From machine learning to deep learning: Advances of the recent data-driven paradigm shift in medicine and healthcare

Current Research in Biotechnology, Journal Year: 2023, Volume and Issue: 7, P. 100164 - 100164

Published: Nov. 22, 2023

The medicine and healthcare sector has been evolving advancing very fast. advancement initiated shaped by the applications of data-driven, robust, efficient machine learning (ML) to deep (DL) technologies. ML in medical is developing quickly, causing rapid progress, reshaping medicine, improving clinician patient experiences. technologies evolved into data-hungry DL approaches, which are more robust dealing with data. This article reviews some critical data-driven aspects intelligence field. In this direction, illustrated recent progress science using two categories: firstly, development data uses and, secondly, Chabot particularly on ChatGPT. Here, we discuss ML, DL, transition requirements from DL. To science, illustrate prospective studies image data, newly interpretation EMR or EHR, big personalized dataset shifts artificial (AI). Simultaneously, recently developed DL-enabled ChatGPT technology. Finally, summarize broad role significant challenges for implementing healthcare. overview paradigm shift will benefit researchers immensely.

Language: Английский

---

Skin cancer classification using NASNet

International Journal of Science and Research Archive, Journal Year: 2024, Volume and Issue: 11(1), P. 775 - 785

Published: Jan. 30, 2024

The importance of making an early diagnosis in both the prevention and treatment skin cancer cannot be overstated. A very effective medical decision support system that can classify lesions based on dermoscopic pictures is essential instrument for determining prognosis cancer. In spite fine-grained variation way different types appear, Deep Convolutional Neural Networks (DCNN) have made great strides recent years toward improving ability to detect using images. It has been claimed there are a few machine learning techniques accurate photos. good number these methods predicated convolutional neural networks (CNNs) already trained, which makes it possible train models only small quantity available training data. However, because so sample images malignant tumors available, classification accuracy still typically severely restricted. primary purpose this study construct DCNN-based model capable automatically classifying as either melanoma or non-melanoma with high level accuracy. We propose optimized NASNet architecture, enhanced additional data basic layer employed CNN added. strategy proposed enhances model's capacity deal incomplete inconsistent dataset 2637 used demonstrate benefits technique proposed. analyze performance suggested method by looking at its precision, sensitivity, specificity, F1-score, area under ROC curve. Optimized Mobile Large provides 85.62% 83.98%, respectively Adam optimizer.

Language: Английский

---

Skin cancer classification using Inception Network

World Journal of Advanced Research and Reviews, Journal Year: 2024, Volume and Issue: 21(2), P. 839 - 849

Published: Feb. 15, 2024

Since skin disease is a universally recognized condition among humans, there has been growing interest in utilizing intelligent systems to classify various ailments. This line of research deep learning holds immense significance for dermatologists. However, accurately determining the presence formidable task due intricate nature texture and visual similarities between different diseases. To address this challenge, images undergo filtration eliminate unwanted noise further processing enhance overall quality image. The primary purpose study construct neural network-based model that capable automatically classifying several types cancer as either melanoma or non-melanoma with prominent level accuracy. We propose an optimized Inception architecture, which InceptionNet enhanced data augmentation basic layers. strategy proposed enhances model's capacity deal incomplete inconsistent data. A dataset 2637 are used demonstrate benefits technique proposed. analyze performance suggested method by looking at its precision, sensitivity, specificity, F1-score, area under ROC curve. Proposed provides accuracy 84.39% 85.94%, respectively Adam Nadam optimizer. training process each subsequent layer exhibits notable enhancement effectiveness. An examination inquiry can assist experts making early diagnoses, thereby providing them insight into infection enabling initiate necessary treatment, if deemed necessary.

Language: Английский

---

Uncovering COVID-19 conversations: Twitter insights and trends

World Journal of Advanced Research and Reviews, Journal Year: 2024, Volume and Issue: 21(1), P. 836 - 842

Published: Jan. 15, 2024

In this paper, we delve into the public discourse surrounding COVID-19 on Twitter to unearth collective sentiments, concerns, and spread of information during pandemic. By leveraging a dataset relevant tweets corresponding ISO country codes, our analysis will map out geographical digital landscape these conversations. The significance work lies in its potential inform health strategies, shape policymaking, contribute social research crisis communication. Stakeholders ranging from officials have vested interest understanding contours dialogue. Our objective is craft data-driven narrative through visualizations that reveal how world engages with pandemic front, providing actionable insights global local responses using Machine Learning techniques.

Language: Английский

---

The Data Heterogeneity Issue Regarding COVID-19 Lung Imaging in Federated Learning: An Experimental Study

Big Data and Cognitive Computing, Journal Year: 2025, Volume and Issue: 9(1), P. 11 - 11

Published: Jan. 14, 2025

Federated learning (FL) has emerged as a transformative framework for collaborative learning, offering robust model training across institutions while ensuring data privacy. In the context of making COVID-19 diagnosis using lung imaging, FL enables to collaboratively train global without sharing sensitive patient data. A central manager aggregates local updates compute updates, secure and effective integration. The model’s generalization capability is evaluated centralized testing before dissemination participating nodes, where assessments facilitate personalized adaptations tailored diverse datasets. Addressing heterogeneity, critical challenge in medical essential improving both performance personalization systems. This study emphasizes importance recognizing real-world variability proposing solutions tackle non-independent non-identically distributed (non-IID) We investigate impact heterogeneity on imaging seven distinct settings. By comprehensively evaluating models metrics, we highlight challenges opportunities optimizing frameworks. findings provide valuable insights that can guide future research toward achieving balance between adaptation, ultimately enhancing diagnostic accuracy outcomes imaging.

Language: Английский

---

Security aspects in IoT based cloud computing

World Journal of Advanced Research and Reviews, Journal Year: 2023, Volume and Issue: 20(3), P. 540 - 551

Published: Dec. 11, 2023

Cloud computing offers a flexible framework in which data and resources are spread across different locations can be accessed from various industrial environments. This technology has revolutionized the way such as data, services, applications used, stored, shared applications. Over past decade, industries have rapidly embraced cloud due to its advantages of enhanced accessibility, cost reduction, improved performance. Moreover, integration led significant advancements field Internet Things (IoT). However, this quick shift also introduced security concerns challenges. Traditional solutions not always suitable or effective for cloud-based systems. Despite continuous use complex cyber weapons, efforts been made recent years address issues associated with platforms. The rapid progress deep learning (DL) artificial intelligence (AI) provided opportunities tackle these challenges cloud. research presented study encompasses comprehensive survey enabling architecture, configurations, models IoT. It categorizes IoT within four major categories (data, network service, applications, people-related issues) provides detailed discussion on each category. Furthermore, examines latest attacks, analyzes category, presents limitations broader perspective encompassing general, intelligence, aspects.

Language: Английский

---

Technological trends in 5G networks for IoT-enabled smart healthcare: A review

International Journal of Science and Research Archive, Journal Year: 2024, Volume and Issue: 12(2), P. 1399 - 1410

Published: July 30, 2024

Smart healthcare is in the process of quick evolution from traditional focused approach towards specialist and hospital to a patient-centric model. The following technological advancements have boosted this revolution vertical. Presently, 4G as well other communication standards like WLAN are applied offer smart services solutions. considers apply for advancement further future. It reason that industry expands, several applications anticipated generate huge volume data various forms sizes. Thus, enormous varying requires special end-to-end delay, bandwidth, latency factors. it becomes highly challenging current technologies effectively support complex sensitive health care these 5G networks being planned implemented address multifaceted requirements IoT. assisted consist IoT devices which need better network performance extended cellular connections. There issues with existing connectivity solutions namely how many can be connected, achieving global standardization, optimizing low power budgets, fit into given area secure communication. This paper aims provide an elaborate review by technology.

Language: Английский

---

Lower Back Pain Prediction Applying Different Classification Algorithm Using WEKA

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 337 - 348

Published: Jan. 1, 2025

Language: Английский

---

Federated learning for solar energy applications: A case study on real-time fault detection

Solar Energy, Journal Year: 2024, Volume and Issue: 282, P. 112942 - 112942

Published: Sept. 21, 2024

Language: Английский

---

Optimizing Lung Condition Categorization through a Deep Learning Approach to Chest X-ray Image Analysis

BioMedInformatics, Journal Year: 2024, Volume and Issue: 4(3), P. 2002 - 2021

Published: Sept. 10, 2024

Background: Evaluating chest X-rays is a complex and high-demand task due to the intrinsic challenges associated with diagnosing wide range of pulmonary conditions. Therefore, advanced methodologies are required categorize multiple conditions from X-ray images accurately. Methods: This study introduces an optimized deep learning approach designed for multi-label categorization images, covering broad spectrum conditions, including lung opacity, normative states, COVID-19, bacterial pneumonia, viral tuberculosis. An model based on modified VGG16 architecture SE blocks was developed applied large dataset images. The evaluated against state-of-the-art techniques using metrics such as accuracy, F1-score, precision, recall, area under curve (AUC). Results: VGG16-SE demonstrated superior performance across all metrics. achieved accuracy 98.49%, F1-score 98.23%, precision 98.41%, recall 98.07% AUC 98.86%. Conclusion: provides effective categorizing X-rays. model’s high various suggests its potential integration into clinical workflows, enhancing speed disease diagnosis.

Language: Английский

---