Method For Medical Diagnosis Research Articles

Comparative Analysis of Advanced Data Mining Methods for Enhancing Medical Diagnosis and Prognosis

Accurate and early diagnosis, coupled with precise prognosis, is critical for improving patient outcomes in various medical conditions. This paper focuses on leveraging advanced data mining techniques to address two key medical challenges: diagnosis and prognosis. Diagnosis involves differentiating between benign and malignant conditions, while prognosis aims to predict the likelihood of recurrence after treatment. Despite significant advances in medical imaging and clinical data collection, achieving high accuracy in both diagnosis and prognosis remains a challenge. This study provides a comprehensive review of state-of-the-art machine learning and data mining techniques used for medical diagnosis and prognosis, including Neural Networks, K-Nearest Neighbors (KNN), Naïve Bayes, Logistic Regression, Decision Trees, and Support Vector Machines (SVM). These methods are evaluated on their ability to process large, complex datasets and produce actionable insights for medical practitioners.We conducted a thorough comparative analysis based on key performance metrics such as accuracy, Area Under the Curve (AUC), precision, recall, and specificity. Our findings reveal that Neural Networks consistently outperform other techniques in terms of diagnostic accuracy and predictive capacity, demonstrating their robustness in handling high-dimensional and nonlinear medical data. This research underscores the potential of advanced machine learning algorithms in revolutionizing early diagnosis and effective prognosis, thus facilitating more personalized treatment plans and improved healthcare outcomes.

Artificial Intelligence And Its Implications In Health Care: A Textual Analysis

This all-inclusive research paper plunges into the transformative nature of artificial intelligence (AI) in healthcare, emphasizing its ability to change patient care and administrative activities. The investigation examines systematically how AI technologies are creating major improvements towards patients’ outcomes and enhanced operational efficiency within the healthcare systems. From diagnostics to personalized treatment plans and administrative tasks, AI is being integrated using sophisticated algorithms in numerous aspects of healthcare delivery. One major focus is improving diagnostic accuracy. AI-backed diagnostic tools such as image recognition software as well as predictive models have outperformed traditional methods in medical condition identification and diagnosis. For instance, artificial intelligence algorithms show exceptional skills in analysing medical images resulting to earlier detection as well as accurate diagnoses of diseases like cancer, cardiovascular conditions among others neurological disorders. These enhancements not only allow for timely intervention but they significantly reduce instances where diagnosis goes wrong hence enhancing patient prognosis while reducing health costs drastically. The ability to customize personalized therapy is yet another essential aspect of AI in healthcare. With such information as genetic data, medical records and lifestyle factors, and other patient information, AI systems can develop individualized treatment plans. It is for this reason that personalization of treatments enhances their efficiency while reducing the risk of any adverse effects as well as ensuring patients’ adherence to prescribed therapies. Besides, it is important to note that AI-driven predictive models are helpful in identifying individuals with a higher probability of developing specific conditions thereby allowing interventions aimed at preventing diseases and bettering overall population health. AI has also transformed administrative tasks within hospitals besides its clinical applications. For example, AI driven automation is now used to streamline scheduling of appointments or billing processes or even storage of patient records which are normally considered routine administrative works. In addition, through these means there is reduced burden on administrative duties for healthcare workers who continue to perform them with increased precision and timeliness. The net effect is that time and resources can be redirected towards more direct patient care thus improving service quality across the board’s entire system

A privacy-preserving expert system for collaborative medical diagnosis across multiple institutions using federated learning

Expert system recommendation assists the healthcare system to develop in real-time monitoring and diagnosis of patient conditions over several healthcare institutions. Privacy concerns, however, present significant problems since patient data leaks can lead to big effects including financial losses for hospitals and invasions of personal privacy for people. To address these issues, the research introduces a privacy-preserving collaborative medical diagnosis (CMD) method on a federated learning (FL). FL maintains patient privacy and data localization by spreading only model parameters, therefore enabling training models on remote datasets. The combination of Partially Homomorphic Cryptosystem (PHC) and Residual Learning based Deep Belief Network (RDBN) ensures an accurate and safe classification of patient physiological data. Experimental results show that the proposed method is successful in maintaining the diagnostic accuracy over numerous healthcare institutions and protecting privacy. The results show that the RDBN and PHC computations requires around 1000 ms and 150 ms, respectively for classification and privacy; the data transmission from the user to server and from server to user is 5 MB and 4 MB, respectively. Finally with a 30% reduction in overhead, the proposed approach offers an average increase in classification accuracy of 10% over multiple datasets.

Optimal extreme learning machine for diagnosing brain tumor based on modified sailfish optimizer

This study proposes a hierarchical automated methodology for detecting brain tumors in Magnetic Resonance Imaging (MRI), focusing on preprocessing images to improve quality and eliminate artifacts or noise. A modified Extreme Learning Machine is then used to diagnose brain tumors that are integrated with the Modified Sailfish optimizer to enhance its performance. The Modified Sailfish optimizer is a metaheuristic algorithm known for efficiently navigating optimization landscapes and enhancing convergence speed. Experiments were conducted using the “Whole Brain Atlas (WBA)” database, which contains annotated MRI images. The results showed superior efficiency in accurately detecting brain tumors from MRI images, demonstrating the potential of the method in enhancing accuracy and efficiency. The proposed method utilizes hierarchical methodology, preprocessing techniques, and optimization of the Extreme Learning Machine with the Modified Sailfish optimizer to improve accuracy rates and decrease the time needed for brain tumor diagnosis. The proposed method outperformed other methods in terms of accuracy, recall, specificity, precision, and F1 score in medical imaging diagnosis. It achieved the highest accuracy at 93.95 %, with End/End and CNN attaining high values of 89.24 % and 93.17 %, respectively. The method also achieved a perfect score of 100 % in recall, 91.38 % in specificity, and 75.64 % in F1 score. However, it is crucial to consider factors like computational complexity, dataset characteristics, and generalizability before evaluating the effectiveness of the method in medical imaging diagnosis. This approach has the potential to make substantial contributions to medical imaging and aid healthcare professionals in making prompt and precise treatment decisions for brain tumors.

Ultra-wideband Imaging of Breast Tumors Based on Global Back Projection Algorithm

Abstract Tumor imaging in medicine requires consideration of human safety, image quality clarity, and cost of imaging. Ultra-wideband (UWB) technology employs large bandwidth channels that enable high-speed data transmission. This determines that it can provide high-quality images quickly while still being a harmless imaging method. Therefore, it is essential to construct a UWB microwave detection tumor system. The creation of a vector network analyzer (VNA) based microwave imaging system in this work. To adapt to breast imaging, this paper improved the imaging algorithm of global back projection (GBP) based on the classical back projection algorithm. To verify the system’s feasibility, this paper performed UWB detection experiments using a breast tumor model. By comparing the simulation results, the final imaging results show that the UWB imaging system can detect tumors located at two different locations in the model and that high-quality images can be obtained in the near field using the GBP algorithm. This paper provides a reliable and low-cost method for medical diagnosis.

A Small Target Segmentation-Based Assistive Medical Diagnosis Method via Multimedia Data Analysis

The assistive medical diagnosis via multimedia data analysis has been a hot research topic in the area of intelligent health management, which saves a lot of human labor for the hospital. In that, a typical task is to detect and extract key small targets from the medical images. How to ensure detection speed and recognition precision is of great importance to the final practicability of the intelligent techniques. In this paper, we proposed a small target segmentation-based intelligent assistive diagnosis method for this purpose. In the stage of data pre-processing, data enhancement is employed to reduce the effects caused by noise, blur, and low image contrast. In the stage of decoding, a new upsampling method is designed to compensate for information in space and channels to help the network recover feature map resolution, reduce information loss, and improve the segmentation accuracy of smaller tissues or lesions. Such design of a multi-scale adaptive detail feature fusion module is able to make full use of features at different scales to recover high-level detail features, thus improving the segmentation accuracy of structurally complex tissues. Some simulative experiments aided by deep learning programming tools are conducted on the real-world multimedia data (CT, MRI, PET, etc.), so as to evaluate the proposed assistive diagnosis method. It can be concluded from the achieved results that the proposal is well suitable for multimedia data analysis of the experimental scenes.

Improved Demons algorithm for non-rigid medical image alignment

Abstract Medical image alignment is an important research field in medical image processing, which is widely used in clinical diagnosis and treatment, such as surgical navigation, lesion tracking, and treatment evaluation. In this paper, an improved algorithm combining the Demons algorithm and SIFT algorithm is proposed, which uses the SIFT algorithm to represent the feature points in non-rigid medical images as a scale space sequence and normalize the descriptors in the scale space sequence. Then, the two-way alignment strategy and multi-resolution strategy are introduced to improve the accuracy of Demons algorithm in the alignment of non-rigid medical images with complex deformation. The study shows that the improved Demons algorithm can achieve better alignment results when the weights of the feature matching terms are taken as −1 and 1, which makes the improved Demons algorithm with the addition of SIFT feature terms perform optimally. Alignment simulation experiments found that the MSE value of this paper’s improved algorithm is only 0.077. The alignment effect of non-rigid medical images is much better than the comparison algorithm and can maintain a shorter running time. The algorithm in this paper can effectively realize the non-rigid alignment of medical images, which provides a reference method for medical diagnosis and the effective formulation of treatment plans.

Hierarchical Hybrid Networks for Automatic Pulmonary Blood Vessel Segmentation in Computed Tomography Images.

Pulmonary arterial hypertension (PAH) is considered the third most common cardiovascular disease after coronary heart disease and hypertension. The diagnosis of PAH is mainly based on the comprehensive judgment of computed tomography and other medical image examinations. Medical image processing based on deep learning has achieved significant success. However, the data belongs to the patient's privacy; therefore, the medical institutions as data custodians have the responsibility to protect the security of their data privacy. This situation makes medical institutions face a dilemma when building data-driven deep learning-assisted medical diagnosis methods. On the one hand, they need to pursue more high-quality data based on Big Data architecture for deep learning; on the other hand, they need to protect patient privacy to avoid data leakage. In response to the above challenges, we propose a hierarchical hybrid automatic segmentation model for pulmonary blood vessels based on local learning and federated learning approaches for segmenting the pulmonary blood vessels. The experiments prove the proposal could automatically segment the vessels from the original CT. It also indicates that the model based on a federated learning approach can achieve impressive performance under the premise of protecting data privacy for Big Data.

Deep Learning Methods in Medical Image-Based Hepatocellular Carcinoma Diagnosis: A Systematic Review and Meta-Analysis

(1) Background: The aim of our research was to systematically review papers specifically focused on the hepatocellular carcinoma (HCC) diagnostic performance of DL methods based on medical images. (2) Materials: To identify related studies, a comprehensive search was conducted in prominent databases, including Embase, IEEE, PubMed, Web of Science, and the Cochrane Library. The search was limited to studies published before 3 July 2023. The inclusion criteria consisted of studies that either developed or utilized DL methods to diagnose HCC using medical images. To extract data, binary information on diagnostic accuracy was collected to determine the outcomes of interest, namely, the sensitivity, specificity, and area under the curve (AUC). (3) Results: Among the forty-eight initially identified eligible studies, thirty studies were included in the meta-analysis. The pooled sensitivity was 89% (95% CI: 87–91), the specificity was 90% (95% CI: 87–92), and the AUC was 0.95 (95% CI: 0.93–0.97). Analyses of subgroups based on medical image methods (contrast-enhanced and non-contrast-enhanced images), imaging modalities (ultrasound, magnetic resonance imaging, and computed tomography), and comparisons between DL methods and clinicians consistently showed the acceptable diagnostic performance of DL models. The publication bias and high heterogeneity observed between studies and subgroups can potentially result in an overestimation of the diagnostic accuracy of DL methods in medical imaging. (4) Conclusions: To improve future studies, it would be advantageous to establish more rigorous reporting standards that specifically address the challenges associated with DL research in this particular field.

Extending statistical data of EEG biofeedback quality improvement with soft computing

Aim. Automatic processing of the data in order to determine the status of work and identification of the activity and brain-wave frequencies becomes necessary for the modern systems in the in the diagnosis of biofeedback among athletes.
 Concept. The study aimed to explore the effects of physical exertion on alterations in the manifestation of brain wave frequencies (pre/post exercises) in a group of 15 endurance athletes.
 Results and conclusion. Statistic methods allowed an identification of data anomalies, such as extreme, outliers and missing values. Combining information with soft computing tool can distinguish the level of electrical activity of the analysed muscles. Used Big Data and Data Mining tools solution with a statistical approach while maintaining high measurement accuracy indicates the effectiveness of this method in medical diagnosis.

Principles of Biomimetic solid-state nanopores and the application to biosensors

The wide application of biomimetic solid-state nanopores in biosensors has made them a high-profile research area. It can be applied in several fields such as genomics, proteomics, biomedicine, and environmental monitoring. Bionic solid-state nanopores have demonstrated the capability to detect biomolecules and creatures, including proteins, nucleic acids, cells, and microbes, with a notable degree of sensitivity and selectivity. Biomimetic solid-state nanopores offer several advantages over conventional biosensors. An innovative kind of biosensor is called biomimetic solid state nanopores. This study provides a comprehensive overview of the principle, construction, and use of the bionic solid state nanopore sensor. Bionic solid-state nanopores are of significant importance within the realm of biosensors. Firstly, it has micrometer or nanometer scale, which can effectively capture and control target molecules; Additionally, the dimensions of the biomimetic solid-state nanopores can be modified, along with the surface functionalization, in order to enhance the performance of the sensor and expand its potential applications. In addition, the structural stability and reusability of biomimetic solid-state nanopores also guarantee the long-term application of biosensors. Through in-depth research and development, it is expected to promote the technological progress in the field of biosensors, and provide more accurate and reliable detection methods for life science, medical diagnosis, environmental protection and other fields.

Explainable Deep Learning Methods in Medical Image Classification: A Survey

The remarkable success of deep learning has prompted interest in its application to medical imaging diagnosis. Even though state-of-the-art deep learning models have achieved human-level accuracy on the classification of different types of medical data, these models are hardly adopted in clinical workflows, mainly due to their lack of interpretability. The black-box nature of deep learning models has raised the need for devising strategies to explain the decision process of these models, leading to the creation of the topic of eXplainable Artificial Intelligence (XAI). In this context, we provide a thorough survey of XAI applied to medical imaging diagnosis, including visual, textual, example-based and concept-based explanation methods. Moreover, this work reviews the existing medical imaging datasets and the existing metrics for evaluating the quality of the explanations. In addition, we include a performance comparison among a set of report generation–based methods. Finally, the major challenges in applying XAI to medical imaging and the future research directions on the topic are discussed.

A Bayesian Inference Based Computational Tool for Parametric and Nonparametric Medical Diagnosis.

Medical diagnosis is the basis for treatment and management decisions in healthcare. Conventional methods for medical diagnosis commonly use established clinical criteria and fixed numerical thresholds. The limitations of such an approach may result in a failure to capture the intricate relations between diagnostic tests and the varying prevalence of diseases. To explore this further, we have developed a freely available specialized computational tool that employs Bayesian inference to calculate the posterior probability of disease diagnosis. This novel software comprises of three distinct modules, each designed to allow users to define and compare parametric and nonparametric distributions effectively. The tool is equipped to analyze datasets generated from two separate diagnostic tests, each performed on both diseased and nondiseased populations. We demonstrate the utility of this software by analyzing fasting plasma glucose, and glycated hemoglobin A1c data from the National Health and Nutrition Examination Survey. Our results are validated using the oral glucose tolerance test as a reference standard, and we explore both parametric and nonparametric distribution models for the Bayesian diagnosis of diabetes mellitus.

Development of quality criteria for long-term testing of intracortical electrodes

Abstract The use of intracortical electrodes is a crucial method for medical diagnosis and treatment and holds the promise for overcoming various neural diseases and challenges in prosthetics. The general physical and electrical function as well as the biocompatibility is extensively tested before intracortical electrodes are implanted, however, their longterm performance, is still limited through tissue scarring and electrode deterioration, and consequently a decrease in signal quality. To overcome this challenge, aspects such as materials selection, coatings, flexibility, and surgical procedures are often addressed. To date, however, a systematic, industry - compatible process for long-term functional testing of new intracortical electrodes technologies is still lacking. Implementation of a general overall in vivo testing procedure with defined quality criteria would enable reliable in vivo longterm (> 30 days) device assessment. This could reduce the risk in developing probes for long-term performance and pave the way for clinical application in patients suffering from neural diseases.

Dynamic controllable residual generative adversarial network for low-dose computed tomography imaging.

Computed tomography (CT) imaging technology has become an indispensable auxiliary method in medical diagnosis and treatment. In mitigating the radiation damage caused by X-rays, low-dose computed tomography (LDCT) scanning is becoming more widely applied. However, LDCT scanning reduces the signal-to-noise ratio of the projection, and the resulting images suffer from serious streak artifacts and spot noise. In particular, the intensity of noise and artifacts varies significantly across different body parts under a single low-dose protocol. To improve the quality of different degraded LDCT images in a unified framework, we developed a generative adversarial learning framework with a dynamic controllable residual. First, the generator network consists of the basic subnetwork and the conditional subnetwork. Inspired by the dynamic control strategy, we designed the basic subnetwork to adopt a residual architecture, with the conditional subnetwork providing weights to control the residual intensity. Second, we chose the Visual Geometry Group Network-128 (VGG-128) as the discriminator to improve the noise artifact suppression and feature retention ability of the generator. Additionally, a hybrid loss function was specifically designed, including the mean square error (MSE) loss, structural similarity index metric (SSIM) loss, adversarial loss, and gradient penalty (GP) loss. The results obtained on two datasets show the competitive performance of the proposed framework, with a 3.22 dB peak signal-to-noise ratio (PSNR) margin, 0.03 SSIM margin, and 0.2 contrast-to-noise ratio margin on the Challenge data and a 1.0 dB PSNR margin and 0.01 SSIM margin on the real data. Experimental results demonstrated the competitive performance of the proposed method in terms of noise decrease, structural retention, and visual impression improvement.

BP-CapsNet: An image-based Deep Learning method for medical diagnosis

Deep Learning is one of the promising branches of artificial intelligence and has made phased progress in medical diagnosis. Widely used Convolution Neural Network (CNN) methods require considerable data to train the models to be comparable to professionals. However, it is difficult to acquire medical data in real life to support the application of the CNN methods due to its industrial particularity. Besides, CNN is easy to lose the spatial relationships among the features, which is caused by pooling. The emergence of Capsule Network (CapsNet) effectively alleviates these problems. Nonetheless, CapsNet has an obvious drawback of overlearning: it is prone to learning the noise latent in the image. The named dynamic routing algorithm may lead to the degeneration of capsules on some datasets as the routing iteration increases, making inaccurate diagnoses. This paper proposes a Bayes–Pearson routing CapsNet (BP-CapsNet) with a Singular Value Decomposition (SVD) module to solve the above problems and process medical images to achieve an adequate diagnosis. The proposed method’s effectiveness was evaluated by training and testing the entire model on seven distinct medical image datasets. It achieves state-of-the-art performance on two datasets and the greatest accuracy on another two datasets. The simulation results show that the method can significantly reduce the impact of noise, achieving effective diagnosis and potent generality.

Development of a one-shot dual aptamer-based fluorescence nanosensor for rapid, sensitive, and label-free detection of periostin

Periostin is associated with several diseases, including cancers. Therefore, monitoring blood periostin levels is a powerful tool for diagnosing various diseases and identifying their severity. However, conventional detection methods pose several challenges, including high costs. To address these issues, we developed a novel one-shot dual aptamer-based fluorescence nanosensor for detecting periostin. The proposed nanosensor facilitates rapid, label-free, and sensitive detection of periostin using gold nanoprobes constructed by rhodamine-b isothiocyanate, PL2trunc aptamer, and gold nanoparticles and silver nanoprobes fabricated by the PL5trunc aptamer and silver nanoparticles. The two nanoprobes form a core-satellite structure by interacting with periostin, and the nanosensor detects periostin through the fluorescence regenerated by the increased proximity between them. The nanosensor successfully detected periostin with remarkable detection limits of 106.68 pM in buffer and 463.3 pM in serum-spiked conditions within 30 min without additional washing or signal amplification processes. Considering serum periostin levels in various diseases, the proposed nanosensor provides a suitable method for identifying patients with various diseases and determining disease severity. Moreover, the platform can be helpful as a practical method for on-site medical diagnosis because it can be adapted to detect other biomarkers simply by replacing the aptamer with other detection probes.

Room temperature sensing of primary alcohols via polyaniline/zirconium disulphide

Among the primary alcohols, ethanol is referred to as a heavy chemical due to its many applications in a variety of industries. Detection of primary alcohols can be deployed as a non-invasive method in medical diagnosis and safety measures in food processing companies. Zirconium disulphide is a novel 2D layered material with exotic features when in mono or few layers, which include fast electron transport, high carrier mobility and sizeable band gap. ZrS2 and PANI were fabricated using liquid exfoliation and chemical polymerization methods respectively. Functionalization of the conducting polyaniline with ZrS2 was done using facile sonication process. The sensor showed good sensitivities (43%, 58% and 104%) which were estimated from slopes of the linear fitted plots with fast response-recovery times of 8 s and 27 s (111 ppm); 12 s and 130 s (77 ppm); and 58 s and 88 s (58 ppm). Good reproducibility at three repeated measurements (111 ppm, 77 ppm and 58 ppm) was also observed for methanol, ethanol, and isopropanol vapours respectively. Meanwhile, the sensor displayed more linearity and sensitivity towards isopropanol compared to methanol and ethanol. The sensor showed good performance even at RH values close to 100% making it a potential alcohol breath analyser.

Modeling and analytics of multi-factor disease evolutionary process by fusing petri nets and machine learning methods

Recent years, informatization methods have been gradually applied to medical treatment, in which machine learning and evolutionary computation play an important role. However, the effective methods for the study of multi-factor disease evolutionary process are still largely open. There are some issues in the field of disease analysis, such as the lack of visual multi-factor disease evolution model and effective analysis methods. For a universal method of data analysis and medical diagnosis, the machine learning algorithms should be combined with the formal modeling methods to fully realize the complementary advantages, make model has the advantages of visualization and efficient data analysis. This work proposes a novel research idea for the modeling analysis of current multi-factor diseases and reveal its feasibility, so as to explore potential pharmaceutical targets and enable doctors and patients to better understand the evolution process of multi-factor diseases. It is worth mentioning that, in order to verify the feasibility of the proposed idea, we applied it to the analysis of the role of monoamine hormones in depression. The model incorporates the machine learning algorithms, and it finally outputs the pathogenic probability under different hormone levels, reflecting the importance of different factors on depression. The application case proved that we provide a clear process model and a novel research method for multi-factor disease evolutionary process analysis.

CTMLP: Can MLPs replace CNNs or transformers for COVID-19 diagnosis?

BackgroundConvolutional Neural Networks (CNNs) and the hybrid models of CNNs and Vision Transformers (VITs) are the recent mainstream methods for COVID-19 medical image diagnosis. However, pure CNNs lack global modeling ability, and the hybrid models of CNNs and VITs have problems such as large parameters and computational complexity. These models are difficult to be used effectively for medical diagnosis in just-in-time applications. MethodsTherefore, a lightweight medical diagnosis network CTMLP based on convolutions and multi-layer perceptrons (MLPs) is proposed for the diagnosis of COVID-19. The previous self-supervised algorithms are based on CNNs and VITs, and the effectiveness of such algorithms for MLPs is not yet known. At the same time, due to the lack of ImageNet-scale datasets in the medical image domain for model pre-training. So, a pre-training scheme TL-DeCo based on transfer learning and self-supervised learning was constructed. In addition, TL-DeCo is too tedious and resource-consuming to build a new model each time. Therefore, a guided self-supervised pre-training scheme was constructed for the new lightweight model pre-training. ResultsThe proposed CTMLP achieves an accuracy of 97.51%, an f1-score of 97.43%, and a recall of 98.91% without pre-training, even with only 48% of the number of ResNet50 parameters. Furthermore, the proposed guided self-supervised learning scheme can improve the baseline of simple self-supervised learning by 1%–1.27%. ConclusionThe final results show that the proposed CTMLP can replace CNNs or Transformers for a more efficient diagnosis of COVID-19. In addition, the additional pre-training framework was developed to make it more promising in clinical practice.