Fundamentals of Cost-efficient Ai : In Healthcare and Biomedicine

Fundamentals of Cost-Efficient AI: In Healthcare and Biomedicine provides a comprehensive yet accessible introduction to the principles of designing, training, and deploying efficient artificial intelligence systems. It explains the theory behind cost-aware machine learning and data mining and examines methods across deep learning, graph neural networks (GNNs), transformer architectures, diffusion models, reinforcement learning, and knowledge distillation.
The book covers fine-tuning and compression techniques such as low-rank adaptation (LoRA), parameter-efficient fine-tuning (PEFT), adapter-based tuning, pruning, and quantization. It also explores inference acceleration through Flash Attention, prefill optimization, and speculative decoding, and explains how mixture-of-experts (MoE) architectures can scale models efficiently across GPUs and edge devices.
To build a strong conceptual understanding, the text introduces fundamentals of GPU architecture, matrix multiplication, memory hierarchies, and parallelization strategies, helping readers develop an intuition for optimizing training and inference pipelines.
While applicable across domains, the book places special emphasis on healthcare and biomedicine, where efficient AI can reduce costs and improve diagnostics, precision medicine, and clinical decision support. Real-world case studies and interviews with experts from organizations such as Google and Microsoft provide practical insights into building scalable healthcare AI systems. Aimed at graduate students, researchers, clinicians, biomedical engineers, data scientists, and AI practitioners, this book bridges algorithmic principles with applied implementation.

• Covers state-of-the-art techniques, including LoRA, PEFT, diffusion models, RAG, Flash Attention, and MoE architectures
• Explains methods for model compression, quantization, pruning, and knowledge distillation with practical examples
• Integrates GPU fundamentals, matrix operations, and system-level optimization for efficient model training and deployment
• Includes case studies and interviews demonstrating the use of cost-efficient AI in healthcare and biomedicine
• Balances mathematical foundations with implementation guidance and applied intuition

Rohit Kumar studied at Stanford, IIT Delhi, and RPI, specializing in machine learning. He is the Global Head of AI & Analytics at HCLTech (Digital Business), a visiting faculty at Shiv Nadar University, and a PhD scholar at IIT researching AI hallucinations. With over 20 years of product development experience in Silicon Valley, he has served as the Head of R&D at the Ministry of IT (Government of India), Senior Director at WalmartLabs, and CEO of a blockchain startup. He holds multiple patents and publications on generative AI, data mining, and large-scale distributed systems.