement the model for clinical use.

• #19 Prognosis Prediction in Head and Neck Squamous Cell Carcinoma by Radiomics and Clinical Information

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11352052/

  We noticed that several clinical factors are more important for prognosis prediction using MDA, MDG, and chi-square tests. These factors include T stage, age, and disease site. […] Based on our findings, it is suggested that T stage, age, and disease site were crucial for prognosis prediction and should be considered for building future prediction models. […] To conclude, we employed a probability-weighted approach integrating both radiomic and clinical information to predict HNSCC survival. Our radiomicclinical combined model revealed superior performance (AUC = 0.86) when compared to radiomic and clinical factor models (AUC = 0.77 and 0.78, respectively) alone. It is evident that the ensemble model can improve prognosis prediction.

• #20 Prognosis Prediction in Head and Neck Squamous Cell Carcinoma by Radiomics and Clinical Information

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11352052/

  Heterogeneity remains a major concern affecting HNSCC prognosis and HPV information has been emerging as an important biomarker in HNSCC. Meanwhile, the use of an ensembled technique with both radiomic and clinical information may offer excellent predictive capability compared to previous studies. In this study, we aimed to predict 5-year overall survival in HNSCC radiotherapy patients by integrating radiomic and clinical information in machine-learning models. […] The PWEM achieved an AUC of 0.86 with the accuracy significantly greater than the VCF model. This highlights the complementary nature of radiomic and clinical factors, resulting in a more reliable and precise prognosis prediction. […] Therefore, our prediction model of PWEM achieved a good AUC of 0.86 in predicting HNSCC prognosis with slightly better performance than previous studies. It is anticipated that PWEM could be further investigated for HNSCC prognosis prediction in clinical environments.

• #21

  https://link.springer.com/article/10.1007/s12672-023-00796-y

  The development of a robust and validated prognostic model like APMHO can have significant clinical impact for head and neck cancer management. If incorporated into clinical decision making, it can identify patients at high risk of mortality who may benefit from more aggressive treatment or closer monitoring after standard therapy. Conversely, patients classified as low risk by APMHO may be considered for treatment de-escalation to reduce toxicity without compromising outcomes. […] Overall, the present study demonstrated that the constructed APMHO scoring showed good prognostic value for HNSCC and was consistently associated with variations in clinicopathological, mutational, functional, immune cell landscapes, and cancer immunotherapy-related gene expression patterns.

• #22 Predicting progression-free survival after systemic therapy in advanced head and neck cancer: Bayesian regression and model development | eLife

  https://elifesciences.org/articles/73288

  A predictive biomarker signature for patients with advanced HNSCC will help individualize discussions with patients regarding the risk-benefit balance of treatment and may guide patients who are likely to perform poorly towards alternative therapy regimens or clinical trials. […] The absence of predictive biomarkers in this patient cohort represents a significant clinical unmet need. […] We hypothesize that a multimodal analysis, taking into account both clinicopathological and laboratory-based biological covariates at different timepoints, would provide better predictive value. […] The risk signature can serve as a non-invasive risk stratification for patients with R/M HNSCC using only peripheral blood, guiding the clinician toward the likelihood of success early during the treatment course. […] The combined risk signature strongly correlated with a poorer treatment outcome.

• #23 Physicians’ clinical prediction of survival in head and neck cancer patients in the palliative phase | BMC Palliative Care | Full Text

  https://bmcpalliatcare.biomedcentral.com/articles/10.1186/s12904-020-00682-2

  Discussing prognosis as soon as possible in the disease trajectory enables patients to make well-considered end-of-life choices and prepare for a good death. We hope that physicians treating HNC will become more aware of their tendency to overestimate survival, as this optimism can result in suboptimal use of palliative and end-of-life care. The future development of a prognostic model for incurable HNC patients, could help physicians with personalized prognostic counseling.

Zobacz więcej