Machine Learning in Neuroimaging and Computational Pathophysiology of Parkinson’s Disease: A comprehensive review and meta-analysis

Asian Journal of Psychiatry, Год журнала: 2025, Номер 109, С. 104537 - 104537

Опубликована: Май 20, 2025

Язык: Английский

---

Scalable and robust machine learning framework for HIV classification using clinical and laboratory data

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 28, 2025

Язык: Английский

---

TriKSV-LG: a robust approach to disease prediction in healthcare systems using AI and Levy Gazelle optimization

Computer Methods in Biomechanics & Biomedical Engineering, Год журнала: 2024, Номер unknown, С. 1 - 17

Опубликована: Апрель 30, 2024

A seamless connection between the Internet and people is provided by of Things (IoT). Furthermore, lives are enhanced using integration cloud layer. In healthcare domain, a reactive strategy turned into proactive one predictive analysis. The challenges faced existing techniques inaccurate prediction time-consuming process. This paper introduces an Artificial Intelligence (AI) IoT-based disease method, TriKernel Support Vector-based Levy Gazelle (TriKSV-LG) Algorithm, which aims to improve accuracy, reduce time predicting diseases (kidney heart) in systems. IoT sensors collect information about patients' health conditions, AI employs prediction. TriKSV utilizes multiple kernel functions, including linear, polynomial, radial basis classify features more effectively. By learning from different representations data, better handles variations complexities within dataset, leading robust models. Flight with optimization algorithm tunes hyperparameters balances exploration exploitation for optimal hyperparameter configurations chronic kidney (CKD) heart (HD). TriKSV's incorporation combined strategy, helps mitigate overfitting providing comprehensive search space selection. proposed TriKSV-LG method applied two datasets, namely CKD dataset HD evaluated performance measures such as AUC-ROC, specificity, F1-score, recall, precision, accuracy. results demonstrate that achieved accuracy 98.56% 98.11% dataset.

Язык: Английский

---

Cognitive driven gait freezing phase detection and classification for neuro-rehabilitated patients using machine learning algorithms

Journal of Neuroscience Methods, Год журнала: 2024, Номер 409, С. 110183 - 110183

Опубликована: Июнь 3, 2024

Язык: Английский

---

Enhancing ensemble classifiers utilizing gaze tracking data for autism spectrum disorder diagnosis

Computers in Biology and Medicine, Год журнала: 2024, Номер 182, С. 109184 - 109184

Опубликована: Сен. 30, 2024

Язык: Английский

---

A deep learning based assisted analysis approach for Sjogren’s syndrome pathology images

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 21, 2024

Abstract Diagnosing Sjogren’s syndrome requires considerable time and effort from physicians, primarily because it necessitates rigorously establishing the presence lymphatic infiltration in pathological tissue of labial gland. The aim this study is to use deep learning techniques overcome these limitations improve diagnostic accuracy efficiency pathology. We develop an auxiliary system for syndrome. incorporates state-of-the-art object detection neural network, YOLOv8, enables precise identification flagging suspicious lesions. design multi-dimensional attention module S-MPDIoU loss function performance YOLOv8. By extracting features multiple dimensions feature map, utilization mechanism enhances interaction across disparate positions, enabling network proficiently learn retain salient cell features. introduces angle penalty term that efficiently minimizes diagonal distance between predicted ground truth boxes. Additionally, a flexible scale factor tailored different size maps, which balances issue sudden gradient decrease during high overlap, thereby accelerating overall convergence rate. To verify effectiveness our methods, we create dataset lymphocytes using gland biopsy pathology images collected YanTaiShan hospital trained model with dataset. proposed assessed standard metrics like precision, recall, mAP. improved achieves increase recall by 9.1%, mAP.5 3.2%, mAP.95 2%. demonstrated learning’s potential analysis images, offering reference framework application technology medical domain.

Язык: Английский

---

Automatic cross‐ and multi‐lingual recognition of dysphonia by ensemble classification using deep speaker embedding models

Expert Systems, Год журнала: 2024, Номер 41(10)

Опубликована: Июнь 12, 2024

Abstract Machine Learning (ML) algorithms have demonstrated remarkable performance in dysphonia detection using speech samples. However, their efficacy often diminishes when tested on languages different from the training data, raising questions about suitability clinical settings. This study aims to develop a robust method for cross‐ and multi‐lingual that overcomes limitation of language dependency existing ML methods. We propose an innovative approach leverages embeddings speaker verification models, especially ECAPA x‐vector employs majority voting ensemble classifier. utilize features extracted train three distinct classifiers. The significant advantage these embedding models lies capability capture characteristics language‐independent manner, forming fixed‐dimensional feature spaces. Additionally, we investigate impact generating synthetic data within space Synthetic Minority Oversampling Technique (SMOTE). Our experimental results unveil effectiveness proposed detection. Compared obtained embeddings, consistently demonstrates superior distinguishing between healthy dysphonic speech, achieving accuracy values 93.33% 96.55% both cross‐lingual scenarios, respectively. highlights capabilities ECAPA, capturing enhance overall performance. effectively addresses challenges combined with classifiers, show potential improving reliability scenarios.

Язык: Английский

---

Innovative approaches for coronary heart disease management: integrating biomedical sensors, deep learning, and stellate ganglion modulation

Computer Methods in Biomechanics & Biomedical Engineering, Год журнала: 2024, Номер unknown, С. 1 - 18

Опубликована: Июль 18, 2024

Coronary heart disease (CHD) is a significant global health concern, necessitating continuous advancements in treatment modalities to improve patient outcomes. Traditional Chinese medicine (TCM) offers alternative therapeutic approaches, but integration with modern biomedical technologies remains relatively unexplored. This study aimed assess the efficacy of combined approach for CHD, integrating traditional medicinal interventions sensors and stellate ganglion modulation. The objective was evaluate impact this on symptom relief, clinical outcomes, hemorheological indicators, inflammatory biomarkers. A randomized controlled trial conducted 117 CHD patients phlegm-turbidity congestion excessiveness type. Patients were divided into group (CTG) (CMG). CTG received combination herbal decoctions, thread-embedding therapy, modulation, while CMG only decoctions. demonstrated superior outcomes compared across multiple parameters. Significant reductions TCM scores, improved effects, reduced angina manifestation, favorable changes decreased serum biomarkers observed post-intervention. modulation has shown promising results improving symptoms, markers patients. holistic enhances Further research sensor technology are needed optimize approach.

Язык: Английский

---

A systematic literature review of neuroimaging coupled with machine learning approaches for diagnosis of attention deficit hyperactivity disorder

Journal Of Big Data, Год журнала: 2024, Номер 11(1)

Опубликована: Окт. 4, 2024

Язык: Английский

---

Early Parkinson's Disease Diagnosis Using Multi-Modal CASENet CNN-LSTM

Advances in healthcare information systems and administration book series, Год журнала: 2024, Номер unknown, С. 248 - 264

Опубликована: Май 17, 2024

By analyzing the deviation of features earlier stages can be segmented with subtle patterns in patients' handwriting dynamics and voice recordings, this innovative method showcases deep learning's potential to revolutionize medical diagnostics. applying Casenet convolutional neural network framework, a hybrid architecture incorporating CNNs improved long short-term memory networks is implemented using Kaggle datasets, which excels spatial feature extraction from individual cases. while LSTM captures temporal recordings. Demonstrating robust 94.6% accuracy rate, model proves its effectiveness Parkinson's disease prediction that support complete diagnosis. Model assessment includes precision, recall, F1-score evaluations Principal Component Analysis (PCA) by integrating CNN framework enhance diagnosis system reliable predict early detection multimodal data.

Язык: Английский

---