Hina Bansal

Digital Twin (DT) technology has emerged as a continuously updated, bidirectional virtual replica of a physical system that enables real-time data exchange and predictive analysis. This capability offers significant potential for enhancing human-robot collaboration (HRC) in clinical environments. This chapter explores the role of Digital Twins in transforming healthcare robotics across four high-impact healthcare domains: surgical robotics, rehabilitation, remote patient monitoring, and hospital logistics. It presents a unified conceptual framework grounded in ISO 23247 standards and examines the enabling technology ecosystem, including AI, IoT, 5G communications, augmented and virtual reality (AR/VR), federated learning and edge computing. The chapter further analyzes key challenges related to interoperability, cybersecurity, ethics, regulations and workforce adoption that influence large-scale implementation. Finally, the chapter outlines governance strategies and future research priorities necessary for developing a trustworthy, safe and human-centred DT-enabled healthcare system.

Given that ovarian cancer is a major health concern for women worldwide, we explored the potential of Indian medicinal plants, namely Curcuma longa (Turmeric), Azadirachta indica (Neem), and Asparagus racemosus (Shatavari) via a combined approach of network pharmacology and molecular docking. Initially, bioactive phytochemicals of these plants were sourced from the IMPPAT and SwissTargetPrediction databases, resulting in the identification of 202 compounds along with 1,124 corresponding protein targets. These were then compared with ovarian cancer–related genes obtained from the GeneCards database, leading to the identification of 885 common targets. A protein–protein interaction network was constructed and analyzed using Cytoscape to identify the cluster modules. Additionally, gene ontology and pathway enrichment analyses revealed the multifaceted nature of ovarian cancer, indicating its disruptive impact on various cellular processes, signaling pathways, immune responses, and metabolic regulations. Importantly, EGFR, PIK3CA, JAK2, and PIK3CD were identified as crucial therapeutic nodes within the network. Subsequent molecular docking recognized the strong binding affinity between the active compounds and these key targets, thereby supporting the network analysis. In conclusion, the study highlighted the therapeutic action of C. longa , A. indica , and A. racemosus in combating ovarian cancer and promoting the development of plant-based treatments for this cancer.

Drug discovery is traditionally a long, expensive and high-risk endeavour, often spanning more than a decade. Artificial Intelligence (AI) is reshaping this landscape by accelerating discovery timelines, improving accuracy, and reducing costs across the entire drug development pipeline. This chapter highlights the applications of AI in the early stage of drug discovery, including target identification, hit screening, lead optimization, and de novo design. In the preclinical and clinical phases, AI contributes to predictive toxicology, pharmacokinetics and pharmacodynamics, adaptive trial design, patient recruitment and real-time monitoring. Even after product launch, AI supports risk management, regulatory submissions and pharmacovigilance. The chapter further explores emerging opportunities, including digital twins, federated learning, and autonomous R&D pipelines. Overall, AI is not a replacement for scientists but represents a paradigm shift toward faster, safer and more personalized therapeutic development through collaborative and ethical integration.

This chapter investigates the integration of artificial intelligence, nutrigenomics, and the human polybiome to enhance precision healthcare. It outlines how deep learning and multiomics approaches decode host–microbe interactions influencing nutrition, gene expression, and disease risk. This chapter introduces advanced analytical frameworks linking microbial metabolites, epigenetic regulation, and metabolic balance. By merging computational biology with clinical insight, AI-driven strategies for predictive nutrition, individualized therapy, and early disease intervention can be developed. Furthermore, this chapter discusses the ethical and interpretability dimensions of AI in biomedical data, emphasizing transparent algorithms and privacy-preserving models that ensure reliability, reproducibility, and responsible innovation in personalized healthcare systems.

Metabolic disorders—including diabetes, weight problems, excessive blood pressure, etc, are getting increasingly more common in today's quick-moving, challenging world. These ailments don't arise instantly. Often, some subtle signs and vulnerabilities accumulate over time, however, they pass neglected till it is too overdue. Conventional checkout frameworks depend closely on inflexible criteria and obstacles, which can overlook the hidden systems. Artificial intelligence, however, is transforming this approach. With its capability to examine extensive information pools, computational intelligence is aiding healthcare providers in identifying threats earlier, tailoring therapy, and even foreseeing health deterioration. The essence of this chapter is to explore the developing function of artificial intelligence in determining metabolic disorders, emphasizing forecasting, predictive analysis, and risk assessment. We shall explore the most recent studies, AI models, current systems, tangible issues, and the personal consequences of these innovations, both now and in the future.

Federated Learning empowers hospitals and research centres to train AI models collaboratively without sharing patient records. It is the decentralized alternative in which AI models can be trained across multiple healthcare organizations. The patient data is stored securely at multiple parties rather than being shared in raw data. FL makes it possible to share learned knowledge while still adhering to strict data-specific privacy regulations. This chapter provides a comprehensive overview of FL's foundational principles, architecture, and challenges. It highlights the various ways FL can assist with data protection for patients and research participants, decentralized data governance, enhance security, and scale FL across hospitals and research institutions. It gives insights on FL implementation in healthcare practice, including radiology with NVIDIA Clara, AI-driven rare disease diagnosis, COVID response solutions, and wearable health monitoring trackers. Additionally, it discusses possible combinations of FL and blockchain systems, edge AI, IoT in a medical context.

Emotions are a part of our experiences impacting how we think, act and relate to others. They manifest through behavioral cues like tears, sweat or smiles reflecting social influences. Facial expressions are crucial for conveying emotions nonverbally involving muscle movements that create facial configurations. Though they are often spontaneous, these expressions can also be consciously adjusted for interactions. Technology like facial expression recognition has advanced significantly through learning enhancing precision in fields such as security, marketing and healthcare. This chapter explores emotions, facial expressions and learning techniques used for their analysis. These strategies enable real-time applications for automatic facial expression analysis, with potential in emotion recognition, deception detection, and human-computer interaction.