Breast cancer (BC) is the most frequently diagnosed malignancy worldwide and a leading cause of death in women. Machine learning (ML) enables data-driven risk stratification and outcome prediction, potentially improving screening, treatment choices, and overall care. This scoping review cataloged ML models used to predict BC risk and post-treatment outcomes. A PubMed search using MeSH terms (“breast neoplasms,” “breast cancer,” “machine learning,” and “predictive value of tests”) retrieved 44 records, with 9 added by manual searching; 24 studies were included. We excluded 29 reports limited to imaging/radiomics or biomolecular/omics, plus other ineligible items. Model usage among included studies: 13 random forest (RF); 13 support vector machine; 7 decision tree; 5 k-nearest neighbors; 4 deep learning; 3 naïve Bayes; 2 artificial neural networks. Average RF accuracy surpassed 90% in most reports, indicating RF is both common and consistently strong for predictive modeling, supporting targeted clinical translation.
breast neoplasm ; machine learning ; predictive value of tests

Renal cell carcinoma (RCC) is notorious for its propensity to metastasize even after a prolonged period of remission following nephrectomy. The metastatic spread can occur months or even years after initial treatment, which necessitates a heightened level of clinical awareness and vigilance in patients with a history of renal malignancy, particularly who present with new or unexplained nasal symptoms. Although RCC most commonly metastasize to the lungs, bones and liver, its involvement in the nasal cavity is exceedingly rare, posing significant diagnostic challenges due to the non-specific nature of symptoms. We describe a case of metastatic renal cell clear cell carcinoma presenting with recurrent epistaxis and unilateral nasal obstruction. Immunohistochemistry studies play a crucial role in confirming the diagnosis and ruling out potential differential diagnoses, along with a comprehensive clinical history of the patient.

INTRODUCTION: The most recent local study on the incidence of histological subtypes of all brain and spinal tumours treated surgically was published in 2000. In view of the outdated data, we investigated the presenting characteristics, histological subtypes and outcomes of adult patients who underwent surgery for brain or spinal tumours at our institution. METHODS: A single-centre retrospective review of 501 patients who underwent surgery for brain or spinal tumours from 2016 to 2020 was conducted. The inclusion criteria were (a) patients who had a brain or spinal tumour that was histologically verified and (b) patients who were aged 18 years and above at the time of surgery. RESULTS: Four hundred and thirty-five patients (86.8%) had brain tumours and 66 patients (13.2%) had spinal tumours. Patients with brain tumours frequently presented with cranial nerve palsy, headache and weakness, while patients with spinal tumours frequently presented with weakness, numbness and back pain. Overall, the most common histological types of brain and spinal tumours were metastases, meningiomas and tumours of the sellar region. The most common complications after surgery were cerebrospinal fluid leak, diabetes insipidus and urinary tract infection. In addition, 15.2% of the brain tumours and 13.6% of the spinal tumours recurred, while 25.7% of patients with brain tumours and 18.2% of patients with spinal tumours died. High-grade gliomas and metastases had the poorest survival and highest recurrence rates. CONCLUSION This study serves as a comprehensive update of the epidemiology of brain and spinal tumours and could help guide further studies on brain and spinal tumours.
Humans ; Retrospective Studies ; Female ; Male ; Middle Aged ; Adult ; Aged ; Central Nervous System Neoplasms/pathology* ; Brain Neoplasms/pathology* ; Treatment Outcome ; Postoperative Complications ; Young Adult ; Spinal Neoplasms/pathology* ; Neoplasm Recurrence, Local ; Aged, 80 and over ; Adolescent

INTRODUCTION: Testicular tumours in childhood have diverse characteristics for different age ranges. This study aimed to describe the pattern, presentation and outcomes of primary testicular tumours in a paediatric population. METHODS: A retrospective study was conducted from January 2010 to December 2020 on children (≤18 years) with a diagnosis of primary testicular tumour. Baseline demographics, clinical characteristics, pathology, treatment and outcomes of these patients were analysed. The data were entered into IBM SPSS Statistics version 20.0. Chi-square test and Fisher's exact test were applied to find the statistical significance, which was set at P value ≤ 0.05. RESULTS: The study included 115 males, with 85 (73.9%) patients in the prepubertal age range with a mean age of 2.53 ± 2.06 years and 30 (26.1%) patients in the postpubertal group with a mean age of 15.73 ± 1.25 years. Yolk sac tumour was the most common (62.6%) histological subtype. Majority (46.1%) of patients had stage I disease on presentation, while 29.6% had stage IV disease. All patients underwent upfront high inguinal radical orchiectomy, which was followed by platinum-based adjuvant chemotherapy in 67% of the patients. The five-year event-free survival and overall survival for all patients were 75% and 91%, respectively. CONCLUSION Primary testicular tumours follow a bimodal age distribution pattern. Majority of patients can be cured with platinum-based chemotherapy despite having advanced disease at presentation.
Humans ; Male ; Testicular Neoplasms/mortality* ; Retrospective Studies ; Adolescent ; Child ; Child, Preschool ; Orchiectomy/methods* ; Chemotherapy, Adjuvant ; Treatment Outcome ; Neoplasm Staging ; Infant ; Endodermal Sinus Tumor/therapy* ; Neoplasms, Germ Cell and Embryonal

OBJECTIVES: Renal cell carcinoma (RCC) is a malignant renal tumor that poses a significant threat to patient health. Accurate preoperative pathological grading plays a crucial role in determining the appropriate treatment for this disease. Currently, deep learning technology has become an important method for pathological grading of RCC. However, existing methods primarily rely on single-phase computed tomography (CT) imaging for analysis and prediction, which has limitations such as missing small lesions, one-sided evaluation, and local focusing issues. Therefore, this study proposes a multi-modal deep learning algorithm that integrates multi-phase enhanced CT images with clinical variable data, aiming to provide a basis for predicting the pathological grading of RCC. METHODS: First, the algorithm took four-phase enhanced CT images from the plain scan, arterial phase, venous phase, and delayed phase, along with clinical variables, as inputs. Then, an embedding encoding module was used to extract heterogeneous information from the clinical variables, and a 3-dimensional (3D) ResNet50 model was employed to capture spatial information from the multi-phase enhanced CT image data. Finally, a Fusion module deeply integrated the feature information from clinical variables and each phase's CT image features, further utilizing a cross-self-attention mechanism to achieve multi-phase feature fusion. This approach comprehensively captures the deep semantic information from the patient data, fully leveraging the complementary advantages of multi-modal and multi-phase data. To validate the effectiveness of the proposed method, a total of 1 229 RCC patients were approved by ethics review were included to train the model. RESULTS: Experimental results demonstrated superior performance compared to traditional radiomics and state-of-the-art deep learning methods, achieving an accuracy of 83.87%, a recall rate of 95.04%, and an F1-score of 82.23%. CONCLUSIONS The proposed algorithm exhibits strong stability and sensitivity, significantly enhancing the predictive performance of RCC pathological grading. It offers a novel approach for accurate RCC diagnosis and personalized treatment planning.
Humans ; Carcinoma, Renal Cell/pathology* ; Deep Learning ; Kidney Neoplasms/diagnostic imaging* ; Tomography, X-Ray Computed/methods* ; Algorithms ; Neoplasm Grading ; Male ; Female ; Middle Aged

OBJECTIVES: Increasing detection of low-risk papillary thyroid carcinoma (PTC) is associated with overdiagnosis and overtreatment. N6-methyladenosine (m⁶A)-mediated microRNA (miRNA) dysregulation plays a critical role in tumor metastasis and progression. However, the functional role of m⁶A-miRNAs in PTC remains unclear. This study aims to elucidate the regulatory mechanism of m⁶A-miR-139-5p expression in PTC, determine its association with PTC metastasis, and evaluate its potential as a diagnostic biomarker for PTC metastasis, thereby providing experimental evidence for precision diagnosis and therapy. METHODS: Expression profiles of m⁶A-miRNAs were compared between the The Cancer Genome Atlas (TCGA) and GSE130512 cohorts to identify metastasis-associated candidates. Clinical specimens from 13 metastasis and 18 non-metastasis PTC patients were analyzed to assess m⁶A-miR-139-5p expression and its correlation with metastasis. Functional experiments were conducted to investigate the effect of fat mass and obesity-associated protein (FTO) on pri-miR-139 methylation and processing, clarifying its regulatory role in miR-139-5p expression. In TPC-1 cells, MTT assays were performed to evaluate whether miR-139-5p overexpression could counteract FTO-mediated cell proliferation. Transwell invasion assays were used to determine the impact of miR-139-5p on PTC cell invasion, exploring whether it functions through the ZEB1/E-cadherin axis. RESULTS: By comparing TCGA and GSE130512 cohorts, it was found that circulating m⁶A-miR-139-5p could serve as a biological indicator for detecting PTC metastasis. Detection of 13 metastatic and 18 non-metastatic clinical specimens showed that FTO inhibited the processing of pri-miR-139 by reducing its methylation level, leading to the dysregulation of miR-139-5p in PTC (P<0.05). In TPC-1 cells, MTT assay showed that overexpression of miR-139-5p could partially reverse FTO overexpression-mediated cell proliferation (P<0.05). In addition, miR-139-5p inhibited the invasive ability of PTC cells by targeting the ZEB1/E-cadherin axis, while FTO overexpression could partially weaken this inhibitory effect. CONCLUSIONS Circulating miR-139-5p can be a potential marker for evaluating PTC metastasis. FTO affects the expression and function of miR-139-5p by regulating m⁶A modification of pri-miR-139, but its clinical value needs further verification.
Humans ; MicroRNAs/metabolism* ; Thyroid Cancer, Papillary/metabolism* ; Alpha-Ketoglutarate-Dependent Dioxygenase FTO/metabolism* ; Thyroid Neoplasms/metabolism* ; Cell Line, Tumor ; Neoplasm Metastasis ; Adenosine/genetics* ; Gene Expression Regulation, Neoplastic ; Female ; Male ; Cadherins/metabolism* ; Cell Proliferation ; Zinc Finger E-box-Binding Homeobox 1/genetics*

Stathmin 1 (STMN1) is a microtubule-binding cytoplasmic phosphoprotein that promotes microtubule depolymerization or inhibits microtubule assembly, thereby regulating cytoskeletal organization and cell cycle progression. STMN1 is upregulated in a variety of malignant tumors, where it drives proliferation, invasion, metastasis, and angiogenesis through classic pathways such as nuclear factor-κB (NF-κB), mitogen-activated protein kinase (MAPK), and ferroptosis. STMN1 can also modulate the function of immune cells, thereby influencing antitumor immunity. Clinical data show that its high expression correlates positively with tumor drug resistance and poor prognosis, suggesting that STMN1 has potential as a tumor biomarker and therapeutic molecular target with important clinical significance.
Humans ; Stathmin/metabolism* ; Neoplasms/genetics* ; Biomarkers, Tumor/metabolism* ; NF-kappa B/metabolism* ; Cell Proliferation ; Drug Resistance, Neoplasm

Objective:To investigate optimal treatment strategy for pT3N0 laryngeal squamous cell carcinoma（SCC）. Methods:A retrospective study of 150 patients with pT3N0 laryngeal SCC treated in the First Affiliated Hospital of Chongqing Medical University was performed. The efficacies of partial laryngectomy and total laryngectomy, as well as surgery alone and postoperative radiotherapy were evaluated. The overall survival（OS）, disease specific survival（DSS） and disease-free survival（DFS） were analyzed with statistical package from SPSS. Results:Among the 108 patients with glottic laryngeal SCC, there were no significant differences in OS, DSS and DFS between the partial laryngectomy group and the total laryngectomy group（Log-rank=0.184, 0.010 and 0.051, P>0.05）. Similarly, there were no significant differences in OS, DSS and DFS between the surgery-alone group and postoperative radiotherapy group（Log-rank=0.214, 0.251 and 0.003, P>0.05）. Among the 38 patients with supraglottic laryngeal SCC, the OS in the total laryngectomy group was significantly higher than that in the partial laryngectomy group（Log-rank=7.338, P=0.007）. The DSS and DFS in the total laryngectomy group were higher than in the partial laryngectomy group, but the differences were not statistically significant（Log-rank=0.895 and 1.792; P>0.05）. The DFS in the postoperative radiotherapy group was significantly higher than in the surgery-alone group（Log-rank=7.172, P=0.007）, but there were no significant differences in OS and DSS between these two groups（Log-rank=0.010 and 0.876, P>0.05）. Conclusion:For pT3N0 glottic laryngeal cancer patients, the efficacy of partial laryngectomy is comparable to total laryngectomy, same as surgery alone and postoperative radiotherapy. For pT3N0 supraglottic laryngeal cancer patients, total laryngectomy could improve the overall survival, and postoperative radiotherapy could reduce the recurrence. Prospectively randomized study with large samples is still needed.
Humans ; Laryngeal Neoplasms/therapy* ; Laryngectomy/methods* ; Retrospective Studies ; Carcinoma, Squamous Cell/surgery* ; Male ; Female ; Middle Aged ; Disease-Free Survival ; Neoplasm Staging ; Aged ; Survival Rate ; Treatment Outcome

Objective:To investigate the expression of NFAT5 and IGF1R in nasopharyngeal carcinoma tissues and analyze their expression levels in relation to clinical features and prognosis. Methods:From January 1, 2019, to December 31, 2019, 69 cases of nasopharyngeal carcinoma tissues and adjacent non-cancerous tissues were collected from patients treated at Yunnan Cancer Hospital. Immunohistochemistry was employed to detect the expression of NFAT5 and IGF1R in nasopharyngeal carcinoma tissues. The Kaplan-Meier method was used to predict survival time, and the clinicopathological features were evaluated using the log-Rank test. Results:The positive expression rates of NFAT5 and IGF1R in nasopharyngeal carcinoma tissues were 87.0% and 84.5%, respectively. Compared to adjacent normal tissues, the expression levels of NFAT5 and IGF1R in nasopharyngeal carcinoma tissues were significantly increased （P<0.05）. Furthermore, the expression of NFAT5 and IGF1R was positively correlated with T stage, N stage, skull base invasion, and cranial nerve palsy （P<0.05）. The overexpression of NFAT5 and IGF1R significantly affected the survival rate of patients with nasopharyngeal carcinoma and was negatively correlated with prognosis （P<0.05）. Conclusion:In nasopharyngeal carcinoma tissues, overexpression of NFAT5 and IGF1R is observed, which is closely linked to clinical features and patient outcomes. These markers may serve as valuable indicators for predicting the prognosis of nasopharyngeal carcinoma.
Humans ; Nasopharyngeal Carcinoma/pathology* ; Nasopharyngeal Neoplasms/metabolism* ; Prognosis ; Female ; Receptor, IGF Type 1/metabolism* ; Male ; Transcription Factors/metabolism* ; Middle Aged ; Survival Rate ; Adult ; Neoplasm Staging

Head and neck squamous cell carcinoma （HNSCC） is one of the ten most common cancers worldwide and is one of the refractory cancers with a poor prognosis in otorhinolaryngology-head and neck surgery. Cetuximab is widely used in the clinical treatment of HNSCC and has been approved by the FDA as a first-line chemotherapeutic agent. However, its efficacy varies significantly among different individuals. Therefore, exploring the resistance mechanisms of cetuximab in the treatment of HNSCC and screening for sensitive populations are essential for the precision treatment of head and neck cancer. This article summarizes the research progress on cetuximab resistance mechanisms in HNSCC, and the main aspects include: alterations in epidermal growth factor receptor （EGFR） and its ligands, changes in downstream effectors of EGFR, bypass activation and crosstalk, epithelial-mesenchymal transition, epigenetic modifications, and immunosuppression in the tumor microenvironment.
Humans ; Cetuximab/therapeutic use* ; Drug Resistance, Neoplasm ; Squamous Cell Carcinoma of Head and Neck/drug therapy* ; Head and Neck Neoplasms/drug therapy* ; ErbB Receptors/metabolism* ; Tumor Microenvironment ; Epithelial-Mesenchymal Transition ; Molecular Targeted Therapy ; Antineoplastic Agents, Immunological/therapeutic use*