Digital twins (DTHs) and virtual twins (VTHs) in healthcare represent emerging technologies towards precision medicine, providing opportunities for patient-centric healthcare. Our scoping review aimed to map the current DTH and VTH technologies in oncology, summarize their technical solutions, and assess their credibility. A systematic search was conducted in the main bibliographic databases, identifying 441 records, of which 30 were included. The studies covered a wide range of cancers, including breast, lung, colorectal, and gastrointestinal malignancies, with DTH and VTH applications focusing on diagnosis, therapy, and monitoring. The results revealed heterogeneity in targeted topics, technical approaches, and outcomes. Most twining solutions use synthetic or limited real-world data, raising concerns regarding their reliability. Few studies have integrated real-time data and machine learning for predictive modeling. Technical challenges include data integration, scalability, and ethical considerations, such as data privacy and security. Moreover, the evidence lacks sufficient clinical validation, with only partial credibility in most cases. Our findings underscore the need for multidisciplinary collaboration among end-users and developers to address the technical and ethical challenges of DTH and VTH systems. Although promising for the future of personalized oncology, substantial steps are required to move beyond experimental frameworks and to achieve clinical implementation.

Vital sign monitoring outside the clinical environment based on wearable sensors ensures better support in assessing a patient’s health condition, and in case of health deterioration, automatic alerts can be sent to the care providers. In everyday life, the users can perform different physical activities, and considering that vital sign measurements depend on the intensity of the activity, we proposed an architecture based on the multi-agent paradigm to handle this issue dynamically. Different types of agents were proposed that processed different sensor signals and recognized simple activities of daily living. The system was validated using a real-life dataset where subjects wore accelerometer sensors on the chest, wrist, and ankle. The system relied on ontology-based models to address the data heterogeneity and combined different wearable sensor sources in order to achieve better performance. The results showed an accuracy of 95.25% on intersubject activity classification. Moreover, the proposed method, which automatically extracted vital sign threshold ranges for each physical activity recognized by the system, showed promising results for remote health status evaluation.

The third most prevalent cancer nowadays is colorectal cancer. Colonoscopy is an important procedure in the stage of detection of polyps’ malignancy because it helps in early identification and establishes effective therapy. This paper explores specific deep-learning architectures for the binary classification of colorectal polyps and considers the evaluation of their premalignancy risk. The main scope is to create a custom-based deep learning architecture that classifies adenomatous, hyperplastic, and serrated polyps’ samples into benign and premalignant based on images from the colonoscopic dataset. Each image’s output is modified through masked autoencoders which enhance the classification performance of the proposed model, called Bionnica . From the four evaluated state-of-the-art deep learning models (ZF NET, VGG-16, AlexNet, and ResNet-50), our experiments showed that ResNet-50 and ZF NET are most accurate (above 84%), with ResNet-50 excelling at indicating patients with premalignant colorectal polyps (above 92%). ZF NET is the fastest at handling 700 images. Our proposed deep learning model, Bionnica , is more performant than ZF NET and provides an efficient classification of colorectal polyps given its simple structure. The advantage of our model comes from the custom enhancement interpretability with a rule-based layer that guides the learning process and supports medical personnel in their decisions.

The third most prevalent cancer nowadays is colorectal cancer. Colonoscopy is an important procedure in the stage of detection of polyps’ malignancy because it helps in early identification and establishes effective therapy. This paper explores specific deep-learning architectures for the binary classification of colorectal polyps and considers the evaluation of their premalignancy risk. The main scope is to create a custom-based deep learning architecture that classifies adenomatous, hyperplastic, and serrated polyps’ samples into benign and premalignant based on images from the colonoscopic dataset. Each image’s output is modified through masked autoencoders which enhance the classification performance of the proposed model, called Bionnica . From the four evaluated state-of-the-art deep learning models (ZF NET, VGG-16, AlexNet, and ResNet-50), our experiments showed that ResNet-50 and ZF NET are most accurate (above 84%), with ResNet-50 excelling at indicating patients with premalignant colorectal polyps (above 92%). ZF NET is the fastest at handling 700 images. Our proposed deep learning model, Bionnica , is more performant than ZF NET and provides an efficient classification of colorectal polyps given its simple structure. The advantage of our model comes from the custom enhancement interpretability with a rule-based layer that guides the learning process and supports medical personnel in their decisions.