-
Radiation Oncology (London, England) Jun 2024This study aims to develop an ensemble machine learning-based (EML-based) risk prediction model for radiation dermatitis (RD) in patients with head and neck cancer...
PURPOSE
This study aims to develop an ensemble machine learning-based (EML-based) risk prediction model for radiation dermatitis (RD) in patients with head and neck cancer undergoing proton radiotherapy, with the goal of achieving superior predictive performance compared to traditional models.
MATERIALS AND METHODS
Data from 57 head and neck cancer patients treated with intensity-modulated proton therapy at Kaohsiung Chang Gung Memorial Hospital were analyzed. The study incorporated 11 clinical and 9 dosimetric parameters. Pearson's correlation was used to eliminate highly correlated variables, followed by feature selection via LASSO to focus on potential RD predictors. Model training involved traditional logistic regression (LR) and advanced ensemble methods such as Random Forest and XGBoost, which were optimized through hyperparameter tuning.
RESULTS
Feature selection identified six key predictors, including smoking history and specific dosimetric parameters. Ensemble machine learning models, particularly XGBoost, demonstrated superior performance, achieving the highest AUC of 0.890. Feature importance was assessed using SHAP (SHapley Additive exPlanations) values, which underscored the relevance of various clinical and dosimetric factors in predicting RD.
CONCLUSION
The study confirms that EML methods, especially XGBoost with its boosting algorithm, provide superior predictive accuracy, enhanced feature selection, and improved data handling compared to traditional LR. While LR offers greater interpretability, the precision and broader applicability of EML make it more suitable for complex medical prediction tasks, such as predicting radiation dermatitis. Given these advantages, EML is highly recommended for further research and application in clinical settings.
Topics: Humans; Machine Learning; Head and Neck Neoplasms; Proton Therapy; Radiodermatitis; Male; Female; Middle Aged; Aged; Radiotherapy, Intensity-Modulated; Risk Assessment; Radiotherapy Dosage; Adult
PubMed: 38915112
DOI: 10.1186/s13014-024-02470-1 -
Biomedical Engineering Online Jun 2024The monitoring and analysis of quasi-periodic biological signals such as electrocardiography (ECG), intracranial pressure (ICP), and cerebral blood flow velocity (CBFV)... (Comparative Study)
Comparative Study
BACKGROUND
The monitoring and analysis of quasi-periodic biological signals such as electrocardiography (ECG), intracranial pressure (ICP), and cerebral blood flow velocity (CBFV) waveforms plays an important role in the early detection of adverse patient events and contributes to improved care management in the intensive care unit (ICU). This work quantitatively evaluates existing computational frameworks for automatically extracting peaks within ICP waveforms.
METHODS
Peak detection techniques based on state-of-the-art machine learning models were evaluated in terms of robustness to varying noise levels. The evaluation was performed on a dataset of ICP signals assembled from 700 h of monitoring from 64 neurosurgical patients. The groundtruth of the peak locations was established manually on a subset of 13, 611 pulses. Additional evaluation was performed using a simulated dataset of ICP with controlled temporal dynamics and noise.
RESULTS
The quantitative analysis of peak detection algorithms applied to individual waveforms indicates that most techniques provide acceptable accuracy with a mean absolute error (MAE) ms without noise. In the presence of a higher noise level, however, only kernel spectral regression and random forest remain below that error threshold while the performance of other techniques deteriorates. Our experiments also demonstrated that tracking methods such as Bayesian inference and long short-term memory (LSTM) can be applied continuously and provide additional robustness in situations where single pulse analysis methods fail, such as missing data.
CONCLUSION
While machine learning-based peak detection methods require manually labeled data for training, these models outperform conventional signal processing ones based on handcrafted rules and should be considered for peak detection in modern frameworks. In particular, peak tracking methods that incorporate temporal information between successive periods of the signals have demonstrated in our experiments to provide more robustness to noise and temporary artifacts that commonly arise as part of the monitoring setup in the clinical setting.
Topics: Intracranial Pressure; Humans; Signal Processing, Computer-Assisted; Monitoring, Physiologic; Machine Learning; Algorithms; Cerebrovascular Circulation; Signal-To-Noise Ratio
PubMed: 38915091
DOI: 10.1186/s12938-024-01245-9 -
Genome Biology Jun 2024Spatial transcriptomics has transformed our ability to study tissue complexity. However, it remains challenging to accurately dissect tissue organization at single-cell...
Spatial transcriptomics has transformed our ability to study tissue complexity. However, it remains challenging to accurately dissect tissue organization at single-cell resolution. Here we introduce scHolography, a machine learning-based method designed to reconstruct single-cell spatial neighborhoods and facilitate 3D tissue visualization using spatial and single-cell RNA sequencing data. scHolography employs a high-dimensional transcriptome-to-space projection that infers spatial relationships among cells, defining spatial neighborhoods and enhancing analyses of cell-cell communication. When applied to both human and mouse datasets, scHolography enables quantitative assessments of spatial cell neighborhoods, cell-cell interactions, and tumor-immune microenvironment. Together, scHolography offers a robust computational framework for elucidating 3D tissue organization and analyzing spatial dynamics at the cellular level.
Topics: Single-Cell Analysis; Animals; Humans; Mice; Machine Learning; Computational Biology; Cell Communication; Transcriptome; Tumor Microenvironment
PubMed: 38915088
DOI: 10.1186/s13059-024-03299-3 -
Learning and depicting lobe-based radiomics feature for COPD Severity staging in low-dose CT images.BMC Pulmonary Medicine Jun 2024Chronic obstructive pulmonary disease (COPD) is a prevalent and debilitating respiratory condition that imposes a significant healthcare burden worldwide. Accurate...
BACKGROUND
Chronic obstructive pulmonary disease (COPD) is a prevalent and debilitating respiratory condition that imposes a significant healthcare burden worldwide. Accurate staging of COPD severity is crucial for patient management and treatment planning.
METHODS
The retrospective study included 530 hospital patients. A lobe-based radiomics method was proposed to classify COPD severity using computed tomography (CT) images. First, we segmented the lung lobes with a convolutional neural network model. Secondly, the radiomic features of each lung lobe are extracted from CT images, the features of the five lung lobes are merged, and the selection of features is accomplished through the utilization of a variance threshold, t-Test, least absolute shrinkage and selection operator (LASSO). Finally, the COPD severity was classified by a support vector machine (SVM) classifier.
RESULTS
104 features were selected for staging COPD according to the Global initiative for chronic Obstructive Lung Disease (GOLD). The SVM classifier showed remarkable performance with an accuracy of 0.63. Moreover, an additional set of 132 features were selected to distinguish between milder (GOLD I + GOLD II) and more severe instances (GOLD III + GOLD IV) of COPD. The accuracy for SVM stood at 0.87.
CONCLUSIONS
The proposed method proved that the novel lobe-based radiomics method can significantly contribute to the refinement of COPD severity staging. By combining radiomic features from each lung lobe, it can obtain a more comprehensive and rich set of features and better capture the CT radiomic features of the lung than simply observing the lung as a whole.
Topics: Humans; Pulmonary Disease, Chronic Obstructive; Tomography, X-Ray Computed; Retrospective Studies; Severity of Illness Index; Male; Female; Middle Aged; Aged; Support Vector Machine; Lung; Neural Networks, Computer; Radiomics
PubMed: 38915049
DOI: 10.1186/s12890-024-03109-3 -
BMC Medical Informatics and Decision... Jun 2024This study aimed to develop and validate a quantitative index system for evaluating the data quality of Electronic Medical Records (EMR) in disease risk prediction using...
OBJECTIVE
This study aimed to develop and validate a quantitative index system for evaluating the data quality of Electronic Medical Records (EMR) in disease risk prediction using Machine Learning (ML).
MATERIALS AND METHODS
The index system was developed in four steps: (1) a preliminary index system was outlined based on literature review; (2) we utilized the Delphi method to structure the indicators at all levels; (3) the weights of these indicators were determined using the Analytic Hierarchy Process (AHP) method; and (4) the developed index system was empirically validated using real-world EMR data in a ML-based disease risk prediction task.
RESULTS
The synthesis of review findings and the expert consultations led to the formulation of a three-level index system with four first-level, 11 second-level, and 33 third-level indicators. The weights of these indicators were obtained through the AHP method. Results from the empirical analysis illustrated a positive relationship between the scores assigned by the proposed index system and the predictive performances of the datasets.
DISCUSSION
The proposed index system for evaluating EMR data quality is grounded in extensive literature analysis and expert consultation. Moreover, the system's high reliability and suitability has been affirmed through empirical validation.
CONCLUSION
The novel index system offers a robust framework for assessing the quality and suitability of EMR data in ML-based disease risk predictions. It can serve as a guide in building EMR databases, improving EMR data quality control, and generating reliable real-world evidence.
Topics: Electronic Health Records; Humans; Machine Learning; Data Accuracy; Risk Assessment; Delphi Technique
PubMed: 38915008
DOI: 10.1186/s12911-024-02533-z -
BMC Musculoskeletal Disorders Jun 2024Ankylosing spondylitis (AS) with radiographic damage is more prevalent in men than in women. IL-17, which is mainly secreted from peripheral blood mononuclear cells...
BACKGROUND
Ankylosing spondylitis (AS) with radiographic damage is more prevalent in men than in women. IL-17, which is mainly secreted from peripheral blood mononuclear cells (PBMCs), plays an important role in the development of AS. Its expression is different between male and female. However, it is still unclear whether sex dimorphism of IL-17 contribute to sex differences in AS.
METHODS
GSE221786, GSE73754, GSE25101, GSE181364 and GSE205812 datasets were collected from the Gene Expression Omnibus (GEO) database. Differential expressed genes (DEGs) were analyzed with the Gene Set Enrichment Analysis (GSEA), Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) methods. CIBERSORTx and EcoTyper algorithms were used for immune infiltration analyses. Machine learning based on the XGBoost algorithm model was used to identify the impact of DEGs. The Connectivity Map (CMAP) database was used as a drug discovery tool for exploring potential drugs based on the DEGs.
RESULTS
According to immune infiltration analyses, T cells accounted for the largest proportion of IL-17-secreting PBMCs, and KEGG analyses suggested an enhanced activation of mast cells among male AS patients, whereas the expression of TNF was higher in female AS patients. Other signaling pathways, including those involving metastasis-associated 1 family member 3 (MAT3) or proteasome, were found to be more activated in male AS patients. Regarding metabolic patterns, oxidative phosphorylation pathways and lipid oxidation were significantly upregulated in male AS patients. In XGBoost algorithm model, DEGs including METRN and TMC4 played important roles in the disease process. we integrated the CMAP database for systematic analyses of polypharmacology and drug repurposing, which indicated that atorvastatin, famciclocir, ATN-161 and taselisib may be applicable to the treatment of AS.
CONCLUSIONS
We analyzed the sex dimorphism of IL-17-secreting PBMCs in AS. The results showed that mast cell activation was stronger in males, while the expression of TNF was higher in females. In addition, through machine learning and the CMAP database, we found that genes such as METRN and TMC4 may promote the development of AS, and drugs such as atorvastatin potentially could be used for AS treatment.
Topics: Humans; Female; Male; Interleukin-17; Spondylitis, Ankylosing; Machine Learning; Leukocytes, Mononuclear; Sex Characteristics; Computational Biology; Databases, Genetic; Gene Expression Profiling
PubMed: 38914997
DOI: 10.1186/s12891-024-07589-6 -
BMC Ophthalmology Jun 2024This study aimed to explore differences in vitreous humour metabolites and metabolic pathways between patients with and without diabetic retinopathy (DR) and identify...
BACKGROUND
This study aimed to explore differences in vitreous humour metabolites and metabolic pathways between patients with and without diabetic retinopathy (DR) and identify potential metabolite biomarkers.
METHODS
Clinical data and vitreous fluid samples were collected from 125 patients (40 without diabetes, 85 with DR). The metabolite profiles of the vitreous fluid samples were analysed using ultra-high performance liquid chromatography, Q-Exactive mass spectrometry, and multivariate statistical analysis. A machine learning model based on Least Absolute Shrinkage and Selection Operator Regularized logistic regression was used to build a risk scoring model based on selected metabolite levels. Candidate metabolites were regressed to glycated haemoglobin levels by a logistic regression model.
RESULTS
Twenty differential metabolites were identified between the DR and control groups and were significantly enriched in five Kyoto Encyclopedia of Genes and Genomes pathways (arginine biosynthesis; tricarboxylic acid cycle; alanine, aspartate, and glutamate metabolism; tyrosine metabolism; and D-glutamate metabolism). Ferrous ascorbate significantly contributes to poorer glycaemic control outcomes, offering insights into potential new pathogenic pathways in DR.
CONCLUSIONS
Disorders in the metabolic pathways of arginine biosynthesis, tricarboxylic acid cycle, alanine, aspartate, glutamate metabolism, tyrosine metabolism, and D-glutamate metabolism were associated with DR. Risk scores based on vitreous fluid metabolites can be used for the diagnosis and management of DR. Ferrous ascorbate can provide insights into potential new pathogenic pathways for DR.
Topics: Humans; Diabetic Retinopathy; Vitreous Body; Biomarkers; Male; Metabolomics; Female; Middle Aged; Ascorbic Acid; Aged; Chromatography, High Pressure Liquid
PubMed: 38914965
DOI: 10.1186/s12886-024-03530-6 -
BMC Medical Imaging Jun 2024For prostate electrosurgery, where real-time surveillance screens are relied upon for operations, manual identification of the prostate capsule remains the primary...
BACKGROUND
For prostate electrosurgery, where real-time surveillance screens are relied upon for operations, manual identification of the prostate capsule remains the primary method. With the need for rapid and accurate detection becoming increasingly urgent, we set out to develop a deep learning approach for detecting the prostate capsule using endoscopic optical images.
METHODS
Our method involves utilizing the Simple, Parameter-Free Attention Module(SimAM) residual attention fusion module to enhance the extraction of texture and detail information, enabling better feature extraction capabilities. This enhanced detail information is then hierarchically transferred from lower to higher levels to aid in the extraction of semantic information. By employing a forward feature-by-feature hierarchical fusion network based on the 3D residual attention mechanism, we have proposed an improved single-shot multibox detector model.
RESULTS
Our proposed model achieves a detection precision of 83.12% and a speed of 0.014 ms on NVIDIA RTX 2060, demonstrating its effectiveness in rapid detection. Furthermore, when compared to various existing methods including Faster Region-based Convolutional Neural Network (Faster R-CNN), Single Shot Multibox Detector (SSD), EfficientDet and others, our method Attention based Feature Fusion Single Shot Multibox Detector (AFFSSD) stands out with the highest mean Average Precision (mAP) and faster speed, ranking only below You Only Look Once version 7 (YOLOv7).
CONCLUSIONS
This network excels in extracting regional features from images while retaining the spatial structure, facilitating the rapid detection of medical images.
Topics: Humans; Male; Deep Learning; Imaging, Three-Dimensional; Prostate; Prostatic Neoplasms
PubMed: 38914956
DOI: 10.1186/s12880-024-01336-y -
BMC Medical Imaging Jun 2024The assessment of in vitro wound healing images is critical for determining the efficacy of the therapy-of-interest that may influence the wound healing process....
BACKGROUND
The assessment of in vitro wound healing images is critical for determining the efficacy of the therapy-of-interest that may influence the wound healing process. Existing methods suffer significant limitations, such as user dependency, time-consuming nature, and lack of sensitivity, thus paving the way for automated analysis approaches.
METHODS
Hereby, three structurally different variations of U-net architectures based on convolutional neural networks (CNN) were implemented for the segmentation of in vitro wound healing microscopy images. The developed models were fed using two independent datasets after applying a novel augmentation method aimed at the more sensitive analysis of edges after the preprocessing. Then, predicted masks were utilized for the accurate calculation of wound areas. Eventually, the therapy efficacy-indicator wound areas were thoroughly compared with current well-known tools such as ImageJ and TScratch.
RESULTS
The average dice similarity coefficient (DSC) scores were obtained as 0.958 0.968 for U-net-based deep learning models. The averaged absolute percentage errors (PE) of predicted wound areas to ground truth were 6.41%, 3.70%, and 3.73%, respectively for U-net, U-net++, and Attention U-net, while ImageJ and TScratch had considerable averaged error rates of 22.59% and 33.88%, respectively.
CONCLUSIONS
Comparative analyses revealed that the developed models outperformed the conventional approaches in terms of analysis time and segmentation sensitivity. The developed models also hold great promise for the prediction of the in vitro wound area, regardless of the therapy-of-interest, cell line, magnification of the microscope, or other application-dependent parameters.
Topics: Deep Learning; Wound Healing; Microscopy; Humans; Image Processing, Computer-Assisted; Neural Networks, Computer
PubMed: 38914942
DOI: 10.1186/s12880-024-01332-2 -
Scientific Reports Jun 2024Ischemic stroke (IS) is of increasing concern given the aging population and prevalence of unhealthy lifestyles, with older females exhibiting higher susceptibility....
Ischemic stroke (IS) is of increasing concern given the aging population and prevalence of unhealthy lifestyles, with older females exhibiting higher susceptibility. This study aimed to identify practical diagnostic markers, develop a diagnostic model for immunogenic cell death (ICD)-associated IS, and investigate alterations in the immune environment caused by hub genes. Differentially expressed genes associated with ICD in IS were identified based on weighted gene co-expression network analysis and the identification of significant modules. Subsequently, machine learning algorithms were employed to screened hub genes, which were further assessed using Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, and Gene Set Enrichment Analysis. A nomogram mode lwas then constructed for IS diagnosis, and its diagnostic value was assessed using a receiver operating characteristic curve. Finally, alterations in immune cell infiltration were assessed within patients with IS, and the pan-cancer expression patterns of hub genes were evaluated. Three hub genes associated with ICD (PDK4, CCL20, and FBL) were identified. The corresponding nomogram model for IS diagnosis could effectively identify older female patients with IS (area under the curve (AUC) = 0.9555). Overall, the three hub genes exhibit good diagnostic value (AUC > 0.8). CCL20 and FBL are significantly associated with the extent of immune cells infiltration. Moreover, a strong link exists between hub gene expression and pan-cancer prognosis. Cumulatively, these results indicate that ICD-related hub genes critically influence IS progression in older females, presenting novel diagnostic and therapeutic targets for personalized treatment.
Topics: Humans; Female; Ischemic Stroke; Aged; Immunogenic Cell Death; Chemokine CCL20; Biomarkers; Nomograms; Gene Regulatory Networks; Machine Learning; Gene Expression Profiling; ROC Curve; Aged, 80 and over
PubMed: 38914792
DOI: 10.1038/s41598-024-65390-w