Blockchain-enabled healthcare monitoring system for early Monkeypox detection

Abstract

The recent emergence of monkeypox poses a life-threatening challenge to humans and has become one of the global health concerns after COVID-19. Currently, machine learning-based smart healthcare monitoring systems have demonstrated significant potential in image-based diagnosis including brain tumor identification and lung cancer diagnosis. In a similar fashion, the applications of machine learning can be utilized for the early identification of monkeypox cases. However, sharing critical health information with various actors such as patients, doctors, and other healthcare professionals in a secure manner remains a research challenge. Motivated by this fact, our paper presents a blockchain-enabled conceptual framework for the early detection and classification of monkeypox using transfer learning. The proposed framework is experimentally demonstrated in Python 3.9 using a monkeypox dataset of 1905 images obtained from the GitHub repository. To validate the effectiveness of the proposed model, various performance estimators, namely accuracy, recall, precision, and F1-score, are employed. The performance of different transfer learning models, namely Xception, VGG19, and VGG16, is compared against the presented methodology. Based on the comparison, it is evident that the proposed methodology effectively detects and classifies the monkeypox disease with a classification accuracy of 98.80%. In future, multiple skin diseases such as measles and chickenpox can be diagnosed using the proposed model on the skin lesion datasets.

Deep hybrid model for Mpox disease diagnosis from skin lesion images

“…In the domain of DL‐based classification of MPox disease, several studies have focused on classifying MPox skin lesions using DL methods, such as VGG‐16, 26 ResNet50, 27 and InceptionV3 28 . Another study utilized the Xception 29 TL model in combination with Grad‐Cam and LIME techniques, achieving high accuracy and F1‐score. TL was also employed to detect MPox disease using a modified VGG16 model.…”

A healthcare data management system: Blockchain enabled IPFS providing algorithmic solution for increased privacy preserving scalability and interoperability

“…From algorithm 2, we can evaluate the step-by-step procedure, through which the user authentication is done with the help of a smart contract [32]. The complexity of the authentication algorithm is O(n).…”

“…Because of the public channels, there are chances to break the security measures by the attackers they may intercept and alter the data. To address this problem, here in this framework a public-private key-based structure is used for the authentication process [32]. Each user will get a unique key pair (Public-Private keys) and these are used for storing as well as accessing the data.…”

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

“…Recently, several studies have explored innovative approaches in healthcare technology, focusing on AI for remote patient monitoring (RPM) and skin disease classification [115][116][117][118][119][120][121][122][123][124]. These studies established the synergy between emerging technologies like IoMT devices, and mobile applications in tackling complex skin disease challenges.…”

“…Shi, Li and Chen [122] developed a federated contrastive learning framework for skin lesion diagnosis in edge computing networks, enhancing diagnostic accuracy by utilizing contrastive learning and dual encoder networks. Gupta, Bhagat and Jain [123] presented a blockchain-enabled system for early monkeypox detection, utilizing transfer learning and achieving a classification accuracy of 98.80%. Lastly, Hossen, Panneerselvam, Koundal, Ahmed, Bui and Ibrahim [124] explored the classification of skin diseases using a custom dataset and CNN, achieving precision rates up to 86% for diseases like acne, eczema, and psoriasis.…”