Development and Validation of a Nomogram for Predicting Survival Based on Ferritin and Transferrin Ratio in Breast Cancer Patients.

BACKGROUND: Our objective is to develop a predictive model utilizing the ferritin and transferrin ratio (FTR) and clinical factors to forecast overall survival (OS) in breast cancer (BC) patients. METHODS: We conducted a retrospective analysis of clinical data from 2858 BC patients diagnosed between 2013 and 2021. Subsequently, the cohort of 2858 BC patients underwent random assignment into distinct subsets: a training cohort comprising 2002 patients and a validation cohort comprising 856 patients, maintaining a proportional ratio of 7:3. Employing multivariable Cox regression analysis within the training cohort, we derived a prognostic nomogram. The predictive performance was assessed using calibration curves, C-index, and decision curve analysis. RESULTS: The final prognostic model included the TNM stage, subtype, hemoglobin levels, and the ferritin-transferrin ratio. The nomogram achieved a C-index of .794 (95% CI: .777-.810). The nomogram demonstrated superior predictive accuracy for OS at 3, 5, and 7 years for BC, with area under the time-dependent curves of .812, .782, and .773, respectively. These values notably outperformed those of the conventional TNM stage. Decision curve analysis reaffirmed the greater net benefit of our nomogram compared to the TNM stage. These findings were subsequently validated in the independent validation cohort. CONCLUSION: The FTR-based prognostic model may predict a patient's OS better than the TNM stage in a clinical setting. The nomogram can provide an early, affordable, and reliable tool for survival prediction, as well as aid clinicians in treatment option-making and prognosis evaluation. However, further multi-center prospective trials are required to confirm the reliability of the existing nomogram.

BackgroundOur objective is to develop a predictive model utilizing the ferritin and transferrin ratio (FTR) and clinical factors to forecast overall survival (OS) in breast cancer (BC) patients.MethodsWe conducted a retrospective analysis of clinical data from 2858 BC patients diagnosed between 2013 and 2021. Subsequently, the cohort of 2858 BC patients underwent random assignment into distinct subsets: a training cohort comprising 2002 patients and a validation cohort comprising 856 patients, maintaining a proportional ratio of 7:3. Employing multivariable Cox regression analysis within the training cohort, we derived a prognostic nomogram. The predictive performance was assessed using calibration curves, C-index, and decision curve analysis.ResultsThe final prognostic model included the TNM stage, subtype, hemoglobin levels, and the ferritin-transferrin ratio. The nomogram achieved a C-index of .794 (95% CI: .777-.810). The nomogram demonstrated superior predictive accuracy for OS at 3, 5, and 7 years for BC, with area under the time-dependent curves of .812, .782, and .773, respectively. These values notably outperformed those of the conventional TNM stage. Decision curve analysis reaffirmed the greater net benefit of our nomogram compared to the TNM stage. These findings were subsequently validated in the independent validation cohort.ConclusionThe FTR-based prognostic model may predict a patient's OS better than the TNM stage in a clinical setting. The nomogram can provide an early, affordable, and reliable tool for survival prediction, as well as aid clinicians in treatment option-making and prognosis evaluation. However, further multi-center prospective trials are required to confirm the reliability of the existing nomogram.

Discovering and Validating Cuproptosis-Associated Marker Genes for Accurate Keloid Diagnosis Through Multiple Machine Learning Models.

Background: Keloid is a common condition characterized by abnormal scarring of the skin, affecting a significant number of individuals worldwide. Objective: The occurrence of keloids may be related to the reduction of cell death. Recently, a new cell death mode that relies on copper ions has been discovered. This study aimed to identify novel cuproptosis-related genes that are associated with keloid diagnosis. Methods: We utilized several gene expression datasets, including GSE44270 and GSE145725 as the training group, and GSE7890, GSE92566, and GSE121618 as the testing group. We integrated machine learning models (SVM, RF, GLM, and XGB) to identify 10 cuproptosis-related genes (CRGs) for keloid diagnosis in the training group. The diagnostic capability of the identified CRGs was validated using independent datasets, RT-qPCR, Western blotting, and IHC analysis. Results: Our study successfully categorized keloid samples into two clusters based on the expression of cuproptosis-related genes. Utilizing WGCNA analysis, we identified 110 candidate genes associated with cuproptosis. Subsequent functional enrichment analysis results revealed that these genes may play a regulatory role in cell growth within keloid tissue through the MAPK pathway. By integrating machine learning models, we identified CRGs that can be used for diagnosing keloid. The diagnostic efficacy of CRGs was confirmed using independent datasets, RT-qPCR, Western blotting, and IHC analysis. GSVA analysis indicated that high expression of CRGs influenced the gene set related to ECM receptor interaction. Conclusion: This study identified 10 cuproptosis-related genes that provide insights into the molecular mechanisms underlying keloid development and may have implications for the development of targeted therapies.

Effect of respiratory muscle training in patients with stable chronic obstructive pulmonary disease: A systematic review and meta-analysis.

Objectives: Chronic obstructive pulmonary disease (COPD) is a prevalent respiratory disorder characterized by progressive airflow limitation. This meta-analysis aims to evaluate the effectiveness of respiratory muscle training (RMT) on key pulmonary function parameters, inspiratory muscle strength and quality of life in patients with stable COPD. Methods: A comprehensive search was conducted in the databases including PubMed, Cochrane, Web of Science, Embase, and ClinicalTrials.gov, from their inception to June 12, 2023. Randomized controlled trials (RCTs) evaluating the impact of RMT on stable COPD were included for meta-analysis. Results: In total, 12 RCTs involving 453 participants were included in the meta-analysis. RMT demonstrated a significant increase in maximal inspiratory pressure (PImax, MD, 95% CI: 14.34, 8.17 to 20.51, P < 0.001) but not on maximal expiratory pressure (PEmax). No significant improvement was observed in 6-Min walk test (6MWT), dyspnea, forced expiratory volume in 1 s (FEV1), forced vital capacity ratio (FVC) and quality of life between RMT and control groups. However, subgroup analysis revealed a significant negative effect of RMT alone on FEV1/FVC (MD, 95% CI: 2.59, -5.11 to -0.06, P = 0.04). When RMT was combined with other interventions, improvements in FEV1/FVC and FEV1 were found, although not statistically significant. Conclusion: RMT can effectively improve maximal inspiratory pressure in stable COPD patients, but the effect is slight in improving lung function, dyspnea and quality of life. It is recommended to combine with other treatment strategies to comprehensively improve the prognosis of COPD patients.

Four-Level Cervical Disc Arthroplasty.

BACKGROUND: Multilevel anterior cervical discectomy and fusion inevitably yields a higher chance of pseudarthrosis or require more reoperations than single-level procedures. Therefore, multilevel cervical disc arthroplasty (CDA) could be an alternative surgery for cervical spondylosis, as it (particularly 3- and 4-level CDA) could preserve more functional motility than single-level disc diseases. This study aimed to investigate the clinical and radiological outcomes of 4-level CDA, a relatively infrequently indicated surgery. METHODS: The medical records of consecutive patients who underwent 4-level CDA were retrospectively reviewed. These highly selected patients typically had multilevel disc herniations with mild spondylosis. The inclusion criteria were symptomatic cervical spondylotic myelopathy, radiculopathy, or both, that were medically refractory. The clinical outcomes were assessed. The radiographic outcomes, including global and individual segmental range of motion (ROM) at C3-7, and any complications were also analyzed. RESULTS: Data from a total of 20 patients (mean age: 56 ± 8 years) with an average follow-up of 34 ± 20 months were analyzed. All patients reported improved clinical outcomes compared with that of preoperation, and the ROMs at C3-7 were not only preserved but also trended toward an increase (35 ± 8 vs 37 ± 10 degrees, pre- vs postoperation, P = 0.271) after the 4-level CDA. However, global cervical alignment remained unchanged. There was one permanent C5 radiculopathy, but no other neurological deteriorations or any reoperations occurred. CONCLUSION: For these rare but unique indications, 4-level CDA yielded clinical improvement and preserved segmental motility with low rates of complications. Four-level CDA is a safe and effective surgery, maintaining the ROM in patients with primarily disc herniations and mild spondylosis. CLINICAL RELEVANCE: For patients with mild spondylosis, whose degeneration at the cervical spine is not so severe, CDA is more suitable.

Decoding Micro-Electrocorticographic Signals by Using Explainable 3D Convolutional Neural Network to Predict Finger Movements.

BACKGROUND: Electroencephalography (EEG) and electrocorticography (ECoG) recordings have been used to decode finger movements by analyzing brain activity. Traditional methods focused on single bandpass power changes for movement decoding, utilizing machine learning models requiring manual feature extraction. NEW METHOD: This study introduces a 3D convolutional neural network (3D-CNN) model to decode finger movements using ECoG data. The model employs adaptive, explainable AI (xAI) techniques to interpret the physiological relevance of brain signals. ECoG signals from epilepsy patients during awake craniotomy were processed to extract power spectral density across multiple frequency bands. These data formed a 3D matrix used to train the 3D-CNN to predict finger trajectories. RESULTS: The 3D-CNN model showed significant accuracy in predicting finger movements, with root-mean-square error (RMSE) values of 0.26-0.38 for single finger movements and 0.20-0.24 for combined movements. Explainable AI techniques, Grad-CAM and SHAP, identified the high gamma (HG) band as crucial for movement prediction, showing specific cortical regions involved in different finger movements. These findings highlighted the physiological significance of the HG band in motor control. COMPARISON WITH EXISTING METHODS: The 3D-CNN model outperformed traditional machine learning approaches by effectively capturing spatial and temporal patterns in ECoG data. The use of xAI techniques provided clearer insights into the model's decision-making process, unlike the "black box" nature of standard deep learning models. CONCLUSIONS: The proposed 3D-CNN model, combined with xAI methods, enhances the decoding accuracy of finger movements from ECoG data. This approach offers a more efficient and interpretable solution for brain-computer interface (BCI) applications, emphasizing the HG band's role in motor control.

The Quantitative Evaluation of Automatic Segmentation in Lumbar Magnetic Resonance Images.

OBJECTIVE: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. METHODS: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net's segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. RESULTS: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. CONCLUSION: Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.